mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2026-06-14 16:40:17 +00:00
Compare commits
154 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 36ef9d9509 | |||
| f0242b98a8 | |||
| 782d021327 | |||
| 26dc98c5ca | |||
| c444b69644 | |||
| c3c160f402 | |||
| 59f945e799 | |||
| d2e9088ee4 | |||
| 167e13273e | |||
| 40f283d159 | |||
| 6a020a3218 | |||
| e275a2f1ab | |||
| 8afb663891 | |||
| 1df8afcc18 | |||
| b0035c3448 | |||
| 8c6f08911f | |||
| 7fc3fe2b54 | |||
| 6a6bbc01f5 | |||
| 774e0d72cd | |||
| 00221fad40 | |||
| c0716886d8 | |||
| 386cc2f23e | |||
| 1a93d2ce6e | |||
| 86d55e2f99 | |||
| 1d97efec15 | |||
| 31326e8739 | |||
| 843060b2e0 | |||
| 9c49a1a8bd | |||
| da9084a061 | |||
| caae7db812 | |||
| a29e9ec53c | |||
| 29a8bfbaa9 | |||
| 5e4ecfe225 | |||
| b2ee8bf786 | |||
| da0a0d59a1 | |||
| 52f8db8b79 | |||
| 644f92f6a5 | |||
| 54a1852f08 | |||
| 0b33704b43 | |||
| 17e311adf0 | |||
| 809987a65c | |||
| 2f0e8ad0a6 | |||
| a5bd123ec0 | |||
| c74d3d5d80 | |||
| c20b2894ff | |||
| 005caca467 | |||
| abb88dcb2f | |||
| c052029267 | |||
| 0669b923c0 | |||
| 110c975154 | |||
| 8005b349a4 | |||
| d185f03455 | |||
| 420cf88aeb | |||
| 504afbe65d | |||
| d929dd31d1 | |||
| 49698bfaa3 | |||
| 633f6f9b39 | |||
| 71c8858fcd | |||
| 83f5182bcf | |||
| fb65f76630 | |||
| 1f69efb978 | |||
| 3bcc0a565c | |||
| 2840ae3a8f | |||
| b51355ef99 | |||
| 1762b604b1 | |||
| 8c64aa48d2 | |||
| 8c3a45b6e4 | |||
| dc9e2d8e0c | |||
| e7d727efc2 | |||
| a89c5d20c7 | |||
| 044cb16590 | |||
| 81db2d8040 | |||
| 2811949f4c | |||
| 3a2c78a2da | |||
| 23cf656bd1 | |||
| 41ff5333f7 | |||
| 571d094858 | |||
| 96679b26cf | |||
| b7d1a2247e | |||
| 9746c518a5 | |||
| 959fa33ef9 | |||
| a44c76cdf4 | |||
| 6a3ff26a01 | |||
| 60a1c34662 | |||
| 49bd2af54f | |||
| a5999b83fd | |||
| 82eedd7d83 | |||
| 759320387a | |||
| 0be94d4c6a | |||
| 6bd03617e6 | |||
| a3d06cfe6d | |||
| cd891850ec | |||
| cdee681a2c | |||
| db2c6281eb | |||
| 06a129c9dd | |||
| 5a938b5d04 | |||
| b0e67d2404 | |||
| 92961845c3 | |||
| f9c3398449 | |||
| bffe76ba4b | |||
| 0d29baa7c6 | |||
| dd9d3efcfb | |||
| 9014805f26 | |||
| f973da57a4 | |||
| a073eb792f | |||
| f202278fe1 | |||
| 3328f34eb3 | |||
| 50d7a239ae | |||
| 81eb98e4bd | |||
| 78ef538449 | |||
| 6e3ed6385c | |||
| a2dafa7316 | |||
| 86e5e08789 | |||
| e397cf5b47 | |||
| 3fd01c88c5 | |||
| d2cbb552b7 | |||
| 9c358a8982 | |||
| 7923514ea0 | |||
| 004759c8f2 | |||
| 95f029a5d8 | |||
| ac47cfe369 | |||
| 463fe92d26 | |||
| ba8a90b0bf | |||
| 3a6c68881a | |||
| a290358c2f | |||
| 17faaa4548 | |||
| 3ea19089f9 | |||
| 9077650490 | |||
| 2ecbfb4cbc | |||
| 3519974510 | |||
| e76e4dc8b1 | |||
| 01e013b5e3 | |||
| 64ea994344 | |||
| a3e9208c01 | |||
| ec0d2e46c5 | |||
| 1b3dbefb04 | |||
| c3003bb4db | |||
| 6c7d5d8d14 | |||
| 35c0ad4587 | |||
| 941383109a | |||
| c95ac4f062 | |||
| 0732b1f39f | |||
| 8d78373ea0 | |||
| 17082ad9db | |||
| 725d763c48 | |||
| a993428ac9 | |||
| 7136abc8f3 | |||
| 790622091e | |||
| db03ff92a6 | |||
| b294d9fa38 | |||
| 5de4c645e2 | |||
| 05703c8f9c | |||
| f37b138766 | |||
| 5c7359365f |
+13
@@ -0,0 +1,13 @@
|
||||
*.kate-swp
|
||||
downloads/*
|
||||
updates_key.pem
|
||||
youtube_dl.egg-info
|
||||
test
|
||||
build/
|
||||
dist/
|
||||
youtube-dl.1
|
||||
youtube-dl.fish
|
||||
youtube-dl.zsh
|
||||
README.txt
|
||||
youtube-dl.bash-completion
|
||||
latest_version
|
||||
@@ -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/$1 [R=302,L]
|
||||
RewriteRule ^\.git - [F]
|
||||
|
||||
ErrorDocument 302 "302"
|
||||
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
# Just a placeholder script so that travis doesn't complain
|
||||
language: python
|
||||
script: true
|
||||
@@ -0,0 +1,5 @@
|
||||
RewriteEngine On
|
||||
|
||||
RewriteRule ^$ https://github.com/ytdl-org/youtube-dl/releases
|
||||
RewriteRule latest(.*) /downloads/2019.03.09$1 [L,R=302]
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
RewriteEngine On
|
||||
|
||||
RewriteRule ^$ 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]
|
||||
|
||||
@@ -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>
|
||||
@@ -0,0 +1,3 @@
|
||||
<?php
|
||||
header('Content-Type: text/plain');
|
||||
echo $_SERVER['REMOTE_ADDR'];
|
||||
@@ -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;
|
||||
}
|
||||
Executable
+19
@@ -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
|
||||
-622
@@ -1,622 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
# Author: Ricardo Garcia Gonzalez
|
||||
# License: Public domain code
|
||||
import htmlentitydefs
|
||||
import httplib
|
||||
import math
|
||||
import netrc
|
||||
import os
|
||||
import os.path
|
||||
import re
|
||||
import socket
|
||||
import string
|
||||
import sys
|
||||
import time
|
||||
import urllib
|
||||
import urllib2
|
||||
|
||||
std_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1',
|
||||
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
|
||||
'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
|
||||
'Accept-Language': 'en-us,en;q=0.5',
|
||||
}
|
||||
|
||||
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
|
||||
|
||||
class DownloadError(Exception):
|
||||
"""Download Error exception.
|
||||
|
||||
This exception may be thrown by FileDownloader objects if they are not
|
||||
configured to continue on errors. They will contain the appropriate
|
||||
error message.
|
||||
"""
|
||||
pass
|
||||
|
||||
class SameFileError(Exception):
|
||||
"""Same File exception.
|
||||
|
||||
This exception will be thrown by FileDownloader objects if they detect
|
||||
multiple files would have to be downloaded to the same file on disk.
|
||||
"""
|
||||
pass
|
||||
|
||||
class FileDownloader(object):
|
||||
"""File Downloader class.
|
||||
|
||||
File downloader objects are the ones responsible of downloading the
|
||||
actual video file and writing it to disk if the user has requested
|
||||
it, among some other tasks. In most cases there should be one per
|
||||
program. As, given a video URL, the downloader doesn't know how to
|
||||
extract all the needed information, task that InfoExtractors do, it
|
||||
has to pass the URL to one of them.
|
||||
|
||||
For this, file downloader objects have a method that allows
|
||||
InfoExtractors to be registered in a given order. When it is passed
|
||||
a URL, the file downloader handles it to the first InfoExtractor it
|
||||
finds that reports being able to handle it. The InfoExtractor returns
|
||||
all the information to the FileDownloader and the latter downloads the
|
||||
file or does whatever it's instructed to do.
|
||||
|
||||
File downloaders accept a lot of parameters. In order not to saturate
|
||||
the object constructor with arguments, it receives a dictionary of
|
||||
options instead. These options are available through the get_params()
|
||||
method for the InfoExtractors to use. The FileDownloader also registers
|
||||
itself as the downloader in charge for the InfoExtractors that are
|
||||
added to it, so this is a "mutual registration".
|
||||
|
||||
Available options:
|
||||
|
||||
username: Username for authentication purposes.
|
||||
password: Password for authentication purposes.
|
||||
usenetrc: Use netrc for authentication instead.
|
||||
quiet: Do not print messages to stdout.
|
||||
forceurl: Force printing final URL.
|
||||
forcetitle: Force printing title.
|
||||
simulate: Do not download the video files.
|
||||
format: Video format code.
|
||||
outtmpl: Template for output names.
|
||||
ignoreerrors: Do not stop on download errors.
|
||||
"""
|
||||
|
||||
_params = None
|
||||
_ies = []
|
||||
|
||||
def __init__(self, params):
|
||||
"""Create a FileDownloader object with the given options."""
|
||||
self._ies = []
|
||||
self.set_params(params)
|
||||
|
||||
@staticmethod
|
||||
def pmkdir(filename):
|
||||
"""Create directory components in filename. Similar to Unix "mkdir -p"."""
|
||||
components = filename.split(os.sep)
|
||||
aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
|
||||
for dir in aggregate:
|
||||
if not os.path.exists(dir):
|
||||
os.mkdir(dir)
|
||||
|
||||
@staticmethod
|
||||
def format_bytes(bytes):
|
||||
if bytes is None:
|
||||
return 'N/A'
|
||||
if bytes == 0:
|
||||
exponent = 0
|
||||
else:
|
||||
exponent = long(math.log(float(bytes), 1024.0))
|
||||
suffix = 'bkMGTPEZY'[exponent]
|
||||
converted = float(bytes) / float(1024**exponent)
|
||||
return '%.2f%s' % (converted, suffix)
|
||||
|
||||
@staticmethod
|
||||
def calc_percent(byte_counter, data_len):
|
||||
if data_len is None:
|
||||
return '---.-%'
|
||||
return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
|
||||
|
||||
@staticmethod
|
||||
def calc_eta(start, now, total, current):
|
||||
if total is None:
|
||||
return '--:--'
|
||||
dif = now - start
|
||||
if current == 0 or dif < 0.001: # One millisecond
|
||||
return '--:--'
|
||||
rate = float(current) / dif
|
||||
eta = long((float(total) - float(current)) / rate)
|
||||
(eta_mins, eta_secs) = divmod(eta, 60)
|
||||
if eta_mins > 99:
|
||||
return '--:--'
|
||||
return '%02d:%02d' % (eta_mins, eta_secs)
|
||||
|
||||
@staticmethod
|
||||
def calc_speed(start, now, bytes):
|
||||
dif = now - start
|
||||
if bytes == 0 or dif < 0.001: # One millisecond
|
||||
return '%10s' % '---b/s'
|
||||
return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
|
||||
|
||||
@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)
|
||||
|
||||
def set_params(self, params):
|
||||
"""Sets parameters."""
|
||||
if type(params) != dict:
|
||||
raise ValueError('params: dictionary expected')
|
||||
self._params = params
|
||||
|
||||
def get_params(self):
|
||||
"""Get parameters."""
|
||||
return self._params
|
||||
|
||||
def add_info_extractor(self, ie):
|
||||
"""Add an InfoExtractor object to the end of the list."""
|
||||
self._ies.append(ie)
|
||||
ie.set_downloader(self)
|
||||
|
||||
def to_stdout(self, message, skip_eol=False):
|
||||
"""Print message to stdout if not in quiet mode."""
|
||||
if not self._params.get('quiet', False):
|
||||
sys.stdout.write('%s%s' % (message, ['\n', ''][skip_eol]))
|
||||
sys.stdout.flush()
|
||||
|
||||
def to_stderr(self, message):
|
||||
"""Print message to stderr."""
|
||||
sys.stderr.write('%s\n' % message)
|
||||
|
||||
def fixed_template(self):
|
||||
"""Checks if the output template is fixed."""
|
||||
return (re.search(ur'(?u)%\(.+?\)s', self._params['outtmpl']) is None)
|
||||
|
||||
def trouble(self, message=None):
|
||||
"""Determine action to take when a download problem appears.
|
||||
|
||||
Depending on if the downloader has been configured to ignore
|
||||
download errors or not, this method may throw an exception or
|
||||
not when errors are found, after printing the message. If it
|
||||
doesn't raise, it returns an error code suitable to be returned
|
||||
later as a program exit code to indicate error.
|
||||
"""
|
||||
if message is not None:
|
||||
self.to_stderr(message)
|
||||
if not self._params.get('ignoreerrors', False):
|
||||
raise DownloadError(message)
|
||||
return 1
|
||||
|
||||
def report_destination(self, filename):
|
||||
"""Report destination filename."""
|
||||
self.to_stdout('[download] Destination: %s' % filename)
|
||||
|
||||
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
|
||||
"""Report download progress."""
|
||||
self.to_stdout('\r[download] %s of %s at %s ETA %s' %
|
||||
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
|
||||
|
||||
def report_finish(self):
|
||||
"""Report download finished."""
|
||||
self.to_stdout('')
|
||||
|
||||
def download(self, url_list):
|
||||
"""Download a given list of URLs."""
|
||||
retcode = 0
|
||||
if len(url_list) > 1 and self.fixed_template():
|
||||
raise SameFileError(self._params['outtmpl'])
|
||||
|
||||
for url in url_list:
|
||||
suitable_found = False
|
||||
for ie in self._ies:
|
||||
if not ie.suitable(url):
|
||||
continue
|
||||
# Suitable InfoExtractor found
|
||||
suitable_found = True
|
||||
all_results = ie.extract(url)
|
||||
results = [x for x in all_results if x is not None]
|
||||
if len(results) != len(all_results):
|
||||
retcode = self.trouble()
|
||||
|
||||
if len(results) > 1 and self.fixed_template():
|
||||
raise SameFileError(self._params['outtmpl'])
|
||||
|
||||
for result in results:
|
||||
|
||||
# Forced printings
|
||||
if self._params.get('forcetitle', False):
|
||||
print result['title']
|
||||
if self._params.get('forceurl', False):
|
||||
print result['url']
|
||||
|
||||
# Do nothing else if in simulate mode
|
||||
if self._params.get('simulate', False):
|
||||
continue
|
||||
|
||||
try:
|
||||
filename = self._params['outtmpl'] % result
|
||||
self.report_destination(filename)
|
||||
except (ValueError, KeyError), err:
|
||||
retcode = self.trouble('ERROR: invalid output template: %s' % str(err))
|
||||
continue
|
||||
try:
|
||||
self.pmkdir(filename)
|
||||
except (OSError, IOError), err:
|
||||
retcode = self.trouble('ERROR: unable to create directories: %s' % str(err))
|
||||
continue
|
||||
try:
|
||||
outstream = open(filename, 'wb')
|
||||
except (OSError, IOError), err:
|
||||
retcode = self.trouble('ERROR: unable to open for writing: %s' % str(err))
|
||||
continue
|
||||
try:
|
||||
self._do_download(outstream, result['url'])
|
||||
outstream.close()
|
||||
except (OSError, IOError), err:
|
||||
retcode = self.trouble('ERROR: unable to write video data: %s' % str(err))
|
||||
continue
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
retcode = self.trouble('ERROR: unable to download video data: %s' % str(err))
|
||||
continue
|
||||
break
|
||||
if not suitable_found:
|
||||
retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
|
||||
|
||||
return retcode
|
||||
|
||||
def _do_download(self, stream, url):
|
||||
request = urllib2.Request(url, None, std_headers)
|
||||
data = urllib2.urlopen(request)
|
||||
data_len = data.info().get('Content-length', None)
|
||||
data_len_str = self.format_bytes(data_len)
|
||||
byte_counter = 0
|
||||
block_size = 1024
|
||||
start = time.time()
|
||||
while True:
|
||||
# Progress message
|
||||
percent_str = self.calc_percent(byte_counter, data_len)
|
||||
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
|
||||
speed_str = self.calc_speed(start, time.time(), byte_counter)
|
||||
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
|
||||
|
||||
# Download and write
|
||||
before = time.time()
|
||||
data_block = data.read(block_size)
|
||||
after = time.time()
|
||||
data_block_len = len(data_block)
|
||||
if data_block_len == 0:
|
||||
break
|
||||
byte_counter += data_block_len
|
||||
stream.write(data_block)
|
||||
block_size = self.best_block_size(after - before, data_block_len)
|
||||
|
||||
self.report_finish()
|
||||
if data_len is not None and str(byte_counter) != data_len:
|
||||
raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
|
||||
|
||||
class InfoExtractor(object):
|
||||
"""Information Extractor class.
|
||||
|
||||
Information extractors are the classes that, given a URL, extract
|
||||
information from the video (or videos) the URL refers to. This
|
||||
information includes the real video URL, the video title and simplified
|
||||
title, author and others. It is returned in a list of dictionaries when
|
||||
calling its extract() method. It is a list because a URL can refer to
|
||||
more than one video (think of playlists). The dictionaries must include
|
||||
the following fields:
|
||||
|
||||
id: Video identifier.
|
||||
url: Final video URL.
|
||||
uploader: Nickname of the video uploader.
|
||||
title: Literal title.
|
||||
stitle: Simplified title.
|
||||
ext: Video filename extension.
|
||||
|
||||
Subclasses of this one should re-define the _real_initialize() and
|
||||
_real_extract() methods, as well as the suitable() static method.
|
||||
Probably, they should also be instantiated and added to the main
|
||||
downloader.
|
||||
"""
|
||||
|
||||
_ready = False
|
||||
_downloader = None
|
||||
|
||||
def __init__(self, downloader=None):
|
||||
"""Constructor. Receives an optional downloader."""
|
||||
self._ready = False
|
||||
self.set_downloader(downloader)
|
||||
|
||||
@staticmethod
|
||||
def suitable(url):
|
||||
"""Receives a URL and returns True if suitable for this IE."""
|
||||
return True
|
||||
|
||||
def initialize(self):
|
||||
"""Initializes an instance (authentication, etc)."""
|
||||
if not self._ready:
|
||||
self._real_initialize()
|
||||
self._ready = True
|
||||
|
||||
def extract(self, url):
|
||||
"""Extracts URL information and returns it in list of dicts."""
|
||||
self.initialize()
|
||||
return self._real_extract(url)
|
||||
|
||||
def set_downloader(self, downloader):
|
||||
"""Sets the downloader for this IE."""
|
||||
self._downloader = downloader
|
||||
|
||||
def to_stdout(self, message):
|
||||
"""Print message to stdout if downloader is not in quiet mode."""
|
||||
if self._downloader is None or not self._downloader.get_params().get('quiet', False):
|
||||
print message
|
||||
|
||||
def to_stderr(self, message):
|
||||
"""Print message to stderr."""
|
||||
sys.stderr.write('%s\n' % message)
|
||||
|
||||
def _real_initialize(self):
|
||||
"""Real initialization process. Redefine in subclasses."""
|
||||
pass
|
||||
|
||||
def _real_extract(self, url):
|
||||
"""Real extraction process. Redefine in subclasses."""
|
||||
pass
|
||||
|
||||
class YoutubeIE(InfoExtractor):
|
||||
"""Information extractor for youtube.com."""
|
||||
|
||||
_LOGIN_URL = 'http://www.youtube.com/login?next=/'
|
||||
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/'
|
||||
_NETRC_MACHINE = 'youtube'
|
||||
|
||||
def report_login(self):
|
||||
"""Report attempt to log in."""
|
||||
self.to_stdout('[youtube] Logging in')
|
||||
|
||||
def report_age_confirmation(self):
|
||||
"""Report attempt to confirm age."""
|
||||
self.to_stdout('[youtube] Confirming age')
|
||||
|
||||
def report_webpage_download(self, video_id):
|
||||
"""Report attempt to download webpage."""
|
||||
self.to_stdout('[youtube] %s: Downloading video webpage' % video_id)
|
||||
|
||||
def report_information_extraction(self, video_id):
|
||||
"""Report attempt to extract video information."""
|
||||
self.to_stdout('[youtube] %s: Extracting video information' % video_id)
|
||||
|
||||
def report_video_url(self, video_id, video_real_url):
|
||||
"""Report extracted video URL."""
|
||||
self.to_stdout('[youtube] %s: URL: %s' % (video_id, video_real_url))
|
||||
|
||||
def _real_initialize(self):
|
||||
if self._downloader is None:
|
||||
return
|
||||
|
||||
username = None
|
||||
password = None
|
||||
downloader_params = self._downloader.get_params()
|
||||
|
||||
# Attempt to use provided username and password or .netrc data
|
||||
if downloader_params.get('username', None) is not None:
|
||||
username = downloader_params['username']
|
||||
password = downloader_params['password']
|
||||
elif downloader_params.get('usenetrc', False):
|
||||
try:
|
||||
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
|
||||
if info is not None:
|
||||
username = info[0]
|
||||
password = info[2]
|
||||
else:
|
||||
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
|
||||
except (IOError, netrc.NetrcParseError), err:
|
||||
self.to_stderr('WARNING: parsing .netrc: %s' % str(err))
|
||||
return
|
||||
|
||||
# No authentication to be performed
|
||||
if username is None:
|
||||
return
|
||||
|
||||
# Log in
|
||||
login_form = {
|
||||
'current_form': 'loginForm',
|
||||
'next': '/',
|
||||
'action_login': 'Log In',
|
||||
'username': username,
|
||||
'password': password,
|
||||
}
|
||||
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
|
||||
try:
|
||||
self.report_login()
|
||||
login_results = urllib2.urlopen(request).read()
|
||||
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
|
||||
self.to_stderr('WARNING: unable to log in: bad username or password')
|
||||
return
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr('WARNING: unable to log in: %s' % str(err))
|
||||
return
|
||||
|
||||
# Confirm age
|
||||
age_form = {
|
||||
'next_url': '/',
|
||||
'action_confirm': 'Confirm',
|
||||
}
|
||||
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
|
||||
try:
|
||||
self.report_age_confirmation()
|
||||
age_results = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr('ERROR: unable to confirm age: %s' % str(err))
|
||||
return
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract video id from URL
|
||||
mobj = re.match(r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$', url)
|
||||
if mobj is None:
|
||||
self.to_stderr('ERROR: invalid URL: %s' % url)
|
||||
return [None]
|
||||
video_id = mobj.group(2)
|
||||
|
||||
# Downloader parameters
|
||||
format_param = None
|
||||
if self._downloader is not None:
|
||||
params = self._downloader.get_params()
|
||||
format_param = params.get('format', None)
|
||||
|
||||
# Extension
|
||||
video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv')
|
||||
|
||||
# Normalize URL, including format
|
||||
normalized_url = 'http://www.youtube.com/watch?v=%s' % video_id
|
||||
if format_param is not None:
|
||||
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
|
||||
request = urllib2.Request(normalized_url, None, std_headers)
|
||||
try:
|
||||
self.report_webpage_download(video_id)
|
||||
video_webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self.to_stderr('ERROR: unable to download video webpage: %s' % str(err))
|
||||
return [None]
|
||||
self.report_information_extraction(video_id)
|
||||
|
||||
# "t" param
|
||||
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr('ERROR: unable to extract "t" parameter')
|
||||
return [None]
|
||||
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
|
||||
if format_param is not None:
|
||||
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
|
||||
self.report_video_url(video_id, video_real_url)
|
||||
|
||||
# uploader
|
||||
mobj = re.search(r'More From: ([^<]*)<', video_webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr('ERROR: unable to extract uploader nickname')
|
||||
return [None]
|
||||
video_uploader = mobj.group(1)
|
||||
|
||||
# title
|
||||
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
|
||||
if mobj is None:
|
||||
self.to_stderr('ERROR: unable to extract video title')
|
||||
return [None]
|
||||
video_title = mobj.group(1).decode('utf-8')
|
||||
video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
|
||||
video_title = video_title.replace(os.sep, u'%')
|
||||
|
||||
# simplified title
|
||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||
simple_title = simple_title.strip(ur'_')
|
||||
|
||||
# Return information
|
||||
return [{
|
||||
'id': video_id,
|
||||
'url': video_real_url,
|
||||
'uploader': video_uploader,
|
||||
'title': video_title,
|
||||
'stitle': simple_title,
|
||||
'ext': video_extension,
|
||||
}]
|
||||
|
||||
if __name__ == '__main__':
|
||||
try:
|
||||
# Modules needed only when running the main program
|
||||
import getpass
|
||||
import optparse
|
||||
|
||||
# General configuration
|
||||
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
|
||||
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
|
||||
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
|
||||
|
||||
# Parse command line
|
||||
parser = optparse.OptionParser(
|
||||
usage='Usage: %prog [options] url...',
|
||||
version='2008.07.22',
|
||||
conflict_handler='resolve',
|
||||
)
|
||||
parser.add_option('-h', '--help',
|
||||
action='help', help='print this help text and exit')
|
||||
parser.add_option('-v', '--version',
|
||||
action='version', help='print program version and exit')
|
||||
parser.add_option('-u', '--username',
|
||||
dest='username', metavar='UN', help='account username')
|
||||
parser.add_option('-p', '--password',
|
||||
dest='password', metavar='PW', help='account password')
|
||||
parser.add_option('-o', '--output',
|
||||
dest='outtmpl', metavar='TPL', help='output filename template')
|
||||
parser.add_option('-q', '--quiet',
|
||||
action='store_true', dest='quiet', help='activates quiet mode', default=False)
|
||||
parser.add_option('-s', '--simulate',
|
||||
action='store_true', dest='simulate', help='do not download video', default=False)
|
||||
parser.add_option('-t', '--title',
|
||||
action='store_true', dest='usetitle', help='use title in file name', default=False)
|
||||
parser.add_option('-l', '--literal',
|
||||
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
|
||||
parser.add_option('-n', '--netrc',
|
||||
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
|
||||
parser.add_option('-g', '--get-url',
|
||||
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
|
||||
parser.add_option('-e', '--get-title',
|
||||
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
|
||||
parser.add_option('-f', '--format',
|
||||
dest='format', metavar='FMT', help='video format code')
|
||||
parser.add_option('-b', '--best-quality',
|
||||
action='store_const', dest='format', help='alias for -f 18', const='18')
|
||||
parser.add_option('-m', '--mobile-version',
|
||||
action='store_const', dest='format', help='alias for -f 17', const='17')
|
||||
parser.add_option('-i', '--ignore-errors',
|
||||
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
|
||||
(opts, args) = parser.parse_args()
|
||||
|
||||
# Conflicting, missing and erroneous options
|
||||
if len(args) < 1:
|
||||
sys.exit('ERROR: you must provide at least one URL')
|
||||
if opts.usenetrc and (opts.username is not None or opts.password is not None):
|
||||
sys.exit('ERROR: using .netrc conflicts with giving username/password')
|
||||
if opts.password is not None and opts.username is None:
|
||||
sys.exit('ERROR: account username missing')
|
||||
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
|
||||
sys.exit('ERROR: using output template conflicts with using title or literal title')
|
||||
if opts.usetitle and opts.useliteral:
|
||||
sys.exit('ERROR: using title conflicts with using literal title')
|
||||
if opts.username is not None and opts.password is None:
|
||||
opts.password = getpass.getpass('Type account password and press return:')
|
||||
|
||||
# Information extractors
|
||||
youtube_ie = YoutubeIE()
|
||||
|
||||
# File downloader
|
||||
fd = FileDownloader({
|
||||
'usenetrc': opts.usenetrc,
|
||||
'username': opts.username,
|
||||
'password': opts.password,
|
||||
'quiet': (opts.quiet or opts.geturl or opts.gettitle),
|
||||
'forceurl': opts.geturl,
|
||||
'forcetitle': opts.gettitle,
|
||||
'simulate': (opts.simulate or opts.geturl or opts.gettitle),
|
||||
'format': opts.format,
|
||||
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl)
|
||||
or (opts.usetitle and '%(stitle)s-%(id)s.%(ext)s')
|
||||
or (opts.useliteral and '%(title)s-%(id)s.%(ext)s')
|
||||
or '%(id)s.%(ext)s'),
|
||||
'ignoreerrors': opts.ignoreerrors,
|
||||
})
|
||||
fd.add_info_extractor(youtube_ie)
|
||||
retcode = fd.download(args)
|
||||
sys.exit(retcode)
|
||||
|
||||
except DownloadError:
|
||||
sys.exit(1)
|
||||
except SameFileError:
|
||||
sys.exit('ERROR: fixed output name but more than one file to download')
|
||||
except KeyboardInterrupt:
|
||||
sys.exit('\nERROR: Interrupted by user')
|
||||
Reference in New Issue
Block a user