1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2026-06-15 00:50:13 +00:00

Compare commits

..

35 Commits

Author SHA1 Message Date
Sergey M․ a4a2fa8754 release 2020.12.09 2020-12-09 04:25:24 +07:00
Sergey M․ 9da0504a09 [ChangeLog] Actualize
[ci skip]
2020-12-09 04:24:31 +07:00
Sergey M․ 470cf496f5 [youtube:tab] Improve identity token extraction (closes #27197) 2020-12-09 04:17:47 +07:00
Sergey M․ e029da9add [youtube:tab] Make click tracking params on continuation optional 2020-12-09 04:06:44 +07:00
Sergey M․ e00b8f60d4 [youtube:tab] Delegate inline playlists to tab-based playlists (closes #27298) 2020-12-09 03:40:02 +07:00
EntranceJew 644c3ef886 [tubitv] Extract release year (#27317) 2020-12-09 01:14:46 +07:00
Soneé John 9d8d0f8b4a [youtube] Remove unused code (#27343) 2020-12-09 00:41:47 +07:00
Sergey M․ 5a1fbbf8b7 [extractor/common] Fix inline HTML5 media tags processing and add test (closes #27345) 2020-12-09 00:05:21 +07:00
Remita Amine e2bdf8bf4f [amcnetworks] Fix free content extraction(closes #20354) 2020-12-08 17:11:28 +01:00
Remita Amine c368dc98e0 [lbry] add support for channel extraction(closes #25584) 2020-12-08 14:53:22 +01:00
Remita Amine e7eff914cd [lbry] add support for short and embed URLs and fix channel metadata extraction 2020-12-08 10:52:52 +01:00
Remita Amine 07333d0062 [telequebec] Fix Extraction and Add Support for video.telequebec.tv
closes #25733
closes #26883
closes #27339
2020-12-08 00:35:47 +01:00
Sergey M․ 5bd7ad2e81 [youtube:tab] Capture and output alerts (closes #27340) 2020-12-08 01:12:00 +07:00
Remita Amine 3ded751985 [generic] comment a test covered now by AmericasTestKitchenIE 2020-12-07 15:27:13 +01:00
Remita Amine 6956db3606 [tvplay:home] Fix extraction(closes #21153) 2020-12-07 15:12:54 +01:00
Remita Amine 17b01228f8 [americastestkitchen] Fix Extraction and add support for Cook's Country and Cook's Illustrated
closes #17234
closes #27322
2020-12-06 23:41:18 +01:00
Sergey M․ 4f1ecca58d [slideslive] Add support for yoda service videos and extract subtitles (closes #27323) 2020-12-07 03:27:21 +07:00
Sergey M․ 2717036489 release 2020.12.07 2020-12-07 02:03:34 +07:00
Sergey M․ d9482c0083 [ChangeLog] Actualize
[ci skip]
2020-12-07 02:01:53 +07:00
Sergey M․ 791b743765 [extractor/generic] Remove unused import 2020-12-07 02:01:47 +07:00
Remita Amine fa604d9083 [aenetworks] Fix extraction
- Fix Fastly format extraction
- Add support for play and watch subdomains
- Extract series metadata

closes #23363
closes #23390
closes #26795
closes #26985
2020-12-06 19:50:05 +01:00
Sergey M․ 2bf0634d16 [youtube] Improve youtu.be extraction in non-existing playlists (closes #27324) 2020-12-07 01:48:10 +07:00
Sergey M․ dccf4932e1 [extractor/common] Extract timestamp from Last-Modified header 2020-12-07 01:15:30 +07:00
Sergey M․ 91dd25fe1e [extractor/common] Add support for dl8-* media tags (closes #27283) 2020-12-07 01:08:22 +07:00
Sergey M․ 06bf2ac20f [extractor/common] Eliminate media tag name regex duplication 2020-12-07 00:56:29 +07:00
Sergey M․ 6ad0d8781e [extractor/common] Fix media type extraction for HTML5 media tags in start/end form 2020-12-07 00:45:16 +07:00
Sergey M․ f2c704e112 [generic] Extract RSS video itunes metadata 2020-12-06 23:08:03 +07:00
Sergey M․ 5e822c2526 [generic] Extract RSS video timestamp 2020-12-06 22:30:30 +07:00
renalid cc017e07ca [generic] Extract RSS video description (#27177) 2020-12-06 22:12:25 +07:00
Remita Amine 082da36416 [nrk] reduce requests for Radio series 2020-12-05 16:24:49 +01:00
Remita Amine 6bf95b15ee [nrk] reduce the number of instalments requests 2020-12-05 15:35:29 +01:00
Remita Amine 4c93b2fd15 [nrk] improve format extraction 2020-12-05 09:13:42 +01:00
Remita Amine 1b26bfd425 [nrk] improve extraction
- improve format extraction for old akamai formats
- update some of the tests
- add is_live value to entry info dict
- request instalments only when their available
- fix skole extraction
2020-12-05 00:40:03 +01:00
Sergey M․ 13ec444a98 [peertube] Extract fps 2020-12-05 04:45:30 +07:00
Sergey M․ 51579d87e4 [peertube] Recognize audio-only formats (closes #27295) 2020-12-05 04:41:33 +07:00
23 changed files with 939 additions and 618 deletions
+3 -3
View File
@@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2020.12.05
[debug] youtube-dl version 2020.12.09
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}
@@ -19,7 +19,7 @@ labels: 'site-support-request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
- Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a new site support request
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones
@@ -18,13 +18,13 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a site feature request
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
+3 -3
View File
@@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support issue
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2020.12.05
[debug] youtube-dl version 2020.12.09
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}
+2 -2
View File
@@ -19,13 +19,13 @@ labels: 'request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.12.09. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a feature request
- [ ] I've verified that I'm running youtube-dl version **2020.12.05**
- [ ] I've verified that I'm running youtube-dl version **2020.12.09**
- [ ] I've searched the bugtracker for similar feature requests including closed ones
+50
View File
@@ -1,3 +1,53 @@
version <unreleaed>
Core
* [extractor/common] Fix inline HTML5 media tags processing (#27345)
Extractors
* [youtube:tab] Improve identity token extraction (#27197)
* [youtube:tab] Make click tracking params on continuation optional
* [youtube:tab] Delegate inline playlists to tab-based playlists (27298)
+ [tubitv] Extract release year (#27317)
* [amcnetworks] Fix free content extraction (#20354)
+ [lbry:channel] Add support for channels (#25584)
+ [lbry] Add support for short and embed URLs
* [lbry] Fix channel metadata extraction
+ [telequebec] Add support for video.telequebec.tv (#27339)
* [telequebec] Fix extraction (#25733, #26883)
+ [youtube:tab] Capture and output alerts (#27340)
* [tvplay:home] Fix extraction (#21153)
* [americastestkitchen] Fix Extraction and add support
for Cook's Country and Cook's Illustrated (#17234, #27322)
+ [slideslive] Add support for yoda service videos and extract subtitles
(#27323)
version 2020.12.07
Core
* [extractor/common] Extract timestamp from Last-Modified header
+ [extractor/common] Add support for dl8-* media tags (#27283)
* [extractor/common] Fix media type extraction for HTML5 media tags
in start/end form
Extractors
* [aenetworks] Fix extraction (#23363, #23390, #26795, #26985)
* Fix Fastly format extraction
+ Add support for play and watch subdomains
+ Extract series metadata
* [youtube] Improve youtu.be extraction in non-existing playlists (#27324)
+ [generic] Extract RSS video description, timestamp and itunes metadata
(#27177)
* [nrk] Reduce the number of instalments and episodes requests
* [nrk] Improve extraction
* Improve format extraction for old akamai formats
+ Add is_live value to entry info dict
* Request instalments only when available
* Fix skole extraction
+ [peertube] Extract fps
+ [peertube] Recognize audio-only formats (#27295)
version 2020.12.05
Core
+6 -1
View File
@@ -35,6 +35,8 @@
- **adobetv:video**
- **AdultSwim**
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault
- **aenetworks:collection**
- **aenetworks:show**
- **afreecatv**: afreecatv.com
- **AirMozilla**
- **AliExpressLive**
@@ -422,7 +424,8 @@
- **la7.it**
- **laola1tv**
- **laola1tv:embed**
- **lbry.tv**
- **lbry**
- **lbry:channel**
- **LCI**
- **Lcp**
- **LcpPlay**
@@ -898,6 +901,7 @@
- **TeleQuebecEmission**
- **TeleQuebecLive**
- **TeleQuebecSquat**
- **TeleQuebecVideo**
- **TeleTask**
- **Telewebion**
- **TennisTV**
@@ -1164,6 +1168,7 @@
- **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- **youtube:tab**: YouTube.com tab
- **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **YoutubeYtBe**
- **YoutubeYtUser**
- **Zapiks**
- **Zaq1**
+12
View File
@@ -108,6 +108,18 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
def test_parse_html5_media_entries(self):
# inline video tag
expect_dict(
self,
self.ie._parse_html5_media_entries(
'https://127.0.0.1/video.html',
r'<html><video src="/vid.mp4" /></html>', None)[0],
{
'formats': [{
'url': 'https://127.0.0.1/vid.mp4',
}],
})
# from https://www.r18.com/
# with kpbs in label
expect_dict(
+163 -114
View File
@@ -5,20 +5,30 @@ import re
from .theplatform import ThePlatformIE
from ..utils import (
extract_attributes,
ExtractorError,
int_or_none,
smuggle_url,
update_url_query,
)
from ..compat import (
compat_urlparse,
urlencode_postdata,
)
class AENetworksBaseIE(ThePlatformIE):
_BASE_URL_REGEX = r'''(?x)https?://
(?:(?:www|play|watch)\.)?
(?P<domain>
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/'''
_THEPLATFORM_KEY = 'crazyjava'
_THEPLATFORM_SECRET = 's3cr3t'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),
'mylifetime.com': ('LIFETIME', 'lifetime'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
'fyi.tv': ('FYI', 'fyi'),
'historyvault.com': (None, 'historyvault'),
}
def _extract_aen_smil(self, smil_url, video_id, auth=None):
query = {'mbr': 'true'}
@@ -31,7 +41,7 @@ class AENetworksBaseIE(ThePlatformIE):
'assetTypes': 'high_video_s3'
}, {
'assetTypes': 'high_video_s3',
'switch': 'hls_ingest_fastly'
'switch': 'hls_high_fastly',
}]
formats = []
subtitles = {}
@@ -61,20 +71,13 @@ class AENetworksBaseIE(ThePlatformIE):
class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?P<domain>
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/
(?:
shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
specials/(?P<special_display_id>[^/]+)/(?:full-special|preview-)|
collections/[^/]+/(?P<collection_display_id>[^/]+)
)
'''
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'''(?P<id>
shows/[^/]+/season-\d+/episode-\d+|
(?:
(?:movie|special)s/[^/]+|
(?:shows/[^/]+/)?videos
)/[^/?#&]+
)'''
_TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'info_dict': {
@@ -91,22 +94,23 @@ class AENetworksIE(AENetworksBaseIE):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.history.com/shows/ancient-aliens/season-1',
'info_dict': {
'id': '71889446852',
},
'playlist_mincount': 5,
}, {
'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
'info_dict': {
'id': 'SERIES4317',
'title': 'Atlanta Plastic',
},
'playlist_mincount': 2,
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'only_matching': True
'info_dict': {
'id': '600587331957',
'ext': 'mp4',
'title': 'Inlawful Entry',
'description': 'md5:57c12115a2b384d883fe64ca50529e08',
'timestamp': 1452634428,
'upload_date': '20160112',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True
@@ -117,80 +121,152 @@ class AENetworksIE(AENetworksBaseIE):
'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
'only_matching': True
}, {
'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
'url': 'https://watch.lifetimemovieclub.com/movies/10-year-reunion/full-movie',
'only_matching': True
}, {
'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
'only_matching': True
}, {
'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
'only_matching': True
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
'only_matching': True
}, {
'url': 'http://www.history.com/videos/history-of-valentines-day',
'only_matching': True
}, {
'url': 'https://play.aetv.com/shows/duck-dynasty/videos/best-of-duck-dynasty-getting-quack-in-shape',
'only_matching': True
}]
_DOMAIN_TO_REQUESTOR_ID = {
'history.com': 'HISTORY',
'aetv.com': 'AETV',
'mylifetime.com': 'LIFETIME',
'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB',
'fyi.tv': 'FYI',
}
def _real_extract(self, url):
domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups()
display_id = show_path or movie_display_id or special_display_id or collection_display_id
webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers())
if show_path:
url_parts = show_path.split('/')
url_parts_len = len(url_parts)
if url_parts_len == 1:
entries = []
for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
entries.append(self.url_result(
compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
if entries:
return self.playlist_result(
entries, self._html_search_meta('aetn:SeriesId', webpage),
self._html_search_meta('aetn:SeriesTitle', webpage))
else:
# single season
url_parts_len = 2
if url_parts_len == 2:
entries = []
for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
episode_attributes = extract_attributes(episode_item)
episode_url = compat_urlparse.urljoin(
url, episode_attributes['data-canonical'])
entries.append(self.url_result(
episode_url, 'AENetworks',
episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
return self.playlist_result(
entries, self._html_search_meta('aetn:SeasonId', webpage))
video_id = self._html_search_meta('aetn:VideoID', webpage)
media_url = self._search_regex(
[r"media_url\s*=\s*'(?P<url>[^']+)'",
r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
webpage, 'video url', group='url')
domain, canonical = re.match(self._VALID_URL, url).groups()
requestor_id, brand = self._DOMAIN_MAP[domain]
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
canonical, query={'filter[canonical]': '/' + canonical})['results'][0]
title = result['title']
video_id = result['id']
media_url = result['publicUrl']
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
auth = None
if theplatform_metadata.get('AETN$isBehindWall'):
requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
resource = self._get_mvpd_resource(
requestor_id, theplatform_metadata['title'],
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
theplatform_metadata['ratings'][0]['rating'])
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
info.update(self._search_json_ld(webpage, video_id, fatal=False))
info.update(self._extract_aen_smil(media_url, video_id, auth))
info.update({
'title': title,
'series': result.get('seriesName'),
'season_number': int_or_none(result.get('tvSeasonNumber')),
'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')),
})
return info
class AENetworksListBaseIE(AENetworksBaseIE):
def _call_api(self, resource, slug, brand, fields):
return self._download_json(
'https://yoga.appsvcs.aetnd.com/graphql',
slug, query={'brand': brand}, data=urlencode_postdata({
'query': '''{
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields),
}))['data'][resource]
def _real_extract(self, url):
domain, slug = re.match(self._VALID_URL, url).groups()
_, brand = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = 'http://watch.%s' % domain
entries = []
for item in (playlist.get(self._ITEMS_KEY) or []):
doc = self._get_doc(item)
canonical = doc.get('canonical')
if not canonical:
continue
entries.append(self.url_result(
base_url + canonical, AENetworksIE.ie_key(), doc.get('id')))
description = None
if self._PLAYLIST_DESCRIPTION_KEY:
description = playlist.get(self._PLAYLIST_DESCRIPTION_KEY)
return self.playlist_result(
entries, playlist.get('id'),
playlist.get(self._PLAYLIST_TITLE_KEY), description)
class AENetworksCollectionIE(AENetworksListBaseIE):
IE_NAME = 'aenetworks:collection'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'(?:[^/]+/)*(?:list|collections)/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'https://watch.historyvault.com/list/america-the-story-of-us',
'info_dict': {
'id': '282',
'title': 'America The Story of Us',
},
'playlist_mincount': 12,
}, {
'url': 'https://watch.historyvault.com/shows/america-the-story-of-us-2/season-1/list/america-the-story-of-us',
'only_matching': True
}, {
'url': 'https://www.historyvault.com/collections/mysteryquest',
'only_matching': True
}]
_RESOURCE = 'list'
_ITEMS_KEY = 'items'
_PLAYLIST_TITLE_KEY = 'display_title'
_PLAYLIST_DESCRIPTION_KEY = None
_FIELDS = '''id
display_title
items {
... on ListVideoItem {
doc {
canonical
id
}
}
}'''
def _get_doc(self, item):
return item.get('doc') or {}
class AENetworksShowIE(AENetworksListBaseIE):
IE_NAME = 'aenetworks:show'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'shows/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'http://www.history.com/shows/ancient-aliens',
'info_dict': {
'id': 'SH012427480000',
'title': 'Ancient Aliens',
'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
},
'playlist_mincount': 168,
}]
_RESOURCE = 'series'
_ITEMS_KEY = 'episodes'
_PLAYLIST_TITLE_KEY = 'title'
_PLAYLIST_DESCRIPTION_KEY = 'description'
_FIELDS = '''description
id
title
episodes {
canonical
id
}'''
def _get_doc(self, item):
return item
class HistoryTopicIE(AENetworksBaseIE):
IE_NAME = 'history:topic'
IE_DESC = 'History.com Topic'
@@ -204,6 +280,7 @@ class HistoryTopicIE(AENetworksBaseIE):
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729,
'upload_date': '20130806',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
@@ -212,36 +289,8 @@ class HistoryTopicIE(AENetworksBaseIE):
'add_ie': ['ThePlatform'],
}]
def theplatform_url_result(self, theplatform_url, video_id, query):
return {
'_type': 'url_transparent',
'id': video_id,
'url': smuggle_url(
update_url_query(theplatform_url, query),
{
'sig': {
'key': self._THEPLATFORM_KEY,
'secret': self._THEPLATFORM_SECRET,
},
'force_smil_url': True
}),
'ie_key': 'ThePlatform',
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'<phoenix-iframe[^>]+src="[^"]+\btpid=(\d+)', webpage, 'tpid')
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/history/videos',
video_id, query={'filter[id]': video_id})['results'][0]
title = result['title']
info = self._extract_aen_smil(result['publicUrl'], video_id)
info.update({
'title': title,
'description': result.get('description'),
'duration': int_or_none(result.get('duration')),
'timestamp': int_or_none(result.get('added'), 1000),
})
return info
return self.url_result(
'http://www.history.com/videos/' + display_id,
AENetworksIE.ie_key())
+25 -25
View File
@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .theplatform import ThePlatformIE
from ..utils import (
int_or_none,
@@ -11,25 +13,22 @@ from ..utils import (
class AMCNetworksIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?:movies|shows(?:/[^/]+)+)/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
_TESTS = [{
'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
'md5': '',
'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
'info_dict': {
'id': 's3MX01Nl4vPH',
'id': '4Lq1dzOnZGt0',
'ext': 'mp4',
'title': 'Maron - Season 4 - Step 1',
'description': 'In denial about his current situation, Marc is reluctantly convinced by his friends to enter rehab. Starring Marc Maron and Constance Zimmer.',
'age_limit': 17,
'upload_date': '20160505',
'timestamp': 1462468831,
'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
'description': "It turns out child stewardesses are very generous with the wine! All-new episodes of 'The Graham Norton Show' premiere Fridays at 11/10c on BBC America.",
'upload_date': '20201120',
'timestamp': 1605904350,
'uploader': 'AMCN',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Requires TV provider accounts',
}, {
'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
'only_matching': True,
@@ -55,32 +54,33 @@ class AMCNetworksIE(ThePlatformIE):
'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
'only_matching': True,
}]
_REQUESTOR_ID_MAP = {
'amc': 'AMC',
'bbcamerica': 'BBCA',
'ifc': 'IFC',
'sundancetv': 'SUNDANCE',
'wetv': 'WETV',
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
site, display_id = re.match(self._VALID_URL, url).groups()
requestor_id = self._REQUESTOR_ID_MAP[site]
properties = self._download_json(
'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s' % (requestor_id.lower(), display_id),
display_id)['data']['properties']
query = {
'mbr': 'true',
'manifest': 'm3u',
}
media_url = self._search_regex(
r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)',
webpage, 'media url')
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'link\.theplatform\.com/s/([^?]+)',
media_url, 'theplatform_path'), display_id)
tp_path = 'M_UwQC/media/' + properties['videoPid']
media_url = 'https://link.theplatform.com/s/' + tp_path
theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
video_id = theplatform_metadata['pid']
title = theplatform_metadata['title']
rating = try_get(
theplatform_metadata, lambda x: x['ratings'][0]['rating'])
auth_required = self._search_regex(
r'window\.authRequired\s*=\s*(true|false);',
webpage, 'auth required')
if auth_required == 'true':
requestor_id = self._search_regex(
r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)',
webpage, 'requestor id')
if properties.get('videoCategory') == 'TVE-Auth':
resource = self._get_mvpd_resource(
requestor_id, title, video_id, rating)
query['auth'] = self._extract_mvpd_auth(
+26 -42
View File
@@ -1,33 +1,33 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
js_to_json,
try_get,
unified_strdate,
)
class AmericasTestKitchenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
'md5': 'b861c3e365ac38ad319cfd509c30577f',
'info_dict': {
'id': '5b400b9ee338f922cb06450c',
'title': 'Weeknight Japanese Suppers',
'title': 'Japanese Suppers',
'ext': 'mp4',
'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8',
'description': 'md5:64e606bfee910627efc4b5f050de92b3',
'thumbnail': r're:^https?://',
'timestamp': 1523664000,
'upload_date': '20180414',
'release_date': '20180414',
'release_date': '20180410',
'series': "America's Test Kitchen",
'season_number': 18,
'episode': 'Weeknight Japanese Suppers',
'episode': 'Japanese Suppers',
'episode_number': 15,
},
'params': {
@@ -36,47 +36,31 @@ class AmericasTestKitchenIE(InfoExtractor):
}, {
'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
'only_matching': True,
}, {
'url': 'https://www.cooksillustrated.com/videos/4478-beef-wellington',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
resource_type, video_id = re.match(self._VALID_URL, url).groups()
is_episode = resource_type == 'episode'
if is_episode:
resource_type = 'episodes'
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(
self._search_regex(
r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
webpage, 'initial context'),
video_id, js_to_json)
ep_data = try_get(
video_data,
(lambda x: x['episodeDetail']['content']['data'],
lambda x: x['videoDetail']['content']['data']), dict)
ep_meta = ep_data.get('full_video', {})
zype_id = ep_data.get('zype_id') or ep_meta['zype_id']
title = ep_data.get('title') or ep_meta.get('title')
description = clean_html(ep_meta.get('episode_description') or ep_data.get(
'description') or ep_meta.get('description'))
thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url'])
release_date = unified_strdate(ep_data.get('aired_at'))
season_number = int_or_none(ep_meta.get('season_number'))
episode = ep_meta.get('title')
episode_number = int_or_none(ep_meta.get('episode_number'))
resource = self._download_json(
'https://www.americastestkitchen.com/api/v6/%s/%s' % (resource_type, video_id), video_id)
video = resource['video'] if is_episode else resource
episode = resource if is_episode else resource.get('episode') or {}
return {
'_type': 'url_transparent',
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id,
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
'ie_key': 'Zype',
'title': title,
'description': description,
'thumbnail': thumbnail,
'release_date': release_date,
'series': "America's Test Kitchen",
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'description': clean_html(video.get('description')),
'release_date': unified_strdate(video.get('publishDate')),
'series': try_get(episode, lambda x: x['show']['title']),
'episode': episode.get('title'),
}
+7 -5
View File
@@ -2513,16 +2513,18 @@ class InfoExtractor(object):
# amp-video and amp-audio are very similar to their HTML5 counterparts
# so we wll include them right here (see
# https://www.ampproject.org/docs/reference/components/amp-video)
media_tags = [(media_tag, media_type, '')
for media_tag, media_type
in re.findall(r'(?s)(<(?:amp-)?(video|audio)[^>]*/>)', webpage)]
# For dl8-* tags see https://delight-vr.com/documentation/dl8-video/
_MEDIA_TAG_NAME_RE = r'(?:(?:amp|dl8(?:-live)?)-)?(video|audio)'
media_tags = [(media_tag, media_tag_name, media_type, '')
for media_tag, media_tag_name, media_type
in re.findall(r'(?s)(<(%s)[^>]*/>)' % _MEDIA_TAG_NAME_RE, webpage)]
media_tags.extend(re.findall(
# We only allow video|audio followed by a whitespace or '>'.
# Allowing more characters may end up in significant slow down (see
# https://github.com/ytdl-org/youtube-dl/issues/11979, example URL:
# http://www.porntrex.com/maps/videositemap.xml).
r'(?s)(<(?P<tag>(?:amp-)?(?:video|audio))(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
for media_tag, media_type, media_content in media_tags:
r'(?s)(<(?P<tag>%s)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>' % _MEDIA_TAG_NAME_RE, webpage))
for media_tag, _, media_type, media_content in media_tags:
media_info = {
'formats': [],
'subtitles': {},
+8 -1
View File
@@ -30,6 +30,8 @@ from .adobetv import (
from .adultswim import AdultSwimIE
from .aenetworks import (
AENetworksIE,
AENetworksCollectionIE,
AENetworksShowIE,
HistoryTopicIE,
)
from .afreecatv import AfreecaTVIE
@@ -532,7 +534,10 @@ from .laola1tv import (
EHFTVIE,
ITTFIE,
)
from .lbry import LBRYIE
from .lbry import (
LBRYIE,
LBRYChannelIE,
)
from .lci import LCIIE
from .lcp import (
LcpPlayIE,
@@ -1150,6 +1155,7 @@ from .telequebec import (
TeleQuebecSquatIE,
TeleQuebecEmissionIE,
TeleQuebecLiveIE,
TeleQuebecVideoIE,
)
from .teletask import TeleTaskIE
from .telewebion import TelewebionIE
@@ -1520,6 +1526,7 @@ from .youtube import (
YoutubeSubscriptionsIE,
YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE,
YoutubeYtBeIE,
YoutubeYtUserIE,
YoutubeWatchLaterIE,
)
+68 -25
View File
@@ -20,19 +20,23 @@ from ..utils import (
ExtractorError,
float_or_none,
HEADRequest,
int_or_none,
is_html,
js_to_json,
KNOWN_EXTENSIONS,
merge_dicts,
mimetype2ext,
orderedSet,
parse_duration,
sanitized_Request,
smuggle_url,
unescapeHTML,
unified_strdate,
unified_timestamp,
unsmuggle_url,
UnsupportedError,
url_or_none,
xpath_text,
xpath_with_ns,
)
from .commonprotocols import RtmpIE
from .brightcove import (
@@ -198,11 +202,21 @@ class GenericIE(InfoExtractor):
{
'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
'info_dict': {
'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
'ext': 'm4v',
'upload_date': '20150228',
'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
}
'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
'title': 'MSNBC Rachel Maddow (video)',
'description': 're:.*her unique approach to storytelling.*',
},
'playlist': [{
'info_dict': {
'ext': 'mov',
'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
'title': 're:MSNBC Rachel Maddow',
'description': 're:.*her unique approach to storytelling.*',
'timestamp': int,
'upload_date': compat_str,
'duration': float,
},
}],
},
# RSS feed with enclosures and unsupported link URLs
{
@@ -2103,23 +2117,23 @@ class GenericIE(InfoExtractor):
'skip_download': True,
},
},
{
# Zype embed
'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
'info_dict': {
'id': '5b400b834b32992a310622b9',
'ext': 'mp4',
'title': 'Smoky Barbecue Favorites',
'thumbnail': r're:^https?://.*\.jpe?g',
'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
'upload_date': '20170909',
'timestamp': 1504915200,
},
'add_ie': [ZypeIE.ie_key()],
'params': {
'skip_download': True,
},
},
# {
# # Zype embed
# 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
# 'info_dict': {
# 'id': '5b400b834b32992a310622b9',
# 'ext': 'mp4',
# 'title': 'Smoky Barbecue Favorites',
# 'thumbnail': r're:^https?://.*\.jpe?g',
# 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
# 'upload_date': '20170909',
# 'timestamp': 1504915200,
# },
# 'add_ie': [ZypeIE.ie_key()],
# 'params': {
# 'skip_download': True,
# },
# },
{
# videojs embed
'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
@@ -2180,6 +2194,10 @@ class GenericIE(InfoExtractor):
playlist_desc_el = doc.find('./channel/description')
playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
NS_MAP = {
'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
}
entries = []
for it in doc.findall('./channel/item'):
next_url = None
@@ -2195,10 +2213,33 @@ class GenericIE(InfoExtractor):
if not next_url:
continue
def itunes(key):
return xpath_text(
it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
default=None)
duration = itunes('duration')
explicit = itunes('explicit')
if explicit == 'true':
age_limit = 18
elif explicit == 'false':
age_limit = 0
else:
age_limit = None
entries.append({
'_type': 'url_transparent',
'url': next_url,
'title': it.find('title').text,
'description': xpath_text(it, 'description', default=None),
'timestamp': unified_timestamp(
xpath_text(it, 'pubDate', default=None)),
'duration': int_or_none(duration) or parse_duration(duration),
'thumbnail': url_or_none(itunes('image')),
'episode': itunes('title'),
'episode_number': int_or_none(itunes('episode')),
'season_number': int_or_none(itunes('season')),
'age_limit': age_limit,
})
return {
@@ -2318,7 +2359,7 @@ class GenericIE(InfoExtractor):
info_dict = {
'id': video_id,
'title': self._generic_title(url),
'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
}
# Check for direct link to a video
@@ -2424,7 +2465,9 @@ class GenericIE(InfoExtractor):
# Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
# Unescaping the whole page allows to handle those cases in a generic way
webpage = compat_urllib_parse_unquote(webpage)
# FIXME: unescaping the whole page may break URLs, commenting out for now.
# There probably should be a second run of generic extractor on unescaped webpage.
# webpage = compat_urllib_parse_unquote(webpage)
# Unescape squarespace embeds to be detected by generic extractor,
# see https://github.com/ytdl-org/youtube-dl/issues/21294
+163 -40
View File
@@ -1,6 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
import functools
import json
from .common import InfoExtractor
@@ -10,13 +11,73 @@ from ..utils import (
ExtractorError,
int_or_none,
mimetype2ext,
OnDemandPagedList,
try_get,
urljoin,
)
class LBRYIE(InfoExtractor):
IE_NAME = 'lbry.tv'
_VALID_URL = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/(?P<id>@[^:]+:[0-9a-z]+/[^:]+:[0-9a-z])'
class LBRYBaseIE(InfoExtractor):
_BASE_URL_REGEX = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/'
_CLAIM_ID_REGEX = r'[0-9a-f]{1,40}'
_OPT_CLAIM_ID = '[^:/?#&]+(?::%s)?' % _CLAIM_ID_REGEX
_SUPPORTED_STREAM_TYPES = ['video', 'audio']
def _call_api_proxy(self, method, display_id, params, resource):
return self._download_json(
'https://api.lbry.tv/api/v1/proxy',
display_id, 'Downloading %s JSON metadata' % resource,
headers={'Content-Type': 'application/json-rpc'},
data=json.dumps({
'method': method,
'params': params,
}).encode())['result']
def _resolve_url(self, url, display_id, resource):
return self._call_api_proxy(
'resolve', display_id, {'urls': url}, resource)[url]
def _permanent_url(self, url, claim_name, claim_id):
return urljoin(url, '/%s:%s' % (claim_name, claim_id))
def _parse_stream(self, stream, url):
stream_value = stream.get('value') or {}
stream_type = stream_value.get('stream_type')
source = stream_value.get('source') or {}
media = stream_value.get(stream_type) or {}
signing_channel = stream.get('signing_channel') or {}
channel_name = signing_channel.get('name')
channel_claim_id = signing_channel.get('claim_id')
channel_url = None
if channel_name and channel_claim_id:
channel_url = self._permanent_url(url, channel_name, channel_claim_id)
info = {
'thumbnail': try_get(stream_value, lambda x: x['thumbnail']['url'], compat_str),
'description': stream_value.get('description'),
'license': stream_value.get('license'),
'timestamp': int_or_none(stream.get('timestamp')),
'tags': stream_value.get('tags'),
'duration': int_or_none(media.get('duration')),
'channel': try_get(signing_channel, lambda x: x['value']['title']),
'channel_id': channel_claim_id,
'channel_url': channel_url,
'ext': determine_ext(source.get('name')) or mimetype2ext(source.get('media_type')),
'filesize': int_or_none(source.get('size')),
}
if stream_type == 'audio':
info['vcodec'] = 'none'
else:
info.update({
'width': int_or_none(media.get('width')),
'height': int_or_none(media.get('height')),
})
return info
class LBRYIE(LBRYBaseIE):
IE_NAME = 'lbry'
_VALID_URL = LBRYBaseIE._BASE_URL_REGEX + r'(?P<id>\$/[^/]+/[^/]+/{1}|@{0}/{0}|(?!@){0})'.format(LBRYBaseIE._OPT_CLAIM_ID, LBRYBaseIE._CLAIM_ID_REGEX)
_TESTS = [{
# Video
'url': 'https://lbry.tv/@Mantega:1/First-day-LBRY:1',
@@ -28,6 +89,8 @@ class LBRYIE(InfoExtractor):
'description': 'md5:f6cb5c704b332d37f5119313c2c98f51',
'timestamp': 1595694354,
'upload_date': '20200725',
'width': 1280,
'height': 720,
}
}, {
# Audio
@@ -40,6 +103,12 @@ class LBRYIE(InfoExtractor):
'description': 'md5:661ac4f1db09f31728931d7b88807a61',
'timestamp': 1591312601,
'upload_date': '20200604',
'tags': list,
'duration': 2570,
'channel': 'The LBRY Foundation',
'channel_id': '0ed629d2b9c601300cacf7eabe9da0be79010212',
'channel_url': 'https://lbry.tv/@LBRYFoundation:0ed629d2b9c601300cacf7eabe9da0be79010212',
'vcodec': 'none',
}
}, {
'url': 'https://odysee.com/@BrodieRobertson:5/apple-is-tracking-everything-you-do-on:e',
@@ -47,45 +116,99 @@ class LBRYIE(InfoExtractor):
}, {
'url': "https://odysee.com/@ScammerRevolts:b0/I-SYSKEY'D-THE-SAME-SCAMMERS-3-TIMES!:b",
'only_matching': True,
}, {
'url': 'https://lbry.tv/Episode-1:e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True,
}, {
'url': 'https://lbry.tv/$/embed/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True,
}, {
'url': 'https://lbry.tv/Episode-1:e7',
'only_matching': True,
}, {
'url': 'https://lbry.tv/@LBRYFoundation/Episode-1',
'only_matching': True,
}, {
'url': 'https://lbry.tv/$/download/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True,
}]
def _call_api_proxy(self, method, display_id, params):
return self._download_json(
'https://api.lbry.tv/api/v1/proxy', display_id,
headers={'Content-Type': 'application/json-rpc'},
data=json.dumps({
'method': method,
'params': params,
}).encode())['result']
def _real_extract(self, url):
display_id = self._match_id(url)
if display_id.startswith('$/'):
display_id = display_id.split('/', 2)[-1].replace('/', ':')
else:
display_id = display_id.replace(':', '#')
uri = 'lbry://' + display_id
result = self._resolve_url(uri, display_id, 'stream')
result_value = result['value']
if result_value.get('stream_type') not in self._SUPPORTED_STREAM_TYPES:
raise ExtractorError('Unsupported URL', expected=True)
claim_id = result['claim_id']
title = result_value['title']
streaming_url = self._call_api_proxy(
'get', claim_id, {'uri': uri}, 'streaming url')['streaming_url']
info = self._parse_stream(result, url)
info.update({
'id': claim_id,
'title': title,
'url': streaming_url,
})
return info
class LBRYChannelIE(LBRYBaseIE):
IE_NAME = 'lbry:channel'
_VALID_URL = LBRYBaseIE._BASE_URL_REGEX + r'(?P<id>@%s)/?(?:[?#&]|$)' % LBRYBaseIE._OPT_CLAIM_ID
_TESTS = [{
'url': 'https://lbry.tv/@LBRYFoundation:0',
'info_dict': {
'id': '0ed629d2b9c601300cacf7eabe9da0be79010212',
'title': 'The LBRY Foundation',
'description': 'Channel for the LBRY Foundation. Follow for updates and news.',
},
'playlist_count': 29,
}, {
'url': 'https://lbry.tv/@LBRYFoundation',
'only_matching': True,
}]
_PAGE_SIZE = 50
def _fetch_page(self, claim_id, url, page):
page += 1
result = self._call_api_proxy(
'claim_search', claim_id, {
'channel_ids': [claim_id],
'claim_type': 'stream',
'no_totals': True,
'page': page,
'page_size': self._PAGE_SIZE,
'stream_types': self._SUPPORTED_STREAM_TYPES,
}, 'page %d' % page)
for item in (result.get('items') or []):
stream_claim_name = item.get('name')
stream_claim_id = item.get('claim_id')
if not (stream_claim_name and stream_claim_id):
continue
info = self._parse_stream(item, url)
info.update({
'_type': 'url',
'id': stream_claim_id,
'title': try_get(item, lambda x: x['value']['title']),
'url': self._permanent_url(url, stream_claim_name, stream_claim_id),
})
yield info
def _real_extract(self, url):
display_id = self._match_id(url).replace(':', '#')
uri = 'lbry://' + display_id
result = self._call_api_proxy(
'resolve', display_id, {'urls': [uri]})[uri]
result_value = result['value']
if result_value.get('stream_type') not in ('video', 'audio'):
raise ExtractorError('Unsupported URL', expected=True)
streaming_url = self._call_api_proxy(
'get', display_id, {'uri': uri})['streaming_url']
source = result_value.get('source') or {}
media = result_value.get('video') or result_value.get('audio') or {}
signing_channel = result_value.get('signing_channel') or {}
return {
'id': result['claim_id'],
'title': result_value['title'],
'thumbnail': try_get(result_value, lambda x: x['thumbnail']['url'], compat_str),
'description': result_value.get('description'),
'license': result_value.get('license'),
'timestamp': int_or_none(result.get('timestamp')),
'tags': result_value.get('tags'),
'width': int_or_none(media.get('width')),
'height': int_or_none(media.get('height')),
'duration': int_or_none(media.get('duration')),
'channel': signing_channel.get('name'),
'channel_id': signing_channel.get('claim_id'),
'ext': determine_ext(source.get('name')) or mimetype2ext(source.get('media_type')),
'filesize': int_or_none(source.get('size')),
'url': streaming_url,
}
result = self._resolve_url(
'lbry://' + display_id, display_id, 'channel')
claim_id = result['claim_id']
entries = OnDemandPagedList(
functools.partial(self._fetch_page, claim_id, url),
self._PAGE_SIZE)
result_value = result.get('value') or {}
return self.playlist_result(
entries, claim_id, result_value.get('title'),
result_value.get('description'))
+108 -178
View File
@@ -2,6 +2,7 @@
from __future__ import unicode_literals
import itertools
import random
import re
from .common import InfoExtractor
@@ -13,8 +14,6 @@ from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
js_to_json,
NO_DEFAULT,
parse_age_limit,
parse_duration,
try_get,
@@ -25,11 +24,25 @@ from ..utils import (
class NRKBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['NO']
_CDN_REPL_REGEX = r'''(?x)://
(?:
nrkod\d{1,2}-httpcache0-47115-cacheod0\.dna\.ip-only\.net/47115-cacheod0|
nrk-od-no\.telenorcdn\.net|
minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no
)/'''
def _extract_nrk_formats(self, asset_url, video_id):
return self._extract_m3u8_formats(
re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url),
video_id, 'mp4', 'm3u8_native', fatal=False)
if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url):
return self._extract_akamai_formats(
re.sub(r'(?:b=\d+-\d+|__a__=off)&?', '', asset_url), video_id)
asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url)
formats = self._extract_m3u8_formats(
asset_url, video_id, 'mp4', 'm3u8_native', fatal=False)
if not formats and re.search(self._CDN_REPL_REGEX, asset_url):
formats = self._extract_m3u8_formats(
re.sub(self._CDN_REPL_REGEX, '://nrk-od-%02d.akamaized.net/no/' % random.randint(0, 99), asset_url),
video_id, 'mp4', 'm3u8_native', fatal=False)
return formats
def _raise_error(self, data):
MESSAGES = {
@@ -47,6 +60,12 @@ class NRKBaseIE(InfoExtractor):
message = data.get('endUserMessage') or MESSAGES.get(message_type, message_type)
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
def _call_api(self, path, video_id, item=None, note=None, fatal=True, query=None):
return self._download_json(
urljoin('http://psapi.nrk.no/', path),
video_id, note or 'Downloading %s JSON' % item,
fatal=fatal, query=query)
class NRKIE(NRKBaseIE):
_VALID_URL = r'''(?x)
@@ -64,7 +83,7 @@ class NRKIE(NRKBaseIE):
_TESTS = [{
# video
'url': 'http://www.nrk.no/video/PS*150533',
'md5': '706f34cdf1322577589e369e522b50ef',
'md5': 'f46be075326e23ad0e524edfcb06aeb6',
'info_dict': {
'id': '150533',
'ext': 'mp4',
@@ -78,7 +97,7 @@ class NRKIE(NRKBaseIE):
# MD5 is unstable
'info_dict': {
'id': '154915',
'ext': 'flv',
'ext': 'mp4',
'title': 'Slik høres internett ut når du er blind',
'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
'duration': 20,
@@ -101,9 +120,12 @@ class NRKIE(NRKBaseIE):
}]
def _extract_from_playback(self, video_id):
manifest = self._download_json(
'http://psapi.nrk.no/playback/manifest/%s' % video_id,
video_id, 'Downloading manifest JSON')
path_templ = 'playback/%s/' + video_id
def call_playback_api(item, query=None):
return self._call_api(path_templ % item, video_id, item, query=query)
# known values for preferredCdn: akamai, iponly, minicdn and telenor
manifest = call_playback_api('manifest', {'preferredCdn': 'akamai'})
if manifest.get('playability') == 'nonPlayable':
self._raise_error(manifest['nonPlayable'])
@@ -123,9 +145,7 @@ class NRKIE(NRKBaseIE):
formats.extend(self._extract_nrk_formats(format_url, video_id))
self._sort_formats(formats)
data = self._download_json(
'http://psapi.nrk.no/playback/metadata/%s' % video_id,
video_id, 'Downloading metadata JSON')
data = call_playback_api('metadata')
preplay = data['preplay']
titles = preplay['titles']
@@ -171,18 +191,18 @@ class NRKTVIE(NRKBaseIE):
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
_TESTS = [{
'url': 'https://tv.nrk.no/program/MDDP12000117',
'md5': '8270824df46ec629b66aeaa5796b36fb',
'md5': 'c4a5960f1b00b40d47db65c1064e0ab1',
'info_dict': {
'id': 'MDDP12000117AA',
'ext': 'mp4',
'title': 'Alarm Trolltunga',
'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
'duration': 2223,
'duration': 2223.44,
'age_limit': 6,
},
}, {
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
'md5': '9a167e54d04671eb6317a37b7bc8a280',
'md5': '8d40dab61cea8ab0114e090b029a0565',
'info_dict': {
'id': 'MUHH48000314AA',
'ext': 'mp4',
@@ -192,7 +212,6 @@ class NRKTVIE(NRKBaseIE):
'series': '20 spørsmål',
'episode': '23.05.2014',
},
'skip': 'NoProgramRights',
}, {
'url': 'https://tv.nrk.no/program/mdfp15000514',
'info_dict': {
@@ -200,7 +219,7 @@ class NRKTVIE(NRKBaseIE):
'ext': 'mp4',
'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
'duration': 4605,
'duration': 4605.08,
'series': 'Kunnskapskanalen',
'episode': '24.05.2014',
},
@@ -211,51 +230,25 @@ class NRKTVIE(NRKBaseIE):
# single playlist video
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
'info_dict': {
'id': 'MSPO40010515-part2',
'ext': 'flv',
'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
'id': 'MSPO40010515AH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
'description': 'md5:c03aba1e917561eface5214020551b7a',
},
'params': {
'skip_download': True,
},
'expected_warnings': ['Video is geo restricted'],
'expected_warnings': ['Failed to download m3u8 information'],
'skip': 'particular part is not supported currently',
}, {
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
'playlist': [{
'info_dict': {
'id': 'MSPO40010515AH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
'duration': 772,
'series': 'Tour de Ski',
'episode': '06.01.2015',
},
'params': {
'skip_download': True,
},
}, {
'info_dict': {
'id': 'MSPO40010515BH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
'duration': 6175,
'series': 'Tour de Ski',
'episode': '06.01.2015',
},
'params': {
'skip_download': True,
},
}],
'info_dict': {
'id': 'MSPO40010515',
'id': 'MSPO40010515AH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
'description': 'md5:c03aba1e917561eface5214020551b7a',
},
'expected_warnings': ['Video is geo restricted'],
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
'info_dict': {
@@ -286,6 +279,7 @@ class NRKTVIE(NRKBaseIE):
'params': {
'skip_download': True,
},
'skip': 'ProgramRightsHasExpired',
}, {
'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
'only_matching': True,
@@ -334,6 +328,7 @@ class NRKTVIE(NRKBaseIE):
asset_url = asset.get('url')
if not asset_url or asset_url in urls:
continue
urls.append(asset_url)
formats = self._extract_nrk_formats(asset_url, video_id)
if not formats:
continue
@@ -354,6 +349,7 @@ class NRKTVIE(NRKBaseIE):
'duration': duration,
'subtitles': subtitles,
'formats': formats,
'is_live': live,
})
if not entries:
@@ -368,6 +364,7 @@ class NRKTVIE(NRKBaseIE):
'title': make_title(title),
'duration': duration,
'formats': formats,
'is_live': live,
}]
if not entries:
@@ -513,49 +510,7 @@ class NRKTVEpisodeIE(InfoExtractor):
return info
class NRKTVSerieBaseIE(InfoExtractor):
def _extract_series(self, webpage, display_id, fatal=True):
config = self._parse_json(
self._search_regex(
(r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>',
r'PRELOADED_STATE_*\s*=\s*({.+?})\s*\n'),
webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
display_id, fatal=False, transform_source=js_to_json)
if not config:
return
return try_get(
config,
(lambda x: x['initialState']['series'], lambda x: x['series']),
dict)
def _extract_seasons(self, domain, series_id, seasons):
if isinstance(seasons, dict):
seasons = seasons.get('seasons')
if not isinstance(seasons, list):
return []
entries = []
for season in seasons:
if not isinstance(season, dict):
continue
episodes = self._extract_episodes(season)
if episodes:
entries.extend(episodes)
continue
season_name = season.get('name')
if season_name and isinstance(season_name, compat_str):
entries.append(self.url_result(
'https://%s.nrk.no/serie/%s/sesong/%s'
% (domain, series_id, season_name),
ie=NRKTVSeasonIE.ie_key(),
video_title=season.get('title')))
return entries
def _extract_episodes(self, season):
if not isinstance(season, dict):
return []
return self._extract_entries(season.get('episodes'))
class NRKTVSerieBaseIE(NRKBaseIE):
def _extract_entries(self, entry_list):
if not isinstance(entry_list, list):
return []
@@ -579,7 +534,7 @@ class NRKTVSerieBaseIE(InfoExtractor):
def _entries(self, data, display_id):
for page_num in itertools.count(1):
embedded = data.get('_embedded')
embedded = data.get('_embedded') or data
if not isinstance(embedded, dict):
break
assets_key = self._extract_assets_key(embedded)
@@ -594,18 +549,16 @@ class NRKTVSerieBaseIE(InfoExtractor):
for e in self._extract_entries(entries):
yield e
# Find next URL
next_url = urljoin(
'https://psapi.nrk.no/',
try_get(
data,
(lambda x: x['_links']['next']['href'],
lambda x: x['_embedded'][assets_key]['_links']['next']['href']),
compat_str))
if not next_url:
next_url_path = try_get(
data,
(lambda x: x['_links']['next']['href'],
lambda x: x['_embedded'][assets_key]['_links']['next']['href']),
compat_str)
if not next_url_path:
break
data = self._download_json(
next_url, display_id,
'Downloading %s JSON page %d' % (assets_key, page_num),
data = self._call_api(
next_url_path, display_id,
note='Downloading %s JSON page %d' % (assets_key, page_num),
fatal=False)
if not data:
break
@@ -656,15 +609,12 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
else super(NRKTVSeasonIE, cls).suitable(url))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
domain = mobj.group('domain')
serie = mobj.group('serie')
season_id = mobj.group('id')
domain, serie, season_id = re.match(self._VALID_URL, url).groups()
display_id = '%s/%s' % (serie, season_id)
data = self._download_json(
'https://psapi.nrk.no/%s/catalog/series/%s/seasons/%s'
% (domain, serie, season_id), display_id, query={'pageSize': 50})
data = self._call_api(
'%s/catalog/series/%s/seasons/%s' % (domain, serie, season_id),
display_id, 'season', query={'pageSize': 50})
title = try_get(data, lambda x: x['titles']['title'], compat_str) or display_id
return self.playlist_result(
@@ -673,8 +623,7 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
class NRKTVSeriesIE(NRKTVSerieBaseIE):
_VALID_URL = r'https?://(?P<domain>tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
_ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
_VALID_URL = r'https?://(?P<domain>(?:tv|radio)\.nrk|(?:tv\.)?nrksuper)\.no/serie/(?P<id>[^/]+)'
_TESTS = [{
# new layout, instalments
'url': 'https://tv.nrk.no/serie/groenn-glede',
@@ -696,7 +645,6 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
},
'playlist_mincount': 30,
'expected_warnings': ['HTTP Error 404: Not Found'],
}, {
# new layout, seasons
'url': 'https://tv.nrk.no/serie/backstage',
@@ -706,14 +654,13 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
'description': 'md5:63692ceb96813d9a207e9910483d948b',
},
'playlist_mincount': 60,
'expected_warnings': ['HTTP Error 404: Not Found'],
}, {
# old layout
'url': 'https://tv.nrksuper.no/serie/labyrint',
'info_dict': {
'id': 'labyrint',
'title': 'Labyrint',
'description': 'md5:318b597330fdac5959247c9b69fdb1ec',
'description': 'I Daidalos sin undersjøiske Labyrint venter spennende oppgaver, skumle robotskapninger og slim.',
},
'playlist_mincount': 3,
}, {
@@ -729,9 +676,13 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
'url': 'https://radio.nrk.no/serie/dickie-dick-dickens',
'info_dict': {
'id': 'dickie-dick-dickens',
'title': 'Dickie Dick Dickens',
'description': 'md5:19e67411ffe57f7dce08a943d7a0b91f',
},
'playlist_mincount': 8,
'expected_warnings': ['HTTP Error 404: Not Found'],
}, {
'url': 'https://nrksuper.no/serie/labyrint',
'only_matching': True,
}]
@classmethod
@@ -742,57 +693,42 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
else super(NRKTVSeriesIE, cls).suitable(url))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
domain = mobj.group('domain')
series_id = mobj.group('id')
site, series_id = re.match(self._VALID_URL, url).groups()
is_radio = site == 'radio.nrk'
domain = 'radio' if is_radio else 'tv'
title = description = None
size_prefix = 'p' if is_radio else 'embeddedInstalmentsP'
series = self._call_api(
'%s/catalog/series/%s' % (domain, series_id),
series_id, 'serie', query={size_prefix + 'ageSize': 50})
titles = try_get(series, [
lambda x: x['titles'],
lambda x: x[x['type']]['titles'],
lambda x: x[x['seriesType']]['titles'],
]) or {}
webpage = self._download_webpage(url, series_id)
entries = []
entries.extend(self._entries(series, series_id))
embedded = series.get('_embedded') or {}
linked_seasons = try_get(series, lambda x: x['_links']['seasons']) or []
embedded_seasons = embedded.get('seasons') or []
if len(linked_seasons) > len(embedded_seasons):
for season in linked_seasons:
season_name = season.get('name')
if season_name and isinstance(season_name, compat_str):
entries.append(self.url_result(
'https://%s.nrk.no/serie/%s/sesong/%s'
% (domain, series_id, season_name),
ie=NRKTVSeasonIE.ie_key(),
video_title=season.get('title')))
else:
for season in embedded_seasons:
entries.extend(self._entries(season, series_id))
entries.extend(self._entries(
embedded.get('extraMaterial') or {}, series_id))
series = self._extract_series(webpage, series_id, fatal=False)
if series:
title = try_get(series, lambda x: x['titles']['title'], compat_str)
description = try_get(
series, lambda x: x['titles']['subtitle'], compat_str)
data = self._download_json(
'https://psapi.nrk.no/%s/catalog/series/%s/instalments'
% (domain, series_id), series_id, query={'pageSize': 50},
fatal=False)
if data:
return self.playlist_result(
self._entries(data, series_id), series_id, title, description)
# New layout (e.g. https://tv.nrk.no/serie/backstage)
if series:
entries = []
entries.extend(self._extract_seasons(domain, series_id, series.get('seasons')))
entries.extend(self._extract_entries(series.get('instalments')))
entries.extend(self._extract_episodes(series.get('extraMaterial')))
return self.playlist_result(entries, series_id, title, description)
# Old layout (e.g. https://tv.nrksuper.no/serie/labyrint)
entries = [
self.url_result(
'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
series=series_id, season=season_id))
for season_id in re.findall(self._ITEM_RE, webpage)
]
title = self._html_search_meta(
'seriestitle', webpage,
'title', default=None) or self._og_search_title(
webpage, fatal=False)
if title:
title = self._search_regex(
r'NRK (?:Super )?TV\s*[-]\s*(.+)', title, 'title', default=title)
description = self._html_search_meta(
'series_description', webpage,
'description', default=None) or self._og_search_description(webpage)
return self.playlist_result(entries, series_id, title, description)
return self.playlist_result(
entries, series_id, titles.get('title'), titles.get('subtitle'))
class NRKTVDirekteIE(NRKTVIE):
@@ -896,14 +832,8 @@ class NRKSkoleIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
video_id)
nrk_id = self._parse_json(
self._search_regex(
r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
webpage, 'application json'),
video_id)['activeMedia']['psId']
nrk_id = self._download_json(
'https://nrkno-skole-prod.kube.nrk.no/skole/api/media/%s' % video_id,
video_id)['psId']
return self.url_result('nrk:%s' % nrk_id)
+4
View File
@@ -541,6 +541,10 @@ class PeerTubeIE(InfoExtractor):
'format_id': format_id,
'filesize': file_size,
})
if format_id == '0p':
f['vcodec'] = 'none'
else:
f['fps'] = int_or_none(file_.get('fps'))
formats.append(f)
self._sort_formats(formats)
+51 -4
View File
@@ -2,7 +2,12 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import smuggle_url
from ..utils import (
bool_or_none,
smuggle_url,
try_get,
url_or_none,
)
class SlidesLiveIE(InfoExtractor):
@@ -18,8 +23,21 @@ class SlidesLiveIE(InfoExtractor):
'description': 'Watch full version of this video at https://slideslive.com/38902413.',
'uploader': 'SlidesLive Videos - A',
'uploader_id': 'UC62SdArr41t_-_fX40QCLRw',
'timestamp': 1597615266,
'upload_date': '20170925',
}
}, {
# video_service_name = yoda
'url': 'https://slideslive.com/38935785',
'md5': '575cd7a6c0acc6e28422fe76dd4bcb1a',
'info_dict': {
'id': 'RMraDYN5ozA_',
'ext': 'mp4',
'title': 'Offline Reinforcement Learning: From Algorithms to Practical Challenges',
},
'params': {
'format': 'bestvideo',
},
}, {
# video_service_name = youtube
'url': 'https://slideslive.com/38903721/magic-a-scientific-resurrection-of-an-esoteric-legend',
@@ -39,18 +57,47 @@ class SlidesLiveIE(InfoExtractor):
video_data = self._download_json(
'https://ben.slideslive.com/player/' + video_id, video_id)
service_name = video_data['video_service_name'].lower()
assert service_name in ('url', 'vimeo', 'youtube')
assert service_name in ('url', 'yoda', 'vimeo', 'youtube')
service_id = video_data['video_service_id']
subtitles = {}
for sub in try_get(video_data, lambda x: x['subtitles'], list) or []:
if not isinstance(sub, dict):
continue
webvtt_url = url_or_none(sub.get('webvtt_url'))
if not webvtt_url:
continue
lang = sub.get('language') or 'en'
subtitles.setdefault(lang, []).append({
'url': webvtt_url,
})
info = {
'id': video_id,
'thumbnail': video_data.get('thumbnail'),
'url': service_id,
'is_live': bool_or_none(video_data.get('is_live')),
'subtitles': subtitles,
}
if service_name == 'url':
if service_name in ('url', 'yoda'):
info['title'] = video_data['title']
if service_name == 'url':
info['url'] = service_id
else:
formats = []
_MANIFEST_PATTERN = 'https://01.cdn.yoda.slideslive.com/%s/master.%s'
formats.extend(self._extract_m3u8_formats(
_MANIFEST_PATTERN % (service_id, 'm3u8'), service_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
formats.extend(self._extract_mpd_formats(
_MANIFEST_PATTERN % (service_id, 'mpd'), service_id,
mpd_id='dash', fatal=False))
self._sort_formats(formats)
info.update({
'id': service_id,
'formats': formats,
})
else:
info.update({
'_type': 'url_transparent',
'url': service_id,
'ie_key': service_name.capitalize(),
'title': video_data.get('title'),
})
+87 -73
View File
@@ -12,25 +12,16 @@ from ..utils import (
class TeleQuebecBaseIE(InfoExtractor):
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
@staticmethod
def _result(url, ie_key):
def _brightcove_result(brightcove_id, player_id, account_id='6150020952001'):
return {
'_type': 'url_transparent',
'url': smuggle_url(url, {'geo_countries': ['CA']}),
'ie_key': ie_key,
'url': smuggle_url(TeleQuebecBaseIE.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, brightcove_id), {'geo_countries': ['CA']}),
'ie_key': 'BrightcoveNew',
}
@staticmethod
def _limelight_result(media_id):
return TeleQuebecBaseIE._result(
'limelight:media:' + media_id, 'LimelightMedia')
@staticmethod
def _brightcove_result(brightcove_id):
return TeleQuebecBaseIE._result(
'http://players.brightcove.net/6150020952001/default_default/index.html?videoId=%s'
% brightcove_id, 'BrightcoveNew')
class TeleQuebecIE(TeleQuebecBaseIE):
_VALID_URL = r'''(?x)
@@ -44,14 +35,18 @@ class TeleQuebecIE(TeleQuebecBaseIE):
# available till 01.01.2023
'url': 'http://zonevideo.telequebec.tv/media/37578/un-petit-choc-et-puis-repart/un-chef-a-la-cabane',
'info_dict': {
'id': '577116881b4b439084e6b1cf4ef8b1b3',
'id': '6155972771001',
'ext': 'mp4',
'title': 'Un petit choc et puis repart!',
'description': 'md5:067bc84bd6afecad85e69d1000730907',
'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374',
'timestamp': 1589262469,
'uploader_id': '6150020952001',
'upload_date': '20200512',
},
'params': {
'skip_download': True,
'format': 'bestvideo',
},
'add_ie': ['BrightcoveNew'],
}, {
'url': 'https://zonevideo.telequebec.tv/media/55267/le-soleil/passe-partout',
'info_dict': {
@@ -65,7 +60,6 @@ class TeleQuebecIE(TeleQuebecBaseIE):
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
'add_ie': ['BrightcoveNew'],
}, {
@@ -79,25 +73,20 @@ class TeleQuebecIE(TeleQuebecBaseIE):
def _real_extract(self, url):
media_id = self._match_id(url)
media_data = self._download_json(
'https://mnmedias.api.telequebec.tv/api/v2/media/' + media_id,
media = self._download_json(
'https://mnmedias.api.telequebec.tv/api/v3/media/' + media_id,
media_id)['media']
source_id = media_data['streamInfo']['sourceId']
source = (try_get(
media_data, lambda x: x['streamInfo']['source'],
compat_str) or 'limelight').lower()
if source == 'brightcove':
info = self._brightcove_result(source_id)
else:
info = self._limelight_result(source_id)
source_id = next(source_info['sourceId'] for source_info in media['streamInfos'] if source_info.get('source') == 'Brightcove')
info = self._brightcove_result(source_id, '22gPKdt7f')
product = media.get('product') or {}
season = product.get('season') or {}
info.update({
'title': media_data.get('title'),
'description': try_get(
media_data, lambda x: x['descriptions'][0]['text'], compat_str),
'duration': int_or_none(
media_data.get('durationInMilliseconds'), 1000),
'description': try_get(media, lambda x: x['descriptions'][-1]['text'], compat_str),
'series': try_get(season, lambda x: x['serie']['titre']),
'season': season.get('name'),
'season_number': int_or_none(season.get('seasonNo')),
'episode': product.get('titre'),
'episode_number': int_or_none(product.get('episodeNo')),
})
return info
@@ -148,7 +137,7 @@ class TeleQuebecSquatIE(InfoExtractor):
}
class TeleQuebecEmissionIE(TeleQuebecBaseIE):
class TeleQuebecEmissionIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
@@ -160,15 +149,16 @@ class TeleQuebecEmissionIE(TeleQuebecBaseIE):
_TESTS = [{
'url': 'http://lindicemcsween.telequebec.tv/emissions/100430013/des-soins-esthetiques-a-377-d-interets-annuels-ca-vous-tente',
'info_dict': {
'id': '66648a6aef914fe3badda25e81a4d50a',
'id': '6154476028001',
'ext': 'mp4',
'title': "Des soins esthétiques à 377 % d'intérêts annuels, ça vous tente?",
'description': 'md5:369e0d55d0083f1fc9b71ffb640ea014',
'upload_date': '20171024',
'timestamp': 1508862118,
'title': 'Des soins esthétiques à 377 % dintérêts annuels, ça vous tente?',
'description': 'md5:cb4d378e073fae6cce1f87c00f84ae9f',
'upload_date': '20200505',
'timestamp': 1588713424,
'uploader_id': '6150020952001',
},
'params': {
'skip_download': True,
'format': 'bestvideo',
},
}, {
'url': 'http://bancpublic.telequebec.tv/emissions/emission-49/31986/jeunes-meres-sous-pression',
@@ -187,26 +177,26 @@ class TeleQuebecEmissionIE(TeleQuebecBaseIE):
webpage = self._download_webpage(url, display_id)
media_id = self._search_regex(
r'mediaUID\s*:\s*["\'][Ll]imelight_(?P<id>[a-z0-9]{32})', webpage,
'limelight id')
r'mediaId\s*:\s*(?P<id>\d+)', webpage, 'media id')
info = self._limelight_result(media_id)
info.update({
'title': self._og_search_title(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
})
return info
return self.url_result(
'http://zonevideo.telequebec.tv/media/' + media_id,
TeleQuebecIE.ie_key())
class TeleQuebecLiveIE(InfoExtractor):
class TeleQuebecLiveIE(TeleQuebecBaseIE):
_VALID_URL = r'https?://zonevideo\.telequebec\.tv/(?P<id>endirect)'
_TEST = {
'url': 'http://zonevideo.telequebec.tv/endirect/',
'info_dict': {
'id': 'endirect',
'id': '6159095684001',
'ext': 'mp4',
'title': 're:^Télé-Québec - En direct [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'title': 're:^Télé-Québec [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'is_live': True,
'description': 'Canal principal de Télé-Québec',
'uploader_id': '6150020952001',
'timestamp': 1590439901,
'upload_date': '20200525',
},
'params': {
'skip_download': True,
@@ -214,25 +204,49 @@ class TeleQuebecLiveIE(InfoExtractor):
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self._brightcove_result('6159095684001', 'skCsmi2Uw')
m3u8_url = None
webpage = self._download_webpage(
'https://player.telequebec.tv/Tq_VideoPlayer.js', video_id,
fatal=False)
if webpage:
m3u8_url = self._search_regex(
r'm3U8Url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'm3u8 url', default=None, group='url')
if not m3u8_url:
m3u8_url = 'https://teleqmmd.mmdlive.lldns.net/teleqmmd/f386e3b206814e1f8c8c1c71c0f8e748/manifest.m3u8'
formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', m3u8_id='hls')
self._sort_formats(formats)
return {
'id': video_id,
'title': self._live_title('Télé-Québec - En direct'),
'is_live': True,
'formats': formats,
}
class TeleQuebecVideoIE(TeleQuebecBaseIE):
_VALID_URL = r'https?://video\.telequebec\.tv/player(?:-live)?/(?P<id>\d+)'
_TESTS = [{
'url': 'https://video.telequebec.tv/player/31110/stream',
'info_dict': {
'id': '6202570652001',
'ext': 'mp4',
'title': 'Le coût du véhicule le plus vendu au Canada / Tous les frais liés à la procréation assistée',
'description': 'md5:685a7e4c450ba777c60adb6e71e41526',
'upload_date': '20201019',
'timestamp': 1603115930,
'uploader_id': '6101674910001',
},
'params': {
'format': 'bestvideo',
},
}, {
'url': 'https://video.telequebec.tv/player-live/28527',
'only_matching': True,
}]
def _call_api(self, path, video_id):
return self._download_json(
'http://beacon.playback.api.brightcove.com/telequebec/api/assets/' + path,
video_id, query={'device_layout': 'web', 'device_type': 'web'})['data']
def _real_extract(self, url):
asset_id = self._match_id(url)
asset = self._call_api(asset_id, asset_id)['asset']
stream = self._call_api(
asset_id + '/streams/' + asset['streams'][0]['id'], asset_id)['stream']
stream_url = stream['url']
account_id = try_get(
stream, lambda x: x['video_provider_details']['account_id']) or '6101674910001'
info = self._brightcove_result(stream_url, 'default', account_id)
info.update({
'description': asset.get('long_description') or asset.get('short_description'),
'series': asset.get('series_original_name'),
'season_number': int_or_none(asset.get('season_number')),
'episode': asset.get('original_name'),
'episode_number': int_or_none(asset.get('episode_number')),
})
return info
+14
View File
@@ -33,6 +33,19 @@ class TubiTvIE(InfoExtractor):
}, {
'url': 'http://tubitv.com/movies/383676/tracker',
'only_matching': True,
}, {
'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
'info_dict': {
'id': '560057',
'ext': 'mp4',
'title': 'Penitentiary',
'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
'release_year': 1979,
},
'params': {
'skip_download': True,
},
}]
def _login(self):
@@ -93,4 +106,5 @@ class TubiTvIE(InfoExtractor):
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'uploader_id': video_data.get('publisher_id'),
'release_year': int_or_none(video_data.get('year')),
}
+35 -55
View File
@@ -12,11 +12,13 @@ from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
parse_iso8601,
qualities,
try_get,
update_url_query,
url_or_none,
urljoin,
)
@@ -414,7 +416,7 @@ class ViafreeIE(InfoExtractor):
class TVPlayHomeIE(InfoExtractor):
_VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)'
_VALID_URL = r'https?://(?:tv3?)?play\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/(?:[^/]+/)*[^/?#&]+-(?P<id>\d+)'
_TESTS = [{
'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
'info_dict': {
@@ -433,80 +435,58 @@ class TVPlayHomeIE(InfoExtractor):
'params': {
'skip_download': True,
},
'add_ie': [TVPlayIE.ie_key()],
}, {
'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
'only_matching': True,
}, {
'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
'only_matching': True,
}, {
'url': 'https://play.tv3.lt/aferistai-10047125',
'only_matching': True,
}, {
'url': 'https://tv3play.skaties.lv/vinas-melo-labak-10280317',
'only_matching': True,
}, {
'url': 'https://play.tv3.ee/cool-d-ga-mehhikosse-10044354',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
asset = self._download_json(
urljoin(url, '/sb/public/asset/' + video_id), video_id)
video_id = self._search_regex(
r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id')
if len(video_id) < 8:
return self.url_result(
'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
m3u8_url = self._search_regex(
r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'm3u8 url', group='url')
m3u8_url = asset['movie']['contentUrl']
video_id = asset['assetId']
asset_title = asset['title']
title = asset_title['title']
formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
self._sort_formats(formats)
title = self._search_regex(
r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
'title', default=None, group='value') or self._html_search_meta(
'title', webpage, default=None) or self._og_search_title(
webpage)
thumbnails = None
image_url = asset.get('imageUrl')
if image_url:
thumbnails = [{
'url': urljoin(url, image_url),
'ext': 'jpg',
}]
description = self._html_search_meta(
'description', webpage,
default=None) or self._og_search_description(webpage)
thumbnail = self._search_regex(
r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'thumbnail', default=None, group='url') or self._html_search_meta(
'thumbnail', webpage, default=None) or self._og_search_thumbnail(
webpage)
duration = int_or_none(self._search_regex(
r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
fatal=False))
season = self._search_regex(
(r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
'season', default=None, group='value')
season_number = int_or_none(self._search_regex(
r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
default=None))
episode = self._search_regex(
(r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
'episode', default=None, group='value')
episode_number = int_or_none(self._search_regex(
r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
default=None))
metadata = asset.get('metadata') or {}
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'season': season,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'description': asset_title.get('summaryLong') or asset_title.get('summaryShort'),
'thumbnails': thumbnails,
'duration': parse_duration(asset_title.get('runTime')),
'series': asset.get('tvSeriesTitle'),
'season': asset.get('tvSeasonTitle'),
'season_number': int_or_none(metadata.get('seasonNumber')),
'episode': asset_title.get('titleBrief'),
'episode_number': int_or_none(metadata.get('episodeNumber')),
'formats': formats,
}
+99 -42
View File
@@ -67,11 +67,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
_PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM)'
_YOUTUBE_CLIENT_HEADERS = {
'x-youtube-client-name': '1',
'x-youtube-client-version': '1.20200609.04.02',
}
def _set_language(self):
self._set_cookie(
'.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en',
@@ -2693,6 +2688,10 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
# no longer available?
'url': 'https://www.youtube.com/feed/recommended',
'only_matching': True,
}, {
# inline playlist with not always working continuations
'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
'only_matching': True,
}
# TODO
# {
@@ -2871,6 +2870,16 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
for entry in self._post_thread_entries(renderer):
yield entry
@staticmethod
def _build_continuation_query(continuation, ctp=None):
query = {
'ctoken': continuation,
'continuation': continuation,
}
if ctp:
query['itct'] = ctp
return query
@staticmethod
def _extract_next_continuation_data(renderer):
next_continuation = try_get(
@@ -2881,11 +2890,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
if not continuation:
return
ctp = next_continuation.get('clickTrackingParams')
return {
'ctoken': continuation,
'continuation': continuation,
'itct': ctp,
}
return YoutubeTabIE._build_continuation_query(continuation, ctp)
@classmethod
def _extract_continuation(cls, renderer):
@@ -2908,13 +2913,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
if not continuation:
continue
ctp = continuation_ep.get('clickTrackingParams')
if not ctp:
continue
return {
'ctoken': continuation,
'continuation': continuation,
'itct': ctp,
}
return YoutubeTabIE._build_continuation_query(continuation, ctp)
def _entries(self, tab, identity_token):
tab_content = try_get(tab, lambda x: x['content'], dict)
@@ -3060,6 +3059,24 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
return uploader
@staticmethod
def _extract_alert(data):
alerts = []
for alert in try_get(data, lambda x: x['alerts'], list) or []:
if not isinstance(alert, dict):
continue
alert_text = try_get(
alert, lambda x: x['alertRenderer']['text'], dict)
if not alert_text:
continue
text = try_get(
alert_text,
(lambda x: x['simpleText'], lambda x: x['runs'][0]['text']),
compat_str)
if text:
alerts.append(text)
return '\n'.join(alerts)
def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token):
selected_tab = self._extract_selected_tab(tabs)
renderer = try_get(
@@ -3086,14 +3103,37 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
playlist.update(self._extract_uploader(data))
return playlist
def _extract_from_playlist(self, item_id, data, playlist):
def _extract_from_playlist(self, item_id, url, data, playlist):
title = playlist.get('title') or try_get(
data, lambda x: x['titleText']['simpleText'], compat_str)
playlist_id = playlist.get('playlistId') or item_id
# Inline playlist rendition continuation does not always work
# at Youtube side, so delegating regular tab-based playlist URL
# processing whenever possible.
playlist_url = urljoin(url, try_get(
playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
compat_str))
if playlist_url and playlist_url != url:
return self.url_result(
playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
video_title=title)
return self.playlist_result(
self._playlist_entries(playlist), playlist_id=playlist_id,
playlist_title=title)
def _extract_identity_token(self, webpage, item_id):
ytcfg = self._parse_json(
self._search_regex(
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
default='{}'), item_id, fatal=False)
if ytcfg:
token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
if token:
return token
return self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
def _real_extract(self, url):
item_id = self._match_id(url)
url = compat_urlparse.urlunparse(
@@ -3108,9 +3148,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
webpage = self._download_webpage(url, item_id)
identity_token = self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
identity_token = self._extract_identity_token(webpage, item_id)
data = self._extract_yt_initial_data(item_id, webpage)
tabs = try_get(
data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
@@ -3119,7 +3157,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
playlist = try_get(
data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
if playlist:
return self._extract_from_playlist(item_id, data, playlist)
return self._extract_from_playlist(item_id, url, data, playlist)
# Fallback to video extraction if no playlist alike page is recognized.
# First check for the current video then try the v attribute of URL query.
video_id = try_get(
@@ -3127,6 +3165,10 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
compat_str) or video_id
if video_id:
return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
# Capture and output alerts
alert = self._extract_alert(data)
if alert:
raise ExtractorError(alert, expected=True)
# Failed to recognize
raise ExtractorError('Unable to recognize tab page')
@@ -3139,8 +3181,7 @@ class YoutubePlaylistIE(InfoExtractor):
(?:
(?:
youtube(?:kids)?\.com|
invidio\.us|
youtu\.be
invidio\.us
)
/.*?\?.*?\blist=
)?
@@ -3185,6 +3226,32 @@ class YoutubePlaylistIE(InfoExtractor):
'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
}
}, {
'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
'only_matching': True,
}, {
# music album playlist
'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if YoutubeTabIE.suitable(url) else super(
YoutubePlaylistIE, cls).suitable(url)
def _real_extract(self, url):
playlist_id = self._match_id(url)
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
if not qs:
qs = {'list': playlist_id}
return self.url_result(
update_url_query('https://www.youtube.com/playlist', qs),
ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
class YoutubeYtBeIE(InfoExtractor):
_VALID_URL = r'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{11})/*?.*?\blist=(?P<playlist_id>%(playlist_id)s)' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_TESTS = [{
'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
'info_dict': {
'id': 'yeWKywCrFtk',
@@ -3207,28 +3274,18 @@ class YoutubePlaylistIE(InfoExtractor):
}, {
'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
'only_matching': True,
}, {
'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
'only_matching': True,
}, {
# music album playlist
'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if YoutubeTabIE.suitable(url) else super(
YoutubePlaylistIE, cls).suitable(url)
def _real_extract(self, url):
playlist_id = self._match_id(url)
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
if not qs:
qs = {'list': playlist_id}
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
playlist_id = mobj.group('playlist_id')
return self.url_result(
update_url_query('https://www.youtube.com/playlist', qs),
ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
update_url_query('https://www.youtube.com/watch', {
'v': video_id,
'list': playlist_id,
'feature': 'youtu.be',
}), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
class YoutubeYtUserIE(InfoExtractor):
+1 -1
View File
@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2020.12.05'
__version__ = '2020.12.09'