1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2026-06-12 23:50:12 +00:00

Compare commits

..

154 Commits

Author SHA1 Message Date
Sergey M․ 36ef9d9509 Add rewrite rules for copyright infringement URL 2019-04-27 03:13:40 +07:00
Sergey M․ f0242b98a8 Add rewrite rules for README and FAQ URLs 2019-04-27 02:54:12 +07:00
Sergey M․ 782d021327 Add rewrite rule for search issues URL 2019-04-27 02:47:06 +07:00
Sergey M․ 26dc98c5ca Add rewrite rule for escaping special characters URLs 2019-04-27 02:41:45 +07:00
Sergey M․ c444b69644 [.htaccess] Add rewrite rules for LATEST_VERSION and versions.json 2019-03-17 07:02:16 +07:00
Sergey M․ c3c160f402 Fix links to gh-pages 2019-03-11 04:11:04 +07:00
Sergey M․ 59f945e799 Start moving to ytdl-org 2019-03-11 04:02:28 +07:00
Philipp Hagemeister d2e9088ee4 prevent access to .git
The repository wasn't secret per se, but there's no reason to allow access to the git files.

Thanks to Ben Stock and CISPA for notifying us.
2017-02-03 22:07:13 +01:00
Sergey M․ 167e13273e Use latest in download URLs 2016-07-17 18:45:31 +07:00
Sergey M․ 40f283d159 Add some more shortcuts 2016-06-26 02:20:59 +07:00
Sergey M․ 6a020a3218 Add yt-dl.org/questions shortcut 2016-06-26 02:00:20 +07:00
Sergey M․ e275a2f1ab [update_latest.sh] Fix root latest redirection 2016-06-11 03:55:38 +07:00
Sergey M․ 8afb663891 [update_latest.sh] Fix download links redirection (2) 2016-06-11 03:19:16 +07:00
Sergey M․ 1df8afcc18 [update_latest.sh] Fix download links redirection 2016-06-11 02:56:11 +07:00
Sergey M․ b0035c3448 Allow latest without trailing slash 2016-06-11 02:25:05 +07:00
Sergey M․ 8c6f08911f [update_latest.sh] Redirect all releases to GitHub 2016-06-11 02:20:39 +07:00
Philipp Hagemeister 7fc3fe2b54 save traffic on 302 2016-06-04 11:58:05 +02:00
Philipp Hagemeister 6a6bbc01f5 ignore latest_version file 2016-06-04 11:41:53 +02:00
Philipp Hagemeister 774e0d72cd modify index 2016-06-04 11:41:04 +02:00
Philipp Hagemeister 00221fad40 add better rewrite rules 2016-06-04 11:39:40 +02:00
Philipp Hagemeister c0716886d8 readd /latest directory 2016-06-04 10:20:14 +02:00
Philipp Hagemeister 386cc2f23e update latest etc. 2016-06-04 10:18:57 +02:00
Philipp Hagemeister 1a93d2ce6e Redirect current version to GitHub releases
Our hoster uberspace noted that we're by far exceeding our traffic limit.
For now, redirect everything to GitHub releases.
2016-06-04 10:08:23 +02:00
Philipp Hagemeister 86d55e2f99 Add shortcut URL for 403 errors when used in webbrowser 2015-12-30 13:13:17 +01:00
Philipp Hagemeister 1d97efec15 [htaccess] Add a shortcut for missing example URLs 2015-02-18 10:32:26 +01:00
Philipp Hagemeister 31326e8739 FAQ for -citw 2015-02-11 20:30:16 +01:00
Philipp Hagemeister 843060b2e0 Correct htaccess 2015-02-03 14:22:45 +01:00
Philipp Hagemeister 9c49a1a8bd Add a redirect for anime/illegal sites 2015-02-03 14:20:54 +01:00
Philipp Hagemeister da9084a061 [.htaccess] Link to https 2015-01-04 02:43:34 +01:00
Philipp Hagemeister caae7db812 [.htaccess] Add short URL yt-dl.org/donate 2015-01-04 02:41:24 +01:00
Philipp Hagemeister a29e9ec53c Change link to support on yt-dl.org (#4484) 2014-12-16 00:27:34 +01:00
Philipp Hagemeister 29a8bfbaa9 [/update] Fix hash 2014-11-14 00:41:41 +01:00
Philipp Hagemeister 5e4ecfe225 [/latest] Correct content type and prevent caching 2014-11-13 23:37:57 +01:00
Philipp Hagemeister b2ee8bf786 add /update 302 2014-11-13 22:42:59 +01:00
Philipp Hagemeister da0a0d59a1 Ignore test from master branch 2014-11-13 22:41:21 +01:00
Philipp Hagemeister 52f8db8b79 Filter string latest in list of latest versions 2014-06-01 10:27:01 +02:00
Philipp Hagemeister 644f92f6a5 Write downloads .htaccess, not main one 2014-04-30 10:40:14 +02:00
Philipp Hagemeister 54a1852f08 Add a redirect for downloads/latest 2014-04-30 10:39:23 +02:00
Philipp Hagemeister 0b33704b43 Re-add +Indexes 2014-04-30 10:34:58 +02:00
Philipp Hagemeister 17e311adf0 Add latest symlink in downloads (Fixes #2835) 2014-04-30 10:21:09 +02:00
Philipp Hagemeister 809987a65c Do not escape redirect URL 2014-04-19 15:00:04 +02:00
Philipp Hagemeister 2f0e8ad0a6 Rename reporting shortener 2014-04-19 14:57:36 +02:00
Philipp Hagemeister a5bd123ec0 Shorten bug reporting URL (Suggested by @AGSPhoenix) 2014-04-19 14:55:46 +02:00
Philipp Hagemeister c74d3d5d80 echo latest version, too 2013-06-25 20:54:43 +02:00
Philipp Hagemeister c20b2894ff Linkify latest 2013-06-25 20:53:54 +02:00
Philipp Hagemeister 005caca467 Disable automatic directory detection 2013-06-25 20:51:29 +02:00
Philipp Hagemeister abb88dcb2f Allow latest to be called from everywhere 2013-06-25 19:13:59 +02:00
Philipp Hagemeister c052029267 Add an error message if number of arguments is incorrect 2013-06-25 19:04:30 +02:00
Philipp Hagemeister 0669b923c0 Allow listing latest/ 2013-06-25 18:32:45 +02:00
Philipp Hagemeister 110c975154 Script to update the latest/ directory (#925) 2013-06-25 18:29:07 +02:00
Philipp Hagemeister 8005b349a4 Add latest/ directory 2013-06-25 18:00:37 +02:00
Philipp Hagemeister d185f03455 Record changes to download server 2013-06-25 17:33:24 +02:00
Philipp Hagemeister 420cf88aeb Remove copyright note (this page is trivial) 2013-06-25 17:28:55 +02:00
Philipp Hagemeister 504afbe65d Update gitignore 2013-05-10 02:09:43 +02:00
Philipp Hagemeister d929dd31d1 IP check 2013-05-10 02:09:39 +02:00
Philipp Hagemeister 49698bfaa3 Merge pull request #828 from jaimeMF/download-server
Fix float display
2013-05-09 16:48:07 -07:00
Jaime Marquínez Ferrándiz 633f6f9b39 Fix float display 2013-05-07 14:25:15 +02:00
Filippo Valsorda 71c8858fcd fixes 2012-12-31 17:04:16 +01:00
Philipp Hagemeister 83f5182bcf let travis-lint pass as well ... 2012-12-12 20:37:20 +01:00
Philipp Hagemeister fb65f76630 Tell travis not to test this 2012-12-12 20:35:36 +01:00
Philipp Hagemeister 1f69efb978 Correct download links 2012-12-12 20:32:00 +01:00
Philipp Hagemeister 3bcc0a565c New downloads page for git 2012-12-12 20:21:16 +01:00
Philipp Hagemeister 2840ae3a8f Update homepage 2012-12-11 17:52:56 +01:00
Philipp Hagemeister b51355ef99 Credit @FiloSottile 2012-12-11 17:43:50 +01:00
Philipp Hagemeister 1762b604b1 new release 2012-12-11 17:34:56 +01:00
Philipp Hagemeister 8c64aa48d2 New generate-download for the new build mechanism 2012-12-11 17:34:33 +01:00
Philipp Hagemeister 8c3a45b6e4 Update supported extractors 2012-11-30 08:38:14 +01:00
Philipp Hagemeister dc9e2d8e0c Document CollegeHumor and arte.tv 2012-11-28 17:57:06 +01:00
Philipp Hagemeister e7d727efc2 Drop 2.5 support 2012-11-28 03:30:44 +01:00
Philipp Hagemeister a89c5d20c7 2012.11.29 2012-11-27 18:37:27 +01:00
Philipp Hagemeister 044cb16590 release 2012.11.28 2012-11-27 16:16:51 +01:00
Philipp Hagemeister 81db2d8040 Document --restrict-filenames, remove stitle 2012-11-27 16:06:59 +01:00
Philipp Hagemeister 2811949f4c Update doc for 2012.11.27 2012-11-27 00:26:05 +01:00
Philipp Hagemeister 3a2c78a2da Document configuration options 2012-11-26 23:23:33 +01:00
Philipp Hagemeister 23cf656bd1 Automatically update copyright (Closes #549) 2012-11-26 11:19:40 +01:00
Philipp Hagemeister 41ff5333f7 ignore temporary files 2012-11-26 11:18:31 +01:00
Philipp Hagemeister 571d094858 Clarify required Python version (#549) 2012-11-26 11:18:08 +01:00
Philipp Hagemeister 96679b26cf release 2012.11.17 2012-11-26 04:05:23 +01:00
Philipp Hagemeister b7d1a2247e Python 2.6 instead of 2.5 in about (Closes #516) 2012-11-07 01:49:35 +01:00
Philipp Hagemeister 9746c518a5 update docs 2012-10-10 19:33:08 +02:00
Philipp Hagemeister 959fa33ef9 release youtube-dl 2012.10.09 2012-10-10 19:27:50 +02:00
Philipp Hagemeister a44c76cdf4 release release 2012.09.27 2012-09-28 13:27:54 +02:00
Philipp Hagemeister 6a3ff26a01 Add recent breakages to FAQ (#433) 2012-09-27 23:29:40 +02:00
Philipp Hagemeister 60a1c34662 Drop 2.5 compatibility 2012-09-27 15:33:20 +02:00
Philipp Hagemeister 49bd2af54f Clarify 402 2012-02-28 02:00:00 +01:00
Philipp Hagemeister a5999b83fd release 2012.02.27 2012-02-27 20:20:08 +01:00
Philipp Hagemeister 82eedd7d83 update docs for 2012.02.26 2012-02-27 00:43:20 +01:00
Philipp Hagemeister 759320387a Use stitle instead of title in doc 2012-01-12 20:15:54 +01:00
Philipp Hagemeister 0be94d4c6a release 2012.01.08b docs 2012-01-08 17:24:46 +01:00
Philipp Hagemeister 6bd03617e6 docs for 2012.01.05 2012-01-05 11:10:14 +01:00
Philipp Hagemeister a3d06cfe6d doc for 2011.12.18 2011-12-17 01:35:45 +01:00
Philipp Hagemeister cd891850ec Release 2011.12.15 2011-12-15 20:33:49 +01:00
Philipp Hagemeister cdee681a2c Release 2011.12.08 2011-12-08 21:41:43 +01:00
Philipp Hagemeister db2c6281eb Release 2011.11.23: Update webpage 2011-11-23 10:39:50 +01:00
Philipp Hagemeister 06a129c9dd Release 2011.11.22 2011-11-22 15:39:04 +01:00
Philipp Hagemeister 5a938b5d04 +Makefile 2011-11-22 15:38:32 +01:00
Philipp Hagemeister b0e67d2404 Release 2011.11.21 2011-11-21 21:54:04 +01:00
Philipp Hagemeister 92961845c3 docs for 2011.10.19 2011-10-19 00:40:55 +02:00
Philipp Hagemeister f9c3398449 release 2011.09.30 2011-09-30 09:08:53 +02:00
Philipp Hagemeister bffe76ba4b Remove empty <tr>s in index 2011-09-28 09:55:54 +02:00
Philipp Hagemeister 0d29baa7c6 Make documentation valid HTML 2011-09-28 09:53:50 +02:00
Philipp Hagemeister dd9d3efcfb Make FAQ valid HTML 2011-09-28 09:52:01 +02:00
Philipp Hagemeister 9014805f26 Fix stray </a> in FAQ 2011-09-28 09:50:04 +02:00
Philipp Hagemeister f973da57a4 Switch to HTML5 doctype 2011-09-28 09:49:19 +02:00
Philipp Hagemeister a073eb792f Update documentation and FAQ 2011-09-28 09:47:54 +02:00
Philipp Hagemeister f202278fe1 Close <ul> in first FAQ question 2011-09-28 09:29:19 +02:00
Philipp Hagemeister 3328f34eb3 Update homepage for 2011.09.27 2011-09-27 21:44:59 +02:00
Philipp Hagemeister 50d7a239ae Raise correct args in exception 2011-09-27 21:44:02 +02:00
Philipp Hagemeister 81eb98e4bd Update docs 2011-09-27 21:17:50 +02:00
Philipp Hagemeister 78ef538449 Updated bug reporting instructions in the FAQ 2011-09-27 20:58:37 +02:00
Philipp Hagemeister 6e3ed6385c Download regeneration works with python 2.5 2011-09-27 20:50:03 +02:00
Ricardo Garcia a2dafa7316 Add creative commons license to webpages 2011-09-27 20:17:34 +02:00
Philipp Hagemeister 86e5e08789 release 2011.09.18c 2011-09-17 00:59:45 +02:00
Philipp Hagemeister e397cf5b47 2011.09.18b 2011-09-16 22:33:54 +02:00
Philipp Hagemeister 3fd01c88c5 Update documentation for 2011.09.18 2011-09-15 19:29:53 +02:00
Philipp Hagemeister d2cbb552b7 Update documentation for 2011.09.17 2011-09-15 19:25:07 +02:00
Philipp Hagemeister 9c358a8982 Release 2011.09.16 2011-09-15 18:49:20 +02:00
Philipp Hagemeister 7923514ea0 Release 2011.09.15 2011-09-14 22:56:50 +02:00
Philipp Hagemeister 004759c8f2 Add a prominent Develop link in the documentation (Closes #155) 2011-09-14 00:42:45 +02:00
Philipp Hagemeister 95f029a5d8 Release 2011.09.14 2011-09-14 00:02:16 +02:00
Philipp Hagemeister ac47cfe369 Update generate-download 2011-09-13 23:06:09 +02:00
Philipp Hagemeister 463fe92d26 Release new version 2011-09-13 23:05:58 +02:00
Ricardo Garcia ba8a90b0bf Regenerate download page 2011-08-04 19:16:25 +02:00
Ricardo Garcia 3a6c68881a Regenerate download page 2011-03-29 20:33:22 +02:00
Ricardo Garcia a290358c2f Regenerate download page 2011-02-26 00:48:41 +01:00
Ricardo Garcia 17faaa4548 Regenerate download page 2011-02-25 21:54:55 +01:00
Ricardo Garcia 3ea19089f9 Regenerate download page 2011-02-25 20:13:32 +01:00
Ricardo Garcia 9077650490 Add Gergely Imreh to the author list 2011-02-20 18:03:52 +01:00
Ricardo Garcia 2ecbfb4cbc Properly update Python version requirement in the documentation 2011-01-30 13:14:45 +01:00
Ricardo Garcia 3519974510 Regenerate download page 2011-01-30 13:12:45 +01:00
Ricardo Garcia e76e4dc8b1 Add Paweł Paprota to the list of authors in the documentation 2011-01-30 13:12:10 +01:00
Ricardo Garcia 01e013b5e3 Mention support for YouTube.com user videos in the documentation 2011-01-30 13:10:22 +01:00
Ricardo Garcia 64ea994344 Update documentation to reflect Python 2.5 requirement 2011-01-30 12:56:52 +01:00
Ricardo Garcia a3e9208c01 Add Witold Baryluk to the author list 2011-01-21 18:19:43 +01:00
Ricardo Garcia ec0d2e46c5 Add link to the project page from the about page 2011-01-07 10:43:13 +01:00
Ricardo Garcia 1b3dbefb04 Modify pages increasing the copyright year 2011-01-03 10:54:47 +01:00
Ricardo Garcia c3003bb4db Add question about option -g to the FAQ 2011-01-03 10:54:07 +01:00
Ricardo Garcia 6c7d5d8d14 Regenerate download page 2010-12-09 19:58:30 +01:00
Ricardo Garcia 35c0ad4587 Regenerate download page 2010-12-09 19:38:15 +01:00
Ricardo Garcia 941383109a Document new DepositFiles InfoExtractor 2010-12-08 10:59:59 +01:00
Ricardo Garcia c95ac4f062 Regenerate download page 2010-11-19 19:42:22 +01:00
Ricardo Garcia 0732b1f39f Document change from "ord" to "autonumber" in template 2010-11-19 19:38:36 +01:00
Ricardo Garcia 8d78373ea0 Document new upload_date template parameter 2010-11-19 19:38:07 +01:00
Ricardo Garcia 17082ad9db Put the main buttons ordered vertically 2010-11-19 18:24:03 +01:00
Ricardo Garcia 725d763c48 Reorganize website 2010-11-19 18:19:41 +01:00
Ricardo Garcia a993428ac9 Document rtmpdump's optional requirement in the main page 2010-11-06 18:46:50 +01:00
Ricardo Garcia 7136abc8f3 Improve documentation on "SyntaxError" to take Python 3.x into account 2010-11-06 18:45:10 +01:00
Ricardo Garcia 790622091e Renamed "generate-home" to "generate-index" for consistency 2010-11-06 11:29:10 +01:00
Ricardo Garcia db03ff92a6 Changed a few style aspects to make the page look better under IE 2010-11-06 11:29:10 +01:00
Ricardo Garcia b294d9fa38 Use SSL in URLs where possible 2010-11-06 11:28:56 +01:00
Ricardo Garcia 5de4c645e2 Make web pages valid HTML and remove a few glitches 2010-11-02 21:28:56 +01:00
Ricardo Garcia 05703c8f9c Minor changes to stylesheet 2010-11-01 11:28:23 +01:00
Ricardo Garcia f37b138766 Add copyright notice at the bottom of every page 2010-11-01 08:23:57 +01:00
Ricardo Garcia 5c7359365f Initial pages commit, using the wiki contents 2010-10-31 23:50:48 +01:00
306 changed files with 262 additions and 31383 deletions
+8 -25
View File
@@ -1,30 +1,13 @@
*.pyc
*.pyo
*~
*.DS_Store
wine-py2exe/
py2exe.log
*.kate-swp
downloads/*
updates_key.pem
youtube_dl.egg-info
test
build/
dist/
MANIFEST
README.txt
youtube-dl.1
youtube-dl.fish
youtube-dl.zsh
README.txt
youtube-dl.bash-completion
youtube-dl
youtube-dl.exe
youtube-dl.tar.gz
.coverage
cover/
updates_key.pem
*.egg-info
*.srt
*.sbv
*.vtt
*.flv
*.mp4
*.m4a
*.m4v
*.part
test/testdata
.tox
latest_version
+32
View File
@@ -0,0 +1,32 @@
Options +Indexes
RewriteEngine On
RewriteRule ^ip/?$ ip.php
RewriteRule ^bugs?/? https://github.com/ytdl-org/youtube-dl/issues [R=302,L]
RewriteRule ^readme/?$ https://github.com/ytdl-org/youtube-dl/blob/master/README.md [R=302,L,NE]
RewriteRule ^reporting/? https://github.com/ytdl-org/youtube-dl/blob/master/README.md#bugs [R=302,L,NE]
RewriteRule ^update/?$ https://github.com/ytdl-org/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl [R=302,L,NE]
RewriteRule ^donat(e|ions)/?$ https://ytdl-org.github.io/youtube-dl/donations.html [R=302,L]
RewriteRule ^faq/?$ https://github.com/ytdl-org/youtube-dl/blob/master/README.md#faq [R=302,L,NE]
RewriteRule ^(faq-)?anime/?$ https://github.com/ytdl-org/youtube-dl/blob/master/README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free [R=302,L,NE]
RewriteRule ^copyright-infringement/?$ https://github.com/ytdl-org/youtube-dl/blob/master/README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free [R=302,L,NE]
RewriteRule ^(faq-)?citw/?$ https://github.com/ytdl-org/youtube-dl/blob/master/README.md#do-i-always-have-to-pass-in---max-quality-format-or--citw [R=302,L,NE]
RewriteRule ^(?:example-url|questions)/?$ https://github.com/ytdl-org/youtube-dl/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient [R=302,L,NE]
RewriteRule ^g403/?$ https://github.com/ytdl-org/youtube-dl/blob/master/README.md#i-extracted-a-video-url-with--g-but-it-does-not-play-on-another-machine--in-my-webbrowser [R=302,L,NE]
RewriteRule ^format-selection/?$ https://github.com/ytdl-org/youtube-dl#format-selection [R=302,L,NE]
RewriteRule ^output-template/?$ https://github.com/ytdl-org/youtube-dl#output-template [R=302,L,NE]
RewriteRule ^escape/?$ https://github.com/ytdl-org/youtube-dl#video-url-contains-an-ampersand-and-im-getting-some-strange-output-1-2839-or-v-is-not-recognized-as-an-internal-or-external-command [R=302,L,NE]
RewriteRule ^search-issues/?$ https://github.com/ytdl-org/youtube-dl/issues?q=is:issue [R=302,L,NE]
RewriteRule ^update/LATEST_VERSION$ https://ytdl-org.github.io/youtube-dl/update/LATEST_VERSION [R=302,L]
RewriteRule ^update/versions.json https://ytdl-org.github.io/youtube-dl/update/versions.json [R=302,L]
RewriteRule ^latest/version/?$ latest_version [L,T=text/plain]
RewriteRule ^latest_version/?$ - [T=text/plain]
RewriteRule ^latest(?:/(.*))?$ /downloads/latest/$1 [R=302,L]
RewriteRule ^\.git - [F]
ErrorDocument 302 "302"
+2 -15
View File
@@ -1,16 +1,3 @@
# Just a placeholder script so that travis doesn't complain
language: python
python:
- "2.6"
- "2.7"
- "3.3"
script: nosetests test --verbose
notifications:
email:
- filippo.valsorda@gmail.com
- phihag@phihag.de
- jaime.marquinez.ferrandiz+travis@gmail.com
- yasoob.khld@gmail.com
# irc:
# channels:
# - "irc.freenode.org#youtube-dl"
# skip_join: true
script: true
-14
View File
@@ -1,14 +0,0 @@
2013.01.02 Codename: GIULIA
* Add support for ComedyCentral clips <nto>
* Corrected Vimeo description fetching <Nick Daniels>
* Added the --no-post-overwrites argument <Barbu Paul - Gheorghe>
* --verbose offers more environment info
* New info_dict field: uploader_id
* New updates system, with signature checking
* New IEs: NBA, JustinTV, FunnyOrDie, TweetReel, Steam, Ustream
* Fixed IEs: BlipTv
* Fixed for Python 3 IEs: Xvideo, Youku, XNXX, Dailymotion, Vimeo, InfoQ
* Simplified IEs and test code
* Various (Python 3 and other) fixes
* Revamped and expanded tests
-1
View File
@@ -1 +0,0 @@
2012.12.99
-24
View File
@@ -1,24 +0,0 @@
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
For more information, please refer to <http://unlicense.org/>
-5
View File
@@ -1,5 +0,0 @@
include README.md
include test/*.py
include test/*.json
include youtube-dl.bash-completion
include youtube-dl.1
-79
View File
@@ -1,79 +0,0 @@
all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
clean:
rm -rf youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz
cleanall: clean
rm -f youtube-dl youtube-dl.exe
PREFIX=/usr/local
BINDIR=$(PREFIX)/bin
MANDIR=$(PREFIX)/man
PYTHON=/usr/bin/env python
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
ifeq ($(PREFIX),/usr)
SYSCONFDIR=/etc
else
ifeq ($(PREFIX),/usr/local)
SYSCONFDIR=/etc
else
SYSCONFDIR=$(PREFIX)/etc
endif
endif
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
install -d $(DESTDIR)$(BINDIR)
install -m 755 youtube-dl $(DESTDIR)$(BINDIR)
install -d $(DESTDIR)$(MANDIR)/man1
install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1
install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
test:
#nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
nosetests --verbose test
tar: youtube-dl.tar.gz
.PHONY: all clean install test tar bash-completion pypi-files
pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1
youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
zip --quiet youtube-dl youtube_dl/*.py youtube_dl/*/*.py
zip --quiet --junk-paths youtube-dl youtube_dl/__main__.py
echo '#!$(PYTHON)' > youtube-dl
cat youtube-dl.zip >> youtube-dl
rm youtube-dl.zip
chmod a+x youtube-dl
README.md: youtube_dl/*.py youtube_dl/*/*.py
COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
README.txt: README.md
pandoc -f markdown -t plain README.md -o README.txt
youtube-dl.1: README.md
pandoc -s -f markdown -t man README.md -o youtube-dl.1
youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
python devscripts/bash-completion.py
bash-completion: youtube-dl.bash-completion
youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion
@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
--exclude '*.DS_Store' \
--exclude '*.kate-swp' \
--exclude '*.pyc' \
--exclude '*.pyo' \
--exclude '*~' \
--exclude '__pycache' \
--exclude '.git' \
--exclude 'testdata' \
-- \
bin devscripts test youtube_dl \
CHANGELOG LICENSE README.md README.txt \
Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion setup.py \
youtube-dl
-428
View File
@@ -1,428 +0,0 @@
% YOUTUBE-DL(1)
# NAME
youtube-dl - download videos from youtube.com or other video platforms
# SYNOPSIS
**youtube-dl** [OPTIONS] URL [URL...]
# DESCRIPTION
**youtube-dl** is a small command-line program to download videos from
YouTube.com and a few more sites. It requires the Python interpreter, version
2.6, 2.7, or 3.3+, and it is not platform specific. It should work on
your Unix box, on Windows or on Mac OS X. It is released to the public domain,
which means you can modify it, redistribute it or use it however you like.
# OPTIONS
-h, --help print this help text and exit
--version print program version and exit
-U, --update update this program to latest version. Make
sure that you have sufficient permissions
(run with sudo if needed)
-i, --ignore-errors continue on download errors, for example to
skip unavailable videos in a playlist
--abort-on-error Abort downloading of further videos (in the
playlist or the command line) if an error
occurs
--dump-user-agent display the current browser identification
--user-agent UA specify a custom user agent
--referer REF specify a custom referer, use if the video
access is restricted to one domain
--list-extractors List all supported extractors and the URLs
they would handle
--extractor-descriptions Output descriptions of all supported
extractors
--proxy URL Use the specified HTTP/HTTPS proxy. Pass in
an empty string (--proxy "") for direct
connection
--no-check-certificate Suppress HTTPS certificate validation.
--cache-dir DIR Location in the filesystem where youtube-dl
can store some downloaded information
permanently. By default $XDG_CACHE_HOME
/youtube-dl or ~/.cache/youtube-dl . At the
moment, only YouTube player files (for
videos with obfuscated signatures) are
cached, but that may change.
--no-cache-dir Disable filesystem caching
--socket-timeout None Time to wait before giving up, in seconds
--bidi-workaround Work around terminals that lack
bidirectional text support. Requires bidiv
or fribidi executable in PATH
--default-search PREFIX Use this prefix for unqualified URLs. For
example "gvsearch2:" downloads two videos
from google videos for youtube-dl "large
apple". By default (with value "auto")
youtube-dl guesses.
--ignore-config Do not read configuration files. When given
in the global configuration file /etc
/youtube-dl.conf: do not read the user
configuration in ~/.config/youtube-dl.conf
(%APPDATA%/youtube-dl/config.txt on
Windows)
## Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last)
--match-title REGEX download only matching titles (regex or
caseless sub-string)
--reject-title REGEX skip download for matching titles (regex or
caseless sub-string)
--max-downloads NUMBER Abort after downloading NUMBER files
--min-filesize SIZE Do not download any videos smaller than
SIZE (e.g. 50k or 44.6m)
--max-filesize SIZE Do not download any videos larger than SIZE
(e.g. 50k or 44.6m)
--date DATE download only videos uploaded in this date
--datebefore DATE download only videos uploaded on or before
this date (i.e. inclusive)
--dateafter DATE download only videos uploaded on or after
this date (i.e. inclusive)
--min-views COUNT Do not download any videos with less than
COUNT views
--max-views COUNT Do not download any videos with more than
COUNT views
--no-playlist download only the currently playing video
--age-limit YEARS download only videos suitable for the given
age
--download-archive FILE Download only videos not listed in the
archive file. Record the IDs of all
downloaded videos in it.
--include-ads Download advertisements as well
(experimental)
--youtube-include-dash-manifest Try to download the DASH manifest on
YouTube videos (experimental)
## Download Options:
-r, --rate-limit LIMIT maximum download rate in bytes per second
(e.g. 50K or 4.2M)
-R, --retries RETRIES number of retries (default is 10)
--buffer-size SIZE size of download buffer (e.g. 1024 or 16K)
(default is 1024)
--no-resize-buffer do not automatically adjust the buffer
size. By default, the buffer size is
automatically resized from an initial value
of SIZE.
## Filesystem Options:
-t, --title use title in file name (default)
--id use only video ID in file name
-l, --literal [deprecated] alias of --title
-A, --auto-number number downloaded files starting from 00000
-o, --output TEMPLATE output filename template. Use %(title)s to
get the title, %(uploader)s for the
uploader name, %(uploader_id)s for the
uploader nickname if different,
%(autonumber)s to get an automatically
incremented number, %(ext)s for the
filename extension, %(format)s for the
format description (like "22 - 1280x720" or
"HD"), %(format_id)s for the unique id of
the format (like Youtube's itags: "137"),
%(upload_date)s for the upload date
(YYYYMMDD), %(extractor)s for the provider
(youtube, metacafe, etc), %(id)s for the
video id, %(playlist)s for the playlist the
video is in, %(playlist_index)s for the
position in the playlist and %% for a
literal percent. %(height)s and %(width)s
for the width and height of the video
format. %(resolution)s for a textual
description of the resolution of the video
format. Use - to output to stdout. Can also
be used to download to a different
directory, for example with -o '/my/downloa
ds/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
--autonumber-size NUMBER Specifies the number of digits in
%(autonumber)s when it is present in output
filename template or --auto-number option
is given
--restrict-filenames Restrict filenames to only ASCII
characters, and avoid "&" and spaces in
filenames
-a, --batch-file FILE file containing URLs to download ('-' for
stdin)
--load-info FILE json file containing the video information
(created with the "--write-json" option)
-w, --no-overwrites do not overwrite files
-c, --continue force resume of partially downloaded files.
By default, youtube-dl will resume
downloads if possible.
--no-continue do not resume partially downloaded files
(restart from beginning)
--cookies FILE file to read cookies from and dump cookie
jar in
--no-part do not use .part files
--no-mtime do not use the Last-modified header to set
the file modification time
--write-description write video description to a .description
file
--write-info-json write video metadata to a .info.json file
--write-annotations write video annotations to a .annotation
file
--write-thumbnail write thumbnail image to disk
## Verbosity / Simulation Options:
-q, --quiet activates quiet mode
-s, --simulate do not download the video and do not write
anything to disk
--skip-download do not download the video
-g, --get-url simulate, quiet but print URL
-e, --get-title simulate, quiet but print title
--get-id simulate, quiet but print id
--get-thumbnail simulate, quiet but print thumbnail URL
--get-description simulate, quiet but print video description
--get-duration simulate, quiet but print video length
--get-filename simulate, quiet but print output filename
--get-format simulate, quiet but print output format
-j, --dump-json simulate, quiet but print JSON information
--newline output progress bar as new lines
--no-progress do not print progress bar
--console-title display progress in console titlebar
-v, --verbose print various debugging information
--dump-intermediate-pages print downloaded pages to debug problems
(very verbose)
--write-pages Write downloaded intermediary pages to
files in the current directory to debug
problems
--print-traffic Display sent and read HTTP traffic
## Video Format Options:
-f, --format FORMAT video format code, specify the order of
preference using slashes: "-f 22/17/18".
"-f mp4" and "-f flv" are also supported.
You can also use the special names "best",
"bestaudio", "worst", and "worstaudio". By
default, youtube-dl will pick the best
quality.
--all-formats download all available video formats
--prefer-free-formats prefer free video formats unless a specific
one is requested
--max-quality FORMAT highest quality format to download
-F, --list-formats list all available formats
## Subtitle Options:
--write-sub write subtitle file
--write-auto-sub write automatic subtitle file (youtube
only)
--all-subs downloads all the available subtitles of
the video
--list-subs lists all available subtitles for the video
--sub-format FORMAT subtitle format (default=srt) ([sbv/vtt]
youtube only)
--sub-lang LANGS languages of the subtitles to download
(optional) separated by commas, use IETF
language tags like 'en,pt'
## Authentication Options:
-u, --username USERNAME account username
-p, --password PASSWORD account password
-n, --netrc use .netrc authentication data
--video-password PASSWORD video password (vimeo, smotri)
## Post-processing Options:
-x, --extract-audio convert video files to audio-only files
(requires ffmpeg or avconv and ffprobe or
avprobe)
--audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a",
"opus", or "wav"; best by default
--audio-quality QUALITY ffmpeg/avconv audio quality specification,
insert a value between 0 (better) and 9
(worse) for VBR or a specific bitrate like
128K (default 5)
--recode-video FORMAT Encode the video to another format if
necessary (currently supported:
mp4|flv|ogg|webm)
-k, --keep-video keeps the video file on disk after the
post-processing; the video is erased by
default
--no-post-overwrites do not overwrite post-processed files; the
post-processed files are overwritten by
default
--embed-subs embed subtitles in the video (only for mp4
videos)
--add-metadata write metadata to the video file
--xattrs write metadata to the video file's xattrs
(using dublin core and xdg standards)
--prefer-avconv Prefer avconv over ffmpeg for running the
postprocessors (default)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
postprocessors
# CONFIGURATION
You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
# OUTPUT TEMPLATE
The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are:
- `id`: The sequence will be replaced by the video identifier.
- `url`: The sequence will be replaced by the video URL.
- `uploader`: The sequence will be replaced by the nickname of the person who uploaded the video.
- `upload_date`: The sequence will be replaced by the upload date in YYYYMMDD format.
- `title`: The sequence will be replaced by the video title.
- `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4).
- `epoch`: The sequence will be replaced by the Unix epoch when creating the file.
- `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
- `playlist`: The name or the id of the playlist that contains the video.
- `playlist_index`: The index of the video in the playlist, a five-digit number.
The current default template is `%(title)s-%(id)s.%(ext)s`.
In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc
youtube-dl test video ''_ä↭𝕐.mp4 # All kinds of weird characters
$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
youtube-dl_test_video_.mp4 # A simple file name
# VIDEO SELECTION
Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
- Absolute dates: Dates in the format `YYYYMMDD`.
- Relative dates: Dates in the format `(now|today)[+-][0-9](day|week|month|year)(s)?`
Examples:
# Download only the videos uploaded in the last 6 months
$ youtube-dl --dateafter now-6months
# Download only the videos uploaded on January 1, 1970
$ youtube-dl --date 19700101
$ # will only download the videos uploaded in the 200x decade
$ youtube-dl --dateafter 20000101 --datebefore 20091231
# FAQ
### Can you please put the -b option back?
Most people asking this question are not aware that youtube-dl now defaults to downloading the highest available quality as reported by YouTube, which will be 1080p or 720p in some cases, so you no longer need the `-b` option. For some specific videos, maybe YouTube does not report them to be available in a specific high quality format you're interested in. In that case, simply request it with the `-f` option and youtube-dl will try to download it.
### I get HTTP error 402 when trying to download a video. What's this?
Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a webbrowser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
### I have downloaded a video but how can I play it?
Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
### The links provided by youtube-dl -g are not working anymore
The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
### ERROR: no fmt_url_map or conn information found in video info
youtube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`.
### ERROR: unable to download video ###
youtube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`.
### SyntaxError: Non-ASCII character ###
The error
File "youtube-dl", line 2
SyntaxError: Non-ASCII character '\x93' ...
means you're using an outdated version of Python. Please update to Python 2.6 or 2.7.
### What is this binary file? Where has the code gone?
Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
### The exe throws a *Runtime error from Visual C++*
To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
# DEVELOPER INSTRUCTIONS
Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
To run youtube-dl as a developer, you don't need to build anything either. Simply execute
python -m youtube_dl
To run the test, simply invoke your favorite test runner, or execute a test file directly; any of the following work:
python -m unittest discover
python test/test_download.py
nosetests
If you want to create a build of youtube-dl yourself, you'll need
* python
* make
* pandoc
* zip
* nosetests
### Adding support for a new site
If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Don't forget to run the tests with `python test/test_download.py TestDownload.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
# BUGS
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email.
Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
For discussions, join us in the irc channel #youtube-dl on freenode.
When you submit a request, please re-read it once to avoid a couple of mistakes (you can and should use this as a checklist):
### Is the description of the issue itself sufficient?
We often get issue reports that we cannot really decipher. While in most cases we eventually get the required information after asking back multiple times, this poses an unnecessary drain on our resources. Many contributors, including myself, are also not native speakers, so we may misread some parts.
So please elaborate on what feature you are requesting, or what bug you want to be fixed. Make sure that it's obvious
- What the problem is
- How it could be fixed
- How your proposed solution would look like
If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
Site support requests must contain an example URL. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
### Are you using the latest version?
Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
### Is the issue already documented?
Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
### Why are existing options not enough?
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
### Is there enough context in your bug report?
People want to solve problems, and often think they do us a favor by breaking down their larger problems (e.g. wanting to skip already downloaded files) to a specific request (e.g. requesting us to look whether the file exists before downloading the info page). However, what often happens is that they break down the problem into two steps: One simple, and one impossible (or extremely complicated one).
We are then presented with a very complicated request when the original problem could be solved far easier, e.g. by recording the downloaded video IDs in a separate file. To avoid this, you must include the greater context where it is non-obvious. In particular, every feature request that does not consist of adding support for a new site should contain a use case scenario that explains in what situation the missing feature would be useful.
### Does the issue involve one problem, and one problem only?
Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
### Is anyone going to need the feature?
Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
### Is your question about youtube-dl?
It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
# COPYRIGHT
youtube-dl is released into the public domain by the copyright holders.
This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain.
-6
View File
@@ -1,6 +0,0 @@
#!/usr/bin/env python
import youtube_dl
if __name__ == '__main__':
youtube_dl.main()
Binary file not shown.
Binary file not shown.
-29
View File
@@ -1,29 +0,0 @@
__youtube_dl()
{
local cur prev opts fileopts diropts keywords
COMPREPLY=()
cur="${COMP_WORDS[COMP_CWORD]}"
prev="${COMP_WORDS[COMP_CWORD-1]}"
opts="{{flags}}"
keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
fileopts="-a|--batch-file|--download-archive|--cookies|--load-info"
diropts="--cache-dir"
if [[ ${prev} =~ ${fileopts} ]]; then
COMPREPLY=( $(compgen -f -- ${cur}) )
return 0
elif [[ ${prev} =~ ${diropts} ]]; then
COMPREPLY=( $(compgen -d -- ${cur}) )
return 0
fi
if [[ ${cur} =~ : ]]; then
COMPREPLY=( $(compgen -W "${keywords}" -- ${cur}) )
return 0
elif [[ ${cur} == * ]] ; then
COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
return 0
fi
}
complete -F __youtube_dl youtube-dl
-26
View File
@@ -1,26 +0,0 @@
#!/usr/bin/env python
import os
from os.path import dirname as dirn
import sys
sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
import youtube_dl
BASH_COMPLETION_FILE = "youtube-dl.bash-completion"
BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
def build_completion(opt_parser):
opts_flag = []
for group in opt_parser.option_groups:
for option in group.option_list:
#for every long flag
opts_flag.append(option.get_opt_string())
with open(BASH_COMPLETION_TEMPLATE) as f:
template = f.read()
with open(BASH_COMPLETION_FILE, "w") as f:
#just using the special char
filled_template = template.replace("{{flags}}", " ".join(opts_flag))
f.write(filled_template)
parser = youtube_dl.parseOpts()[0]
build_completion(parser)
-405
View File
@@ -1,405 +0,0 @@
#!/usr/bin/python3
from http.server import HTTPServer, BaseHTTPRequestHandler
from socketserver import ThreadingMixIn
import argparse
import ctypes
import functools
import sys
import threading
import traceback
import os.path
class BuildHTTPServer(ThreadingMixIn, HTTPServer):
allow_reuse_address = True
advapi32 = ctypes.windll.advapi32
SC_MANAGER_ALL_ACCESS = 0xf003f
SC_MANAGER_CREATE_SERVICE = 0x02
SERVICE_WIN32_OWN_PROCESS = 0x10
SERVICE_AUTO_START = 0x2
SERVICE_ERROR_NORMAL = 0x1
DELETE = 0x00010000
SERVICE_STATUS_START_PENDING = 0x00000002
SERVICE_STATUS_RUNNING = 0x00000004
SERVICE_ACCEPT_STOP = 0x1
SVCNAME = 'youtubedl_builder'
LPTSTR = ctypes.c_wchar_p
START_CALLBACK = ctypes.WINFUNCTYPE(None, ctypes.c_int, ctypes.POINTER(LPTSTR))
class SERVICE_TABLE_ENTRY(ctypes.Structure):
_fields_ = [
('lpServiceName', LPTSTR),
('lpServiceProc', START_CALLBACK)
]
HandlerEx = ctypes.WINFUNCTYPE(
ctypes.c_int, # return
ctypes.c_int, # dwControl
ctypes.c_int, # dwEventType
ctypes.c_void_p, # lpEventData,
ctypes.c_void_p, # lpContext,
)
def _ctypes_array(c_type, py_array):
ar = (c_type * len(py_array))()
ar[:] = py_array
return ar
def win_OpenSCManager():
res = advapi32.OpenSCManagerW(None, None, SC_MANAGER_ALL_ACCESS)
if not res:
raise Exception('Opening service manager failed - '
'are you running this as administrator?')
return res
def win_install_service(service_name, cmdline):
manager = win_OpenSCManager()
try:
h = advapi32.CreateServiceW(
manager, service_name, None,
SC_MANAGER_CREATE_SERVICE, SERVICE_WIN32_OWN_PROCESS,
SERVICE_AUTO_START, SERVICE_ERROR_NORMAL,
cmdline, None, None, None, None, None)
if not h:
raise OSError('Service creation failed: %s' % ctypes.FormatError())
advapi32.CloseServiceHandle(h)
finally:
advapi32.CloseServiceHandle(manager)
def win_uninstall_service(service_name):
manager = win_OpenSCManager()
try:
h = advapi32.OpenServiceW(manager, service_name, DELETE)
if not h:
raise OSError('Could not find service %s: %s' % (
service_name, ctypes.FormatError()))
try:
if not advapi32.DeleteService(h):
raise OSError('Deletion failed: %s' % ctypes.FormatError())
finally:
advapi32.CloseServiceHandle(h)
finally:
advapi32.CloseServiceHandle(manager)
def win_service_report_event(service_name, msg, is_error=True):
with open('C:/sshkeys/log', 'a', encoding='utf-8') as f:
f.write(msg + '\n')
event_log = advapi32.RegisterEventSourceW(None, service_name)
if not event_log:
raise OSError('Could not report event: %s' % ctypes.FormatError())
try:
type_id = 0x0001 if is_error else 0x0004
event_id = 0xc0000000 if is_error else 0x40000000
lines = _ctypes_array(LPTSTR, [msg])
if not advapi32.ReportEventW(
event_log, type_id, 0, event_id, None, len(lines), 0,
lines, None):
raise OSError('Event reporting failed: %s' % ctypes.FormatError())
finally:
advapi32.DeregisterEventSource(event_log)
def win_service_handler(stop_event, *args):
try:
raise ValueError('Handler called with args ' + repr(args))
TODO
except Exception as e:
tb = traceback.format_exc()
msg = str(e) + '\n' + tb
win_service_report_event(service_name, msg, is_error=True)
raise
def win_service_set_status(handle, status_code):
svcStatus = SERVICE_STATUS()
svcStatus.dwServiceType = SERVICE_WIN32_OWN_PROCESS
svcStatus.dwCurrentState = status_code
svcStatus.dwControlsAccepted = SERVICE_ACCEPT_STOP
svcStatus.dwServiceSpecificExitCode = 0
if not advapi32.SetServiceStatus(handle, ctypes.byref(svcStatus)):
raise OSError('SetServiceStatus failed: %r' % ctypes.FormatError())
def win_service_main(service_name, real_main, argc, argv_raw):
try:
#args = [argv_raw[i].value for i in range(argc)]
stop_event = threading.Event()
handler = HandlerEx(functools.partial(stop_event, win_service_handler))
h = advapi32.RegisterServiceCtrlHandlerExW(service_name, handler, None)
if not h:
raise OSError('Handler registration failed: %s' %
ctypes.FormatError())
TODO
except Exception as e:
tb = traceback.format_exc()
msg = str(e) + '\n' + tb
win_service_report_event(service_name, msg, is_error=True)
raise
def win_service_start(service_name, real_main):
try:
cb = START_CALLBACK(
functools.partial(win_service_main, service_name, real_main))
dispatch_table = _ctypes_array(SERVICE_TABLE_ENTRY, [
SERVICE_TABLE_ENTRY(
service_name,
cb
),
SERVICE_TABLE_ENTRY(None, ctypes.cast(None, START_CALLBACK))
])
if not advapi32.StartServiceCtrlDispatcherW(dispatch_table):
raise OSError('ctypes start failed: %s' % ctypes.FormatError())
except Exception as e:
tb = traceback.format_exc()
msg = str(e) + '\n' + tb
win_service_report_event(service_name, msg, is_error=True)
raise
def main(args=None):
parser = argparse.ArgumentParser()
parser.add_argument('-i', '--install',
action='store_const', dest='action', const='install',
help='Launch at Windows startup')
parser.add_argument('-u', '--uninstall',
action='store_const', dest='action', const='uninstall',
help='Remove Windows service')
parser.add_argument('-s', '--service',
action='store_const', dest='action', const='service',
help='Run as a Windows service')
parser.add_argument('-b', '--bind', metavar='<host:port>',
action='store', default='localhost:8142',
help='Bind to host:port (default %default)')
options = parser.parse_args(args=args)
if options.action == 'install':
fn = os.path.abspath(__file__).replace('v:', '\\\\vboxsrv\\vbox')
cmdline = '%s %s -s -b %s' % (sys.executable, fn, options.bind)
win_install_service(SVCNAME, cmdline)
return
if options.action == 'uninstall':
win_uninstall_service(SVCNAME)
return
if options.action == 'service':
win_service_start(SVCNAME, main)
return
host, port_str = options.bind.split(':')
port = int(port_str)
print('Listening on %s:%d' % (host, port))
srv = BuildHTTPServer((host, port), BuildHTTPRequestHandler)
thr = threading.Thread(target=srv.serve_forever)
thr.start()
input('Press ENTER to shut down')
srv.shutdown()
thr.join()
def rmtree(path):
for name in os.listdir(path):
fname = os.path.join(path, name)
if os.path.isdir(fname):
rmtree(fname)
else:
os.chmod(fname, 0o666)
os.remove(fname)
os.rmdir(path)
#==============================================================================
class BuildError(Exception):
def __init__(self, output, code=500):
self.output = output
self.code = code
def __str__(self):
return self.output
class HTTPError(BuildError):
pass
class PythonBuilder(object):
def __init__(self, **kwargs):
pythonVersion = kwargs.pop('python', '2.7')
try:
key = _winreg.OpenKey(_winreg.HKEY_LOCAL_MACHINE, r'SOFTWARE\Python\PythonCore\%s\InstallPath' % pythonVersion)
try:
self.pythonPath, _ = _winreg.QueryValueEx(key, '')
finally:
_winreg.CloseKey(key)
except Exception:
raise BuildError('No such Python version: %s' % pythonVersion)
super(PythonBuilder, self).__init__(**kwargs)
class GITInfoBuilder(object):
def __init__(self, **kwargs):
try:
self.user, self.repoName = kwargs['path'][:2]
self.rev = kwargs.pop('rev')
except ValueError:
raise BuildError('Invalid path')
except KeyError as e:
raise BuildError('Missing mandatory parameter "%s"' % e.args[0])
path = os.path.join(os.environ['APPDATA'], 'Build archive', self.repoName, self.user)
if not os.path.exists(path):
os.makedirs(path)
self.basePath = tempfile.mkdtemp(dir=path)
self.buildPath = os.path.join(self.basePath, 'build')
super(GITInfoBuilder, self).__init__(**kwargs)
class GITBuilder(GITInfoBuilder):
def build(self):
try:
subprocess.check_output(['git', 'clone', 'git://github.com/%s/%s.git' % (self.user, self.repoName), self.buildPath])
subprocess.check_output(['git', 'checkout', self.rev], cwd=self.buildPath)
except subprocess.CalledProcessError as e:
raise BuildError(e.output)
super(GITBuilder, self).build()
class YoutubeDLBuilder(object):
authorizedUsers = ['fraca7', 'phihag', 'rg3', 'FiloSottile']
def __init__(self, **kwargs):
if self.repoName != 'youtube-dl':
raise BuildError('Invalid repository "%s"' % self.repoName)
if self.user not in self.authorizedUsers:
raise HTTPError('Unauthorized user "%s"' % self.user, 401)
super(YoutubeDLBuilder, self).__init__(**kwargs)
def build(self):
try:
subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'],
cwd=self.buildPath)
except subprocess.CalledProcessError as e:
raise BuildError(e.output)
super(YoutubeDLBuilder, self).build()
class DownloadBuilder(object):
def __init__(self, **kwargs):
self.handler = kwargs.pop('handler')
self.srcPath = os.path.join(self.buildPath, *tuple(kwargs['path'][2:]))
self.srcPath = os.path.abspath(os.path.normpath(self.srcPath))
if not self.srcPath.startswith(self.buildPath):
raise HTTPError(self.srcPath, 401)
super(DownloadBuilder, self).__init__(**kwargs)
def build(self):
if not os.path.exists(self.srcPath):
raise HTTPError('No such file', 404)
if os.path.isdir(self.srcPath):
raise HTTPError('Is a directory: %s' % self.srcPath, 401)
self.handler.send_response(200)
self.handler.send_header('Content-Type', 'application/octet-stream')
self.handler.send_header('Content-Disposition', 'attachment; filename=%s' % os.path.split(self.srcPath)[-1])
self.handler.send_header('Content-Length', str(os.stat(self.srcPath).st_size))
self.handler.end_headers()
with open(self.srcPath, 'rb') as src:
shutil.copyfileobj(src, self.handler.wfile)
super(DownloadBuilder, self).build()
class CleanupTempDir(object):
def build(self):
try:
rmtree(self.basePath)
except Exception as e:
print('WARNING deleting "%s": %s' % (self.basePath, e))
super(CleanupTempDir, self).build()
class Null(object):
def __init__(self, **kwargs):
pass
def start(self):
pass
def close(self):
pass
def build(self):
pass
class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, CleanupTempDir, Null):
pass
class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
actionDict = { 'build': Builder, 'download': Builder } # They're the same, no more caching.
def do_GET(self):
path = urlparse.urlparse(self.path)
paramDict = dict([(key, value[0]) for key, value in urlparse.parse_qs(path.query).items()])
action, _, path = path.path.strip('/').partition('/')
if path:
path = path.split('/')
if action in self.actionDict:
try:
builder = self.actionDict[action](path=path, handler=self, **paramDict)
builder.start()
try:
builder.build()
finally:
builder.close()
except BuildError as e:
self.send_response(e.code)
msg = unicode(e).encode('UTF-8')
self.send_header('Content-Type', 'text/plain; charset=UTF-8')
self.send_header('Content-Length', len(msg))
self.end_headers()
self.wfile.write(msg)
except HTTPError as e:
self.send_response(e.code, str(e))
else:
self.send_response(500, 'Unknown build method "%s"' % action)
else:
self.send_response(500, 'Malformed URL')
#==============================================================================
if __name__ == '__main__':
main()
-59
View File
@@ -1,59 +0,0 @@
#!/usr/bin/env python
"""
This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
if we are not 'age_limit' tagging some porn site
A second approach implemented relies on a list of porn domains, to activate it
pass the list filename as the only argument
"""
# Allow direct execution
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_testcases
from youtube_dl.utils import compat_urllib_parse_urlparse
from youtube_dl.utils import compat_urllib_request
if len(sys.argv) > 1:
METHOD = 'LIST'
LIST = open(sys.argv[1]).read().decode('utf8').strip()
else:
METHOD = 'EURISTIC'
for test in get_testcases():
if METHOD == 'EURISTIC':
try:
webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
except:
print('\nFail: {0}'.format(test['name']))
continue
webpage = webpage.decode('utf8', 'replace')
RESULT = 'porn' in webpage.lower()
elif METHOD == 'LIST':
domain = compat_urllib_parse_urlparse(test['url']).netloc
if not domain:
print('\nFail: {0}'.format(test['name']))
continue
domain = '.'.join(domain.split('.')[-2:])
RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict']
or test['info_dict']['age_limit'] != 18):
print('\nPotential missing age_limit check: {0}'.format(test['name']))
elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict']
and test['info_dict']['age_limit'] == 18):
print('\nPotential false negative: {0}'.format(test['name']))
else:
sys.stdout.write('.')
sys.stdout.flush()
print()
-42
View File
@@ -1,42 +0,0 @@
#!/usr/bin/env python3
import json
import sys
import hashlib
import os.path
if len(sys.argv) <= 1:
print('Specify the version number as parameter')
sys.exit()
version = sys.argv[1]
with open('update/LATEST_VERSION', 'w') as f:
f.write(version)
versions_info = json.load(open('update/versions.json'))
if 'signature' in versions_info:
del versions_info['signature']
new_version = {}
filenames = {
'bin': 'youtube-dl',
'exe': 'youtube-dl.exe',
'tar': 'youtube-dl-%s.tar.gz' % version}
build_dir = os.path.join('..', '..', 'build', version)
for key, filename in filenames.items():
url = 'https://yt-dl.org/downloads/%s/%s' % (version, filename)
fn = os.path.join(build_dir, filename)
with open(fn, 'rb') as f:
data = f.read()
if not data:
raise ValueError('File %s is empty!' % fn)
sha256sum = hashlib.sha256(data).hexdigest()
new_version[key] = (url, sha256sum)
versions_info['versions'][version] = new_version
versions_info['latest'] = version
with open('update/versions.json', 'w') as jsonf:
json.dump(versions_info, jsonf, indent=4, sort_keys=True)
-32
View File
@@ -1,32 +0,0 @@
#!/usr/bin/env python3
import hashlib
import shutil
import subprocess
import tempfile
import urllib.request
import json
versions_info = json.load(open('update/versions.json'))
version = versions_info['latest']
URL = versions_info['versions'][version]['bin'][0]
data = urllib.request.urlopen(URL).read()
# Read template page
with open('download.html.in', 'r', encoding='utf-8') as tmplf:
template = tmplf.read()
md5sum = hashlib.md5(data).hexdigest()
sha1sum = hashlib.sha1(data).hexdigest()
sha256sum = hashlib.sha256(data).hexdigest()
template = template.replace('@PROGRAM_VERSION@', version)
template = template.replace('@PROGRAM_URL@', URL)
template = template.replace('@PROGRAM_MD5SUM@', md5sum)
template = template.replace('@PROGRAM_SHA1SUM@', sha1sum)
template = template.replace('@PROGRAM_SHA256SUM@', sha256sum)
template = template.replace('@EXE_URL@', versions_info['versions'][version]['exe'][0])
template = template.replace('@EXE_SHA256SUM@', versions_info['versions'][version]['exe'][1])
template = template.replace('@TAR_URL@', versions_info['versions'][version]['tar'][0])
template = template.replace('@TAR_SHA256SUM@', versions_info['versions'][version]['tar'][1])
with open('download.html', 'w', encoding='utf-8') as dlf:
dlf.write(template)
-32
View File
@@ -1,32 +0,0 @@
#!/usr/bin/env python3
import rsa
import json
from binascii import hexlify
try:
input = raw_input
except NameError:
pass
versions_info = json.load(open('update/versions.json'))
if 'signature' in versions_info:
del versions_info['signature']
print('Enter the PKCS1 private key, followed by a blank line:')
privkey = b''
while True:
try:
line = input()
except EOFError:
break
if line == '':
break
privkey += line.encode('ascii') + b'\n'
privkey = rsa.PrivateKey.load_pkcs1(privkey)
signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).encode('utf-8'), privkey, 'SHA-256')).decode()
print('signature: ' + signature)
versions_info['signature'] = signature
json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
-21
View File
@@ -1,21 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import with_statement
import datetime
import glob
import io # For Python 2 compatibilty
import os
import re
year = str(datetime.datetime.now().year)
for fn in glob.glob('*.html*'):
with io.open(fn, encoding='utf-8') as f:
content = f.read()
newc = re.sub(u'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', u'Copyright © 2006-' + year, content)
if content != newc:
tmpFn = fn + '.part'
with io.open(tmpFn, 'wt', encoding='utf-8') as outf:
outf.write(newc)
os.rename(tmpFn, fn)
-76
View File
@@ -1,76 +0,0 @@
#!/usr/bin/env python3
import datetime
import io
import json
import textwrap
atom_template = textwrap.dedent("""\
<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<link rel="self" href="http://rg3.github.io/youtube-dl/update/releases.atom" />
<title>youtube-dl releases</title>
<id>https://yt-dl.org/feed/youtube-dl-updates-feed</id>
<updated>@TIMESTAMP@</updated>
@ENTRIES@
</feed>""")
entry_template = textwrap.dedent("""
<entry>
<id>https://yt-dl.org/feed/youtube-dl-updates-feed/youtube-dl-@VERSION@</id>
<title>New version @VERSION@</title>
<link href="http://rg3.github.io/youtube-dl" />
<content type="xhtml">
<div xmlns="http://www.w3.org/1999/xhtml">
Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
</div>
</content>
<author>
<name>The youtube-dl maintainers</name>
</author>
<updated>@TIMESTAMP@</updated>
</entry>
""")
now = datetime.datetime.now()
now_iso = now.isoformat() + 'Z'
atom_template = atom_template.replace('@TIMESTAMP@', now_iso)
versions_info = json.load(open('update/versions.json'))
versions = list(versions_info['versions'].keys())
versions.sort()
entries = []
for v in versions:
fields = v.split('.')
year, month, day = map(int, fields[:3])
faked = 0
patchlevel = 0
while True:
try:
datetime.date(year, month, day)
except ValueError:
day -= 1
faked += 1
assert day > 0
continue
break
if len(fields) >= 4:
try:
patchlevel = int(fields[3])
except ValueError:
patchlevel = 1
timestamp = '%04d-%02d-%02dT00:%02d:%02dZ' % (year, month, day, faked, patchlevel)
entry = entry_template.replace('@TIMESTAMP@', timestamp)
entry = entry.replace('@VERSION@', v)
entries.append(entry)
entries_str = textwrap.indent(''.join(entries), '\t')
atom_template = atom_template.replace('@ENTRIES@', entries_str)
with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file:
atom_file.write(atom_template)
-34
View File
@@ -1,34 +0,0 @@
#!/usr/bin/env python3
import sys
import os
import textwrap
# We must be able to import youtube_dl
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
import youtube_dl
def main():
with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf:
template = tmplf.read()
ie_htmls = []
for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
ie_html = '<b>{}</b>'.format(ie.IE_NAME)
ie_desc = getattr(ie, 'IE_DESC', None)
if ie_desc is False:
continue
elif ie_desc is not None:
ie_html += ': {}'.format(ie.IE_DESC)
if ie.working() == False:
ie_html += ' (Currently broken)'
ie_htmls.append('<li>{}</li>'.format(ie_html))
template = template.replace('@SITES@', textwrap.indent('\n'.join(ie_htmls), '\t'))
with open('supportedsites.html', 'w', encoding='utf-8') as sitesf:
sitesf.write(template)
if __name__ == '__main__':
main()
-24
View File
@@ -1,24 +0,0 @@
import io
import sys
import re
README_FILE = 'README.md'
helptext = sys.stdin.read()
if isinstance(helptext, bytes):
helptext = helptext.decode('utf-8')
with io.open(README_FILE, encoding='utf-8') as f:
oldreadme = f.read()
header = oldreadme[:oldreadme.index('# OPTIONS')]
footer = oldreadme[oldreadme.index('# CONFIGURATION'):]
options = helptext[helptext.index(' General Options:') + 19:]
options = re.sub(r'^ (\w.+)$', r'## \1', options, flags=re.M)
options = '# OPTIONS\n' + options + '\n'
with io.open(README_FILE, 'w', encoding='utf-8') as f:
f.write(header)
f.write(options)
f.write(footer)
-6
View File
@@ -1,6 +0,0 @@
# source this file in your shell to get a POSIX locale (which will break many programs, but that's kind of the point)
export LC_ALL=POSIX
export LANG=POSIX
export LANGUAGE=POSIX
-103
View File
@@ -1,103 +0,0 @@
#!/bin/bash
# IMPORTANT: the following assumptions are made
# * the GH repo is on the origin remote
# * the gh-pages branch is named so locally
# * the git config user.signingkey is properly set
# You will need
# pip install coverage nose rsa
# TODO
# release notes
# make hash on local files
set -e
skip_tests=true
if [ "$1" = '--run-tests' ]; then
skip_tests=false
shift
fi
if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
version="$1"
if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi
if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
useless_files=$(find youtube_dl -type f -not -name '*.py')
if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $useless_files"; exit 1; fi
if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
/bin/echo -e "\n### First of all, testing..."
make cleanall
if $skip_tests ; then
echo 'SKIPPING TESTS'
else
nosetests --verbose --with-coverage --cover-package=youtube_dl --cover-html test --stop || exit 1
fi
/bin/echo -e "\n### Changing version in version.py..."
sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
/bin/echo -e "\n### Committing CHANGELOG README.md and youtube_dl/version.py..."
make README.md
git add CHANGELOG README.md youtube_dl/version.py
git commit -m "release $version"
/bin/echo -e "\n### Now tagging, signing and pushing..."
git tag -s -m "Release $version" "$version"
git show "$version"
read -p "Is it good, can I push? (y/n) " -n 1
if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
echo
MASTER=$(git rev-parse --abbrev-ref HEAD)
git push origin $MASTER:master
git push origin "$version"
/bin/echo -e "\n### OK, now it is time to build the binaries..."
REV=$(git rev-parse HEAD)
make youtube-dl youtube-dl.tar.gz
read -p "VM running? (y/n) " -n 1
wget "http://localhost:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
mkdir -p "build/$version"
mv youtube-dl youtube-dl.exe "build/$version"
mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz"
RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
(cd build/$version/ && md5sum $RELEASE_FILES > MD5SUMS)
(cd build/$version/ && sha1sum $RELEASE_FILES > SHA1SUMS)
(cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
(cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
git checkout HEAD -- youtube-dl youtube-dl.exe
/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
/bin/echo -e "\n### Now switching to gh-pages..."
git clone --branch gh-pages --single-branch . build/gh-pages
ROOT=$(pwd)
(
set -e
ORIGIN_URL=$(git config --get remote.origin.url)
cd build/gh-pages
"$ROOT/devscripts/gh-pages/add-version.py" $version
"$ROOT/devscripts/gh-pages/update-feed.py"
"$ROOT/devscripts/gh-pages/sign-versions.py" < "$ROOT/updates_key.pem"
"$ROOT/devscripts/gh-pages/generate-download.py"
"$ROOT/devscripts/gh-pages/update-copyright.py"
"$ROOT/devscripts/gh-pages/update-sites.py"
git add *.html *.html.in update
git commit -m "release $version"
git push "$ROOT" gh-pages
git push "$ORIGIN_URL" gh-pages
)
rm -rf build
make pypi-files
echo "Uploading to PyPi ..."
python setup.py sdist upload
make clean
/bin/echo -e "\n### DONE!"
-40
View File
@@ -1,40 +0,0 @@
#!/usr/bin/env python
import sys, os
try:
import urllib.request as compat_urllib_request
except ImportError: # Python 2
import urllib2 as compat_urllib_request
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
sys.stderr.write(u'The new location of the binaries is https://github.com/rg3/youtube-dl/downloads, not the git repository.\n\n')
try:
raw_input()
except NameError: # Python 3
input()
filename = sys.argv[0]
API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
BIN_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl"
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
try:
urlh = compat_urllib_request.urlopen(BIN_URL)
newcontent = urlh.read()
urlh.close()
except (IOError, OSError) as err:
sys.exit('ERROR: unable to download latest version')
try:
with open(filename, 'wb') as outf:
outf.write(newcontent)
except (IOError, OSError) as err:
sys.exit('ERROR: unable to overwrite current version')
sys.stderr.write(u'Done! Now you can run youtube-dl.\n')
-12
View File
@@ -1,12 +0,0 @@
from distutils.core import setup
import py2exe
py2exe_options = {
"bundle_files": 1,
"compressed": 1,
"optimize": 2,
"dist_dir": '.',
"dll_excludes": ['w9xpopen.exe']
}
setup(console=['youtube-dl.py'], options={ "py2exe": py2exe_options }, zipfile=None)
@@ -1,102 +0,0 @@
#!/usr/bin/env python
import sys, os
import urllib2
import json, hashlib
def rsa_verify(message, signature, key):
from struct import pack
from hashlib import sha256
from sys import version_info
def b(x):
if version_info[0] == 2: return x
else: return x.encode('latin1')
assert(type(message) == type(b('')))
block_size = 0
n = key[0]
while n:
block_size += 1
n >>= 8
signature = pow(int(signature, 16), key[1], key[0])
raw_bytes = []
while signature:
raw_bytes.insert(0, pack("B", signature & 0xFF))
signature >>= 8
signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
if signature[0:2] != b('\x00\x01'): return False
signature = signature[2:]
if not b('\x00') in signature: return False
signature = signature[signature.index(b('\x00'))+1:]
if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
signature = signature[19:]
if signature != sha256(message).digest(): return False
return True
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
sys.stderr.write(u'From now on, get the binaries from http://rg3.github.com/youtube-dl/download.html, not from the git repository.\n\n')
raw_input()
filename = sys.argv[0]
UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
JSON_URL = UPDATE_URL + 'versions.json'
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
exe = os.path.abspath(filename)
directory = os.path.dirname(exe)
if not os.access(directory, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % directory)
try:
versions_info = urllib2.urlopen(JSON_URL).read().decode('utf-8')
versions_info = json.loads(versions_info)
except:
sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
if not 'signature' in versions_info:
sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
signature = versions_info['signature']
del versions_info['signature']
if not rsa_verify(json.dumps(versions_info, sort_keys=True), signature, UPDATES_RSA_KEY):
sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
version = versions_info['versions'][versions_info['latest']]
try:
urlh = urllib2.urlopen(version['exe'][0])
newcontent = urlh.read()
urlh.close()
except (IOError, OSError) as err:
sys.exit('ERROR: unable to download latest version')
newcontent_hash = hashlib.sha256(newcontent).hexdigest()
if newcontent_hash != version['exe'][1]:
sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
try:
with open(exe + '.new', 'wb') as outf:
outf.write(newcontent)
except (IOError, OSError) as err:
sys.exit(u'ERROR: unable to write the new version')
try:
bat = os.path.join(directory, 'youtube-dl-updater.bat')
b = open(bat, 'w')
b.write("""
echo Updating youtube-dl...
ping 127.0.0.1 -n 5 -w 1000 > NUL
move /Y "%s.new" "%s"
del "%s"
\n""" %(exe, exe, bat))
b.close()
os.startfile(bat)
except (IOError, OSError) as err:
sys.exit('ERROR: unable to overwrite current version')
sys.stderr.write(u'Done! Now you can run youtube-dl.\n')
-56
View File
@@ -1,56 +0,0 @@
#!/bin/bash
# Run with as parameter a setup.py that works in the current directory
# e.g. no os.chdir()
# It will run twice, the first time will crash
set -e
SCRIPT_DIR="$( cd "$( dirname "$0" )" && pwd )"
if [ ! -d wine-py2exe ]; then
sudo apt-get install wine1.3 axel bsdiff
mkdir wine-py2exe
cd wine-py2exe
export WINEPREFIX=`pwd`
axel -a "http://www.python.org/ftp/python/2.7/python-2.7.msi"
axel -a "http://downloads.sourceforge.net/project/py2exe/py2exe/0.6.9/py2exe-0.6.9.win32-py2.7.exe"
#axel -a "http://winetricks.org/winetricks"
# http://appdb.winehq.org/objectManager.php?sClass=version&iId=21957
echo "Follow python setup on screen"
wine msiexec /i python-2.7.msi
echo "Follow py2exe setup on screen"
wine py2exe-0.6.9.win32-py2.7.exe
#echo "Follow Microsoft Visual C++ 2008 Redistributable Package setup on screen"
#bash winetricks vcrun2008
rm py2exe-0.6.9.win32-py2.7.exe
rm python-2.7.msi
#rm winetricks
# http://bugs.winehq.org/show_bug.cgi?id=3591
mv drive_c/Python27/Lib/site-packages/py2exe/run.exe drive_c/Python27/Lib/site-packages/py2exe/run.exe.backup
bspatch drive_c/Python27/Lib/site-packages/py2exe/run.exe.backup drive_c/Python27/Lib/site-packages/py2exe/run.exe "$SCRIPT_DIR/SizeOfImage.patch"
mv drive_c/Python27/Lib/site-packages/py2exe/run_w.exe drive_c/Python27/Lib/site-packages/py2exe/run_w.exe.backup
bspatch drive_c/Python27/Lib/site-packages/py2exe/run_w.exe.backup drive_c/Python27/Lib/site-packages/py2exe/run_w.exe "$SCRIPT_DIR/SizeOfImage_w.patch"
cd -
else
export WINEPREFIX="$( cd wine-py2exe && pwd )"
fi
wine "C:\\Python27\\python.exe" "$1" py2exe > "py2exe.log" 2>&1 || true
echo '# Copying python27.dll' >> "py2exe.log"
cp "$WINEPREFIX/drive_c/windows/system32/python27.dll" build/bdist.win32/winexe/bundle-2.7/
wine "C:\\Python27\\python.exe" "$1" py2exe >> "py2exe.log" 2>&1
+5
View File
@@ -0,0 +1,5 @@
RewriteEngine On
RewriteRule ^$ https://github.com/ytdl-org/youtube-dl/releases
RewriteRule latest(.*) /downloads/2019.03.09$1 [L,R=302]
+5
View File
@@ -0,0 +1,5 @@
RewriteEngine On
RewriteRule ^$ https://github.com/ytdl-org/youtube-dl/releases/tag/2016.06.03_tmp [R=302,L]
RewriteRule ^(.+)$ https://github.com/ytdl-org/youtube-dl/releases/download/2016.06.03_tmp/$1 [R=302,L]
+36
View File
@@ -0,0 +1,36 @@
<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-type" content="text/html;charset=UTF-8">
<title>youtube-dl</title>
<link rel="stylesheet" href="style.css" type="text/css">
</head>
<body>
<h1>youtube-dl downloads</h1>
<?php
$latest = file_get_contents('latest_version');
echo '<div class="latest">';
echo '<div><a href="latest">Latest</a> (v' . htmlspecialchars($latest) . ') downloads:</div>';
echo '<a href="downloads/latest/youtube-dl">youtube-dl</a> ';
echo '<a href="downloads/latest/youtube-dl.exe">youtube-dl.exe</a> ';
echo '<a href="downloads/latest/youtube-dl-' . htmlspecialchars($latest) . '.tar.gz">youtube-dl-' . htmlspecialchars($latest) . '.tar.gz</a>';
echo '</div>';
?>
See the right for more resources.
<table border="0" id="rgb" style="float: right;">
<tr><td><a class="button" id="main-homepage" href="http://ytdl-org.github.io/youtube-dl/">Homepage</a></td></tr>
<tr><td><a class="button" id="g" href="http://ytdl-org.github.io/youtube-dl/download.html">Download instructions</a></td></tr>
<tr><td><a class="button" id="r" href="http://ytdl-org.github.io/youtube-dl/documentation.html">Documentation</a></td></tr>
<tr><td><a class="button" id="main-support" href="https://github.com/ytdl-org/youtube-dl/issues/">Support</a></td></tr>
<tr><td><a class="button" id="y" href="https://github.com/ytdl-org/youtube-dl/">Develop</a></td></tr>
<tr><td><a class="button" id="b" href="http://ytdl-org.github.io/youtube-dl/about.html">About</a></td></tr>
</table>
</body>
</html>
+3
View File
@@ -0,0 +1,3 @@
<?php
header('Content-Type: text/plain');
echo $_SERVER['REMOTE_ADDR'];
-109
View File
@@ -1,109 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import print_function
import os.path
import pkg_resources
import warnings
import sys
try:
from setuptools import setup
setuptools_available = True
except ImportError:
from distutils.core import setup
setuptools_available = False
try:
# This will create an exe that needs Microsoft Visual C++ 2008
# Redistributable Package
import py2exe
except ImportError:
if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
print("Cannot import py2exe", file=sys.stderr)
exit(1)
py2exe_options = {
"bundle_files": 1,
"compressed": 1,
"optimize": 2,
"dist_dir": '.',
"dll_excludes": ['w9xpopen.exe'],
}
py2exe_console = [{
"script": "./youtube_dl/__main__.py",
"dest_base": "youtube-dl",
}]
py2exe_params = {
'console': py2exe_console,
'options': {"py2exe": py2exe_options},
'zipfile': None
}
if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
params = py2exe_params
else:
files_spec = [
('etc/bash_completion.d', ['youtube-dl.bash-completion']),
('share/doc/youtube_dl', ['README.txt']),
('share/man/man1', ['youtube-dl.1'])
]
root = os.path.dirname(os.path.abspath(__file__))
data_files = []
for dirname, files in files_spec:
resfiles = []
for fn in files:
if not os.path.exists(fn):
warnings.warn('Skipping file %s since it is not present. Type make to build all automatically generated files.' % fn)
else:
resfiles.append(fn)
data_files.append((dirname, resfiles))
params = {
'data_files': data_files,
}
if setuptools_available:
params['entry_points'] = {'console_scripts': ['youtube-dl = youtube_dl:main']}
else:
params['scripts'] = ['bin/youtube-dl']
# Get the version from youtube_dl/version.py without importing the package
exec(compile(open('youtube_dl/version.py').read(),
'youtube_dl/version.py', 'exec'))
setup(
name='youtube_dl',
version=__version__,
description='YouTube video downloader',
long_description='Small command-line program to download videos from'
' YouTube.com and other video sites.',
url='https://github.com/rg3/youtube-dl',
author='Ricardo Garcia',
author_email='ytdl@yt-dl.org',
maintainer='Philipp Hagemeister',
maintainer_email='phihag@phihag.de',
packages=[
'youtube_dl',
'youtube_dl.extractor', 'youtube_dl.downloader',
'youtube_dl.postprocessor'],
# Provokes warning on most systems (why?!)
# test_suite = 'nose.collector',
# test_requires = ['nosetest'],
classifiers=[
"Topic :: Multimedia :: Video",
"Development Status :: 5 - Production/Stable",
"Environment :: Console",
"License :: Public Domain",
"Programming Language :: Python :: 2.6",
"Programming Language :: Python :: 2.7",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.3"
],
**params
)
+152
View File
@@ -0,0 +1,152 @@
body {
font-family: sans-serif;
margin-left: 10%;
margin-right: 10%;
margin-top: 2ex;
margin-bottom: 3ex;
background-color: white;
color: black;
/*background-color: #fff1db;*/
background-color: white;
/*
background-image: url("gradient.png");
background-repeat: repeat-x;
*/
/*
background-image: url("gradient2.png");
background-repeat: repeat-y;
*/
/*
background-image: url("gradient3.png");
background-repeat: repeat-x;
*/
/*
background-image: url("gradient4.png");
background-repeat: repeat-y;
*/
background-image: url("gradient5.png");
background-repeat: repeat-x;
}
.heading {
border: 0;
color: black;
font-size: xx-large;
font-weight: bold;
padding-bottom: 1ex;
border-bottom: 1px solid black;
margin-bottom: 2ex;
width: 100%;
}
.heading tr {
border: 0;
}
.heading td {
border: 0;
}
.heading a {
text-decoration: none;
color: black;
}
.title {
text-align: left;
}
.subtitle {
text-align: right;
}
.toc {
padding-left: 2ex;
border: 1px solid #aaaaaa;
background-color: white;
padding-bottom: 1ex;
border-radius: 10px;
-moz-border-radius: 10px;
}
.toc ul {
margin: 0; list-style-type: none;
}
hr {
margin-top: 3ex;
margin-bottom: 3ex;
width: 50%;
}
.note {
margin-top: 10ex;
text-align: center;
font-size: x-small;
clear: both;
}
h1 {
font-size: x-large;
margin-top: 2ex;
color: black;
margin-left: 2%;
margin-right: 2%;
}
h2 {
font-size: large;
margin-left: 5%;
margin-right: 5%;
}
p {
margin-left: 5%;
margin-right: 5%;
}
ul {
margin-left: 5%;
margin-right: 5%;
}
li {
margin-left: 3%;
margin-top: 0.5ex;
margin-bottom: 0.5ex;
}
tt {
padding-left: 0.5ex;
padding-right: 0.5ex;
background: #dddddd;
}
#rgb {
width: 33%;
margin: 3ex auto;
}
.button {
color: white;
font-weight: bold;
font-size: x-large;
text-decoration: none;
text-align: center;
display: block;
padding: 2ex;
border-radius: 10px;
-moz-border-radius: 10px;
}
#r {
background-color: #884444;
border: 2px solid #880000;
}
#g {
background-color: #448844;
border: 2px solid #006600;
}
#b {
background-color: #444488;
border: 2px solid #000088;
}
#y {
background-color: #888844;
border: 2px solid #666600;
}
#main-homepage {
background-color: #848;
border: 2px solid #808;
}
#main-support {
background-color: #448888;
border: 2px solid #008888;
}
.all-versions {
float: left;
}
-85
View File
@@ -1,85 +0,0 @@
import errno
import io
import hashlib
import json
import os.path
import re
import types
import sys
import youtube_dl.extractor
from youtube_dl import YoutubeDL
from youtube_dl.utils import preferredencoding
def get_params(override=None):
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
parameters = json.load(pf)
if override:
parameters.update(override)
return parameters
def try_rm(filename):
""" Remove a file if it exists """
try:
os.remove(filename)
except OSError as ose:
if ose.errno != errno.ENOENT:
raise
def report_warning(message):
'''
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
if sys.stderr.isatty() and os.name != 'nt':
_msg_header = u'\033[0;33mWARNING:\033[0m'
else:
_msg_header = u'WARNING:'
output = u'%s %s\n' % (_msg_header, message)
if 'b' in getattr(sys.stderr, 'mode', '') or sys.version_info[0] < 3:
output = output.encode(preferredencoding())
sys.stderr.write(output)
class FakeYDL(YoutubeDL):
def __init__(self, override=None):
# Different instances of the downloader can't share the same dictionary
# some test set the "sublang" parameter, which would break the md5 checks.
params = get_params(override=override)
super(FakeYDL, self).__init__(params)
self.result = []
def to_screen(self, s, skip_eol=None):
print(s)
def trouble(self, s, tb=None):
raise Exception(s)
def download(self, x):
self.result.append(x)
def expect_warning(self, regex):
# Silence an expected warning matching a regex
old_report_warning = self.report_warning
def report_warning(self, message):
if re.match(regex, message): return
old_report_warning(message)
self.report_warning = types.MethodType(report_warning, self)
def get_testcases():
for ie in youtube_dl.extractor.gen_extractors():
t = getattr(ie, '_TEST', None)
if t:
t['name'] = type(ie).__name__[:-len('IE')]
yield t
for t in getattr(ie, '_TESTS', []):
t['name'] = type(ie).__name__[:-len('IE')]
yield t
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
-44
View File
@@ -1,44 +0,0 @@
{
"consoletitle": false,
"continuedl": true,
"forcedescription": false,
"forcefilename": false,
"forceformat": false,
"forcethumbnail": false,
"forcetitle": false,
"forceurl": false,
"format": null,
"format_limit": null,
"ignoreerrors": false,
"listformats": null,
"logtostderr": false,
"matchtitle": null,
"max_downloads": null,
"nooverwrites": false,
"nopart": false,
"noprogress": false,
"outtmpl": "%(id)s.%(ext)s",
"password": null,
"playlistend": -1,
"playliststart": 1,
"prefer_free_formats": false,
"quiet": false,
"ratelimit": null,
"rejecttitle": null,
"retries": 10,
"simulate": false,
"skip_download": false,
"subtitleslang": null,
"subtitlesformat": "srt",
"test": true,
"updatetime": true,
"usenetrc": false,
"username": null,
"verbose": true,
"writedescription": false,
"writeinfojson": true,
"writesubtitles": false,
"allsubtitles": false,
"listssubtitles": false,
"socket_timeout": 20
}
-249
View File
@@ -1,249 +0,0 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from youtube_dl import YoutubeDL
from youtube_dl.extractor import YoutubeIE
class YDL(FakeYDL):
def __init__(self, *args, **kwargs):
super(YDL, self).__init__(*args, **kwargs)
self.downloaded_info_dicts = []
self.msgs = []
def process_info(self, info_dict):
self.downloaded_info_dicts.append(info_dict)
def to_screen(self, msg):
self.msgs.append(msg)
class TestFormatSelection(unittest.TestCase):
def test_prefer_free_formats(self):
# Same resolution => download webm
ydl = YDL()
ydl.params['prefer_free_formats'] = True
formats = [
{'ext': 'webm', 'height': 460},
{'ext': 'mp4', 'height': 460},
]
info_dict = {'formats': formats, 'extractor': 'test'}
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['ext'], 'webm')
# Different resolution => download best quality (mp4)
ydl = YDL()
ydl.params['prefer_free_formats'] = True
formats = [
{'ext': 'webm', 'height': 720},
{'ext': 'mp4', 'height': 1080},
]
info_dict['formats'] = formats
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['ext'], 'mp4')
# No prefer_free_formats => prefer mp4 and flv for greater compatibilty
ydl = YDL()
ydl.params['prefer_free_formats'] = False
formats = [
{'ext': 'webm', 'height': 720},
{'ext': 'mp4', 'height': 720},
{'ext': 'flv', 'height': 720},
]
info_dict['formats'] = formats
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['ext'], 'mp4')
ydl = YDL()
ydl.params['prefer_free_formats'] = False
formats = [
{'ext': 'flv', 'height': 720},
{'ext': 'webm', 'height': 720},
]
info_dict['formats'] = formats
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['ext'], 'flv')
def test_format_limit(self):
formats = [
{'format_id': 'meh', 'url': 'http://example.com/meh', 'preference': 1},
{'format_id': 'good', 'url': 'http://example.com/good', 'preference': 2},
{'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
{'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
]
info_dict = {
'formats': formats, 'extractor': 'test', 'id': 'testvid'}
ydl = YDL()
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'excellent')
ydl = YDL({'format_limit': 'good'})
assert ydl.params['format_limit'] == 'good'
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'good')
ydl = YDL({'format_limit': 'great', 'format': 'all'})
ydl.process_ie_result(info_dict.copy())
self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'meh')
self.assertEqual(ydl.downloaded_info_dicts[1]['format_id'], 'good')
self.assertEqual(ydl.downloaded_info_dicts[2]['format_id'], 'great')
self.assertTrue('3' in ydl.msgs[0])
ydl = YDL()
ydl.params['format_limit'] = 'excellent'
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'excellent')
def test_format_selection(self):
formats = [
{'format_id': '35', 'ext': 'mp4', 'preference': 1},
{'format_id': '45', 'ext': 'webm', 'preference': 2},
{'format_id': '47', 'ext': 'webm', 'preference': 3},
{'format_id': '2', 'ext': 'flv', 'preference': 4},
]
info_dict = {'formats': formats, 'extractor': 'test'}
ydl = YDL({'format': '20/47'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], '47')
ydl = YDL({'format': '20/71/worst'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], '35')
ydl = YDL()
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], '2')
ydl = YDL({'format': 'webm/mp4'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], '47')
ydl = YDL({'format': '3gp/40/mp4'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], '35')
def test_format_selection_audio(self):
formats = [
{'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none'},
{'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none'},
{'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none'},
{'format_id': 'vid', 'ext': 'mp4', 'preference': 4},
]
info_dict = {'formats': formats, 'extractor': 'test'}
ydl = YDL({'format': 'bestaudio'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'audio-high')
ydl = YDL({'format': 'worstaudio'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'audio-low')
formats = [
{'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1},
{'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2},
]
info_dict = {'formats': formats, 'extractor': 'test'}
ydl = YDL({'format': 'bestaudio/worstaudio/best'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'vid-high')
def test_youtube_format_selection(self):
order = [
'38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',
# Apple HTTP Live Streaming
'96', '95', '94', '93', '92', '132', '151',
# 3D
'85', '84', '102', '83', '101', '82', '100',
# Dash video
'138', '137', '248', '136', '247', '135', '246',
'245', '244', '134', '243', '133', '242', '160',
# Dash audio
'141', '172', '140', '139', '171',
]
for f1id, f2id in zip(order, order[1:]):
f1 = YoutubeIE._formats[f1id].copy()
f1['format_id'] = f1id
f2 = YoutubeIE._formats[f2id].copy()
f2['format_id'] = f2id
info_dict = {'formats': [f1, f2], 'extractor': 'youtube'}
ydl = YDL()
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], f1id)
info_dict = {'formats': [f2, f1], 'extractor': 'youtube'}
ydl = YDL()
yie = YoutubeIE(ydl)
yie._sort_formats(info_dict['formats'])
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], f1id)
def test_add_extra_info(self):
test_dict = {
'extractor': 'Foo',
}
extra_info = {
'extractor': 'Bar',
'playlist': 'funny videos',
}
YDL.add_extra_info(test_dict, extra_info)
self.assertEqual(test_dict['extractor'], 'Foo')
self.assertEqual(test_dict['playlist'], 'funny videos')
def test_prepare_filename(self):
info = {
'id': '1234',
'ext': 'mp4',
'width': None,
}
def fname(templ):
ydl = YoutubeDL({'outtmpl': templ})
return ydl.prepare_filename(info)
self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
# Replace missing fields with 'NA'
self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
if __name__ == '__main__':
unittest.main()
-54
View File
@@ -1,54 +0,0 @@
#!/usr/bin/env python
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import try_rm
from youtube_dl import YoutubeDL
def _download_restricted(url, filename, age):
""" Returns true iff the file has been downloaded """
params = {
'age_limit': age,
'skip_download': True,
'writeinfojson': True,
"outtmpl": "%(id)s.%(ext)s",
}
ydl = YoutubeDL(params)
ydl.add_default_info_extractors()
json_filename = os.path.splitext(filename)[0] + '.info.json'
try_rm(json_filename)
ydl.download([url])
res = os.path.exists(json_filename)
try_rm(json_filename)
return res
class TestAgeRestriction(unittest.TestCase):
def _assert_restricted(self, url, filename, age, old_age=None):
self.assertTrue(_download_restricted(url, filename, old_age))
self.assertFalse(_download_restricted(url, filename, age))
def test_youtube(self):
self._assert_restricted('07FYdnEawAQ', '07FYdnEawAQ.mp4', 10)
def test_youporn(self):
self._assert_restricted(
'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'505835.mp4', 2, old_age=25)
def test_pornotube(self):
self._assert_restricted(
'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
'1689755.flv', 13)
if __name__ == '__main__':
unittest.main()
-144
View File
@@ -1,144 +0,0 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_testcases
from youtube_dl.extractor import (
FacebookIE,
gen_extractors,
JustinTVIE,
PBSIE,
YoutubeIE,
)
class TestAllURLsMatching(unittest.TestCase):
def setUp(self):
self.ies = gen_extractors()
def matching_ies(self, url):
return [ie.IE_NAME for ie in self.ies if ie.suitable(url) and ie.IE_NAME != 'generic']
def assertMatch(self, url, ie_list):
self.assertEqual(self.matching_ies(url), ie_list)
def test_youtube_playlist_matching(self):
assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') #585
assertPlaylist('PL63F0C78739B09958')
assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
# Top tracks
assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
def test_youtube_matching(self):
self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
def test_youtube_channel_matching(self):
assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
def test_youtube_user_matching(self):
self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
def test_youtube_feeds(self):
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
def test_youtube_show_matching(self):
self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
def test_youtube_truncated(self):
self.assertMatch('http://www.youtube.com/watch?', ['youtube:truncated_url'])
def test_youtube_search_matching(self):
self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
def test_justin_tv_channelid_matching(self):
self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
self.assertTrue(JustinTVIE.suitable(u"www.justin.tv/vanillatv"))
self.assertTrue(JustinTVIE.suitable(u"www.twitch.tv/vanillatv"))
self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv"))
self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv"))
self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv/"))
self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/"))
def test_justintv_videoid_matching(self):
self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/b/328087483"))
def test_justin_tv_chapterid_matching(self):
self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
def test_youtube_extract(self):
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
def test_facebook_matching(self):
self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
def test_no_duplicates(self):
ies = gen_extractors()
for tc in get_testcases():
url = tc['url']
for ie in ies:
if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
else:
self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
def test_keywords(self):
self.assertMatch(':ytsubs', ['youtube:subscriptions'])
self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
self.assertMatch(':ythistory', ['youtube:history'])
self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
self.assertMatch(':tds', ['ComedyCentralShows'])
self.assertMatch(':colbertreport', ['ComedyCentralShows'])
self.assertMatch(':cr', ['ComedyCentralShows'])
def test_vimeo_matching(self):
self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
# https://github.com/rg3/youtube-dl/issues/1930
def test_soundcloud_not_matching_sets(self):
self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
def test_tumblr(self):
self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
def test_pbs(self):
# https://github.com/rg3/youtube-dl/issues/2350
self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
if __name__ == '__main__':
unittest.main()
-187
View File
@@ -1,187 +0,0 @@
#!/usr/bin/env python
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import (
get_params,
get_testcases,
try_rm,
md5,
report_warning
)
import hashlib
import io
import json
import re
import socket
import youtube_dl.YoutubeDL
from youtube_dl.utils import (
compat_http_client,
compat_str,
compat_urllib_error,
compat_HTTPError,
DownloadError,
ExtractorError,
UnavailableVideoError,
)
from youtube_dl.extractor import get_info_extractor
RETRIES = 3
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
self.to_stderr = self.to_screen
self.processed_info_dicts = []
super(YoutubeDL, self).__init__(*args, **kwargs)
def report_warning(self, message):
# Don't accept warnings during tests
raise ExtractorError(message)
def process_info(self, info_dict):
self.processed_info_dicts.append(info_dict)
return super(YoutubeDL, self).process_info(info_dict)
def _file_md5(fn):
with open(fn, 'rb') as f:
return hashlib.md5(f.read()).hexdigest()
defs = get_testcases()
class TestDownload(unittest.TestCase):
maxDiff = None
def setUp(self):
self.defs = defs
### Dynamically generate tests
def generator(test_case):
def test_template(self):
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
def print_skipping(reason):
print('Skipping %s: %s' % (test_case['name'], reason))
if not ie.working():
print_skipping('IE marked as not _WORKING')
return
if 'playlist' not in test_case:
info_dict = test_case.get('info_dict', {})
if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
if 'skip' in test_case:
print_skipping(test_case['skip'])
return
for other_ie in other_ies:
if not other_ie.working():
print_skipping(u'test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
return
params = get_params(test_case.get('params', {}))
ydl = YoutubeDL(params)
ydl.add_default_info_extractors()
finished_hook_called = set()
def _hook(status):
if status['status'] == 'finished':
finished_hook_called.add(status['filename'])
ydl.add_progress_hook(_hook)
def get_tc_filename(tc):
return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
test_cases = test_case.get('playlist', [test_case])
def try_rm_tcs_files():
for tc in test_cases:
tc_filename = get_tc_filename(tc)
try_rm(tc_filename)
try_rm(tc_filename + '.part')
try_rm(os.path.splitext(tc_filename)[0] + '.info.json')
try_rm_tcs_files()
try:
try_num = 1
while True:
try:
ydl.download([test_case['url']])
except (DownloadError, ExtractorError) as err:
# Check if the exception is not a network related one
if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
raise
if try_num == RETRIES:
report_warning(u'Failed due to network errors, skipping...')
return
print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num))
try_num += 1
else:
break
for tc in test_cases:
tc_filename = get_tc_filename(tc)
if not test_case.get('params', {}).get('skip_download', False):
self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
self.assertTrue(tc_filename in finished_hook_called)
info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
self.assertTrue(os.path.exists(info_json_fn))
if 'md5' in tc:
md5_for_file = _file_md5(tc_filename)
self.assertEqual(md5_for_file, tc['md5'])
with io.open(info_json_fn, encoding='utf-8') as infof:
info_dict = json.load(infof)
for (info_field, expected) in tc.get('info_dict', {}).items():
if isinstance(expected, compat_str) and expected.startswith('re:'):
got = info_dict.get(info_field)
match_str = expected[len('re:'):]
match_rex = re.compile(match_str)
self.assertTrue(
isinstance(got, compat_str) and match_rex.match(got),
u'field %s (value: %r) should match %r' % (info_field, got, match_str))
else:
if isinstance(expected, compat_str) and expected.startswith('md5:'):
got = 'md5:' + md5(info_dict.get(info_field))
else:
got = info_dict.get(info_field)
self.assertEqual(expected, got,
u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
# If checkable fields are missing from the test case, print the info_dict
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
for key, value in info_dict.items()
if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location'))
if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()):
sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n')
# Check for the presence of mandatory fields
for key in ('id', 'url', 'title', 'ext'):
self.assertTrue(key in info_dict.keys() and info_dict[key])
# Check for mandatory fields that are automatically set by YoutubeDL
for key in ['webpage_url', 'extractor', 'extractor_key']:
self.assertTrue(info_dict.get(key), u'Missing field: %s' % key)
finally:
try_rm_tcs_files()
return test_template
### And add them to TestDownload
for n, test_case in enumerate(defs):
test_method = generator(test_case)
tname = 'test_' + str(test_case['name'])
i = 1
while hasattr(TestDownload, tname):
tname = 'test_' + str(test_case['name']) + '_' + str(i)
i += 1
test_method.__name__ = tname
setattr(TestDownload, test_method.__name__, test_method)
del test_method
if __name__ == '__main__':
unittest.main()
-26
View File
@@ -1,26 +0,0 @@
import unittest
import sys
import os
import subprocess
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
try:
_DEV_NULL = subprocess.DEVNULL
except AttributeError:
_DEV_NULL = open(os.devnull, 'wb')
class TestExecution(unittest.TestCase):
def test_import(self):
subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir)
def test_module_exec(self):
if sys.version_info >= (2,7): # Python 2.6 doesn't support package execution
subprocess.check_call([sys.executable, '-m', 'youtube_dl', '--version'], cwd=rootDir, stdout=_DEV_NULL)
def test_main_exec(self):
subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
if __name__ == '__main__':
unittest.main()
-273
View File
@@ -1,273 +0,0 @@
#!/usr/bin/env python
# encoding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from youtube_dl.extractor import (
AcademicEarthCourseIE,
DailymotionPlaylistIE,
DailymotionUserIE,
VimeoChannelIE,
VimeoUserIE,
VimeoAlbumIE,
VimeoGroupsIE,
UstreamChannelIE,
SoundcloudSetIE,
SoundcloudUserIE,
LivestreamIE,
NHLVideocenterIE,
BambuserChannelIE,
BandcampAlbumIE,
SmotriCommunityIE,
SmotriUserIE,
IviCompilationIE,
ImdbListIE,
KhanAcademyIE,
EveryonesMixtapeIE,
RutubeChannelIE,
GoogleSearchIE,
GenericIE,
TEDIE,
)
class TestPlaylists(unittest.TestCase):
def assertIsPlaylist(self, info):
"""Make sure the info has '_type' set to 'playlist'"""
self.assertEqual(info['_type'], 'playlist')
def test_dailymotion_playlist(self):
dl = FakeYDL()
ie = DailymotionPlaylistIE(dl)
result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'SPORT')
self.assertTrue(len(result['entries']) > 20)
def test_dailymotion_user(self):
dl = FakeYDL()
ie = DailymotionUserIE(dl)
result = ie.extract('https://www.dailymotion.com/user/nqtv')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'Rémi Gaillard')
self.assertTrue(len(result['entries']) >= 100)
def test_vimeo_channel(self):
dl = FakeYDL()
ie = VimeoChannelIE(dl)
result = ie.extract('http://vimeo.com/channels/tributes')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'Vimeo Tributes')
self.assertTrue(len(result['entries']) > 24)
def test_vimeo_user(self):
dl = FakeYDL()
ie = VimeoUserIE(dl)
result = ie.extract('http://vimeo.com/nkistudio/videos')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'Nki')
self.assertTrue(len(result['entries']) > 65)
def test_vimeo_album(self):
dl = FakeYDL()
ie = VimeoAlbumIE(dl)
result = ie.extract('http://vimeo.com/album/2632481')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'Staff Favorites: November 2013')
self.assertTrue(len(result['entries']) > 12)
def test_vimeo_groups(self):
dl = FakeYDL()
ie = VimeoGroupsIE(dl)
result = ie.extract('http://vimeo.com/groups/rolexawards')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'Rolex Awards for Enterprise')
self.assertTrue(len(result['entries']) > 72)
def test_ustream_channel(self):
dl = FakeYDL()
ie = UstreamChannelIE(dl)
result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], '5124905')
self.assertTrue(len(result['entries']) >= 11)
def test_soundcloud_set(self):
dl = FakeYDL()
ie = SoundcloudSetIE(dl)
result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'The Royal Concept EP')
self.assertTrue(len(result['entries']) >= 6)
def test_soundcloud_user(self):
dl = FakeYDL()
ie = SoundcloudUserIE(dl)
result = ie.extract('https://soundcloud.com/the-concept-band')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], '9615865')
self.assertTrue(len(result['entries']) >= 12)
def test_livestream_event(self):
dl = FakeYDL()
ie = LivestreamIE(dl)
result = ie.extract('http://new.livestream.com/tedx/cityenglish')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'TEDCity2.0 (English)')
self.assertTrue(len(result['entries']) >= 4)
def test_nhl_videocenter(self):
dl = FakeYDL()
ie = NHLVideocenterIE(dl)
result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], '999')
self.assertEqual(result['title'], 'Highlights')
self.assertEqual(len(result['entries']), 12)
def test_bambuser_channel(self):
dl = FakeYDL()
ie = BambuserChannelIE(dl)
result = ie.extract('http://bambuser.com/channel/pixelversity')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'pixelversity')
self.assertTrue(len(result['entries']) >= 60)
def test_bandcamp_album(self):
dl = FakeYDL()
ie = BandcampAlbumIE(dl)
result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'Nightmare Night EP')
self.assertTrue(len(result['entries']) >= 4)
def test_smotri_community(self):
dl = FakeYDL()
ie = SmotriCommunityIE(dl)
result = ie.extract('http://smotri.com/community/video/kommuna')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'kommuna')
self.assertEqual(result['title'], 'КПРФ')
self.assertTrue(len(result['entries']) >= 4)
def test_smotri_user(self):
dl = FakeYDL()
ie = SmotriUserIE(dl)
result = ie.extract('http://smotri.com/user/inspector')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'inspector')
self.assertEqual(result['title'], 'Inspector')
self.assertTrue(len(result['entries']) >= 9)
def test_AcademicEarthCourse(self):
dl = FakeYDL()
ie = AcademicEarthCourseIE(dl)
result = ie.extract('http://academicearth.org/playlists/laws-of-nature/')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'laws-of-nature')
self.assertEqual(result['title'], 'Laws of Nature')
self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
self.assertEqual(len(result['entries']), 4)
def test_ivi_compilation(self):
dl = FakeYDL()
ie = IviCompilationIE(dl)
result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'dezhurnyi_angel')
self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012)')
self.assertTrue(len(result['entries']) >= 36)
def test_ivi_compilation_season(self):
dl = FakeYDL()
ie = IviCompilationIE(dl)
result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'dezhurnyi_angel/season2')
self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012) 2 сезон')
self.assertTrue(len(result['entries']) >= 20)
def test_imdb_list(self):
dl = FakeYDL()
ie = ImdbListIE(dl)
result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'JFs9NWw6XI0')
self.assertEqual(result['title'], 'March 23, 2012 Releases')
self.assertEqual(len(result['entries']), 7)
def test_khanacademy_topic(self):
dl = FakeYDL()
ie = KhanAcademyIE(dl)
result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'cryptography')
self.assertEqual(result['title'], 'Journey into cryptography')
self.assertEqual(result['description'], 'How have humans protected their secret messages through history? What has changed today?')
self.assertTrue(len(result['entries']) >= 3)
def test_EveryonesMixtape(self):
dl = FakeYDL()
ie = EveryonesMixtapeIE(dl)
result = ie.extract('http://everyonesmixtape.com/#/mix/m7m0jJAbMQi')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'm7m0jJAbMQi')
self.assertEqual(result['title'], 'Driving')
self.assertEqual(len(result['entries']), 24)
def test_rutube_channel(self):
dl = FakeYDL()
ie = RutubeChannelIE(dl)
result = ie.extract('http://rutube.ru/tags/video/1409')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], '1409')
self.assertTrue(len(result['entries']) >= 34)
def test_multiple_brightcove_videos(self):
# https://github.com/rg3/youtube-dl/issues/2283
dl = FakeYDL()
ie = GenericIE(dl)
result = ie.extract('http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'always-never-nuclear-command-and-control')
self.assertEqual(result['title'], 'Always/Never: A Little-Seen Movie About Nuclear Command and Control : The New Yorker')
self.assertEqual(len(result['entries']), 3)
def test_GoogleSearch(self):
dl = FakeYDL()
ie = GoogleSearchIE(dl)
result = ie.extract('gvsearch15:python language')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'python language')
self.assertEqual(result['title'], 'python language')
self.assertTrue(len(result['entries']) == 15)
def test_generic_rss_feed(self):
dl = FakeYDL()
ie = GenericIE(dl)
result = ie.extract('http://www.escapistmagazine.com/rss/videos/list/1.xml')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'http://www.escapistmagazine.com/rss/videos/list/1.xml')
self.assertEqual(result['title'], 'Zero Punctuation')
self.assertTrue(len(result['entries']) > 10)
def test_ted_playlist(self):
dl = FakeYDL()
ie = TEDIE(dl)
result = ie.extract('http://www.ted.com/playlists/who_are_the_hackers')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], '10')
self.assertEqual(result['title'], 'Who are the hackers?')
self.assertTrue(len(result['entries']) >= 6)
if __name__ == '__main__':
unittest.main()
-283
View File
@@ -1,283 +0,0 @@
#!/usr/bin/env python
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL, md5
from youtube_dl.extractor import (
BlipTVIE,
YoutubeIE,
DailymotionIE,
TEDIE,
VimeoIE,
)
class BaseTestSubtitles(unittest.TestCase):
url = None
IE = None
def setUp(self):
self.DL = FakeYDL()
self.ie = self.IE(self.DL)
def getInfoDict(self):
info_dict = self.ie.extract(self.url)
return info_dict
def getSubtitles(self):
info_dict = self.getInfoDict()
return info_dict['subtitles']
class TestYoutubeSubtitles(BaseTestSubtitles):
url = 'QRS8MkLhQmM'
IE = YoutubeIE
def test_youtube_no_writesubtitles(self):
self.DL.params['writesubtitles'] = False
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_youtube_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
def test_youtube_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
def test_youtube_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 13)
def test_youtube_subtitles_sbv_format(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitlesformat'] = 'sbv'
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
def test_youtube_subtitles_vtt_format(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitlesformat'] = 'vtt'
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
def test_youtube_list_subtitles(self):
self.DL.expect_warning(u'Video doesn\'t have automatic captions')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_youtube_automatic_captions(self):
self.url = '8YoUxe5ncPo'
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertTrue(subtitles['it'] is not None)
def test_youtube_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.url = 'sAjKT8FhjI8'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
def test_youtube_multiple_langs(self):
self.url = 'QRS8MkLhQmM'
self.DL.params['writesubtitles'] = True
langs = ['it', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
class TestDailymotionSubtitles(BaseTestSubtitles):
url = 'http://www.dailymotion.com/video/xczg00'
IE = DailymotionIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 5)
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
class TestTedSubtitles(BaseTestSubtitles):
url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
IE = TEDIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 28)
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
class TestBlipTVSubtitles(BaseTestSubtitles):
url = 'http://blip.tv/a/a-6603250'
IE = BlipTVIE
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4')
class TestVimeoSubtitles(BaseTestSubtitles):
url = 'http://vimeo.com/76979871'
IE = VimeoIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.url = 'http://vimeo.com/56015672'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
if __name__ == '__main__':
unittest.main()
-47
View File
@@ -1,47 +0,0 @@
from __future__ import unicode_literals
import io
import os
import re
import unittest
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
IGNORED_FILES = [
'setup.py', # http://bugs.python.org/issue13943
]
class TestUnicodeLiterals(unittest.TestCase):
def test_all_files(self):
print('Skipping this test (not yet fully implemented)')
return
for dirpath, _, filenames in os.walk(rootDir):
for basename in filenames:
if not basename.endswith('.py'):
continue
if basename in IGNORED_FILES:
continue
fn = os.path.join(dirpath, basename)
with io.open(fn, encoding='utf-8') as inf:
code = inf.read()
if "'" not in code and '"' not in code:
continue
imps = 'from __future__ import unicode_literals'
self.assertTrue(
imps in code,
' %s missing in %s' % (imps, fn))
m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code)
if m is not None:
self.assertTrue(
m is None,
'u present in %s, around %s' % (
fn, code[m.start() - 10:m.end() + 10]))
if __name__ == '__main__':
unittest.main()
-265
View File
@@ -1,265 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
# Various small unit tests
import io
import xml.etree.ElementTree
#from youtube_dl.utils import htmlentity_transform
from youtube_dl.utils import (
DateRange,
encodeFilename,
find_xpath_attr,
fix_xml_ampersands,
get_meta_content,
orderedSet,
PagedList,
parse_duration,
read_batch_urls,
sanitize_filename,
shell_quote,
smuggle_url,
str_to_int,
struct_unpack,
timeconvert,
unescapeHTML,
unified_strdate,
unsmuggle_url,
url_basename,
xpath_with_ns,
)
if sys.version_info < (3, 0):
_compat_str = lambda b: b.decode('unicode-escape')
else:
_compat_str = lambda s: s
class TestUtil(unittest.TestCase):
def test_timeconvert(self):
self.assertTrue(timeconvert('') is None)
self.assertTrue(timeconvert('bougrg') is None)
def test_sanitize_filename(self):
self.assertEqual(sanitize_filename('abc'), 'abc')
self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
self.assertEqual(sanitize_filename('123'), '123')
self.assertEqual('abc_de', sanitize_filename('abc/de'))
self.assertFalse('/' in sanitize_filename('abc/de///'))
self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
self.assertEqual('yes no', sanitize_filename('yes? no'))
self.assertEqual('this - that', sanitize_filename('this: that'))
self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
aumlaut = _compat_str('\xe4')
self.assertEqual(sanitize_filename(aumlaut), aumlaut)
tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
self.assertEqual(sanitize_filename(tests), tests)
forbidden = '"\0\\/'
for fc in forbidden:
for fbc in forbidden:
self.assertTrue(fbc not in sanitize_filename(fc))
def test_sanitize_filename_restricted(self):
self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
self.assertEqual(sanitize_filename('123', restricted=True), '123')
self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename
forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
for fc in forbidden:
for fbc in forbidden:
self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
# Handle a common case more neatly
self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
# .. but make sure the file name is never empty
self.assertTrue(sanitize_filename('-', restricted=True) != '')
self.assertTrue(sanitize_filename(':', restricted=True) != '')
def test_sanitize_ids(self):
self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
def test_ordered_set(self):
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
self.assertEqual(orderedSet([]), [])
self.assertEqual(orderedSet([1]), [1])
#keep the list ordered
self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
def test_unescape_html(self):
self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
def test_daterange(self):
_20century = DateRange("19000101","20000101")
self.assertFalse("17890714" in _20century)
_ac = DateRange("00010101")
self.assertTrue("19690721" in _ac)
_firstmilenium = DateRange(end="10000101")
self.assertTrue("07110427" in _firstmilenium)
def test_unified_dates(self):
self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
self.assertEqual(unified_strdate('8/7/2009'), '20090708')
self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
self.assertEqual(unified_strdate('1968-12-10'), '19681210')
def test_find_xpath_attr(self):
testxml = u'''<root>
<node/>
<node x="a"/>
<node x="a" y="c" />
<node x="b" y="d" />
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
def test_meta_parser(self):
testhtml = u'''
<head>
<meta name="description" content="foo &amp; bar">
<meta content='Plato' name='author'/>
</head>
'''
get_meta = lambda name: get_meta_content(name, testhtml)
self.assertEqual(get_meta('description'), u'foo & bar')
self.assertEqual(get_meta('author'), 'Plato')
def test_xpath_with_ns(self):
testxml = u'''<root xmlns:media="http://example.com/">
<media:song>
<media:author>The Author</media:author>
<url>http://server.com/download.mp3</url>
</media:song>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
self.assertTrue(find('media:song') is not None)
self.assertEqual(find('media:song/media:author').text, u'The Author')
self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
def test_smuggle_url(self):
data = {u"ö": u"ö", u"abc": [3]}
url = 'https://foo.bar/baz?x=y#a'
smug_url = smuggle_url(url, data)
unsmug_url, unsmug_data = unsmuggle_url(smug_url)
self.assertEqual(url, unsmug_url)
self.assertEqual(data, unsmug_data)
res_url, res_data = unsmuggle_url(url)
self.assertEqual(res_url, url)
self.assertEqual(res_data, None)
def test_shell_quote(self):
args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
def test_str_to_int(self):
self.assertEqual(str_to_int('123,456'), 123456)
self.assertEqual(str_to_int('123.456'), 123456)
def test_url_basename(self):
self.assertEqual(url_basename(u'http://foo.de/'), u'')
self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz')
self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz')
self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz')
self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
self.assertEqual(
url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
u'trailer.mp4')
def test_parse_duration(self):
self.assertEqual(parse_duration(None), None)
self.assertEqual(parse_duration('1'), 1)
self.assertEqual(parse_duration('1337:12'), 80232)
self.assertEqual(parse_duration('9:12:43'), 33163)
self.assertEqual(parse_duration('12:00'), 720)
self.assertEqual(parse_duration('00:01:01'), 61)
self.assertEqual(parse_duration('x:y'), None)
self.assertEqual(parse_duration('3h11m53s'), 11513)
self.assertEqual(parse_duration('62m45s'), 3765)
self.assertEqual(parse_duration('6m59s'), 419)
self.assertEqual(parse_duration('49s'), 49)
self.assertEqual(parse_duration('0h0m0s'), 0)
self.assertEqual(parse_duration('0m0s'), 0)
self.assertEqual(parse_duration('0s'), 0)
def test_fix_xml_ampersands(self):
self.assertEqual(
fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
self.assertEqual(
fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
'"&amp;x=y&amp;wrong;&amp;z=a')
self.assertEqual(
fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
'&amp;&apos;&gt;&lt;&quot;')
self.assertEqual(
fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
def test_paged_list(self):
def testPL(size, pagesize, sliceargs, expected):
def get_page(pagenum):
firstid = pagenum * pagesize
upto = min(size, pagenum * pagesize + pagesize)
for i in range(firstid, upto):
yield i
pl = PagedList(get_page, pagesize)
got = pl.getslice(*sliceargs)
self.assertEqual(got, expected)
testPL(5, 2, (), [0, 1, 2, 3, 4])
testPL(5, 2, (1,), [1, 2, 3, 4])
testPL(5, 2, (2,), [2, 3, 4])
testPL(5, 2, (4,), [4])
testPL(5, 2, (0, 3), [0, 1, 2])
testPL(5, 2, (1, 4), [1, 2, 3])
testPL(5, 2, (2, 99), [2, 3, 4])
testPL(5, 2, (20, 99), [])
def test_struct_unpack(self):
self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
def test_read_batch_urls(self):
f = io.StringIO(u'''\xef\xbb\xbf foo
bar\r
baz
# More after this line\r
; or after this
bam''')
self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
if __name__ == '__main__':
unittest.main()
-79
View File
@@ -1,79 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_params, try_rm
import io
import xml.etree.ElementTree
import youtube_dl.YoutubeDL
import youtube_dl.extractor
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
super(YoutubeDL, self).__init__(*args, **kwargs)
self.to_stderr = self.to_screen
params = get_params({
'writeannotations': True,
'skip_download': True,
'writeinfojson': False,
'format': 'flv',
})
TEST_ID = 'gr51aVj-mLg'
ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
class TestAnnotations(unittest.TestCase):
def setUp(self):
# Clear old files
self.tearDown()
def test_info_json(self):
expected = list(EXPECTED_ANNOTATIONS) #Two annotations could have the same text.
ie = youtube_dl.extractor.YoutubeIE()
ydl = YoutubeDL(params)
ydl.add_info_extractor(ie)
ydl.download([TEST_ID])
self.assertTrue(os.path.exists(ANNOTATIONS_FILE))
annoxml = None
with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
annoxml = xml.etree.ElementTree.parse(annof)
self.assertTrue(annoxml is not None, 'Failed to parse annotations XML')
root = annoxml.getroot()
self.assertEqual(root.tag, 'document')
annotationsTag = root.find('annotations')
self.assertEqual(annotationsTag.tag, 'annotations')
annotations = annotationsTag.findall('annotation')
#Not all the annotations have TEXT children and the annotations are returned unsorted.
for a in annotations:
self.assertEqual(a.tag, 'annotation')
if a.get('type') == 'text':
textTag = a.find('TEXT')
text = textTag.text
self.assertTrue(text in expected) #assertIn only added in python 2.7
#remove the first occurance, there could be more than one annotation with the same text
expected.remove(text)
#We should have seen (and removed) all the expected annotation texts.
self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')
def tearDown(self):
try_rm(ANNOTATIONS_FILE)
if __name__ == '__main__':
unittest.main()
-75
View File
@@ -1,75 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_params
import io
import json
import youtube_dl.YoutubeDL
import youtube_dl.extractor
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
super(YoutubeDL, self).__init__(*args, **kwargs)
self.to_stderr = self.to_screen
params = get_params({
'writeinfojson': True,
'skip_download': True,
'writedescription': True,
})
TEST_ID = 'BaW_jenozKc'
INFO_JSON_FILE = TEST_ID + '.info.json'
DESCRIPTION_FILE = TEST_ID + '.mp4.description'
EXPECTED_DESCRIPTION = u'''test chars: "'/\ä↭𝕐
test URL: https://github.com/rg3/youtube-dl/issues/1892
This is a test video for youtube-dl.
For more information, contact phihag@phihag.de .'''
class TestInfoJSON(unittest.TestCase):
def setUp(self):
# Clear old files
self.tearDown()
def test_info_json(self):
ie = youtube_dl.extractor.YoutubeIE()
ydl = YoutubeDL(params)
ydl.add_info_extractor(ie)
ydl.download([TEST_ID])
self.assertTrue(os.path.exists(INFO_JSON_FILE))
with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf:
jd = json.load(jsonf)
self.assertEqual(jd['upload_date'], u'20121002')
self.assertEqual(jd['description'], EXPECTED_DESCRIPTION)
self.assertEqual(jd['id'], TEST_ID)
self.assertEqual(jd['extractor'], 'youtube')
self.assertEqual(jd['title'], u'''youtube-dl test video "'/\ä↭𝕐''')
self.assertEqual(jd['uploader'], 'Philipp Hagemeister')
self.assertTrue(os.path.exists(DESCRIPTION_FILE))
with io.open(DESCRIPTION_FILE, 'r', encoding='utf-8') as descf:
descr = descf.read()
self.assertEqual(descr, EXPECTED_DESCRIPTION)
def tearDown(self):
if os.path.exists(INFO_JSON_FILE):
os.remove(INFO_JSON_FILE)
if os.path.exists(DESCRIPTION_FILE):
os.remove(DESCRIPTION_FILE)
if __name__ == '__main__':
unittest.main()
-147
View File
@@ -1,147 +0,0 @@
#!/usr/bin/env python
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from youtube_dl.extractor import (
YoutubeUserIE,
YoutubePlaylistIE,
YoutubeIE,
YoutubeChannelIE,
YoutubeShowIE,
YoutubeTopListIE,
YoutubeSearchURLIE,
)
class TestYoutubeLists(unittest.TestCase):
def assertIsPlaylist(self, info):
"""Make sure the info has '_type' set to 'playlist'"""
self.assertEqual(info['_type'], 'playlist')
def test_youtube_playlist(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'ytdl test PL')
ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
def test_youtube_playlist_noplaylist(self):
dl = FakeYDL()
dl.params['noplaylist'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertEqual(result['_type'], 'url')
self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
def test_issue_673(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('PLBB231211A4F62143')
self.assertTrue(len(result['entries']) > 25)
def test_youtube_playlist_long(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
self.assertIsPlaylist(result)
self.assertTrue(len(result['entries']) >= 799)
def test_youtube_playlist_with_deleted(self):
#651
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
self.assertFalse('pElCt5oNDuI' in ytie_results)
self.assertFalse('KdPEApIVdWM' in ytie_results)
def test_youtube_playlist_empty(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')
self.assertIsPlaylist(result)
self.assertEqual(len(result['entries']), 0)
def test_youtube_course(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
# TODO find a > 100 (paginating?) videos course
result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
entries = result['entries']
self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
def test_youtube_channel(self):
dl = FakeYDL()
ie = YoutubeChannelIE(dl)
#test paginated channel
result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')
self.assertTrue(len(result['entries']) > 90)
#test autogenerated channel
result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
self.assertTrue(len(result['entries']) >= 18)
def test_youtube_user(self):
dl = FakeYDL()
ie = YoutubeUserIE(dl)
result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')
self.assertTrue(len(result['entries']) >= 320)
def test_youtube_safe_search(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')
self.assertEqual(len(result['entries']), 2)
def test_youtube_show(self):
dl = FakeYDL()
ie = YoutubeShowIE(dl)
result = ie.extract('http://www.youtube.com/show/airdisasters')
self.assertTrue(len(result) >= 3)
def test_youtube_mix(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('http://www.youtube.com/watch?v=lLJf9qJHR3E&list=RDrjFaenf1T-Y')
entries = result['entries']
self.assertTrue(len(entries) >= 20)
original_video = entries[0]
self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
def test_youtube_toptracks(self):
print('Skipping: The playlist page gives error 500')
return
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
entries = result['entries']
self.assertEqual(len(entries), 100)
def test_youtube_toplist(self):
dl = FakeYDL()
ie = YoutubeTopListIE(dl)
result = ie.extract('yttoplist:music:Trending')
entries = result['entries']
self.assertTrue(len(entries) >= 5)
def test_youtube_search_url(self):
dl = FakeYDL()
ie = YoutubeSearchURLIE(dl)
result = ie.extract('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video')
entries = result['entries']
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'youtube-dl test video')
self.assertTrue(len(entries) >= 5)
if __name__ == '__main__':
unittest.main()
-81
View File
@@ -1,81 +0,0 @@
#!/usr/bin/env python
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import io
import re
import string
from youtube_dl.extractor import YoutubeIE
from youtube_dl.utils import compat_str, compat_urlretrieve
_TESTS = [
(
u'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
u'js',
86,
u'>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
),
(
u'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
u'js',
85,
u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
),
(
u'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
u'js',
90,
u']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
),
]
class TestSignature(unittest.TestCase):
def setUp(self):
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
self.TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata')
if not os.path.exists(self.TESTDATA_DIR):
os.mkdir(self.TESTDATA_DIR)
def make_tfunc(url, stype, sig_length, expected_sig):
basename = url.rpartition('/')[2]
m = re.match(r'.*-([a-zA-Z0-9_-]+)\.[a-z]+$', basename)
assert m, '%r should follow URL format' % basename
test_id = m.group(1)
def test_func(self):
fn = os.path.join(self.TESTDATA_DIR, basename)
if not os.path.exists(fn):
compat_urlretrieve(url, fn)
ie = YoutubeIE()
if stype == 'js':
with io.open(fn, encoding='utf-8') as testf:
jscode = testf.read()
func = ie._parse_sig_js(jscode)
else:
assert stype == 'swf'
with open(fn, 'rb') as testf:
swfcode = testf.read()
func = ie._parse_sig_swf(swfcode)
src_sig = compat_str(string.printable[:sig_length])
got_sig = func(src_sig)
self.assertEqual(got_sig, expected_sig)
test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
setattr(TestSignature, test_func.__name__, test_func)
for test_spec in _TESTS:
make_tfunc(*test_spec)
if __name__ == '__main__':
unittest.main()
View File
-8
View File
@@ -1,8 +0,0 @@
[tox]
envlist = py26,py27,py33
[testenv]
deps =
nose
coverage
commands = nosetests --verbose {posargs:test} # --with-coverage --cover-package=youtube_dl --cover-html
# test.test_download:TestDownload.test_NowVideo
+19
View File
@@ -0,0 +1,19 @@
#/bins/sh
set -e
version="$1"
if [ -z "$version" ]; then
echo "Usage: $0 version"
exit 1
fi
cd "$(dirname $(readlink -f $0))"
echo -n "$version" > latest_version
echo -e "RewriteEngine On" > downloads/.htaccess
echo -e "RewriteRule ^$ https://github.com/ytdl-org/youtube-dl/releases" >> downloads/.htaccess
echo -e "RewriteRule ^(\d{4}\.\d{2}\.\d{2}(?:\.\d+)?/?)$ https://github.com/ytdl-org/youtube-dl/releases/tag/\$1" >> downloads/.htaccess
echo -e "RewriteRule ^(\d{4}\.\d{2}\.\d{2}(?:\.\d+)?/.+)$ https://github.com/ytdl-org/youtube-dl/releases/download/\$1" >> downloads/.htaccess
echo -e "RewriteRule latest(.*) /downloads/$1\$1 [L,R=302]" >> downloads/.htaccess
-89
View File
@@ -1,89 +0,0 @@
#!/usr/bin/env python
import sys, os
import json, hashlib
try:
import urllib.request as compat_urllib_request
except ImportError: # Python 2
import urllib2 as compat_urllib_request
def rsa_verify(message, signature, key):
from struct import pack
from hashlib import sha256
from sys import version_info
def b(x):
if version_info[0] == 2: return x
else: return x.encode('latin1')
assert(type(message) == type(b('')))
block_size = 0
n = key[0]
while n:
block_size += 1
n >>= 8
signature = pow(int(signature, 16), key[1], key[0])
raw_bytes = []
while signature:
raw_bytes.insert(0, pack("B", signature & 0xFF))
signature >>= 8
signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
if signature[0:2] != b('\x00\x01'): return False
signature = signature[2:]
if not b('\x00') in signature: return False
signature = signature[signature.index(b('\x00'))+1:]
if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
signature = signature[19:]
if signature != sha256(message).digest(): return False
return True
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
sys.stderr.write(u'From now on, get the binaries from http://rg3.github.io/youtube-dl/download.html, not from the git repository.\n\n')
try:
raw_input()
except NameError: # Python 3
input()
filename = sys.argv[0]
UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
JSON_URL = UPDATE_URL + 'versions.json'
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
try:
versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8')
versions_info = json.loads(versions_info)
except:
sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
if not 'signature' in versions_info:
sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
signature = versions_info['signature']
del versions_info['signature']
if not rsa_verify(json.dumps(versions_info, sort_keys=True).encode('utf-8'), signature, UPDATES_RSA_KEY):
sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
version = versions_info['versions'][versions_info['latest']]
try:
urlh = compat_urllib_request.urlopen(version['bin'][0])
newcontent = urlh.read()
urlh.close()
except (IOError, OSError) as err:
sys.exit('ERROR: unable to download latest version')
newcontent_hash = hashlib.sha256(newcontent).hexdigest()
if newcontent_hash != version['bin'][1]:
sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
try:
with open(filename, 'wb') as outf:
outf.write(newcontent)
except (IOError, OSError) as err:
sys.exit('ERROR: unable to overwrite current version')
sys.stderr.write(u'Done! Now you can run youtube-dl.\n')
BIN
View File
Binary file not shown.
-24
View File
@@ -1,24 +0,0 @@
# This allows the youtube-dl command to be installed in ZSH using antigen.
# Antigen is a bundle manager. It allows you to enhance the functionality of
# your zsh session by installing bundles and themes easily.
# Antigen documentation:
# http://antigen.sharats.me/
# https://github.com/zsh-users/antigen
# Install youtube-dl:
# antigen bundle rg3/youtube-dl
# Bundles installed by antigen are available for use immediately.
# Update youtube-dl (and all other antigen bundles):
# antigen update
# The antigen command will download the git repository to a folder and then
# execute an enabling script (this file). The complete process for loading the
# code is documented here:
# https://github.com/zsh-users/antigen#notes-on-writing-plugins
# This specific script just aliases youtube-dl to the python script that this
# library provides. This requires updating the PYTHONPATH to ensure that the
# full set of code can be located.
alias youtube-dl="PYTHONPATH=$(dirname $0) $(dirname $0)/bin/youtube-dl"
-12
View File
@@ -1,12 +0,0 @@
# Legacy file for backwards compatibility, use youtube_dl.downloader instead!
from .downloader import FileDownloader as RealFileDownloader
from .downloader import get_suitable_downloader
# This class reproduces the old behaviour of FileDownloader
class FileDownloader(RealFileDownloader):
def _do_download(self, filename, info_dict):
real_fd = get_suitable_downloader(info_dict)(self.ydl, self.params)
for ph in self._progress_hooks:
real_fd.add_progress_hook(ph)
return real_fd.download(filename, info_dict)
-4
View File
@@ -1,4 +0,0 @@
# Legacy file for backwards compatibility, use youtube_dl.extractor instead!
from .extractor.common import InfoExtractor, SearchInfoExtractor
from .extractor import gen_extractors, get_info_extractor
File diff suppressed because it is too large Load Diff
-816
View File
@@ -1,816 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
__authors__ = (
'Ricardo Garcia Gonzalez',
'Danny Colligan',
'Benjamin Johnson',
'Vasyl\' Vavrychuk',
'Witold Baryluk',
'Paweł Paprota',
'Gergely Imreh',
'Rogério Brito',
'Philipp Hagemeister',
'Sören Schulze',
'Kevin Ngo',
'Ori Avtalion',
'shizeeg',
'Filippo Valsorda',
'Christian Albrecht',
'Dave Vasilevsky',
'Jaime Marquínez Ferrándiz',
'Jeff Crouse',
'Osama Khalid',
'Michael Walter',
'M. Yasoob Ullah Khalid',
'Julien Fraichard',
'Johny Mo Swag',
'Axel Noack',
'Albert Kim',
'Pierre Rudloff',
'Huarong Huo',
'Ismael Mejía',
'Steffan \'Ruirize\' James',
'Andras Elso',
'Jelle van der Waa',
'Marcin Cieślak',
'Anton Larionov',
'Takuya Tsuchida',
'Sergey M.',
'Michael Orlitzky',
'Chris Gahan',
'Saimadhav Heblikar',
'Mike Col',
'Oleg Prutz',
'pulpe',
'Andreas Schmitz',
'Michael Kaiser',
'Niklas Laxström',
'David Triendl',
'Anthony Weems',
'David Wagner',
'Juan C. Olivares',
)
__license__ = 'Public Domain'
import codecs
import getpass
import io
import locale
import optparse
import os
import random
import re
import shlex
import sys
from .utils import (
compat_print,
DateRange,
decodeOption,
get_term_width,
DownloadError,
get_cachedir,
MaxDownloadsReached,
preferredencoding,
read_batch_urls,
SameFileError,
setproctitle,
std_headers,
write_string,
)
from .update import update_self
from .FileDownloader import (
FileDownloader,
)
from .extractor import gen_extractors
from .version import __version__
from .YoutubeDL import YoutubeDL
from .postprocessor import (
FFmpegMetadataPP,
FFmpegVideoConvertor,
FFmpegExtractAudioPP,
FFmpegEmbedSubtitlePP,
XAttrMetadataPP,
)
def parseOpts(overrideArguments=None):
def _readOptions(filename_bytes, default=[]):
try:
optionf = open(filename_bytes)
except IOError:
return default # silently skip if file is not present
try:
res = []
for l in optionf:
res += shlex.split(l, comments=True)
finally:
optionf.close()
return res
def _readUserConf():
xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
if xdg_config_home:
userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
if not os.path.isfile(userConfFile):
userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
else:
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
if not os.path.isfile(userConfFile):
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
userConf = _readOptions(userConfFile, None)
if userConf is None:
appdata_dir = os.environ.get('appdata')
if appdata_dir:
userConf = _readOptions(
os.path.join(appdata_dir, 'youtube-dl', 'config'),
default=None)
if userConf is None:
userConf = _readOptions(
os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
default=None)
if userConf is None:
userConf = _readOptions(
os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
default=None)
if userConf is None:
userConf = _readOptions(
os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
default=None)
if userConf is None:
userConf = []
return userConf
def _format_option_string(option):
''' ('-o', '--option') -> -o, --format METAVAR'''
opts = []
if option._short_opts:
opts.append(option._short_opts[0])
if option._long_opts:
opts.append(option._long_opts[0])
if len(opts) > 1:
opts.insert(1, ', ')
if option.takes_value(): opts.append(' %s' % option.metavar)
return "".join(opts)
def _comma_separated_values_options_callback(option, opt_str, value, parser):
setattr(parser.values, option.dest, value.split(','))
def _hide_login_info(opts):
opts = list(opts)
for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
try:
i = opts.index(private_opt)
opts[i+1] = '<PRIVATE>'
except ValueError:
pass
return opts
max_width = 80
max_help_position = 80
# No need to wrap help messages if we're on a wide console
columns = get_term_width()
if columns: max_width = columns
fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
fmt.format_option_strings = _format_option_string
kw = {
'version' : __version__,
'formatter' : fmt,
'usage' : '%prog [options] url [url...]',
'conflict_handler' : 'resolve',
}
parser = optparse.OptionParser(**kw)
# option groups
general = optparse.OptionGroup(parser, 'General Options')
selection = optparse.OptionGroup(parser, 'Video Selection')
authentication = optparse.OptionGroup(parser, 'Authentication Options')
video_format = optparse.OptionGroup(parser, 'Video Format Options')
subtitles = optparse.OptionGroup(parser, 'Subtitle Options')
downloader = optparse.OptionGroup(parser, 'Download Options')
postproc = optparse.OptionGroup(parser, 'Post-processing Options')
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
general.add_option('-h', '--help',
action='help', help='print this help text and exit')
general.add_option('-v', '--version',
action='version', help='print program version and exit')
general.add_option('-U', '--update',
action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
general.add_option('-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False)
general.add_option('--abort-on-error',
action='store_false', dest='ignoreerrors',
help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')
general.add_option('--dump-user-agent',
action='store_true', dest='dump_user_agent',
help='display the current browser identification', default=False)
general.add_option('--user-agent',
dest='user_agent', help='specify a custom user agent', metavar='UA')
general.add_option('--referer',
dest='referer', help='specify a custom referer, use if the video access is restricted to one domain',
metavar='REF', default=None)
general.add_option('--list-extractors',
action='store_true', dest='list_extractors',
help='List all supported extractors and the URLs they would handle', default=False)
general.add_option('--extractor-descriptions',
action='store_true', dest='list_extractor_descriptions',
help='Output descriptions of all supported extractors', default=False)
general.add_option(
'--proxy', dest='proxy', default=None, metavar='URL',
help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
general.add_option(
'--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
general.add_option(
'--no-cache-dir', action='store_const', const=None, dest='cachedir',
help='Disable filesystem caching')
general.add_option(
'--socket-timeout', dest='socket_timeout',
type=float, default=None, help=u'Time to wait before giving up, in seconds')
general.add_option(
'--bidi-workaround', dest='bidi_workaround', action='store_true',
help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
general.add_option('--default-search',
dest='default_search', metavar='PREFIX',
help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
general.add_option(
'--ignore-config',
action='store_true',
help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
selection.add_option(
'--playlist-start',
dest='playliststart', metavar='NUMBER', default=1, type=int,
help='playlist video to start at (default is %default)')
selection.add_option(
'--playlist-end',
dest='playlistend', metavar='NUMBER', default=None, type=int,
help='playlist video to end at (default is last)')
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
selection.add_option('--max-downloads', metavar='NUMBER',
dest='max_downloads', type=int, default=None,
help='Abort after downloading NUMBER files')
selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None)
selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None)
selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
selection.add_option(
'--datebefore', metavar='DATE', dest='datebefore', default=None,
help='download only videos uploaded on or before this date (i.e. inclusive)')
selection.add_option(
'--dateafter', metavar='DATE', dest='dateafter', default=None,
help='download only videos uploaded on or after this date (i.e. inclusive)')
selection.add_option(
'--min-views', metavar='COUNT', dest='min_views',
default=None, type=int,
help="Do not download any videos with less than COUNT views",)
selection.add_option(
'--max-views', metavar='COUNT', dest='max_views',
default=None, type=int,
help="Do not download any videos with more than COUNT views",)
selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False)
selection.add_option('--age-limit', metavar='YEARS', dest='age_limit',
help='download only videos suitable for the given age',
default=None, type=int)
selection.add_option('--download-archive', metavar='FILE',
dest='download_archive',
help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.')
selection.add_option(
'--include-ads', dest='include_ads',
action='store_true',
help='Download advertisements as well (experimental)')
selection.add_option(
'--youtube-include-dash-manifest', action='store_true',
dest='youtube_include_dash_manifest', default=False,
help='Try to download the DASH manifest on YouTube videos (experimental)')
authentication.add_option('-u', '--username',
dest='username', metavar='USERNAME', help='account username')
authentication.add_option('-p', '--password',
dest='password', metavar='PASSWORD', help='account password')
authentication.add_option('-n', '--netrc',
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
authentication.add_option('--video-password',
dest='videopassword', metavar='PASSWORD', help='video password (vimeo, smotri)')
video_format.add_option('-f', '--format',
action='store', dest='format', metavar='FORMAT', default=None,
help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestaudio", "worst", and "worstaudio". By default, youtube-dl will pick the best quality.')
video_format.add_option('--all-formats',
action='store_const', dest='format', help='download all available video formats', const='all')
video_format.add_option('--prefer-free-formats',
action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested')
video_format.add_option('--max-quality',
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
video_format.add_option('-F', '--list-formats',
action='store_true', dest='listformats', help='list all available formats')
subtitles.add_option('--write-sub', '--write-srt',
action='store_true', dest='writesubtitles',
help='write subtitle file', default=False)
subtitles.add_option('--write-auto-sub', '--write-automatic-sub',
action='store_true', dest='writeautomaticsub',
help='write automatic subtitle file (youtube only)', default=False)
subtitles.add_option('--all-subs',
action='store_true', dest='allsubtitles',
help='downloads all the available subtitles of the video', default=False)
subtitles.add_option('--list-subs',
action='store_true', dest='listsubtitles',
help='lists all available subtitles for the video', default=False)
subtitles.add_option('--sub-format',
action='store', dest='subtitlesformat', metavar='FORMAT',
help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
default=[], callback=_comma_separated_values_options_callback,
help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
downloader.add_option('-r', '--rate-limit',
dest='ratelimit', metavar='LIMIT', help='maximum download rate in bytes per second (e.g. 50K or 4.2M)')
downloader.add_option('-R', '--retries',
dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
downloader.add_option('--buffer-size',
dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16K) (default is %default)', default="1024")
downloader.add_option('--no-resize-buffer',
action='store_true', dest='noresizebuffer',
help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
downloader.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
verbosity.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
verbosity.add_option('-s', '--simulate',
action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
verbosity.add_option('--skip-download',
action='store_true', dest='skip_download', help='do not download the video', default=False)
verbosity.add_option('-g', '--get-url',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
verbosity.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
verbosity.add_option('--get-id',
action='store_true', dest='getid', help='simulate, quiet but print id', default=False)
verbosity.add_option('--get-thumbnail',
action='store_true', dest='getthumbnail',
help='simulate, quiet but print thumbnail URL', default=False)
verbosity.add_option('--get-description',
action='store_true', dest='getdescription',
help='simulate, quiet but print video description', default=False)
verbosity.add_option('--get-duration',
action='store_true', dest='getduration',
help='simulate, quiet but print video length', default=False)
verbosity.add_option('--get-filename',
action='store_true', dest='getfilename',
help='simulate, quiet but print output filename', default=False)
verbosity.add_option('--get-format',
action='store_true', dest='getformat',
help='simulate, quiet but print output format', default=False)
verbosity.add_option('-j', '--dump-json',
action='store_true', dest='dumpjson',
help='simulate, quiet but print JSON information', default=False)
verbosity.add_option('--newline',
action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
verbosity.add_option('--no-progress',
action='store_true', dest='noprogress', help='do not print progress bar', default=False)
verbosity.add_option('--console-title',
action='store_true', dest='consoletitle',
help='display progress in console titlebar', default=False)
verbosity.add_option('-v', '--verbose',
action='store_true', dest='verbose', help='print various debugging information', default=False)
verbosity.add_option('--dump-intermediate-pages',
action='store_true', dest='dump_intermediate_pages', default=False,
help='print downloaded pages to debug problems (very verbose)')
verbosity.add_option('--write-pages',
action='store_true', dest='write_pages', default=False,
help='Write downloaded intermediary pages to files in the current directory to debug problems')
verbosity.add_option('--youtube-print-sig-code',
action='store_true', dest='youtube_print_sig_code', default=False,
help=optparse.SUPPRESS_HELP)
verbosity.add_option('--print-traffic',
dest='debug_printtraffic', action='store_true', default=False,
help='Display sent and read HTTP traffic')
filesystem.add_option('-t', '--title',
action='store_true', dest='usetitle', help='use title in file name (default)', default=False)
filesystem.add_option('--id',
action='store_true', dest='useid', help='use only video ID in file name', default=False)
filesystem.add_option('-l', '--literal',
action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
filesystem.add_option('-A', '--auto-number',
action='store_true', dest='autonumber',
help='number downloaded files starting from 00000', default=False)
filesystem.add_option('-o', '--output',
dest='outtmpl', metavar='TEMPLATE',
help=('output filename template. Use %(title)s to get the title, '
'%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, '
'%(autonumber)s to get an automatically incremented number, '
'%(ext)s for the filename extension, '
'%(format)s for the format description (like "22 - 1280x720" or "HD"), '
'%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), '
'%(upload_date)s for the upload date (YYYYMMDD), '
'%(extractor)s for the provider (youtube, metacafe, etc), '
'%(id)s for the video id, %(playlist)s for the playlist the video is in, '
'%(playlist_index)s for the position in the playlist and %% for a literal percent. '
'%(height)s and %(width)s for the width and height of the video format. '
'%(resolution)s for a textual description of the resolution of the video format. '
'Use - to output to stdout. Can also be used to download to a different directory, '
'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
filesystem.add_option('--autonumber-size',
dest='autonumber_size', metavar='NUMBER',
help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
filesystem.add_option('--restrict-filenames',
action='store_true', dest='restrictfilenames',
help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
filesystem.add_option('-a', '--batch-file',
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
filesystem.add_option('--load-info',
dest='load_info_filename', metavar='FILE',
help='json file containing the video information (created with the "--write-json" option)')
filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue',
action='store_true', dest='continue_dl', help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.', default=True)
filesystem.add_option('--no-continue',
action='store_false', dest='continue_dl',
help='do not resume partially downloaded files (restart from beginning)')
filesystem.add_option('--cookies',
dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
filesystem.add_option('--no-part',
action='store_true', dest='nopart', help='do not use .part files', default=False)
filesystem.add_option('--no-mtime',
action='store_false', dest='updatetime',
help='do not use the Last-modified header to set the file modification time', default=True)
filesystem.add_option('--write-description',
action='store_true', dest='writedescription',
help='write video description to a .description file', default=False)
filesystem.add_option('--write-info-json',
action='store_true', dest='writeinfojson',
help='write video metadata to a .info.json file', default=False)
filesystem.add_option('--write-annotations',
action='store_true', dest='writeannotations',
help='write video annotations to a .annotation file', default=False)
filesystem.add_option('--write-thumbnail',
action='store_true', dest='writethumbnail',
help='write thumbnail image to disk', default=False)
postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
help='"best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; best by default')
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5',
help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
postproc.add_option('--recode-video', metavar='FORMAT', dest='recodevideo', default=None,
help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm)')
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
help='keeps the video file on disk after the post-processing; the video is erased by default')
postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
help='do not overwrite post-processed files; the post-processed files are overwritten by default')
postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
help='embed subtitles in the video (only for mp4 videos)')
postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False,
help='write metadata to the video file')
postproc.add_option('--xattrs', action='store_true', dest='xattrs', default=False,
help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)')
postproc.add_option('--prefer-avconv', action='store_false', dest='prefer_ffmpeg',
help='Prefer avconv over ffmpeg for running the postprocessors (default)')
postproc.add_option('--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg',
help='Prefer ffmpeg over avconv for running the postprocessors')
parser.add_option_group(general)
parser.add_option_group(selection)
parser.add_option_group(downloader)
parser.add_option_group(filesystem)
parser.add_option_group(verbosity)
parser.add_option_group(video_format)
parser.add_option_group(subtitles)
parser.add_option_group(authentication)
parser.add_option_group(postproc)
if overrideArguments is not None:
opts, args = parser.parse_args(overrideArguments)
if opts.verbose:
write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
else:
commandLineConf = sys.argv[1:]
if '--ignore-config' in commandLineConf:
systemConf = []
userConf = []
else:
systemConf = _readOptions('/etc/youtube-dl.conf')
if '--ignore-config' in systemConf:
userConf = []
else:
userConf = _readUserConf()
argv = systemConf + userConf + commandLineConf
opts, args = parser.parse_args(argv)
if opts.verbose:
write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
write_string(u'[debug] Encodings: locale %r, fs %r, out %r, pref: %r\n' %
(locale.getpreferredencoding(), sys.getfilesystemencoding(), sys.stdout.encoding, preferredencoding()))
return parser, opts, args
def _real_main(argv=None):
# Compatibility fixes for Windows
if sys.platform == 'win32':
# https://github.com/rg3/youtube-dl/issues/820
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
setproctitle(u'youtube-dl')
parser, opts, args = parseOpts(argv)
# Set user agent
if opts.user_agent is not None:
std_headers['User-Agent'] = opts.user_agent
# Set referer
if opts.referer is not None:
std_headers['Referer'] = opts.referer
# Dump user agent
if opts.dump_user_agent:
compat_print(std_headers['User-Agent'])
sys.exit(0)
# Batch file verification
batch_urls = []
if opts.batchfile is not None:
try:
if opts.batchfile == '-':
batchfd = sys.stdin
else:
batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
batch_urls = read_batch_urls(batchfd)
if opts.verbose:
write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
except IOError:
sys.exit(u'ERROR: batch file could not be read')
all_urls = batch_urls + args
all_urls = [url.strip() for url in all_urls]
_enc = preferredencoding()
all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
extractors = gen_extractors()
if opts.list_extractors:
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
matchedUrls = [url for url in all_urls if ie.suitable(url)]
for mu in matchedUrls:
compat_print(u' ' + mu)
sys.exit(0)
if opts.list_extractor_descriptions:
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
if not ie._WORKING:
continue
desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
if desc is False:
continue
if hasattr(ie, 'SEARCH_KEY'):
_SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise')
_COUNTS = (u'', u'5', u'10', u'all')
desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
compat_print(desc)
sys.exit(0)
# Conflicting, missing and erroneous options
if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error(u'using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
parser.error(u'account username missing\n')
if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
parser.error(u'using output template conflicts with using title, video ID or auto number')
if opts.usetitle and opts.useid:
parser.error(u'using title conflicts with using video ID')
if opts.username is not None and opts.password is None:
opts.password = getpass.getpass(u'Type account password and press return:')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
parser.error(u'invalid rate limit specified')
opts.ratelimit = numeric_limit
if opts.min_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
if numeric_limit is None:
parser.error(u'invalid min_filesize specified')
opts.min_filesize = numeric_limit
if opts.max_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
if numeric_limit is None:
parser.error(u'invalid max_filesize specified')
opts.max_filesize = numeric_limit
if opts.retries is not None:
try:
opts.retries = int(opts.retries)
except (TypeError, ValueError):
parser.error(u'invalid retry count specified')
if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None:
parser.error(u'invalid buffer size specified')
opts.buffersize = numeric_buffersize
if opts.playliststart <= 0:
raise ValueError(u'Playlist start must be positive')
if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
raise ValueError(u'Playlist end must be greater than playlist start')
if opts.extractaudio:
if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
parser.error(u'invalid audio format specified')
if opts.audioquality:
opts.audioquality = opts.audioquality.strip('k').strip('K')
if not opts.audioquality.isdigit():
parser.error(u'invalid audio quality specified')
if opts.recodevideo is not None:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg']:
parser.error(u'invalid video recode format specified')
if opts.date is not None:
date = DateRange.day(opts.date)
else:
date = DateRange(opts.dateafter, opts.datebefore)
if opts.default_search not in ('auto', None) and ':' not in opts.default_search:
parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
# Do not download videos when there are audio-only formats
if opts.extractaudio and not opts.keepvideo and opts.format is None:
opts.format = 'bestaudio/best'
# --all-sub automatically sets --write-sub if --write-auto-sub is not given
# this was the old behaviour if only --all-sub was given.
if opts.allsubtitles and (opts.writeautomaticsub == False):
opts.writesubtitles = True
if sys.version_info < (3,):
# In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
if opts.outtmpl is not None:
opts.outtmpl = opts.outtmpl.decode(preferredencoding())
outtmpl =((opts.outtmpl is not None and opts.outtmpl)
or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
or (opts.useid and u'%(id)s.%(ext)s')
or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
or u'%(title)s-%(id)s.%(ext)s')
if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error(u'Cannot download a video and extract audio into the same'
u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
u' template'.format(outtmpl))
any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson
download_archive_fn = os.path.expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
ydl_opts = {
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
'videopassword': opts.videopassword,
'quiet': (opts.quiet or any_printing),
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'forceid': opts.getid,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
'forceduration': opts.getduration,
'forcefilename': opts.getfilename,
'forceformat': opts.getformat,
'forcejson': opts.dumpjson,
'simulate': opts.simulate,
'skip_download': (opts.skip_download or opts.simulate or any_printing),
'format': opts.format,
'format_limit': opts.format_limit,
'listformats': opts.listformats,
'outtmpl': outtmpl,
'autonumber_size': opts.autonumber_size,
'restrictfilenames': opts.restrictfilenames,
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
'retries': opts.retries,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl,
'noprogress': opts.noprogress,
'progress_with_newline': opts.progress_with_newline,
'playliststart': opts.playliststart,
'playlistend': opts.playlistend,
'noplaylist': opts.noplaylist,
'logtostderr': opts.outtmpl == '-',
'consoletitle': opts.consoletitle,
'nopart': opts.nopart,
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson,
'writethumbnail': opts.writethumbnail,
'writesubtitles': opts.writesubtitles,
'writeautomaticsub': opts.writeautomaticsub,
'allsubtitles': opts.allsubtitles,
'listsubtitles': opts.listsubtitles,
'subtitlesformat': opts.subtitlesformat,
'subtitleslangs': opts.subtitleslangs,
'matchtitle': decodeOption(opts.matchtitle),
'rejecttitle': decodeOption(opts.rejecttitle),
'max_downloads': opts.max_downloads,
'prefer_free_formats': opts.prefer_free_formats,
'verbose': opts.verbose,
'dump_intermediate_pages': opts.dump_intermediate_pages,
'write_pages': opts.write_pages,
'test': opts.test,
'keepvideo': opts.keepvideo,
'min_filesize': opts.min_filesize,
'max_filesize': opts.max_filesize,
'min_views': opts.min_views,
'max_views': opts.max_views,
'daterange': date,
'cachedir': opts.cachedir,
'youtube_print_sig_code': opts.youtube_print_sig_code,
'age_limit': opts.age_limit,
'download_archive': download_archive_fn,
'cookiefile': opts.cookiefile,
'nocheckcertificate': opts.no_check_certificate,
'proxy': opts.proxy,
'socket_timeout': opts.socket_timeout,
'bidi_workaround': opts.bidi_workaround,
'debug_printtraffic': opts.debug_printtraffic,
'prefer_ffmpeg': opts.prefer_ffmpeg,
'include_ads': opts.include_ads,
'default_search': opts.default_search,
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
}
with YoutubeDL(ydl_opts) as ydl:
ydl.print_debug_header()
ydl.add_default_info_extractors()
# PostProcessors
# Add the metadata pp first, the other pps will copy it
if opts.addmetadata:
ydl.add_post_processor(FFmpegMetadataPP())
if opts.extractaudio:
ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
if opts.recodevideo:
ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
if opts.embedsubtitles:
ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
if opts.xattrs:
ydl.add_post_processor(XAttrMetadataPP())
# Update version
if opts.update_self:
update_self(ydl.to_screen, opts.verbose)
# Maybe do nothing
if (len(all_urls) < 1) and (opts.load_info_filename is None):
if not opts.update_self:
parser.error(u'you must provide at least one URL')
else:
sys.exit()
try:
if opts.load_info_filename is not None:
retcode = ydl.download_with_info_file(opts.load_info_filename)
else:
retcode = ydl.download(all_urls)
except MaxDownloadsReached:
ydl.to_screen(u'--max-download limit reached, aborting.')
retcode = 101
sys.exit(retcode)
def main(argv=None):
try:
_real_main(argv)
except DownloadError:
sys.exit(1)
except SameFileError:
sys.exit(u'ERROR: fixed output name but more than one file to download')
except KeyboardInterrupt:
sys.exit(u'\nERROR: Interrupted by user')
-18
View File
@@ -1,18 +0,0 @@
#!/usr/bin/env python
# Execute with
# $ python youtube_dl/__main__.py (2.6+)
# $ python -m youtube_dl (2.7+)
import sys
if __package__ is None and not hasattr(sys, "frozen"):
# direct call of __main__.py
import os.path
path = os.path.realpath(os.path.abspath(__file__))
sys.path.append(os.path.dirname(os.path.dirname(path)))
import youtube_dl
if __name__ == '__main__':
youtube_dl.main()
-310
View File
@@ -1,310 +0,0 @@
__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']
import base64
from math import ceil
from .utils import bytes_to_intlist, intlist_to_bytes
BLOCK_SIZE_BYTES = 16
def aes_ctr_decrypt(data, key, counter):
"""
Decrypt with aes in counter mode
@param {int[]} data cipher
@param {int[]} key 16/24/32-Byte cipher key
@param {instance} counter Instance whose next_value function (@returns {int[]} 16-Byte block)
returns the next counter block
@returns {int[]} decrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
decrypted_data=[]
for i in range(block_count):
counter_block = counter.next_value()
block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]
block += [0]*(BLOCK_SIZE_BYTES - len(block))
cipher_counter_block = aes_encrypt(counter_block, expanded_key)
decrypted_data += xor(block, cipher_counter_block)
decrypted_data = decrypted_data[:len(data)]
return decrypted_data
def aes_cbc_decrypt(data, key, iv):
"""
Decrypt with aes in CBC mode
@param {int[]} data cipher
@param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv 16-Byte IV
@returns {int[]} decrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
decrypted_data=[]
previous_cipher_block = iv
for i in range(block_count):
block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]
block += [0]*(BLOCK_SIZE_BYTES - len(block))
decrypted_block = aes_decrypt(block, expanded_key)
decrypted_data += xor(decrypted_block, previous_cipher_block)
previous_cipher_block = block
decrypted_data = decrypted_data[:len(data)]
return decrypted_data
def key_expansion(data):
"""
Generate key schedule
@param {int[]} data 16/24/32-Byte cipher key
@returns {int[]} 176/208/240-Byte expanded key
"""
data = data[:] # copy
rcon_iteration = 1
key_size_bytes = len(data)
expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES
while len(data) < expanded_key_size_bytes:
temp = data[-4:]
temp = key_schedule_core(temp, rcon_iteration)
rcon_iteration += 1
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
for _ in range(3):
temp = data[-4:]
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
if key_size_bytes == 32:
temp = data[-4:]
temp = sub_bytes(temp)
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0):
temp = data[-4:]
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
data = data[:expanded_key_size_bytes]
return data
def aes_encrypt(data, expanded_key):
"""
Encrypt one block with aes
@param {int[]} data 16-Byte state
@param {int[]} expanded_key 176/208/240-Byte expanded key
@returns {int[]} 16-Byte cipher
"""
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
for i in range(1, rounds+1):
data = sub_bytes(data)
data = shift_rows(data)
if i != rounds:
data = mix_columns(data)
data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
return data
def aes_decrypt(data, expanded_key):
"""
Decrypt one block with aes
@param {int[]} data 16-Byte cipher
@param {int[]} expanded_key 176/208/240-Byte expanded key
@returns {int[]} 16-Byte state
"""
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
for i in range(rounds, 0, -1):
data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
if i != rounds:
data = mix_columns_inv(data)
data = shift_rows_inv(data)
data = sub_bytes_inv(data)
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
return data
def aes_decrypt_text(data, password, key_size_bytes):
"""
Decrypt text
- The first 8 Bytes of decoded 'data' are the 8 high Bytes of the counter
- The cipher key is retrieved by encrypting the first 16 Byte of 'password'
with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's)
- Mode of operation is 'counter'
@param {str} data Base64 encoded string
@param {str,unicode} password Password (will be encoded with utf-8)
@param {int} key_size_bytes Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit
@returns {str} Decrypted data
"""
NONCE_LENGTH_BYTES = 8
data = bytes_to_intlist(base64.b64decode(data))
password = bytes_to_intlist(password.encode('utf-8'))
key = password[:key_size_bytes] + [0]*(key_size_bytes - len(password))
key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES)
nonce = data[:NONCE_LENGTH_BYTES]
cipher = data[NONCE_LENGTH_BYTES:]
class Counter:
__value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
def next_value(self):
temp = self.__value
self.__value = inc(self.__value)
return temp
decrypted_data = aes_ctr_decrypt(cipher, key, Counter())
plaintext = intlist_to_bytes(decrypted_data)
return plaintext
RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC, 0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A, 0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0, 0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B, 0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85, 0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5, 0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17, 0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88, 0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C, 0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9, 0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6, 0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16)
SBOX_INV = (0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d)
MIX_COLUMN_MATRIX = ((0x2,0x3,0x1,0x1),
(0x1,0x2,0x3,0x1),
(0x1,0x1,0x2,0x3),
(0x3,0x1,0x1,0x2))
MIX_COLUMN_MATRIX_INV = ((0xE,0xB,0xD,0x9),
(0x9,0xE,0xB,0xD),
(0xD,0x9,0xE,0xB),
(0xB,0xD,0x9,0xE))
RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35,
0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA,
0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31,
0x53, 0xF5, 0x04, 0x0C, 0x14, 0x3C, 0x44, 0xCC, 0x4F, 0xD1, 0x68, 0xB8, 0xD3, 0x6E, 0xB2, 0xCD,
0x4C, 0xD4, 0x67, 0xA9, 0xE0, 0x3B, 0x4D, 0xD7, 0x62, 0xA6, 0xF1, 0x08, 0x18, 0x28, 0x78, 0x88,
0x83, 0x9E, 0xB9, 0xD0, 0x6B, 0xBD, 0xDC, 0x7F, 0x81, 0x98, 0xB3, 0xCE, 0x49, 0xDB, 0x76, 0x9A,
0xB5, 0xC4, 0x57, 0xF9, 0x10, 0x30, 0x50, 0xF0, 0x0B, 0x1D, 0x27, 0x69, 0xBB, 0xD6, 0x61, 0xA3,
0xFE, 0x19, 0x2B, 0x7D, 0x87, 0x92, 0xAD, 0xEC, 0x2F, 0x71, 0x93, 0xAE, 0xE9, 0x20, 0x60, 0xA0,
0xFB, 0x16, 0x3A, 0x4E, 0xD2, 0x6D, 0xB7, 0xC2, 0x5D, 0xE7, 0x32, 0x56, 0xFA, 0x15, 0x3F, 0x41,
0xC3, 0x5E, 0xE2, 0x3D, 0x47, 0xC9, 0x40, 0xC0, 0x5B, 0xED, 0x2C, 0x74, 0x9C, 0xBF, 0xDA, 0x75,
0x9F, 0xBA, 0xD5, 0x64, 0xAC, 0xEF, 0x2A, 0x7E, 0x82, 0x9D, 0xBC, 0xDF, 0x7A, 0x8E, 0x89, 0x80,
0x9B, 0xB6, 0xC1, 0x58, 0xE8, 0x23, 0x65, 0xAF, 0xEA, 0x25, 0x6F, 0xB1, 0xC8, 0x43, 0xC5, 0x54,
0xFC, 0x1F, 0x21, 0x63, 0xA5, 0xF4, 0x07, 0x09, 0x1B, 0x2D, 0x77, 0x99, 0xB0, 0xCB, 0x46, 0xCA,
0x45, 0xCF, 0x4A, 0xDE, 0x79, 0x8B, 0x86, 0x91, 0xA8, 0xE3, 0x3E, 0x42, 0xC6, 0x51, 0xF3, 0x0E,
0x12, 0x36, 0x5A, 0xEE, 0x29, 0x7B, 0x8D, 0x8C, 0x8F, 0x8A, 0x85, 0x94, 0xA7, 0xF2, 0x0D, 0x17,
0x39, 0x4B, 0xDD, 0x7C, 0x84, 0x97, 0xA2, 0xFD, 0x1C, 0x24, 0x6C, 0xB4, 0xC7, 0x52, 0xF6, 0x01)
RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7, 0x1b, 0x68, 0x33, 0xee, 0xdf, 0x03,
0x64, 0x04, 0xe0, 0x0e, 0x34, 0x8d, 0x81, 0xef, 0x4c, 0x71, 0x08, 0xc8, 0xf8, 0x69, 0x1c, 0xc1,
0x7d, 0xc2, 0x1d, 0xb5, 0xf9, 0xb9, 0x27, 0x6a, 0x4d, 0xe4, 0xa6, 0x72, 0x9a, 0xc9, 0x09, 0x78,
0x65, 0x2f, 0x8a, 0x05, 0x21, 0x0f, 0xe1, 0x24, 0x12, 0xf0, 0x82, 0x45, 0x35, 0x93, 0xda, 0x8e,
0x96, 0x8f, 0xdb, 0xbd, 0x36, 0xd0, 0xce, 0x94, 0x13, 0x5c, 0xd2, 0xf1, 0x40, 0x46, 0x83, 0x38,
0x66, 0xdd, 0xfd, 0x30, 0xbf, 0x06, 0x8b, 0x62, 0xb3, 0x25, 0xe2, 0x98, 0x22, 0x88, 0x91, 0x10,
0x7e, 0x6e, 0x48, 0xc3, 0xa3, 0xb6, 0x1e, 0x42, 0x3a, 0x6b, 0x28, 0x54, 0xfa, 0x85, 0x3d, 0xba,
0x2b, 0x79, 0x0a, 0x15, 0x9b, 0x9f, 0x5e, 0xca, 0x4e, 0xd4, 0xac, 0xe5, 0xf3, 0x73, 0xa7, 0x57,
0xaf, 0x58, 0xa8, 0x50, 0xf4, 0xea, 0xd6, 0x74, 0x4f, 0xae, 0xe9, 0xd5, 0xe7, 0xe6, 0xad, 0xe8,
0x2c, 0xd7, 0x75, 0x7a, 0xeb, 0x16, 0x0b, 0xf5, 0x59, 0xcb, 0x5f, 0xb0, 0x9c, 0xa9, 0x51, 0xa0,
0x7f, 0x0c, 0xf6, 0x6f, 0x17, 0xc4, 0x49, 0xec, 0xd8, 0x43, 0x1f, 0x2d, 0xa4, 0x76, 0x7b, 0xb7,
0xcc, 0xbb, 0x3e, 0x5a, 0xfb, 0x60, 0xb1, 0x86, 0x3b, 0x52, 0xa1, 0x6c, 0xaa, 0x55, 0x29, 0x9d,
0x97, 0xb2, 0x87, 0x90, 0x61, 0xbe, 0xdc, 0xfc, 0xbc, 0x95, 0xcf, 0xcd, 0x37, 0x3f, 0x5b, 0xd1,
0x53, 0x39, 0x84, 0x3c, 0x41, 0xa2, 0x6d, 0x47, 0x14, 0x2a, 0x9e, 0x5d, 0x56, 0xf2, 0xd3, 0xab,
0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07)
def sub_bytes(data):
return [SBOX[x] for x in data]
def sub_bytes_inv(data):
return [SBOX_INV[x] for x in data]
def rotate(data):
return data[1:] + [data[0]]
def key_schedule_core(data, rcon_iteration):
data = rotate(data)
data = sub_bytes(data)
data[0] = data[0] ^ RCON[rcon_iteration]
return data
def xor(data1, data2):
return [x^y for x, y in zip(data1, data2)]
def rijndael_mul(a, b):
if(a==0 or b==0):
return 0
return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]
def mix_column(data, matrix):
data_mixed = []
for row in range(4):
mixed = 0
for column in range(4):
# xor is (+) and (-)
mixed ^= rijndael_mul(data[column], matrix[row][column])
data_mixed.append(mixed)
return data_mixed
def mix_columns(data, matrix=MIX_COLUMN_MATRIX):
data_mixed = []
for i in range(4):
column = data[i*4 : (i+1)*4]
data_mixed += mix_column(column, matrix)
return data_mixed
def mix_columns_inv(data):
return mix_columns(data, MIX_COLUMN_MATRIX_INV)
def shift_rows(data):
data_shifted = []
for column in range(4):
for row in range(4):
data_shifted.append( data[((column + row) & 0b11) * 4 + row] )
return data_shifted
def shift_rows_inv(data):
data_shifted = []
for column in range(4):
for row in range(4):
data_shifted.append( data[((column - row) & 0b11) * 4 + row] )
return data_shifted
def inc(data):
data = data[:] # copy
for i in range(len(data)-1,-1,-1):
if data[i] == 255:
data[i] = 0
else:
data[i] = data[i] + 1
break
return data
-29
View File
@@ -1,29 +0,0 @@
from __future__ import unicode_literals
from .common import FileDownloader
from .hls import HlsFD
from .http import HttpFD
from .mplayer import MplayerFD
from .rtmp import RtmpFD
from .f4m import F4mFD
from ..utils import (
determine_ext,
)
def get_suitable_downloader(info_dict):
"""Get the downloader class that can handle the info dict."""
url = info_dict['url']
protocol = info_dict.get('protocol')
if url.startswith('rtmp'):
return RtmpFD
if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
return HlsFD
if url.startswith('mms') or url.startswith('rtsp'):
return MplayerFD
if determine_ext(url) == 'f4m':
return F4mFD
else:
return HttpFD
-316
View File
@@ -1,316 +0,0 @@
import os
import re
import sys
import time
from ..utils import (
encodeFilename,
timeconvert,
format_bytes,
)
class FileDownloader(object):
"""File Downloader class.
File downloader objects are the ones responsible of downloading the
actual video file and writing it to disk.
File downloaders accept a lot of parameters. In order not to saturate
the object constructor with arguments, it receives a dictionary of
options instead.
Available options:
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
ratelimit: Download speed limit, in bytes/sec.
retries: Number of times to retry for HTTP error 5xx
buffersize: Size of download buffer in bytes.
noresizebuffer: Do not automatically resize the download buffer.
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
test: Download only first bytes to test the downloader.
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
Subclasses of this one must re-define the real_download method.
"""
params = None
def __init__(self, ydl, params):
"""Create a FileDownloader object with the given options."""
self.ydl = ydl
self._progress_hooks = []
self.params = params
@staticmethod
def format_seconds(seconds):
(mins, secs) = divmod(seconds, 60)
(hours, mins) = divmod(mins, 60)
if hours > 99:
return '--:--:--'
if hours == 0:
return '%02d:%02d' % (mins, secs)
else:
return '%02d:%02d:%02d' % (hours, mins, secs)
@staticmethod
def calc_percent(byte_counter, data_len):
if data_len is None:
return None
return float(byte_counter) / float(data_len) * 100.0
@staticmethod
def format_percent(percent):
if percent is None:
return '---.-%'
return '%6s' % ('%3.1f%%' % percent)
@staticmethod
def calc_eta(start, now, total, current):
if total is None:
return None
dif = now - start
if current == 0 or dif < 0.001: # One millisecond
return None
rate = float(current) / dif
return int((float(total) - float(current)) / rate)
@staticmethod
def format_eta(eta):
if eta is None:
return '--:--'
return FileDownloader.format_seconds(eta)
@staticmethod
def calc_speed(start, now, bytes):
dif = now - start
if bytes == 0 or dif < 0.001: # One millisecond
return None
return float(bytes) / dif
@staticmethod
def format_speed(speed):
if speed is None:
return '%10s' % '---b/s'
return '%10s' % ('%s/s' % format_bytes(speed))
@staticmethod
def best_block_size(elapsed_time, bytes):
new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001:
return int(new_max)
rate = bytes / elapsed_time
if rate > new_max:
return int(new_max)
if rate < new_min:
return int(new_min)
return int(rate)
@staticmethod
def parse_bytes(bytestr):
"""Parse a string indicating a byte quantity into an integer."""
matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
if matchobj is None:
return None
number = float(matchobj.group(1))
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
return int(round(number * multiplier))
def to_screen(self, *args, **kargs):
self.ydl.to_screen(*args, **kargs)
def to_stderr(self, message):
self.ydl.to_screen(message)
def to_console_title(self, message):
self.ydl.to_console_title(message)
def trouble(self, *args, **kargs):
self.ydl.trouble(*args, **kargs)
def report_warning(self, *args, **kargs):
self.ydl.report_warning(*args, **kargs)
def report_error(self, *args, **kargs):
self.ydl.report_error(*args, **kargs)
def slow_down(self, start_time, byte_counter):
"""Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit', None)
if rate_limit is None or byte_counter == 0:
return
now = time.time()
elapsed = now - start_time
if elapsed <= 0.0:
return
speed = float(byte_counter) / elapsed
if speed > rate_limit:
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
def temp_name(self, filename):
"""Returns a temporary filename for the given filename."""
if self.params.get('nopart', False) or filename == u'-' or \
(os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
return filename
return filename + u'.part'
def undo_temp_name(self, filename):
if filename.endswith(u'.part'):
return filename[:-len(u'.part')]
return filename
def try_rename(self, old_filename, new_filename):
try:
if old_filename == new_filename:
return
os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
except (IOError, OSError) as err:
self.report_error(u'unable to rename file: %s' % str(err))
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
if last_modified_hdr is None:
return
if not os.path.isfile(encodeFilename(filename)):
return
timestr = last_modified_hdr
if timestr is None:
return
filetime = timeconvert(timestr)
if filetime is None:
return filetime
# Ignore obviously invalid dates
if filetime == 0:
return
try:
os.utime(filename, (time.time(), filetime))
except:
pass
return filetime
def report_destination(self, filename):
"""Report destination filename."""
self.to_screen(u'[download] Destination: ' + filename)
def _report_progress_status(self, msg, is_last_line=False):
fullmsg = u'[download] ' + msg
if self.params.get('progress_with_newline', False):
self.to_screen(fullmsg)
else:
if os.name == 'nt':
prev_len = getattr(self, '_report_progress_prev_line_length',
0)
if prev_len > len(fullmsg):
fullmsg += u' ' * (prev_len - len(fullmsg))
self._report_progress_prev_line_length = len(fullmsg)
clear_line = u'\r'
else:
clear_line = (u'\r\x1b[K' if sys.stderr.isatty() else u'\r')
self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
self.to_console_title(u'youtube-dl ' + msg)
def report_progress(self, percent, data_len_str, speed, eta):
"""Report download progress."""
if self.params.get('noprogress', False):
return
if eta is not None:
eta_str = self.format_eta(eta)
else:
eta_str = 'Unknown ETA'
if percent is not None:
percent_str = self.format_percent(percent)
else:
percent_str = 'Unknown %'
speed_str = self.format_speed(speed)
msg = (u'%s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str))
self._report_progress_status(msg)
def report_progress_live_stream(self, downloaded_data_len, speed, elapsed):
if self.params.get('noprogress', False):
return
downloaded_str = format_bytes(downloaded_data_len)
speed_str = self.format_speed(speed)
elapsed_str = FileDownloader.format_seconds(elapsed)
msg = u'%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
self._report_progress_status(msg)
def report_finish(self, data_len_str, tot_time):
"""Report download finished."""
if self.params.get('noprogress', False):
self.to_screen(u'[download] Download completed')
else:
self._report_progress_status(
(u'100%% of %s in %s' %
(data_len_str, self.format_seconds(tot_time))),
is_last_line=True)
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
def report_retry(self, count, retries):
"""Report retry in case of HTTP error 5xx"""
self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
self.to_screen(u'[download] %s has already been downloaded' % file_name)
except UnicodeEncodeError:
self.to_screen(u'[download] The file has already been downloaded')
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
self.to_screen(u'[download] Unable to resume')
def download(self, filename, info_dict):
"""Download to a filename using the info from info_dict
Return True on success and False otherwise
"""
# Check file already present
if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename)
self._hook_progress({
'filename': filename,
'status': 'finished',
'total_bytes': os.path.getsize(encodeFilename(filename)),
})
return True
return self.real_download(filename, info_dict)
def real_download(self, filename, info_dict):
"""Real download process. Redefine in subclasses."""
raise NotImplementedError(u'This method must be implemented by sublcasses')
def _hook_progress(self, status):
for ph in self._progress_hooks:
ph(status)
def add_progress_hook(self, ph):
""" ph gets called on download progress, with a dictionary with the entries
* filename: The final filename
* status: One of "downloading" and "finished"
It can also have some of the following entries:
* downloaded_bytes: Bytes on disks
* total_bytes: Total bytes, None if unknown
* tmpfilename: The filename we're currently writing to
* eta: The estimated time in seconds, None if unknown
* speed: The download speed in bytes/second, None if unknown
Hooks are guaranteed to be called at least once (with status "finished")
if the download is successful.
"""
self._progress_hooks.append(ph)
-314
View File
@@ -1,314 +0,0 @@
from __future__ import unicode_literals
import base64
import io
import itertools
import os
import time
import xml.etree.ElementTree as etree
from .common import FileDownloader
from .http import HttpFD
from ..utils import (
struct_pack,
struct_unpack,
compat_urlparse,
format_bytes,
encodeFilename,
sanitize_open,
)
class FlvReader(io.BytesIO):
"""
Reader for Flv files
The file format is documented in https://www.adobe.com/devnet/f4v.html
"""
# Utility functions for reading numbers and strings
def read_unsigned_long_long(self):
return struct_unpack('!Q', self.read(8))[0]
def read_unsigned_int(self):
return struct_unpack('!I', self.read(4))[0]
def read_unsigned_char(self):
return struct_unpack('!B', self.read(1))[0]
def read_string(self):
res = b''
while True:
char = self.read(1)
if char == b'\x00':
break
res += char
return res
def read_box_info(self):
"""
Read a box and return the info as a tuple: (box_size, box_type, box_data)
"""
real_size = size = self.read_unsigned_int()
box_type = self.read(4)
header_end = 8
if size == 1:
real_size = self.read_unsigned_long_long()
header_end = 16
return real_size, box_type, self.read(real_size-header_end)
def read_asrt(self):
# version
self.read_unsigned_char()
# flags
self.read(3)
quality_entry_count = self.read_unsigned_char()
# QualityEntryCount
for i in range(quality_entry_count):
self.read_string()
segment_run_count = self.read_unsigned_int()
segments = []
for i in range(segment_run_count):
first_segment = self.read_unsigned_int()
fragments_per_segment = self.read_unsigned_int()
segments.append((first_segment, fragments_per_segment))
return {
'segment_run': segments,
}
def read_afrt(self):
# version
self.read_unsigned_char()
# flags
self.read(3)
# time scale
self.read_unsigned_int()
quality_entry_count = self.read_unsigned_char()
# QualitySegmentUrlModifiers
for i in range(quality_entry_count):
self.read_string()
fragments_count = self.read_unsigned_int()
fragments = []
for i in range(fragments_count):
first = self.read_unsigned_int()
first_ts = self.read_unsigned_long_long()
duration = self.read_unsigned_int()
if duration == 0:
discontinuity_indicator = self.read_unsigned_char()
else:
discontinuity_indicator = None
fragments.append({
'first': first,
'ts': first_ts,
'duration': duration,
'discontinuity_indicator': discontinuity_indicator,
})
return {
'fragments': fragments,
}
def read_abst(self):
# version
self.read_unsigned_char()
# flags
self.read(3)
self.read_unsigned_int() # BootstrapinfoVersion
# Profile,Live,Update,Reserved
self.read(1)
# time scale
self.read_unsigned_int()
# CurrentMediaTime
self.read_unsigned_long_long()
# SmpteTimeCodeOffset
self.read_unsigned_long_long()
self.read_string() # MovieIdentifier
server_count = self.read_unsigned_char()
# ServerEntryTable
for i in range(server_count):
self.read_string()
quality_count = self.read_unsigned_char()
# QualityEntryTable
for i in range(quality_count):
self.read_string()
# DrmData
self.read_string()
# MetaData
self.read_string()
segments_count = self.read_unsigned_char()
segments = []
for i in range(segments_count):
box_size, box_type, box_data = self.read_box_info()
assert box_type == b'asrt'
segment = FlvReader(box_data).read_asrt()
segments.append(segment)
fragments_run_count = self.read_unsigned_char()
fragments = []
for i in range(fragments_run_count):
box_size, box_type, box_data = self.read_box_info()
assert box_type == b'afrt'
fragments.append(FlvReader(box_data).read_afrt())
return {
'segments': segments,
'fragments': fragments,
}
def read_bootstrap_info(self):
total_size, box_type, box_data = self.read_box_info()
assert box_type == b'abst'
return FlvReader(box_data).read_abst()
def read_bootstrap_info(bootstrap_bytes):
return FlvReader(bootstrap_bytes).read_bootstrap_info()
def build_fragments_list(boot_info):
""" Return a list of (segment, fragment) for each fragment in the video """
res = []
segment_run_table = boot_info['segments'][0]
# I've only found videos with one segment
segment_run_entry = segment_run_table['segment_run'][0]
n_frags = segment_run_entry[1]
fragment_run_entry_table = boot_info['fragments'][0]['fragments']
first_frag_number = fragment_run_entry_table[0]['first']
for (i, frag_number) in zip(range(1, n_frags+1), itertools.count(first_frag_number)):
res.append((1, frag_number))
return res
def write_flv_header(stream, metadata):
"""Writes the FLV header and the metadata to stream"""
# FLV header
stream.write(b'FLV\x01')
stream.write(b'\x05')
stream.write(b'\x00\x00\x00\x09')
# FLV File body
stream.write(b'\x00\x00\x00\x00')
# FLVTAG
# Script data
stream.write(b'\x12')
# Size of the metadata with 3 bytes
stream.write(struct_pack('!L', len(metadata))[1:])
stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
stream.write(metadata)
# Magic numbers extracted from the output files produced by AdobeHDS.php
#(https://github.com/K-S-V/Scripts)
stream.write(b'\x00\x00\x01\x73')
def _add_ns(prop):
return '{http://ns.adobe.com/f4m/1.0}%s' % prop
class HttpQuietDownloader(HttpFD):
def to_screen(self, *args, **kargs):
pass
class F4mFD(FileDownloader):
"""
A downloader for f4m manifests or AdobeHDS.
"""
def real_download(self, filename, info_dict):
man_url = info_dict['url']
self.to_screen('[download] Downloading f4m manifest')
manifest = self.ydl.urlopen(man_url).read()
self.report_destination(filename)
http_dl = HttpQuietDownloader(self.ydl,
{
'continuedl': True,
'quiet': True,
'noprogress': True,
'test': self.params.get('test', False),
})
doc = etree.fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
formats = sorted(formats, key=lambda f: f[0])
rate, media = formats[-1]
base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).text)
metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
boot_info = read_bootstrap_info(bootstrap)
fragments_list = build_fragments_list(boot_info)
if self.params.get('test', False):
# We only download the first fragment
fragments_list = fragments_list[:1]
total_frags = len(fragments_list)
tmpfilename = self.temp_name(filename)
(dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
write_flv_header(dest_stream, metadata)
# This dict stores the download progress, it's updated by the progress
# hook
state = {
'downloaded_bytes': 0,
'frag_counter': 0,
}
start = time.time()
def frag_progress_hook(status):
frag_total_bytes = status.get('total_bytes', 0)
estimated_size = (state['downloaded_bytes'] +
(total_frags - state['frag_counter']) * frag_total_bytes)
if status['status'] == 'finished':
state['downloaded_bytes'] += frag_total_bytes
state['frag_counter'] += 1
progress = self.calc_percent(state['frag_counter'], total_frags)
byte_counter = state['downloaded_bytes']
else:
frag_downloaded_bytes = status['downloaded_bytes']
byte_counter = state['downloaded_bytes'] + frag_downloaded_bytes
frag_progress = self.calc_percent(frag_downloaded_bytes,
frag_total_bytes)
progress = self.calc_percent(state['frag_counter'], total_frags)
progress += frag_progress / float(total_frags)
eta = self.calc_eta(start, time.time(), estimated_size, byte_counter)
self.report_progress(progress, format_bytes(estimated_size),
status.get('speed'), eta)
http_dl.add_progress_hook(frag_progress_hook)
frags_filenames = []
for (seg_i, frag_i) in fragments_list:
name = 'Seg%d-Frag%d' % (seg_i, frag_i)
url = base_url + name
frag_filename = '%s-%s' % (tmpfilename, name)
success = http_dl.download(frag_filename, {'url': url})
if not success:
return False
with open(frag_filename, 'rb') as down:
down_data = down.read()
reader = FlvReader(down_data)
while True:
_, box_type, box_data = reader.read_box_info()
if box_type == b'mdat':
dest_stream.write(box_data)
break
frags_filenames.append(frag_filename)
self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
self.try_rename(tmpfilename, filename)
for frag_file in frags_filenames:
os.remove(frag_file)
fsize = os.path.getsize(encodeFilename(filename))
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
})
return True
-44
View File
@@ -1,44 +0,0 @@
import os
import subprocess
from .common import FileDownloader
from ..utils import (
encodeFilename,
)
class HlsFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
args = ['-y', '-i', url, '-f', 'mp4', '-c', 'copy',
'-bsf:a', 'aac_adtstoasc', tmpfilename]
for program in ['avconv', 'ffmpeg']:
try:
subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
break
except (OSError, IOError):
pass
else:
self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found')
cmd = [program] + args
retval = subprocess.call(cmd)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen(u'\r[%s] %s bytes' % (cmd[0], fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
})
return True
else:
self.to_stderr(u"\n")
self.report_error(u'ffmpeg exited with code %d' % retval)
return False
-187
View File
@@ -1,187 +0,0 @@
import os
import time
from .common import FileDownloader
from ..utils import (
compat_urllib_request,
compat_urllib_error,
ContentTooShortError,
encodeFilename,
sanitize_open,
format_bytes,
)
class HttpFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
tmpfilename = self.temp_name(filename)
stream = None
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
if 'user_agent' in info_dict:
headers['Youtubedl-user-agent'] = info_dict['user_agent']
basic_request = compat_urllib_request.Request(url, None, headers)
request = compat_urllib_request.Request(url, None, headers)
if self.params.get('test', False):
request.add_header('Range', 'bytes=0-10240')
# Establish possible resume length
if os.path.isfile(encodeFilename(tmpfilename)):
resume_len = os.path.getsize(encodeFilename(tmpfilename))
else:
resume_len = 0
open_mode = 'wb'
if resume_len != 0:
if self.params.get('continuedl', False):
self.report_resuming_byte(resume_len)
request.add_header('Range', 'bytes=%d-' % resume_len)
open_mode = 'ab'
else:
resume_len = 0
count = 0
retries = self.params.get('retries', 0)
while count <= retries:
# Establish connection
try:
data = compat_urllib_request.urlopen(request)
break
except (compat_urllib_error.HTTPError, ) as err:
if (err.code < 500 or err.code >= 600) and err.code != 416:
# Unexpected HTTP error
raise
elif err.code == 416:
# Unable to resume (requested range not satisfiable)
try:
# Open the connection again without the range header
data = compat_urllib_request.urlopen(basic_request)
content_length = data.info()['Content-Length']
except (compat_urllib_error.HTTPError, ) as err:
if err.code < 500 or err.code >= 600:
raise
else:
# Examine the reported length
if (content_length is not None and
(resume_len - 100 < int(content_length) < resume_len + 100)):
# The file had already been fully downloaded.
# Explanation to the above condition: in issue #175 it was revealed that
# YouTube sometimes adds or removes a few bytes from the end of the file,
# changing the file size slightly and causing problems for some users. So
# I decided to implement a suggested change and consider the file
# completely downloaded if the file size differs less than 100 bytes from
# the one in the hard drive.
self.report_file_already_downloaded(filename)
self.try_rename(tmpfilename, filename)
self._hook_progress({
'filename': filename,
'status': 'finished',
})
return True
else:
# The length does not match, we start the download over
self.report_unable_to_resume()
resume_len = 0
open_mode = 'wb'
break
# Retry
count += 1
if count <= retries:
self.report_retry(count, retries)
if count > retries:
self.report_error(u'giving up after %s retries' % retries)
return False
data_len = data.info().get('Content-length', None)
if data_len is not None:
data_len = int(data_len) + resume_len
min_data_len = self.params.get("min_filesize", None)
max_data_len = self.params.get("max_filesize", None)
if min_data_len is not None and data_len < min_data_len:
self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
return False
if max_data_len is not None and data_len > max_data_len:
self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
return False
data_len_str = format_bytes(data_len)
byte_counter = 0 + resume_len
block_size = self.params.get('buffersize', 1024)
start = time.time()
while True:
# Download and write
before = time.time()
data_block = data.read(block_size)
after = time.time()
if len(data_block) == 0:
break
byte_counter += len(data_block)
# Open file just in time
if stream is None:
try:
(stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
assert stream is not None
filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename)
except (OSError, IOError) as err:
self.report_error(u'unable to open for writing: %s' % str(err))
return False
try:
stream.write(data_block)
except (IOError, OSError) as err:
self.to_stderr(u"\n")
self.report_error(u'unable to write data: %s' % str(err))
return False
if not self.params.get('noresizebuffer', False):
block_size = self.best_block_size(after - before, len(data_block))
# Progress message
speed = self.calc_speed(start, time.time(), byte_counter - resume_len)
if data_len is None:
eta = percent = None
else:
percent = self.calc_percent(byte_counter, data_len)
eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
self.report_progress(percent, data_len_str, speed, eta)
self._hook_progress({
'downloaded_bytes': byte_counter,
'total_bytes': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'eta': eta,
'speed': speed,
})
# Apply rate limit
self.slow_down(start, byte_counter - resume_len)
if stream is None:
self.to_stderr(u"\n")
self.report_error(u'Did not get any data blocks')
return False
stream.close()
self.report_finish(data_len_str, (time.time() - start))
if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, int(data_len))
self.try_rename(tmpfilename, filename)
# Update file modification time
if self.params.get('updatetime', True):
info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
self._hook_progress({
'downloaded_bytes': byte_counter,
'total_bytes': byte_counter,
'filename': filename,
'status': 'finished',
})
return True
-40
View File
@@ -1,40 +0,0 @@
import os
import subprocess
from .common import FileDownloader
from ..utils import (
encodeFilename,
)
class MplayerFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url]
# Check for mplayer first
try:
subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
except (OSError, IOError):
self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0])
return False
# Download using mplayer.
retval = subprocess.call(args)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
})
return True
else:
self.to_stderr(u"\n")
self.report_error(u'mplayer exited with code %d' % retval)
return False
-195
View File
@@ -1,195 +0,0 @@
from __future__ import unicode_literals
import os
import re
import subprocess
import sys
import time
from .common import FileDownloader
from ..utils import (
encodeFilename,
format_bytes,
)
class RtmpFD(FileDownloader):
def real_download(self, filename, info_dict):
def run_rtmpdump(args):
start = time.time()
resume_percent = None
resume_downloaded_data_len = None
proc = subprocess.Popen(args, stderr=subprocess.PIPE)
cursor_in_new_line = True
proc_stderr_closed = False
while not proc_stderr_closed:
# read line from stderr
line = ''
while True:
char = proc.stderr.read(1)
if not char:
proc_stderr_closed = True
break
if char in [b'\r', b'\n']:
break
line += char.decode('ascii', 'replace')
if not line:
# proc_stderr_closed is True
continue
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
if mobj:
downloaded_data_len = int(float(mobj.group(1))*1024)
percent = float(mobj.group(2))
if not resume_percent:
resume_percent = percent
resume_downloaded_data_len = downloaded_data_len
eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent)
speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_downloaded_data_len)
data_len = None
if percent > 0:
data_len = int(downloaded_data_len * 100 / percent)
data_len_str = '~' + format_bytes(data_len)
self.report_progress(percent, data_len_str, speed, eta)
cursor_in_new_line = False
self._hook_progress({
'downloaded_bytes': downloaded_data_len,
'total_bytes': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'eta': eta,
'speed': speed,
})
else:
# no percent for live streams
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
if mobj:
downloaded_data_len = int(float(mobj.group(1))*1024)
time_now = time.time()
speed = self.calc_speed(start, time_now, downloaded_data_len)
self.report_progress_live_stream(downloaded_data_len, speed, time_now - start)
cursor_in_new_line = False
self._hook_progress({
'downloaded_bytes': downloaded_data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'speed': speed,
})
elif self.params.get('verbose', False):
if not cursor_in_new_line:
self.to_screen('')
cursor_in_new_line = True
self.to_screen('[rtmpdump] '+line)
proc.wait()
if not cursor_in_new_line:
self.to_screen('')
return proc.returncode
url = info_dict['url']
player_url = info_dict.get('player_url', None)
page_url = info_dict.get('page_url', None)
app = info_dict.get('app', None)
play_path = info_dict.get('play_path', None)
tc_url = info_dict.get('tc_url', None)
flash_version = info_dict.get('flash_version', None)
live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn', None)
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
test = self.params.get('test', False)
# Check for rtmpdump first
try:
subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
except (OSError, IOError):
self.report_error('RTMP download detected but "rtmpdump" could not be run')
return False
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename]
if player_url is not None:
basic_args += ['--swfVfy', player_url]
if page_url is not None:
basic_args += ['--pageUrl', page_url]
if app is not None:
basic_args += ['--app', app]
if play_path is not None:
basic_args += ['--playpath', play_path]
if tc_url is not None:
basic_args += ['--tcUrl', url]
if test:
basic_args += ['--stop', '1']
if flash_version is not None:
basic_args += ['--flashVer', flash_version]
if live:
basic_args += ['--live']
if conn:
basic_args += ['--conn', conn]
args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode
# on Python 2.x
# See http://stackoverflow.com/a/9951851/35070
subprocess_encoding = sys.getfilesystemencoding()
args = [a.encode(subprocess_encoding, 'ignore') for a in args]
else:
subprocess_encoding = None
if self.params.get('verbose', False):
if subprocess_encoding:
str_args = [
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
for a in args]
else:
str_args = args
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
except ImportError:
shell_quote = repr
self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
RD_SUCCESS = 0
RD_FAILED = 1
RD_INCOMPLETE = 2
RD_NO_CONNECT = 3
retval = run_rtmpdump(args)
if retval == RD_NO_CONNECT:
self.report_error('[rtmpdump] Could not connect to RTMP server.')
return False
while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live:
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed
retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == RD_FAILED:
break
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024:
self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
retval = RD_SUCCESS
break
if retval == RD_SUCCESS or (test and retval == RD_INCOMPLETE):
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % fsize)
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
})
return True
else:
self.to_stderr('\n')
self.report_error('rtmpdump exited with code %d' % retval)
return False
-323
View File
@@ -1,323 +0,0 @@
from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE
from .anitube import AnitubeIE
from .aparat import AparatIE
from .appletrailers import AppleTrailersIE
from .archiveorg import ArchiveOrgIE
from .ard import ARDIE
from .arte import (
ArteTvIE,
ArteTVPlus7IE,
ArteTVCreativeIE,
ArteTVFutureIE,
ArteTVDDCIE,
)
from .auengine import AUEngineIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbccouk import BBCCoUkIE
from .blinkx import BlinkxIE
from .bliptv import BlipTVIE, BlipTVUserIE
from .bloomberg import BloombergIE
from .br import BRIE
from .breakcom import BreakIE
from .brightcove import BrightcoveIE
from .c56 import C56IE
from .canal13cl import Canal13clIE
from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
from .cbs import CBSIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .chilloutzone import ChilloutzoneIE
from .cinemassacre import CinemassacreIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
from .cmt import CMTIE
from .cnn import (
CNNIE,
CNNBlogsIE,
)
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .condenast import CondeNastIE
from .criterion import CriterionIE
from .crunchyroll import CrunchyrollIE
from .cspan import CSpanIE
from .d8 import D8IE
from .dailymotion import (
DailymotionIE,
DailymotionPlaylistIE,
DailymotionUserIE,
)
from .daum import DaumIE
from .depositfiles import DepositFilesIE
from .dotsub import DotsubIE
from .dreisat import DreiSatIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .dropbox import DropboxIE
from .ebaumsworld import EbaumsWorldIE
from .ehow import EHowIE
from .eighttracks import EightTracksIE
from .eitb import EitbIE
from .elpais import ElPaisIE
from .escapist import EscapistIE
from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE
from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE
from .faz import FazIE
from .firstpost import FirstpostIE
from .firsttv import FirstTVIE
from .fktv import (
FKTVIE,
FKTVPosteckeIE,
)
from .flickr import FlickrIE
from .fourtube import FourTubeIE
from .franceinter import FranceInterIE
from .francetv import (
PluzzIE,
FranceTvInfoIE,
FranceTVIE,
GenerationQuoiIE,
CultureboxIE,
)
from .freesound import FreesoundIE
from .freespeech import FreespeechIE
from .funnyordie import FunnyOrDieIE
from .gamekings import GamekingsIE
from .gamespot import GameSpotIE
from .gametrailers import GametrailersIE
from .gdcvault import GDCVaultIE
from .generic import GenericIE
from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE
from .hark import HarkIE
from .helsinki import HelsinkiIE
from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .huffpost import HuffPostIE
from .hypem import HypemIE
from .ign import IGNIE, OneUPIE
from .imdb import (
ImdbIE,
ImdbListIE
)
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE
from .internetvideoarchive import InternetVideoArchiveIE
from .iprima import IPrimaIE
from .ivi import (
IviIE,
IviCompilationIE
)
from .jadorecettepub import JadoreCettePubIE
from .jeuxvideo import JeuxVideoIE
from .jukebox import JukeboxIE
from .justintv import JustinTVIE
from .jpopsukitv import JpopsukiIE
from .kankan import KankanIE
from .keezmovies import KeezMoviesIE
from .khanacademy import KhanAcademyIE
from .kickstarter import KickStarterIE
from .keek import KeekIE
from .kontrtube import KontrTubeIE
from .la7 import LA7IE
from .lifenews import LifeNewsIE
from .liveleak import LiveLeakIE
from .livestream import LivestreamIE, LivestreamOriginalIE
from .lynda import (
LyndaIE,
LyndaCourseIE
)
from .m6 import M6IE
from .macgamestore import MacGameStoreIE
from .mailru import MailRuIE
from .malemotion import MalemotionIE
from .mdr import MDRIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mixcloud import MixcloudIE
from .mpora import MporaIE
from .mofosex import MofosexIE
from .mooshare import MooshareIE
from .mtv import (
MTVIE,
MTVIggyIE,
)
from .muzu import MuzuTVIE
from .myspace import MySpaceIE
from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .naver import NaverIE
from .nba import NBAIE
from .nbc import (
NBCIE,
NBCNewsIE,
)
from .ndr import NDRIE
from .ndtv import NDTVIE
from .newgrounds import NewgroundsIE
from .nfb import NFBIE
from .nhl import NHLIE, NHLVideocenterIE
from .niconico import NiconicoIE
from .ninegag import NineGagIE
from .normalboots import NormalbootsIE
from .novamov import NovaMovIE
from .nowness import NownessIE
from .nowvideo import NowVideoIE
from .ooyala import OoyalaIE
from .orf import ORFIE
from .pbs import PBSIE
from .photobucket import PhotobucketIE
from .podomatic import PodomaticIE
from .pornhd import PornHdIE
from .pornhub import PornHubIE
from .pornotube import PornotubeIE
from .prosiebensat1 import ProSiebenSat1IE
from .pyvideo import PyvideoIE
from .radiofrance import RadioFranceIE
from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
from .ringtv import RingTVIE
from .ro220 import Ro220IE
from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rtlnow import RTLnowIE
from .rutube import (
RutubeIE,
RutubeChannelIE,
RutubeMovieIE,
RutubePersonIE,
)
from .savefrom import SaveFromIE
from .servingsys import ServingSysIE
from .sina import SinaIE
from .slashdot import SlashdotIE
from .slideshare import SlideshareIE
from .smotri import (
SmotriIE,
SmotriCommunityIE,
SmotriUserIE,
SmotriBroadcastIE,
)
from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
from .southparkstudios import (
SouthParkStudiosIE,
SouthparkDeIE,
)
from .space import SpaceIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE
from .spike import SpikeIE
from .stanfordoc import StanfordOpenClassroomIE
from .statigram import StatigramIE
from .steam import SteamIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .syfy import SyfyIE
from .sztvhu import SztvHuIE
from .teamcoco import TeamcocoIE
from .techtalks import TechTalksIE
from .ted import TEDIE
from .testurl import TestURLIE
from .tf1 import TF1IE
from .theplatform import ThePlatformIE
from .thisav import ThisAVIE
from .tinypic import TinyPicIE
from .toutv import TouTvIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .trutube import TruTubeIE
from .tube8 import Tube8IE
from .tudou import TudouIE
from .tumblr import TumblrIE
from .tutv import TutvIE
from .tvigle import TvigleIE
from .tvp import TvpIE
from .unistra import UnistraIE
from .ustream import UstreamIE, UstreamChannelIE
from .vbox7 import Vbox7IE
from .veehd import VeeHDIE
from .veoh import VeohIE
from .vesti import VestiIE
from .vevo import VevoIE
from .vice import ViceIE
from .viddler import ViddlerIE
from .videobam import VideoBamIE
from .videodetective import VideoDetectiveIE
from .videofyme import VideofyMeIE
from .videopremium import VideoPremiumIE
from .vimeo import (
VimeoIE,
VimeoChannelIE,
VimeoUserIE,
VimeoAlbumIE,
VimeoGroupsIE,
VimeoReviewIE,
)
from .vine import VineIE
from .viki import VikiIE
from .vk import VKIE
from .vube import VubeIE
from .wat import WatIE
from .weibo import WeiboIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
from .xhamster import XHamsterIE
from .xnxx import XNXXIE
from .xvideos import XVideosIE
from .xtube import XTubeIE
from .yahoo import (
YahooIE,
YahooNewsIE,
YahooSearchIE,
)
from .youjizz import YouJizzIE
from .youku import YoukuIE
from .youporn import YouPornIE
from .youtube import (
YoutubeIE,
YoutubeChannelIE,
YoutubeFavouritesIE,
YoutubeHistoryIE,
YoutubePlaylistIE,
YoutubeRecommendedIE,
YoutubeSearchDateIE,
YoutubeSearchIE,
YoutubeSearchURLIE,
YoutubeShowIE,
YoutubeSubscriptionsIE,
YoutubeTopListIE,
YoutubeTruncatedURLIE,
YoutubeUserIE,
YoutubeWatchLaterIE,
)
from .zdf import ZDFIE
_ALL_CLASSES = [
klass
for name, klass in globals().items()
if name.endswith('IE') and name != 'GenericIE'
]
_ALL_CLASSES.append(GenericIE)
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
"""
return [klass() for klass in _ALL_CLASSES]
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""
return globals()[ie_name+'IE']
-32
View File
@@ -1,32 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class AcademicEarthCourseIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
IE_NAME = 'AcademicEarth:Course'
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
playlist_id = m.group('id')
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
description = self._html_search_regex(
r'<p class="excerpt"[^>]*?>(.*?)</p>',
webpage, u'description', fatal=False)
urls = re.findall(
r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
webpage)
entries = [self.url_result(u) for u in urls]
return {
'_type': 'playlist',
'id': playlist_id,
'title': title,
'description': description,
'entries': entries,
}
-86
View File
@@ -1,86 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
compat_HTTPError,
compat_str,
compat_urllib_parse,
compat_urllib_parse_urlparse,
ExtractorError,
)
class AddAnimeIE(InfoExtractor):
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
IE_NAME = u'AddAnime'
_TEST = {
u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
u'file': u'24MR3YO5SAS9.mp4',
u'md5': u'72954ea10bc979ab5e2eb288b21425a0',
u'info_dict': {
u"description": u"One Piece 606",
u"title": u"One Piece 606"
}
}
def _real_extract(self, url):
try:
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id)
except ExtractorError as ee:
if not isinstance(ee.cause, compat_HTTPError) or \
ee.cause.code != 503:
raise
redir_webpage = ee.cause.read().decode('utf-8')
action = self._search_regex(
r'<form id="challenge-form" action="([^"]+)"',
redir_webpage, u'Redirect form')
vc = self._search_regex(
r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
redir_webpage, u'redirect vc value')
av = re.search(
r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
redir_webpage)
if av is None:
raise ExtractorError(u'Cannot find redirect math task')
av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
parsed_url = compat_urllib_parse_urlparse(url)
av_val = av_res + len(parsed_url.netloc)
confirm_url = (
parsed_url.scheme + u'://' + parsed_url.netloc +
action + '?' +
compat_urllib_parse.urlencode({
'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
self._download_webpage(
confirm_url, video_id,
note=u'Confirming after redirect')
webpage = self._download_webpage(url, video_id)
formats = []
for format_id in ('normal', 'hq'):
rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
video_url = self._search_regex(rex, webpage, u'video file URLx',
fatal=False)
if not video_url:
continue
formats.append({
'format_id': format_id,
'url': video_url,
})
if not formats:
raise ExtractorError(u'Cannot find any video format!')
video_title = self._og_search_title(webpage)
video_description = self._og_search_description(webpage)
return {
'_type': 'video',
'id': video_id,
'formats': formats,
'title': video_title,
'description': video_description
}
-53
View File
@@ -1,53 +0,0 @@
import re
from .common import InfoExtractor
class AnitubeIE(InfoExtractor):
IE_NAME = u'anitube.se'
_VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
_TEST = {
u'url': u'http://www.anitube.se/video/36621',
u'md5': u'59d0eeae28ea0bc8c05e7af429998d43',
u'file': u'36621.mp4',
u'info_dict': {
u'id': u'36621',
u'ext': u'mp4',
u'title': u'Recorder to Randoseru 01',
},
u'skip': u'Blocked in the US',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)',
webpage, u'key')
config_xml = self._download_xml('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
key)
video_title = config_xml.find('title').text
formats = []
video_url = config_xml.find('file')
if video_url is not None:
formats.append({
'format_id': 'sd',
'url': video_url.text,
})
video_url = config_xml.find('filehd')
if video_url is not None:
formats.append({
'format_id': 'hd',
'url': video_url.text,
})
return {
'id': video_id,
'title': video_title,
'formats': formats
}
-56
View File
@@ -1,56 +0,0 @@
#coding: utf-8
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
HEADRequest,
)
class AparatIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
_TEST = {
u'url': u'http://www.aparat.com/v/wP8On',
u'file': u'wP8On.mp4',
u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1',
u'info_dict': {
u"title": u"تیم گلکسی 11 - زومیت",
},
#u'skip': u'Extremely unreliable',
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
# Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work
embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' +
video_id + u'/vt/frame')
webpage = self._download_webpage(embed_url, video_id)
video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
for i, video_url in enumerate(video_urls):
req = HEADRequest(video_url)
res = self._request_webpage(
req, video_id, note=u'Testing video URL %d' % i, errnote=False)
if res:
break
else:
raise ExtractorError(u'No working video URLs found')
title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title')
thumbnail = self._search_regex(
r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False)
return {
'id': video_id,
'title': title,
'url': video_url,
'ext': 'mp4',
'thumbnail': thumbnail,
}
-135
View File
@@ -1,135 +0,0 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
determine_ext,
)
class AppleTrailersIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TEST = {
"url": "http://trailers.apple.com/trailers/wb/manofsteel/",
"playlist": [
{
"file": "manofsteel-trailer4.mov",
"md5": "d97a8e575432dbcb81b7c3acb741f8a8",
"info_dict": {
"duration": 111,
"title": "Trailer 4",
"upload_date": "20130523",
"uploader_id": "wb",
},
},
{
"file": "manofsteel-trailer3.mov",
"md5": "b8017b7131b721fb4e8d6f49e1df908c",
"info_dict": {
"duration": 182,
"title": "Trailer 3",
"upload_date": "20130417",
"uploader_id": "wb",
},
},
{
"file": "manofsteel-trailer.mov",
"md5": "d0f1e1150989b9924679b441f3404d48",
"info_dict": {
"duration": 148,
"title": "Trailer",
"upload_date": "20121212",
"uploader_id": "wb",
},
},
{
"file": "manofsteel-teaser.mov",
"md5": "5fe08795b943eb2e757fa95cb6def1cb",
"info_dict": {
"duration": 93,
"title": "Teaser",
"upload_date": "20120721",
"uploader_id": "wb",
},
}
]
}
_JSON_RE = r'iTunes.playURL\((.*?)\);'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
movie = mobj.group('movie')
uploader_id = mobj.group('company')
playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc')
def fix_html(s):
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', s)
s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
# The ' in the onClick attributes are not escaped, it couldn't be parsed
# like: http://trailers.apple.com/trailers/wb/gravity/
def _clean_json(m):
return u'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
s = re.sub(self._JSON_RE, _clean_json, s)
s = u'<html>' + s + u'</html>'
return s
doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
playlist = []
for li in doc.findall('./div/ul/li'):
on_click = li.find('.//a').attrib['onClick']
trailer_info_json = self._search_regex(self._JSON_RE,
on_click, u'trailer info')
trailer_info = json.loads(trailer_info_json)
title = trailer_info['title']
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
thumbnail = li.find('.//img').attrib['src']
upload_date = trailer_info['posted'].replace('-', '')
runtime = trailer_info['runtime']
m = re.search(r'(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime)
duration = None
if m:
duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
first_url = trailer_info['url']
trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
settings_json = self._download_webpage(settings_json_url, trailer_id, u'Downloading settings json')
settings = json.loads(settings_json)
formats = []
for format in settings['metadata']['sizes']:
# The src is a file pointing to the real video file
format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src'])
formats.append({
'url': format_url,
'ext': determine_ext(format_url),
'format': format['type'],
'width': format['width'],
'height': int(format['height']),
})
self._sort_formats(formats)
playlist.append({
'_type': 'video',
'id': video_id,
'title': title,
'formats': formats,
'title': title,
'duration': duration,
'thumbnail': thumbnail,
'upload_date': upload_date,
'uploader_id': uploader_id,
'user_agent': 'QuickTime compatible (youtube-dl)',
})
return {
'_type': 'playlist',
'id': movie,
'entries': playlist,
}
-61
View File
@@ -1,61 +0,0 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
unified_strdate,
)
class ArchiveOrgIE(InfoExtractor):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos'
_VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_TEST = {
"url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
'md5': '8af1d4cf447933ed3c7f4871162602db',
'info_dict': {
"title": "1968 Demo - FJCC Conference Presentation Reel #1",
"description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>",
"upload_date": "19681210",
"uploader": "SRI International"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
json_url = url + ('?' if '?' in url else '&') + 'output=json'
json_data = self._download_webpage(json_url, video_id)
data = json.loads(json_data)
title = data['metadata']['title'][0]
description = data['metadata']['description'][0]
uploader = data['metadata']['creator'][0]
upload_date = unified_strdate(data['metadata']['date'][0])
formats = [
{
'format': fdata['format'],
'url': 'http://' + data['server'] + data['dir'] + fn,
'file_size': int(fdata['size']),
}
for fn, fdata in data['files'].items()
if 'Video' in fdata['format']]
self._sort_formats(formats)
return {
'_type': 'video',
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'uploader': uploader,
'upload_date': upload_date,
'thumbnail': data.get('misc', {}).get('image'),
}
-83
View File
@@ -1,83 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
)
class ARDIE(InfoExtractor):
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
_TEST = {
'url': 'http://www.ardmediathek.de/das-erste/guenther-jauch/edward-snowden-im-interview-held-oder-verraeter?documentId=19288786',
'file': '19288786.mp4',
'md5': '515bf47ce209fb3f5a61b7aad364634c',
'info_dict': {
'title': 'Edward Snowden im Interview - Held oder Verräter?',
'description': 'Edward Snowden hat alles aufs Spiel gesetzt, um die weltweite \xdcberwachung durch die Geheimdienste zu enttarnen. Nun stellt sich der ehemalige NSA-Mitarbeiter erstmals weltweit in einem TV-Interview den Fragen eines NDR-Journalisten. Die Sendung vom Sonntagabend.',
'thumbnail': 'http://www.ardmediathek.de/ard/servlet/contentblob/19/28/87/90/19288790/bild/2250037',
},
'skip': 'Blocked outside of Germany',
}
def _real_extract(self, url):
# determine video id from url
m = re.match(self._VALID_URL, url)
numid = re.search(r'documentId=([0-9]+)', url)
if numid:
video_id = numid.group(1)
else:
video_id = m.group('video_id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', webpage, 'title')
description = self._html_search_meta(
'dcterms.abstract', webpage, 'description')
thumbnail = self._og_search_thumbnail(webpage)
streams = [
mo.groupdict()
for mo in re.finditer(
r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)', webpage)]
if not streams:
if '"fsk"' in webpage:
raise ExtractorError('This video is only available after 20:00')
formats = []
for s in streams:
format = {
'quality': int(s['quality']),
}
if s.get('rtmp_url'):
format['protocol'] = 'rtmp'
format['url'] = s['rtmp_url']
format['playpath'] = s['video_url']
else:
format['url'] = s['video_url']
quality_name = self._search_regex(
r'[,.]([a-zA-Z0-9_-]+),?\.mp4', format['url'],
'quality name', default='NA')
format['format_id'] = '%s-%s-%s-%s' % (
determine_ext(format['url']), quality_name, s['media_type'],
s['quality'])
formats.append(format)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats,
'thumbnail': thumbnail,
}
-282
View File
@@ -1,282 +0,0 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
find_xpath_attr,
unified_strdate,
determine_ext,
get_element_by_id,
compat_str,
get_element_by_attribute,
)
# There are different sources of video in arte.tv, the extraction process
# is different for each one. The videos usually expire in 7 days, so we can't
# add tests.
class ArteTvIE(InfoExtractor):
_VIDEOS_URL = r'(?:http://)?videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
_LIVEWEB_URL = r'(?:http://)?liveweb\.arte\.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
_LIVE_URL = r'index-[0-9]+\.html$'
IE_NAME = 'arte.tv'
@classmethod
def suitable(cls, url):
return any(re.match(regex, url) for regex in (cls._VIDEOS_URL, cls._LIVEWEB_URL))
# TODO implement Live Stream
# from ..utils import compat_urllib_parse
# def extractLiveStream(self, url):
# video_lang = url.split('/')[-4]
# info = self.grep_webpage(
# url,
# r'src="(.*?/videothek_js.*?\.js)',
# 0,
# [
# (1, 'url', 'Invalid URL: %s' % url)
# ]
# )
# http_host = url.split('/')[2]
# next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
# info = self.grep_webpage(
# next_url,
# r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
# '(http://.*?\.swf).*?' +
# '(rtmp://.*?)\'',
# re.DOTALL,
# [
# (1, 'path', 'could not extract video path: %s' % url),
# (2, 'player', 'could not extract video player: %s' % url),
# (3, 'url', 'could not extract video url: %s' % url)
# ]
# )
# video_url = '%s/%s' % (info.get('url'), info.get('path'))
def _real_extract(self, url):
mobj = re.match(self._VIDEOS_URL, url)
if mobj is not None:
id = mobj.group('id')
lang = mobj.group('lang')
return self._extract_video(url, id, lang)
mobj = re.match(self._LIVEWEB_URL, url)
if mobj is not None:
name = mobj.group('name')
lang = mobj.group('lang')
return self._extract_liveweb(url, name, lang)
if re.search(self._LIVE_URL, url) is not None:
raise ExtractorError(u'Arte live streams are not yet supported, sorry')
# self.extractLiveStream(url)
# return
def _extract_video(self, url, video_id, lang):
"""Extract from videos.arte.tv"""
ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
ref_xml_doc = self._download_xml(ref_xml_url, video_id, note=u'Downloading metadata')
config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
config_xml_url = config_node.attrib['ref']
config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')
video_urls = list(re.finditer(r'<url quality="(?P<quality>.*?)">(?P<url>.*?)</url>', config_xml))
def _key(m):
quality = m.group('quality')
if quality == 'hd':
return 2
else:
return 1
# We pick the best quality
video_urls = sorted(video_urls, key=_key)
video_url = list(video_urls)[-1].group('url')
title = self._html_search_regex(r'<name>(.*?)</name>', config_xml, 'title')
thumbnail = self._html_search_regex(r'<firstThumbnailUrl>(.*?)</firstThumbnailUrl>',
config_xml, 'thumbnail')
return {'id': video_id,
'title': title,
'thumbnail': thumbnail,
'url': video_url,
'ext': 'flv',
}
def _extract_liveweb(self, url, name, lang):
"""Extract form http://liveweb.arte.tv/"""
webpage = self._download_webpage(url, name)
video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, 'event id')
config_doc = self._download_xml('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
video_id, 'Downloading information')
event_doc = config_doc.find('event')
url_node = event_doc.find('video').find('urlHd')
if url_node is None:
url_node = event_doc.find('urlSd')
return {'id': video_id,
'title': event_doc.find('name%s' % lang.capitalize()).text,
'url': url_node.text.replace('MP4', 'mp4'),
'ext': 'flv',
'thumbnail': self._og_search_thumbnail(webpage),
}
class ArteTVPlus7IE(InfoExtractor):
IE_NAME = 'arte.tv:+7'
_VALID_URL = r'https?://www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
@classmethod
def _extract_url_info(cls, url):
mobj = re.match(cls._VALID_URL, url)
lang = mobj.group('lang')
# This is not a real id, it can be for example AJT for the news
# http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
video_id = mobj.group('id')
return video_id, lang
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, video_id)
return self._extract_from_webpage(webpage, video_id, lang)
def _extract_from_webpage(self, webpage, video_id, lang):
json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
return self._extract_from_json_url(json_url, video_id, lang)
def _extract_from_json_url(self, json_url, video_id, lang):
json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
self.report_extraction(video_id)
info = json.loads(json_info)
player_info = info['videoJsonPlayer']
info_dict = {
'id': player_info['VID'],
'title': player_info['VTI'],
'description': player_info.get('VDE'),
'upload_date': unified_strdate(player_info.get('VDA', '').split(' ')[0]),
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
}
all_formats = player_info['VSR'].values()
# Some formats use the m3u8 protocol
all_formats = list(filter(lambda f: f.get('videoFormat') != 'M3U8', all_formats))
def _match_lang(f):
if f.get('versionCode') is None:
return True
# Return true if that format is in the language of the url
if lang == 'fr':
l = 'F'
elif lang == 'de':
l = 'A'
regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
return any(re.match(r, f['versionCode']) for r in regexes)
# Some formats may not be in the same language as the url
formats = filter(_match_lang, all_formats)
formats = list(formats) # in python3 filter returns an iterator
if not formats:
# Some videos are only available in the 'Originalversion'
# they aren't tagged as being in French or German
if all(f['versionCode'] == 'VO' for f in all_formats):
formats = all_formats
else:
raise ExtractorError(u'The formats list is empty')
if re.match(r'[A-Z]Q', formats[0]['quality']) is not None:
def sort_key(f):
return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
else:
def sort_key(f):
return (
# Sort first by quality
int(f.get('height',-1)),
int(f.get('bitrate',-1)),
# The original version with subtitles has lower relevance
re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
# The version with sourds/mal subtitles has also lower relevance
re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None,
)
formats = sorted(formats, key=sort_key)
def _format(format_info):
quality = ''
height = format_info.get('height')
if height is not None:
quality = compat_str(height)
bitrate = format_info.get('bitrate')
if bitrate is not None:
quality += '-%d' % bitrate
if format_info.get('versionCode') is not None:
format_id = '%s-%s' % (quality, format_info['versionCode'])
else:
format_id = quality
info = {
'format_id': format_id,
'format_note': format_info.get('versionLibelle'),
'width': format_info.get('width'),
'height': height,
}
if format_info['mediaType'] == 'rtmp':
info['url'] = format_info['streamer']
info['play_path'] = 'mp4:' + format_info['url']
info['ext'] = 'flv'
else:
info['url'] = format_info['url']
info['ext'] = determine_ext(info['url'])
return info
info_dict['formats'] = [_format(f) for f in formats]
return info_dict
# It also uses the arte_vp_url url from the webpage to extract the information
class ArteTVCreativeIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:creative'
_VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/magazine?/(?P<id>.+)'
_TEST = {
'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
'file': '050489-002.mp4',
'info_dict': {
'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design',
},
}
class ArteTVFutureIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:future'
_VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de)/(thema|sujet)/.*?#article-anchor-(?P<id>\d+)'
_TEST = {
'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
'file': '050940-003.mp4',
'info_dict': {
'title': 'Les champignons au secours de la planète',
},
}
def _real_extract(self, url):
anchor_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, anchor_id)
row = get_element_by_id(anchor_id, webpage)
return self._extract_from_webpage(row, anchor_id, lang)
class ArteTVDDCIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:ddc'
_VALID_URL = r'http?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
if lang == 'folge':
lang = 'de'
elif lang == 'emission':
lang = 'fr'
webpage = self._download_webpage(url, video_id)
scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
return self._extract_from_json_url(json_url, video_id, lang)
-52
View File
@@ -1,52 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
determine_ext,
ExtractorError,
)
class AUEngineIE(InfoExtractor):
_TEST = {
'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
'file': 'lfvlytY6.mp4',
'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
'info_dict': {
'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
}
}
_VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
webpage, 'title')
title = title.strip()
links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
links = map(compat_urllib_parse.unquote, links)
thumbnail = None
video_url = None
for link in links:
if link.endswith('.png'):
thumbnail = link
elif '/videos/' in link:
video_url = link
if not video_url:
raise ExtractorError(u'Could not find video URL')
ext = '.' + determine_ext(video_url)
if ext == title[-len(ext):]:
title = title[:-len(ext)]
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
}
-88
View File
@@ -1,88 +0,0 @@
from __future__ import unicode_literals
import re
import json
import itertools
from .common import InfoExtractor
from ..utils import (
compat_urllib_request,
)
class BambuserIE(InfoExtractor):
IE_NAME = 'bambuser'
_VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
_API_KEY = '005f64509e19a868399060af746a00aa'
_TEST = {
'url': 'http://bambuser.com/v/4050584',
# MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
#u'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
'info_dict': {
'id': '4050584',
'ext': 'flv',
'title': 'Education engineering days - lightning talks',
'duration': 3741,
'uploader': 'pixelversity',
'uploader_id': '344706',
},
'params': {
# It doesn't respect the 'Range' header, it would download the whole video
# caused the travis builds to fail: https://travis-ci.org/rg3/youtube-dl/jobs/14493845#L59
'skip_download': True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
info_url = ('http://player-c.api.bambuser.com/getVideo.json?'
'&api_key=%s&vid=%s' % (self._API_KEY, video_id))
info_json = self._download_webpage(info_url, video_id)
info = json.loads(info_json)['result']
return {
'id': video_id,
'title': info['title'],
'url': info['url'],
'thumbnail': info.get('preview'),
'duration': int(info['length']),
'view_count': int(info['views_total']),
'uploader': info['username'],
'uploader_id': info['uid'],
}
class BambuserChannelIE(InfoExtractor):
IE_NAME = 'bambuser:channel'
_VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
# The maximum number we can get with each request
_STEP = 50
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user = mobj.group('user')
urls = []
last_id = ''
for i in itertools.count(1):
req_url = ('http://bambuser.com/xhr-api/index.php?username={user}'
'&sort=created&access_mode=0%2C1%2C2&limit={count}'
'&method=broadcast&format=json&vid_older_than={last}'
).format(user=user, count=self._STEP, last=last_id)
req = compat_urllib_request.Request(req_url)
# Without setting this header, we wouldn't get any result
req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
info_json = self._download_webpage(req, user,
'Downloading page %d' % i)
results = json.loads(info_json)['result']
if len(results) == 0:
break
last_id = results[-1]['vid']
urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)
return {
'_type': 'playlist',
'title': user,
'entries': urls,
}
-144
View File
@@ -1,144 +0,0 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
compat_str,
compat_urlparse,
ExtractorError,
)
class BandcampIE(InfoExtractor):
_VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
_TESTS = [{
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
'file': '1812978515.mp3',
'md5': 'c557841d5e50261777a6585648adf439',
'info_dict': {
"title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
"duration": 10,
},
'_skip': 'There is a limit of 200 free downloads / month for the test song'
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
# We get the link to the free download page
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
if m_download is None:
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
if m_trackinfo:
json_code = m_trackinfo.group(1)
data = json.loads(json_code)
d = data[0]
duration = int(round(d['duration']))
formats = []
for format_id, format_url in d['file'].items():
ext, _, abr_str = format_id.partition('-')
formats.append({
'format_id': format_id,
'url': format_url,
'ext': format_id.partition('-')[0],
'vcodec': 'none',
'acodec': format_id.partition('-')[0],
'abr': int(format_id.partition('-')[2]),
})
self._sort_formats(formats)
return {
'id': compat_str(d['id']),
'title': d['title'],
'formats': formats,
'duration': duration,
}
else:
raise ExtractorError('No free songs found')
download_link = m_download.group(1)
video_id = re.search(
r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
webpage, re.MULTILINE | re.DOTALL).group('id')
download_webpage = self._download_webpage(download_link, video_id,
'Downloading free downloads page')
# We get the dictionary of the track from some javascrip code
info = re.search(r'items: (.*?),$',
download_webpage, re.MULTILINE).group(1)
info = json.loads(info)[0]
# We pick mp3-320 for now, until format selection can be easily implemented.
mp3_info = info['downloads']['mp3-320']
# If we try to use this url it says the link has expired
initial_url = mp3_info['url']
re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
m_url = re.match(re_url, initial_url)
#We build the url we will use to get the final track url
# This url is build in Bandcamp in the script download_bunde_*.js
request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
# If we could correctly generate the .rand field the url would be
#in the "download_url" key
final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
return {
'id': video_id,
'title': info['title'],
'ext': 'mp3',
'vcodec': 'none',
'url': final_url,
'thumbnail': info.get('thumb_url'),
'uploader': info.get('artist'),
}
class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album'
_VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P<title>.*)'
_TEST = {
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
'playlist': [
{
'file': '1353101989.mp3',
'md5': '39bc1eded3476e927c724321ddf116cf',
'info_dict': {
'title': 'Intro',
}
},
{
'file': '38097443.mp3',
'md5': '1a2c32e2691474643e912cc6cd4bffaa',
'info_dict': {
'title': 'Kero One - Keep It Alive (Blazo remix)',
}
},
],
'params': {
'playlistend': 2
},
'skip': 'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
if not tracks_paths:
raise ExtractorError('The page doesn\'t contain any tracks')
entries = [
self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
for t_path in tracks_paths]
title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
return {
'_type': 'playlist',
'title': title,
'entries': entries,
}
-223
View File
@@ -1,223 +0,0 @@
from __future__ import unicode_literals
import re
from .subtitles import SubtitlesInfoExtractor
from ..utils import ExtractorError
class BBCCoUkIE(SubtitlesInfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
_TESTS = [
{
'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
'info_dict': {
'id': 'b039d07m',
'ext': 'flv',
'title': 'Kaleidoscope: Leonard Cohen',
'description': 'md5:db4755d7a665ae72343779f7dacb402c',
'duration': 1740,
},
'params': {
# rtmp download
'skip_download': True,
}
},
{
'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
'info_dict': {
'id': 'b00yng1d',
'ext': 'flv',
'title': 'The Man in Black: Series 3: The Printed Name',
'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
'duration': 1800,
},
'params': {
# rtmp download
'skip_download': True,
},
'skip': 'Episode is no longer available on BBC iPlayer Radio',
},
{
'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
'info_dict': {
'id': 'b00yng1d',
'ext': 'flv',
'title': 'The Voice UK: Series 3: Blind Auditions 5',
'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
'duration': 5100,
},
'params': {
# rtmp download
'skip_download': True,
},
'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
}
]
def _extract_asx_playlist(self, connection, programme_id):
asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
return [ref.get('href') for ref in asx.findall('./Entry/ref')]
def _extract_connection(self, connection, programme_id):
formats = []
protocol = connection.get('protocol')
supplier = connection.get('supplier')
if protocol == 'http':
href = connection.get('href')
# ASX playlist
if supplier == 'asx':
for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
formats.append({
'url': ref,
'format_id': 'ref%s_%s' % (i, supplier),
})
# Direct link
else:
formats.append({
'url': href,
'format_id': supplier,
})
elif protocol == 'rtmp':
application = connection.get('application', 'ondemand')
auth_string = connection.get('authString')
identifier = connection.get('identifier')
server = connection.get('server')
formats.append({
'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
'play_path': identifier,
'app': '%s?%s' % (application, auth_string),
'page_url': 'http://www.bbc.co.uk',
'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
'rtmp_live': False,
'ext': 'flv',
'format_id': supplier,
})
return formats
def _extract_items(self, playlist):
return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
def _extract_medias(self, media_selection):
return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
def _extract_connections(self, media):
return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
def _extract_video(self, media, programme_id):
formats = []
vbr = int(media.get('bitrate'))
vcodec = media.get('encoding')
service = media.get('service')
width = int(media.get('width'))
height = int(media.get('height'))
file_size = int(media.get('media_file_size'))
for connection in self._extract_connections(media):
conn_formats = self._extract_connection(connection, programme_id)
for format in conn_formats:
format.update({
'format_id': '%s_%s' % (service, format['format_id']),
'width': width,
'height': height,
'vbr': vbr,
'vcodec': vcodec,
'filesize': file_size,
})
formats.extend(conn_formats)
return formats
def _extract_audio(self, media, programme_id):
formats = []
abr = int(media.get('bitrate'))
acodec = media.get('encoding')
service = media.get('service')
for connection in self._extract_connections(media):
conn_formats = self._extract_connection(connection, programme_id)
for format in conn_formats:
format.update({
'format_id': '%s_%s' % (service, format['format_id']),
'abr': abr,
'acodec': acodec,
})
formats.extend(conn_formats)
return formats
def _extract_captions(self, media, programme_id):
subtitles = {}
for connection in self._extract_connections(media):
captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
srt = ''
for pos, p in enumerate(ps):
srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'),
p.text.strip() if p.text is not None else '')
subtitles[lang] = srt
return subtitles
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
group_id = mobj.group('id')
webpage = self._download_webpage(url, group_id, 'Downloading video page')
if re.search(r'id="emp-error" class="notinuk">', webpage):
raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only',
expected=True)
playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
'Downloading playlist XML')
no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
if no_items is not None:
reason = no_items.get('reason')
if reason == 'preAvailability':
msg = 'Episode %s is not yet available' % group_id
elif reason == 'postAvailability':
msg = 'Episode %s is no longer available' % group_id
else:
msg = 'Episode %s is not available: %s' % (group_id, reason)
raise ExtractorError(msg, expected=True)
formats = []
subtitles = None
for item in self._extract_items(playlist):
kind = item.get('kind')
if kind != 'programme' and kind != 'radioProgramme':
continue
title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
programme_id = item.get('identifier')
duration = int(item.get('duration'))
media_selection = self._download_xml(
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id,
programme_id, 'Downloading media selection XML')
for media in self._extract_medias(media_selection):
kind = media.get('kind')
if kind == 'audio':
formats.extend(self._extract_audio(media, programme_id))
elif kind == 'video':
formats.extend(self._extract_video(media, programme_id))
elif kind == 'captions':
subtitles = self._extract_captions(media, programme_id)
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(programme_id, subtitles)
return
self._sort_formats(formats)
return {
'id': programme_id,
'title': title,
'description': description,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}
-95
View File
@@ -1,95 +0,0 @@
from __future__ import unicode_literals
import datetime
import json
import re
from .common import InfoExtractor
from ..utils import (
remove_start,
)
class BlinkxIE(InfoExtractor):
_VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
IE_NAME = 'blinkx'
_TEST = {
'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
'file': '8aQUy7GV.mp4',
'md5': '2e9a07364af40163a908edbf10bb2492',
'info_dict': {
"title": "Police Car Rolls Away",
"uploader": "stupidvideos.com",
"upload_date": "20131215",
"description": "A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!",
"duration": 14.886,
"thumbnails": [{
"width": 100,
"height": 76,
"url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg",
}],
},
}
def _real_extract(self, rl):
m = re.match(self._VALID_URL, rl)
video_id = m.group('id')
display_id = video_id[:8]
api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' +
'video=%s' % video_id)
data_json = self._download_webpage(api_url, display_id)
data = json.loads(data_json)['api']['results'][0]
dt = datetime.datetime.fromtimestamp(data['pubdate_epoch'])
pload_date = dt.strftime('%Y%m%d')
duration = None
thumbnails = []
formats = []
for m in data['media']:
if m['type'] == 'jpg':
thumbnails.append({
'url': m['link'],
'width': int(m['w']),
'height': int(m['h']),
})
elif m['type'] == 'original':
duration = m['d']
elif m['type'] == 'youtube':
yt_id = m['link']
self.to_screen(u'Youtube video detected: %s' % yt_id)
return self.url_result(yt_id, 'Youtube', video_id=yt_id)
elif m['type'] in ('flv', 'mp4'):
vcodec = remove_start(m['vcodec'], 'ff')
acodec = remove_start(m['acodec'], 'ff')
tbr = (int(m['vbr']) + int(m['abr'])) // 1000
format_id = (u'%s-%sk-%s' %
(vcodec,
tbr,
m['w']))
formats.append({
'format_id': format_id,
'url': m['link'],
'vcodec': vcodec,
'acodec': acodec,
'abr': int(m['abr']) // 1000,
'vbr': int(m['vbr']) // 1000,
'tbr': tbr,
'width': int(m['w']),
'height': int(m['h']),
})
self._sort_formats(formats)
return {
'id': display_id,
'fullid': video_id,
'title': data['title'],
'formats': formats,
'uploader': data['channel_name'],
'upload_date': pload_date,
'description': data.get('description'),
'thumbnails': thumbnails,
'duration': duration,
}
-178
View File
@@ -1,178 +0,0 @@
from __future__ import unicode_literals
import datetime
import re
from .common import InfoExtractor
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
compat_str,
compat_urllib_request,
unescapeHTML,
)
class BlipTVIE(SubtitlesInfoExtractor):
"""Information extractor for blip.tv"""
_VALID_URL = r'https?://(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(?P<presumptive_id>.+)$'
_TESTS = [{
'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
'md5': 'c6934ad0b6acf2bd920720ec888eb812',
'info_dict': {
'id': '5779306',
'ext': 'mov',
'upload_date': '20111205',
'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
'uploader': 'Comic Book Resources - CBR TV',
'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
}
}, {
# https://github.com/rg3/youtube-dl/pull/2274
'note': 'Video with subtitles',
'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
'md5': '309f9d25b820b086ca163ffac8031806',
'info_dict': {
'id': '6586561',
'ext': 'mp4',
'uploader': 'Red vs. Blue',
'description': 'One-Zero-One',
'upload_date': '20130614',
'title': 'Red vs. Blue Season 11 Episode 1',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
presumptive_id = mobj.group('presumptive_id')
# See https://github.com/rg3/youtube-dl/issues/857
embed_mobj = re.match(r'https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
if embed_mobj:
info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1)
info_page = self._download_webpage(info_url, embed_mobj.group(1))
video_id = self._search_regex(
r'data-episode-id="([0-9]+)', info_page, 'video_id')
return self.url_result('http://blip.tv/a/a-' + video_id, 'BlipTV')
cchar = '&' if '?' in url else '?'
json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
request = compat_urllib_request.Request(json_url)
request.add_header('User-Agent', 'iTunes/10.6.1')
json_data = self._download_json(request, video_id=presumptive_id)
if 'Post' in json_data:
data = json_data['Post']
else:
data = json_data
video_id = compat_str(data['item_id'])
upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
subtitles = {}
formats = []
if 'additionalMedia' in data:
for f in data['additionalMedia']:
if f.get('file_type_srt') == 1:
LANGS = {
'english': 'en',
}
lang = f['role'].rpartition('-')[-1].strip().lower()
langcode = LANGS.get(lang, lang)
subtitles[langcode] = f['url']
continue
if not int(f['media_width']): # filter m3u8
continue
formats.append({
'url': f['url'],
'format_id': f['role'],
'width': int(f['media_width']),
'height': int(f['media_height']),
})
else:
formats.append({
'url': data['media']['url'],
'width': int(data['media']['width']),
'height': int(data['media']['height']),
})
self._sort_formats(formats)
# subtitles
video_subtitles = self.extract_subtitles(video_id, subtitles)
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id, subtitles)
return
return {
'id': video_id,
'uploader': data['display_name'],
'upload_date': upload_date,
'title': data['title'],
'thumbnail': data['thumbnailUrl'],
'description': data['description'],
'user_agent': 'iTunes/10.6.1',
'formats': formats,
'subtitles': video_subtitles,
}
def _download_subtitle_url(self, sub_lang, url):
# For some weird reason, blip.tv serves a video instead of subtitles
# when we request with a common UA
req = compat_urllib_request.Request(url)
req.add_header('Youtubedl-user-agent', 'youtube-dl')
return self._download_webpage(req, None, note=False)
class BlipTVUserIE(InfoExtractor):
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
_PAGE_SIZE = 12
IE_NAME = 'blip.tv:user'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
username = mobj.group(1)
page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
page = self._download_webpage(url, username, 'Downloading user page')
mobj = re.search(r'data-users-id="([^"]+)"', page)
page_base = page_base % mobj.group(1)
# Download video ids using BlipTV Ajax calls. Result size per
# query is limited (currently to 12 videos) so we need to query
# page by page until there are no video ids - it means we got
# all of them.
video_ids = []
pagenum = 1
while True:
url = page_base + "&page=" + str(pagenum)
page = self._download_webpage(
url, username, 'Downloading video ids from page %d' % pagenum)
# Extract video identifiers
ids_in_page = []
for mobj in re.finditer(r'href="/([^"]+)"', page):
if mobj.group(1) not in ids_in_page:
ids_in_page.append(unescapeHTML(mobj.group(1)))
video_ids.extend(ids_in_page)
# A little optimization - if current page is not
# "full", ie. does not contain PAGE_SIZE video ids then
# we can assume that this page is the last one - there
# are no more ids on further pages - no need to query
# again.
if len(ids_in_page) < self._PAGE_SIZE:
break
pagenum += 1
urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
return [self.playlist_result(url_entries, playlist_title=username)]
-30
View File
@@ -1,30 +0,0 @@
import re
from .common import InfoExtractor
from .ooyala import OoyalaIE
class BloombergIE(InfoExtractor):
_VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
_TEST = {
u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4',
u'info_dict': {
u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies',
u'description': u'md5:abc86e5236f9f0e4866c59ad36736686',
},
u'params': {
# Requires ffmpeg (m3u8 manifest)
u'skip_download': True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
webpage = self._download_webpage(url, name)
embed_code = self._search_regex(
r'<source src="https?://[^/]+/[^/]+/[^/]+/([^/]+)', webpage,
'embed code')
return OoyalaIE._build_url_result(embed_code)
-80
View File
@@ -1,80 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class BRIE(InfoExtractor):
IE_DESC = "Bayerischer Rundfunk Mediathek"
_VALID_URL = r"^https?://(?:www\.)?br\.de/mediathek/video/(?:sendungen/)?(?P<id>[a-z0-9\-]+)\.html$"
_BASE_URL = "http://www.br.de"
_TEST = {
"url": "http://www.br.de/mediathek/video/anselm-gruen-114.html",
"md5": "c4f83cf0f023ba5875aba0bf46860df2",
"info_dict": {
"id": "2c8d81c5-6fb7-4a74-88d4-e768e5856532",
"ext": "mp4",
"title": "Feiern und Verzichten",
"description": "Anselm Grün: Feiern und Verzichten",
"uploader": "BR/Birgit Baier",
"upload_date": "20140301"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
page = self._download_webpage(url, display_id)
xml_url = self._search_regex(
r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/mediathek/video/[a-z0-9/~_.-]+)'}\)\);", page, "XMLURL")
xml = self._download_xml(self._BASE_URL + xml_url, None)
videos = [{
"id": xml_video.get("externalId"),
"title": xml_video.find("title").text,
"formats": self._extract_formats(xml_video.find("assets")),
"thumbnails": self._extract_thumbnails(xml_video.find("teaserImage/variants")),
"description": " ".join(xml_video.find("shareTitle").text.splitlines()),
"uploader": xml_video.find("author").text,
"upload_date": "".join(reversed(xml_video.find("broadcastDate").text.split("."))),
"webpage_url": xml_video.find("permalink").text,
} for xml_video in xml.findall("video")]
if len(videos) > 1:
self._downloader.report_warning(
'found multiple videos; please '
'report this with the video URL to http://yt-dl.org/bug')
if not videos:
raise ExtractorError('No video entries found')
return videos[0]
def _extract_formats(self, assets):
formats = [{
"url": asset.find("downloadUrl").text,
"ext": asset.find("mediaType").text,
"format_id": asset.get("type"),
"width": int(asset.find("frameWidth").text),
"height": int(asset.find("frameHeight").text),
"tbr": int(asset.find("bitrateVideo").text),
"abr": int(asset.find("bitrateAudio").text),
"vcodec": asset.find("codecVideo").text,
"container": asset.find("mediaType").text,
"filesize": int(asset.find("size").text),
} for asset in assets.findall("asset")
if asset.find("downloadUrl") is not None]
self._sort_formats(formats)
return formats
def _extract_thumbnails(self, variants):
thumbnails = [{
"url": self._BASE_URL + variant.find("url").text,
"width": int(variant.find("width").text),
"height": int(variant.find("height").text),
} for variant in variants.findall("variant")]
thumbnails.sort(key=lambda x: x["width"] * x["height"], reverse=True)
return thumbnails
-39
View File
@@ -1,39 +0,0 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
class BreakIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
_TEST = {
'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
'info_dict': {
'id': '2468056',
'ext': 'mp4',
'title': 'When Girls Act Like D-Bags',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1).split("-")[-1]
embed_url = 'http://www.break.com/embed/%s' % video_id
webpage = self._download_webpage(embed_url, video_id)
info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
webpage, 'info json', flags=re.DOTALL)
info = json.loads(info_json)
video_url = info['videoUri']
m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
if m_youtube is not None:
return self.url_result(m_youtube.group(1), 'Youtube')
final_url = video_url + '?' + info['AuthToken']
return {
'id': video_id,
'url': final_url,
'title': info['contentName'],
'thumbnail': info['thumbUri'],
}
-247
View File
@@ -1,247 +0,0 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
import json
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
find_xpath_attr,
fix_xml_ampersands,
compat_urlparse,
compat_str,
compat_urllib_request,
compat_parse_qs,
ExtractorError,
unsmuggle_url,
unescapeHTML,
)
class BrightcoveIE(InfoExtractor):
_VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
_FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
_TESTS = [
{
# From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
'file': '2371591881001.mp4',
'md5': '5423e113865d26e40624dce2e4b45d95',
'note': 'Test Brightcove downloads and detection in GenericIE',
'info_dict': {
'title': 'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
'uploader': '8TV',
'description': 'md5:a950cc4285c43e44d763d036710cd9cd',
}
},
{
# From http://medianetwork.oracle.com/video/player/1785452137001
'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001',
'file': '1785452137001.flv',
'info_dict': {
'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.',
'uploader': 'Oracle',
},
},
{
# From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/
'url': 'http://c.brightcove.com/services/viewer/federated_f9?&playerID=1265504713001&publisherID=AQ%7E%7E%2CAAABBzUwv1E%7E%2CxP-xFHVUstiMFlNYfvF4G9yFnNaqCw_9&videoID=2750934548001',
'info_dict': {
'id': '2750934548001',
'ext': 'mp4',
'title': 'This Bracelet Acts as a Personal Thermostat',
'description': 'md5:547b78c64f4112766ccf4e151c20b6a0',
'uploader': 'Mashable',
},
},
{
# test that the default referer works
# from http://national.ballet.ca/interact/video/Lost_in_Motion_II/
'url': 'http://link.brightcove.com/services/player/bcpid756015033001?bckey=AQ~~,AAAApYJi_Ck~,GxhXCegT1Dp39ilhXuxMJxasUhVNZiil&bctid=2878862109001',
'info_dict': {
'id': '2878862109001',
'ext': 'mp4',
'title': 'Lost in Motion II',
'description': 'md5:363109c02998fee92ec02211bd8000df',
'uploader': 'National Ballet of Canada',
},
}
]
@classmethod
def _build_brighcove_url(cls, object_str):
"""
Build a Brightcove url from a xml string containing
<object class="BrightcoveExperience">{params}</object>
"""
# Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553
object_str = re.sub(r'(<param name="[^"]+" value="[^"]+")>',
lambda m: m.group(1) + '/>', object_str)
# Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
object_str = object_str.replace('<--', '<!--')
object_str = fix_xml_ampersands(object_str)
object_doc = xml.etree.ElementTree.fromstring(object_str)
fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
if fv_el is not None:
flashvars = dict(
(k, v[0])
for k, v in compat_parse_qs(fv_el.attrib['value']).items())
else:
flashvars = {}
def find_param(name):
if name in flashvars:
return flashvars[name]
node = find_xpath_attr(object_doc, './param', 'name', name)
if node is not None:
return node.attrib['value']
return None
params = {}
playerID = find_param('playerID')
if playerID is None:
raise ExtractorError('Cannot find player ID')
params['playerID'] = playerID
playerKey = find_param('playerKey')
# Not all pages define this value
if playerKey is not None:
params['playerKey'] = playerKey
# The three fields hold the id of the video
videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID')
if videoPlayer is not None:
params['@videoPlayer'] = videoPlayer
linkBase = find_param('linkBaseURL')
if linkBase is not None:
params['linkBaseURL'] = linkBase
data = compat_urllib_parse.urlencode(params)
return cls._FEDERATED_URL_TEMPLATE % data
@classmethod
def _extract_brightcove_url(cls, webpage):
"""Try to extract the brightcove url from the webpage, returns None
if it can't be found
"""
urls = cls._extract_brightcove_urls(webpage)
return urls[0] if urls else None
@classmethod
def _extract_brightcove_urls(cls, webpage):
"""Return a list of all Brightcove URLs from the webpage """
url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
if url_m:
return [unescapeHTML(url_m.group(1))]
matches = re.findall(
r'''(?sx)<object
(?:
[^>]+?class=[\'"][^>]*?BrightcoveExperience.*?[\'"] |
[^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
).+?</object>''',
webpage)
return [cls._build_brighcove_url(m) for m in matches]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
# Change the 'videoId' and others field to '@videoPlayer'
url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url)
# Change bckey (used by bcove.me urls) to playerKey
url = re.sub(r'(?<=[?&])bckey', 'playerKey', url)
mobj = re.match(self._VALID_URL, url)
query_str = mobj.group('query')
query = compat_urlparse.parse_qs(query_str)
videoPlayer = query.get('@videoPlayer')
if videoPlayer:
# We set the original url as the default 'Referer' header
referer = smuggled_data.get('Referer', url)
return self._get_video_info(
videoPlayer[0], query_str, query, referer=referer)
else:
player_key = query['playerKey']
return self._get_playlist_info(player_key[0])
def _get_video_info(self, video_id, query_str, query, referer=None):
request_url = self._FEDERATED_URL_TEMPLATE % query_str
req = compat_urllib_request.Request(request_url)
linkBase = query.get('linkBaseURL')
if linkBase is not None:
referer = linkBase[0]
if referer is not None:
req.add_header('Referer', referer)
webpage = self._download_webpage(req, video_id)
self.report_extraction(video_id)
info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
info = json.loads(info)['data']
video_info = info['programmedContent']['videoPlayer']['mediaDTO']
video_info['_youtubedl_adServerURL'] = info.get('adServerURL')
return self._extract_video_info(video_info)
def _get_playlist_info(self, player_key):
info_url = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' % player_key
playlist_info = self._download_webpage(
info_url, player_key, 'Downloading playlist information')
json_data = json.loads(playlist_info)
if 'videoList' not in json_data:
raise ExtractorError('Empty playlist')
playlist_info = json_data['videoList']
videos = [self._extract_video_info(video_info) for video_info in playlist_info['mediaCollectionDTO']['videoDTOs']]
return self.playlist_result(videos, playlist_id=playlist_info['id'],
playlist_title=playlist_info['mediaCollectionDTO']['displayName'])
def _extract_video_info(self, video_info):
info = {
'id': compat_str(video_info['id']),
'title': video_info['displayName'].strip(),
'description': video_info.get('shortDescription'),
'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
'uploader': video_info.get('publisherName'),
}
renditions = video_info.get('renditions')
if renditions:
renditions = sorted(renditions, key=lambda r: r['size'])
info['formats'] = [{
'url': rend['defaultURL'],
'height': rend.get('frameHeight'),
'width': rend.get('frameWidth'),
} for rend in renditions]
elif video_info.get('FLVFullLengthURL') is not None:
info.update({
'url': video_info['FLVFullLengthURL'],
})
if self._downloader.params.get('include_ads', False):
adServerURL = video_info.get('_youtubedl_adServerURL')
if adServerURL:
ad_info = {
'_type': 'url',
'url': adServerURL,
}
if 'url' in info:
return {
'_type': 'playlist',
'title': info['title'],
'entries': [ad_info, info],
}
else:
return ad_info
if 'url' not in info and not info.get('formats'):
raise ExtractorError('Unable to extract video url for %s' % info['id'])
return info
-40
View File
@@ -1,40 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
class C56IE(InfoExtractor):
_VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
IE_NAME = '56.com'
_TEST = {
'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
'file': '93440716.flv',
'md5': 'e59995ac63d0457783ea05f93f12a866',
'info_dict': {
'title': '网事知多少 第32期:车怒',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
text_id = mobj.group('textid')
info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
text_id, 'Downloading video info')
info = json.loads(info_page)['info']
formats = [{
'format_id': f['type'],
'filesize': int(f['filesize']),
'url': f['url']
} for f in info['rfiles']]
self._sort_formats(formats)
return {
'id': info['vid'],
'title': info['Subject'],
'formats': formats,
'thumbnail': info.get('bimg') or info.get('img'),
}
-48
View File
@@ -1,48 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class Canal13clIE(InfoExtractor):
_VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
'md5': '4cb1fa38adcad8fea88487a078831755',
'info_dict': {
'id': '1403022125',
'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
'ext': 'mp4',
'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda',
'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
webpage = self._download_webpage(url, display_id)
title = self._html_search_meta(
'twitter:title', webpage, 'title', fatal=True)
description = self._html_search_meta(
'twitter:description', webpage, 'description')
url = self._html_search_regex(
r'articuloVideo = \"(.*?)\"', webpage, 'url')
real_id = self._search_regex(
r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id)
thumbnail = self._html_search_regex(
r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail')
return {
'id': real_id,
'display_id': display_id,
'url': url,
'title': title,
'description': description,
'ext': 'mp4',
'thumbnail': thumbnail,
}
-41
View File
@@ -1,41 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class Canalc2IE(InfoExtractor):
IE_NAME = 'canalc2.tv'
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
_TEST = {
'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': {
'id': '12163',
'ext': 'mp4',
'title': 'Terrasses du Numérique'
}
}
def _real_extract(self, url):
video_id = re.match(self._VALID_URL, url).group('id')
# We need to set the voir field for getting the file name
url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
webpage = self._download_webpage(url, video_id)
file_name = self._search_regex(
r"so\.addVariable\('file','(.*?)'\);",
webpage, 'file name')
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
title = self._html_search_regex(
r'class="evenement8">(.*?)</a>', webpage, 'title')
return {
'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
}
-53
View File
@@ -1,53 +0,0 @@
# encoding: utf-8
import re
from .common import InfoExtractor
from ..utils import unified_strdate
class CanalplusIE(InfoExtractor):
_VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
IE_NAME = u'canalplus.fr'
_TEST = {
u'url': u'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
u'file': u'922470.flv',
u'info_dict': {
u'title': u'Zapping - 26/08/13',
u'description': u'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
u'upload_date': u'20130826',
},
u'params': {
u'skip_download': True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.groupdict().get('id')
if video_id is None:
webpage = self._download_webpage(url, mobj.group('path'))
video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
info_url = self._VIDEO_INFO_TEMPLATE % video_id
doc = self._download_xml(info_url,video_id,
u'Downloading video info')
self.report_extraction(video_id)
video_info = [video for video in doc if video.find('ID').text == video_id][0]
infos = video_info.find('INFOS')
media = video_info.find('MEDIA')
formats = [media.find('VIDEOS/%s' % format)
for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
video_url = [format.text for format in formats if format is not None][-1]
return {'id': video_id,
'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
infos.find('TITRAGE/SOUS_TITRE').text),
'url': video_url,
'ext': 'flv',
'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
'thumbnail': media.find('IMAGES/GRAND').text,
'description': infos.find('DESCRIPTION').text,
'view_count': int(infos.find('NB_VUES').text),
}
-30
View File
@@ -1,30 +0,0 @@
import re
from .common import InfoExtractor
class CBSIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/video/(?P<id>[^/]+)/.*'
_TEST = {
u'url': u'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
u'file': u'4JUVEwq3wUT7.flv',
u'info_dict': {
u'title': u'Connect Chat feat. Garth Brooks',
u'description': u'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
u'duration': 1495,
},
u'params': {
# rtmp download
u'skip_download': True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
real_id = self._search_regex(
r"video\.settings\.pid\s*=\s*'([^']+)';",
webpage, u'real video ID')
return self.url_result(u'theplatform:%s' % real_id)
-126
View File
@@ -1,126 +0,0 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_request,
compat_urllib_parse,
compat_urllib_parse_urlparse,
ExtractorError,
)
class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
_TESTS = [
{
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
'info_dict': {
'id': '213512120230004',
'ext': 'flv',
'title': 'První republika: Španělská chřipka',
'duration': 3107.4,
},
'params': {
'skip_download': True, # requires rtmpdump
},
'skip': 'Works only from Czech Republic.',
},
{
'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
'info_dict': {
'id': '20138143440',
'ext': 'flv',
'title': 'Tsatsiki, maminka a policajt',
'duration': 6754.1,
},
'params': {
'skip_download': True, # requires rtmpdump
},
'skip': 'Works only from Czech Republic.',
},
{
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
'info_dict': {
'id': '14716',
'ext': 'flv',
'title': 'První republika: Zpěvačka z Dupárny Bobina',
'duration': 90,
},
'params': {
'skip_download': True, # requires rtmpdump
},
},
]
def _real_extract(self, url):
url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
data = {
'playlist[0][type]': typ,
'playlist[0][id]': episode_id,
'requestUrl': compat_urllib_parse_urlparse(url).path,
'requestSource': 'iVysilani',
}
req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
data=compat_urllib_parse.urlencode(data))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
req.add_header('x-addr', '127.0.0.1')
req.add_header('X-Requested-With', 'XMLHttpRequest')
req.add_header('Referer', url)
playlistpage = self._download_json(req, video_id)
req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url']))
req.add_header('Referer', url)
playlist = self._download_xml(req, video_id)
formats = []
for i in playlist.find('smilRoot/body'):
if 'AD' not in i.attrib['id']:
base_url = i.attrib['base']
parsedurl = compat_urllib_parse_urlparse(base_url)
duration = i.attrib['duration']
for video in i.findall('video'):
if video.attrib['label'] != 'AD':
format_id = video.attrib['label']
play_path = video.attrib['src']
vbr = int(video.attrib['system-bitrate'])
formats.append({
'format_id': format_id,
'url': base_url,
'vbr': vbr,
'play_path': play_path,
'app': parsedurl.path[1:] + '?' + parsedurl.query,
'rtmp_live': True,
'ext': 'flv',
})
self._sort_formats(formats)
return {
'id': episode_id,
'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
'duration': float(duration),
'formats': formats,
}
-273
View File
@@ -1,273 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class Channel9IE(InfoExtractor):
'''
Common extractor for channel9.msdn.com.
The type of provided URL (video or playlist) is determined according to
meta Search.PageType from web page HTML rather than URL itself, as it is
not always possible to do.
'''
IE_DESC = 'Channel 9'
IE_NAME = 'channel9'
_VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
_TESTS = [
{
'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
'info_dict': {
'id': 'Events/TechEd/Australia/2013/KOS002',
'ext': 'mp4',
'title': 'Developer Kick-Off Session: Stuff We Love',
'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
'duration': 4576,
'thumbnail': 'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
'session_code': 'KOS002',
'session_day': 'Day 1',
'session_room': 'Arena 1A',
'session_speakers': [ 'Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen' ],
},
},
{
'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
'info_dict': {
'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
'ext': 'mp4',
'title': 'Self-service BI with Power BI - nuclear testing',
'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
'duration': 1540,
'thumbnail': 'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
'authors': [ 'Mike Wilmot' ],
},
}
]
_RSS_URL = 'http://channel9.msdn.com/%s/RSS'
# Sorted by quality
_known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4']
def _restore_bytes(self, formatted_size):
if not formatted_size:
return 0
m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
if not m:
return 0
units = m.group('units')
try:
exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
except ValueError:
return 0
size = float(m.group('size'))
return int(size * (1024 ** exponent))
def _formats_from_html(self, html):
FORMAT_REGEX = r'''
(?x)
<a\s+href="(?P<url>[^"]+)">(?P<quality>[^<]+)</a>\s*
<span\s+class="usage">\((?P<note>[^\)]+)\)</span>\s*
(?:<div\s+class="popup\s+rounded">\s*
<h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
</div>)? # File size part may be missing
'''
# Extract known formats
formats = [{
'url': x.group('url'),
'format_id': x.group('quality'),
'format_note': x.group('note'),
'format': '%s (%s)' % (x.group('quality'), x.group('note')),
'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate
'preference': self._known_formats.index(x.group('quality')),
'vcodec': 'none' if x.group('note') == 'Audio only' else None,
} for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
self._sort_formats(formats)
return formats
def _extract_title(self, html):
title = self._html_search_meta('title', html, 'title')
if title is None:
title = self._og_search_title(html)
TITLE_SUFFIX = ' (Channel 9)'
if title is not None and title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)]
return title
def _extract_description(self, html):
DESCRIPTION_REGEX = r'''(?sx)
<div\s+class="entry-content">\s*
<div\s+id="entry-body">\s*
(?P<description>.+?)\s*
</div>\s*
</div>
'''
m = re.search(DESCRIPTION_REGEX, html)
if m is not None:
return m.group('description')
return self._html_search_meta('description', html, 'description')
def _extract_duration(self, html):
m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
def _extract_slides(self, html):
m = re.search(r'<a href="(?P<slidesurl>[^"]+)" class="slides">Slides</a>', html)
return m.group('slidesurl') if m is not None else None
def _extract_zip(self, html):
m = re.search(r'<a href="(?P<zipurl>[^"]+)" class="zip">Zip</a>', html)
return m.group('zipurl') if m is not None else None
def _extract_avg_rating(self, html):
m = re.search(r'<p class="avg-rating">Avg Rating: <span>(?P<avgrating>[^<]+)</span></p>', html)
return float(m.group('avgrating')) if m is not None else 0
def _extract_rating_count(self, html):
m = re.search(r'<div class="rating-count">\((?P<ratingcount>[^<]+)\)</div>', html)
return int(self._fix_count(m.group('ratingcount'))) if m is not None else 0
def _extract_view_count(self, html):
m = re.search(r'<li class="views">\s*<span class="count">(?P<viewcount>[^<]+)</span> Views\s*</li>', html)
return int(self._fix_count(m.group('viewcount'))) if m is not None else 0
def _extract_comment_count(self, html):
m = re.search(r'<li class="comments">\s*<a href="#comments">\s*<span class="count">(?P<commentcount>[^<]+)</span> Comments\s*</a>\s*</li>', html)
return int(self._fix_count(m.group('commentcount'))) if m is not None else 0
def _fix_count(self, count):
return int(str(count).replace(',', '')) if count is not None else None
def _extract_authors(self, html):
m = re.search(r'(?s)<li class="author">(.*?)</li>', html)
if m is None:
return None
return re.findall(r'<a href="/Niners/[^"]+">([^<]+)</a>', m.group(1))
def _extract_session_code(self, html):
m = re.search(r'<li class="code">\s*(?P<code>.+?)\s*</li>', html)
return m.group('code') if m is not None else None
def _extract_session_day(self, html):
m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
return m.group('day') if m is not None else None
def _extract_session_room(self, html):
m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
return m.group('room') if m is not None else None
def _extract_session_speakers(self, html):
return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
def _extract_content(self, html, content_path):
# Look for downloadable content
formats = self._formats_from_html(html)
slides = self._extract_slides(html)
zip_ = self._extract_zip(html)
# Nothing to download
if len(formats) == 0 and slides is None and zip_ is None:
self._downloader.report_warning('None of recording, slides or zip are available for %s' % content_path)
return
# Extract meta
title = self._extract_title(html)
description = self._extract_description(html)
thumbnail = self._og_search_thumbnail(html)
duration = self._extract_duration(html)
avg_rating = self._extract_avg_rating(html)
rating_count = self._extract_rating_count(html)
view_count = self._extract_view_count(html)
comment_count = self._extract_comment_count(html)
common = {'_type': 'video',
'id': content_path,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'avg_rating': avg_rating,
'rating_count': rating_count,
'view_count': view_count,
'comment_count': comment_count,
}
result = []
if slides is not None:
d = common.copy()
d.update({ 'title': title + '-Slides', 'url': slides })
result.append(d)
if zip_ is not None:
d = common.copy()
d.update({ 'title': title + '-Zip', 'url': zip_ })
result.append(d)
if len(formats) > 0:
d = common.copy()
d.update({ 'title': title, 'formats': formats })
result.append(d)
return result
def _extract_entry_item(self, html, content_path):
contents = self._extract_content(html, content_path)
if contents is None:
return contents
authors = self._extract_authors(html)
for content in contents:
content['authors'] = authors
return contents
def _extract_session(self, html, content_path):
contents = self._extract_content(html, content_path)
if contents is None:
return contents
session_meta = {'session_code': self._extract_session_code(html),
'session_day': self._extract_session_day(html),
'session_room': self._extract_session_room(html),
'session_speakers': self._extract_session_speakers(html),
}
for content in contents:
content.update(session_meta)
return contents
def _extract_list(self, content_path):
rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS')
entries = [self.url_result(session_url.text, 'Channel9')
for session_url in rss.findall('./channel/item/link')]
title_text = rss.find('./channel/title').text
return self.playlist_result(entries, content_path, title_text)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
content_path = mobj.group('contentpath')
webpage = self._download_webpage(url, content_path, 'Downloading web page')
page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage)
if page_type_m is None:
raise ExtractorError('Search.PageType not found, don\'t know how to process this page', expected=True)
page_type = page_type_m.group('pagetype')
if page_type == 'List': # List page, may contain list of 'item'-like objects
return self._extract_list(content_path)
elif page_type == 'Entry.Item': # Any 'item'-like page, may contain downloadable content
return self._extract_entry_item(webpage, content_path)
elif page_type == 'Session': # Event session page, may contain downloadable content
return self._extract_session(webpage, content_path)
else:
raise ExtractorError('Unexpected Search.PageType %s' % page_type, expected=True)
-97
View File
@@ -1,97 +0,0 @@
from __future__ import unicode_literals
import re
import base64
import json
from .common import InfoExtractor
from ..utils import (
clean_html,
ExtractorError
)
class ChilloutzoneIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
_TESTS = [{
'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
'md5': 'a76f3457e813ea0037e5244f509e66d1',
'info_dict': {
'id': 'enemene-meck-alle-katzen-weg',
'ext': 'mp4',
'title': 'Enemene Meck - Alle Katzen weg',
'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
},
}, {
'note': 'Video hosted at YouTube',
'url': 'http://www.chilloutzone.net/video/eine-sekunde-bevor.html',
'info_dict': {
'id': '1YVQaAgHyRU',
'ext': 'mp4',
'title': '16 Photos Taken 1 Second Before Disaster',
'description': 'md5:58a8fcf6a459fe0a08f54140f0ad1814',
'uploader': 'BuzzFeedVideo',
'uploader_id': 'BuzzFeedVideo',
'upload_date': '20131105',
},
}, {
'note': 'Video hosted at Vimeo',
'url': 'http://www.chilloutzone.net/video/icon-blending.html',
'md5': '2645c678b8dc4fefcc0e1b60db18dac1',
'info_dict': {
'id': '85523671',
'ext': 'mp4',
'title': 'The Sunday Times - Icons',
'description': 'md5:3e1c0dc6047498d6728dcdaad0891762',
'uploader': 'Us',
'uploader_id': 'usfilms',
'upload_date': '20140131'
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
base64_video_info = self._html_search_regex(
r'var cozVidData = "(.+?)";', webpage, 'video data')
decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
video_info_dict = json.loads(decoded_video_info)
# get video information from dict
video_url = video_info_dict['mediaUrl']
description = clean_html(video_info_dict.get('description'))
title = video_info_dict['title']
native_platform = video_info_dict['nativePlatform']
native_video_id = video_info_dict['nativeVideoId']
source_priority = video_info_dict['sourcePriority']
# If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
if native_platform is None:
youtube_url = self._html_search_regex(
r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
webpage, 'fallback video URL', default=None)
if youtube_url is not None:
return self.url_result(youtube_url, ie='Youtube')
# Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
# the own CDN
if source_priority == 'native':
if native_platform == 'youtube':
return self.url_result(native_video_id, ie='Youtube')
if native_platform == 'vimeo':
return self.url_result(
'http://vimeo.com/' + native_video_id, ie='Vimeo')
if not video_url:
raise ExtractorError('No video found')
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': description,
}
-81
View File
@@ -1,81 +0,0 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class CinemassacreIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?'
_TESTS = [
{
'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
'file': '19911.mp4',
'md5': 'fde81fbafaee331785f58cd6c0d46190',
'info_dict': {
'upload_date': '20121110',
'title': '“Angry Video Game Nerd: The Movie” Trailer',
'description': 'md5:fb87405fcb42a331742a0dce2708560b',
},
},
{
'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
'file': '521be8ef82b16.mp4',
'md5': 'd72f10cd39eac4215048f62ab477a511',
'info_dict': {
'upload_date': '20131002',
'title': 'The Mummys Hand (1940)',
},
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, None) # Don't know video id yet
video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
if not mobj:
raise ExtractorError('Can\'t extract embed url and video id')
playerdata_url = mobj.group('embed_url')
video_id = mobj.group('video_id')
video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
webpage, 'title')
video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
webpage, 'description', flags=re.DOTALL, fatal=False)
if len(video_description) == 0:
video_description = None
playerdata = self._download_webpage(playerdata_url, video_id)
sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file')
hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_file')
video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
formats = [
{
'url': sd_url,
'ext': 'mp4',
'format': 'sd',
'format_id': 'sd',
},
{
'url': hd_url,
'ext': 'mp4',
'format': 'hd',
'format_id': 'hd',
},
]
return {
'id': video_id,
'title': video_title,
'formats': formats,
'description': video_description,
'upload_date': video_date,
'thumbnail': video_thumbnail,
}
-58
View File
@@ -1,58 +0,0 @@
import re
import time
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import ExtractorError
class ClipfishIE(InfoExtractor):
IE_NAME = u'clipfish'
_VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
_TEST = {
u'url': u'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
u'file': u'3966754.mp4',
u'md5': u'2521cd644e862936cf2e698206e47385',
u'info_dict': {
u'title': u'FIFA 14 - E3 2013 Trailer',
u'duration': 82,
},
u'skip': 'Blocked in the US'
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
(video_id, int(time.time())))
doc = self._download_xml(
info_url, video_id, note=u'Downloading info page')
title = doc.find('title').text
video_url = doc.find('filename').text
if video_url is None:
xml_bytes = xml.etree.ElementTree.tostring(doc)
raise ExtractorError(u'Cannot find video URL in document %r' %
xml_bytes)
thumbnail = doc.find('imageurl').text
duration_str = doc.find('duration').text
m = re.match(
r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
duration_str)
if m:
duration = (
(int(m.group('hours')) * 60 * 60) +
(int(m.group('minutes')) * 60) +
(int(m.group('seconds')))
)
else:
duration = None
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumbnail,
'duration': duration,
}
-56
View File
@@ -1,56 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
translation_table = {
'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
'y': 'l', 'z': 'i',
'$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
}
class CliphunterIE(InfoExtractor):
IE_NAME = 'cliphunter'
_VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
(?P<id>[0-9]+)/
(?P<seo>.+?)(?:$|[#\?])
'''
_TEST = {
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
'file': '1012420.flv',
'md5': '15e7740f30428abf70f4223478dc1225',
'info_dict': {
'title': 'Fun Jynx Maze solo',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
pl_fiji = self._search_regex(
r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
pl_c_qual = self._search_regex(
r'pl_c_qual = "(.)"', webpage, 'video quality')
video_title = self._search_regex(
r'mediaTitle = "([^"]+)"', webpage, 'title')
video_url = ''.join(translation_table.get(c, c) for c in pl_fiji)
formats = [{
'url': video_url,
'format_id': pl_c_qual,
}]
return {
'id': video_id,
'title': video_title,
'formats': formats,
}

Some files were not shown because too many files have changed in this diff Show More