Compare commits

...

36 Commits

Author SHA1 Message Date
Sergey M․
d51e23d9fc release 2020.09.06 2020-09-06 13:00:41 +07:00
Sergey M․
6cd452acff [ChangeLog] Actualize
[ci skip]
2020-09-06 12:57:56 +07:00
Sergey M․
50e9fcc1fd [nrktv:episode] Improve video id extraction (closes #25594, closes #26369, closes #26409) 2020-09-06 12:43:50 +07:00
random-nick
16ee69c1b7 [youtube] Fix age gate content detection (#26100) (closes #26152, closes #26311, closes #26384) 2020-09-06 11:44:53 +07:00
Sergey M․
67171ed7e9 [youtube:user] Extend _VALID_URL (closes #26443) 2020-09-06 11:31:28 +07:00
Sergey M․
1d9bf655e6 [utils] Recognize wav mimetype (closes #26463) 2020-09-06 11:19:53 +07:00
TheRealDude2
62ae19ff76 [xhamster] Improve initials regex (#26526) (closes #26353) 2020-09-06 11:10:27 +07:00
Sergey M․
5ed05f26ad [svtplay] Fix svt id extraction (closes #26425, closes #26428, closes #26438) 2020-09-06 10:45:57 +07:00
Sergey M․
841b683804 [twitch] Rework extractors (closes #12297, closes #20414, closes #20604, closes #21811, closes #21812, closes #22979, closes #24263, closes #25010, closes #25553, closes #25606)
* Switch to GraphQL.
+ Add support for collections.
+ Add support for clips and collections playlists.
2020-09-06 10:45:34 +07:00
Remita Amine
f5863a3ea0 [biqle] improve video_ext extraction 2020-08-27 19:20:41 +01:00
Sergey M․
10709fc7c6 [xhamster] Extend _VALID_URL (closes #25927) 2020-08-12 21:51:50 +07:00
TheRealDude2
a7e348556a [xhamster] Fix extraction (closes #26157) (#26254) 2020-08-12 21:42:17 +07:00
JChris246
6cb30ea5ed [xhamster] Extend _VALID_URL (closes #25789) (#25804) 2020-08-12 21:37:22 +07:00
Sergey M․
a4ed50bb84 release 2020.07.28 2020-07-28 05:13:03 +07:00
Sergey M․
570611955f [ChangeLog] Actualize
[ci skip]
2020-07-28 05:07:54 +07:00
Sergey M․
e450f6cb63 [youtube] Fix sigfunc name extraction (closes #26134, closes #26135, closes #26136, closes #26137) 2020-07-28 05:05:38 +07:00
MRWITEK
a115e07594 [youtube] Improve description extraction (closes #25937) (#25980) 2020-07-14 12:01:15 +01:00
Sergey M․
718393c632 [wistia] Restrict embed regex (closes #25969) 2020-07-11 18:27:19 +07:00
Glenn Slayden
07af16b92e [youtube] Prevent excess HTTP 301 (#25786) 2020-07-01 02:56:16 +07:00
Sergey M․
e942cfd1a7 [youtube:playlists] Extend _VALID_URL (closes #25810) 2020-06-28 10:30:03 +07:00
Remita Amine
9a7e5cb88a [bellmedia] add support for cp24.com clip URLs(closes #25764) 2020-06-23 15:09:13 +01:00
Sergey M․
2391941f28 [brightcove] Improve embed detection (closes #25674) 2020-06-16 17:38:25 +07:00
Sergey M․
9ff6165a81 release 2020.06.16.1 2020-06-16 06:22:01 +07:00
Sergey M․
1c748722f9 [ChangeLog] Actualize
[ci skip]
2020-06-16 06:19:23 +07:00
Sergey M․
ee0b726cd7 [youtube] Force old layout (closes #25682, closes #25683, closes #25680, closes #25686) 2020-06-16 06:17:53 +07:00
Sergey M․
dbeafce5d5 [youtube] Fix categories and improve tags extraction 2020-06-16 03:13:39 +07:00
Sergey M․
ed604ce7bc release 2020.06.16 2020-06-16 02:53:33 +07:00
Sergey M․
7adc7ca547 [ChangeLog] Actualize
[ci skip]
2020-06-16 02:52:09 +07:00
Sergey M․
a6211d237b [youtube] Fix uploader id and uploader URL extraction 2020-06-16 02:43:09 +07:00
Sergey M․
7b16239a49 [youtube] Improve view count extraction 2020-06-16 02:38:45 +07:00
Sergey M․
37357d21a9 [youtube] Fix upload date extraction 2020-06-16 02:37:19 +07:00
Sergey M․
b477fc1314 [youtube] Fix thumbnails extraction and remove uploader id extraction warning (closes #25676) 2020-06-16 02:29:04 +07:00
Sergey M․
d84b21b427 [youtube] Fix playlist and feed extraction (closes #25675) 2020-06-16 02:01:12 +07:00
Philipp Hagemeister
48bd042ce7 [facebook] Support single-video ID links
I stumbled upon this at https://www.facebook.com/bwfbadminton/posts/10157127020046316 . No idea how prevalent it is yet.
2020-06-14 13:17:51 +02:00
Sergey M․
84213ea8d4 [youtube] Extract chapters from JSON (closes #24819) 2020-06-06 04:22:10 +07:00
Sergey M․
562de77f41 [kaltura] Add support for multiple embeds on a webpage (closes #25523) 2020-06-06 02:14:35 +07:00
24 changed files with 732 additions and 346 deletions

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 2020.06.06. 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 2020.09.06. 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 **2020.06.06**
- [ ] I've verified that I'm running youtube-dl version **2020.09.06**
- [ ] 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 2020.06.06
[debug] youtube-dl version 2020.09.06
[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: {}

View File

@@ -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 2020.06.06. 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 2020.09.06. 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 **2020.06.06**
- [ ] I've verified that I'm running youtube-dl version **2020.09.06**
- [ ] 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

View File

@@ -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 2020.06.06. 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 2020.09.06. 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 **2020.06.06**
- [ ] I've verified that I'm running youtube-dl version **2020.09.06**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones

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 2020.06.06. 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 2020.09.06. 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 **2020.06.06**
- [ ] I've verified that I'm running youtube-dl version **2020.09.06**
- [ ] 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 2020.06.06
[debug] youtube-dl version 2020.09.06
[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: {}

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 2020.06.06. 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 2020.09.06. 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 **2020.06.06**
- [ ] I've verified that I'm running youtube-dl version **2020.09.06**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

View File

@@ -1,3 +1,56 @@
version 2020.09.06
Core
+ [utils] Recognize wav mimetype (#26463)
Extractors
* [nrktv:episode] Improve video id extraction (#25594, #26369, #26409)
* [youtube] Fix age gate content detection (#26100, #26152, #26311, #26384)
* [youtube:user] Extend URL regular expression (#26443)
* [xhamster] Improve initials regular expression (#26526, #26353)
* [svtplay] Fix video id extraction (#26425, #26428, #26438)
* [twitch] Rework extractors (#12297, #20414, #20604, #21811, #21812, #22979,
#24263, #25010, #25553, #25606)
* Switch to GraphQL
+ Add support for collections
+ Add support for clips and collections playlists
* [biqle] Improve video ext extraction
* [xhamster] Fix extraction (#26157, #26254)
* [xhamster] Extend URL regular expression (#25789, #25804, #25927))
version 2020.07.28
Extractors
* [youtube] Fix sigfunc name extraction (#26134, #26135, #26136, #26137)
* [youtube] Improve description extraction (#25937, #25980)
* [wistia] Restrict embed regular expression (#25969)
* [youtube] Prevent excess HTTP 301 (#25786)
+ [youtube:playlists] Extend URL regular expression (#25810)
+ [bellmedia] Add support for cp24.com clip URLs (#25764)
* [brightcove] Improve embed detection (#25674)
version 2020.06.16.1
Extractors
* [youtube] Force old layout (#25682, #25683, #25680, #25686)
* [youtube] Fix categories and improve tags extraction
version 2020.06.16
Extractors
* [youtube] Fix uploader id and uploader URL extraction
* [youtube] Improve view count extraction
* [youtube] Fix upload date extraction (#25677)
* [youtube] Fix thumbnails extraction (#25676)
* [youtube] Fix playlist and feed extraction (#25675)
+ [facebook] Add support for single-video ID links
+ [youtube] Extract chapters from JSON (#24819)
+ [kaltura] Add support for multiple embeds on a webpage (#25523)
version 2020.06.06
Extractors

View File

@@ -950,16 +950,13 @@
- **TVPlayHome**
- **Tweakers**
- **TwitCasting**
- **twitch:chapter**
- **twitch:clips**
- **twitch:profile**
- **twitch:stream**
- **twitch:video**
- **twitch:videos:all**
- **twitch:videos:highlights**
- **twitch:videos:past-broadcasts**
- **twitch:videos:uploads**
- **twitch:vod**
- **TwitchCollection**
- **TwitchVideos**
- **TwitchVideosClips**
- **TwitchVideosCollections**
- **twitter**
- **twitter:amplify**
- **twitter:broadcast**

View File

@@ -803,6 +803,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
self.assertEqual(mimetype2ext('audio/x-wav'), 'wav')
self.assertEqual(mimetype2ext('audio/x-wav;codec=pcm'), 'wav')
def test_month_by_name(self):
self.assertEqual(month_by_name(None), None)

View File

@@ -267,7 +267,7 @@ class TestYoutubeChapters(unittest.TestCase):
for description, duration, expected_chapters in self._TEST_CASES:
ie = YoutubeIE()
expect_value(
self, ie._extract_chapters(description, duration),
self, ie._extract_chapters_from_description(description, duration),
expected_chapters, None)

View File

@@ -25,8 +25,8 @@ class BellMediaIE(InfoExtractor):
etalk|
marilyn
)\.ca|
much\.com
)/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
(?:much|cp24)\.com
)/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
_TESTS = [{
'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
'md5': '36d3ef559cfe8af8efe15922cd3ce950',
@@ -62,6 +62,9 @@ class BellMediaIE(InfoExtractor):
}, {
'url': 'http://www.etalk.ca/video?videoid=663455',
'only_matching': True,
}, {
'url': 'https://www.cp24.com/video?clipId=1982548',
'only_matching': True,
}]
_DOMAINS = {
'thecomedynetwork': 'comedy',

View File

@@ -3,10 +3,11 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from .vk import VKIE
from ..utils import (
HEADRequest,
int_or_none,
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote,
)
from ..utils import int_or_none
class BIQLEIE(InfoExtractor):
@@ -47,9 +48,16 @@ class BIQLEIE(InfoExtractor):
if VKIE.suitable(embed_url):
return self.url_result(embed_url, VKIE.ie_key(), video_id)
self._request_webpage(
HEADRequest(embed_url), video_id, headers={'Referer': url})
video_id, sig, _, access_token = self._get_cookies(embed_url)['video_ext'].value.split('%3A')
embed_page = self._download_webpage(
embed_url, video_id, headers={'Referer': url})
video_ext = self._get_cookies(embed_url).get('video_ext')
if video_ext:
video_ext = compat_urllib_parse_unquote(video_ext.value)
if not video_ext:
video_ext = compat_b64decode(self._search_regex(
r'video_ext\s*:\s*[\'"]([A-Za-z0-9+/=]+)',
embed_page, 'video_ext')).decode()
video_id, sig, _, access_token = video_ext.split(':')
item = self._download_json(
'https://api.vk.com/method/video.get', video_id,
headers={'User-Agent': 'okhttp/3.4.1'}, query={

View File

@@ -426,7 +426,7 @@ class BrightcoveNewIE(AdobePassIE):
# [2] looks like:
for video, script_tag, account_id, player_id, embed in re.findall(
r'''(?isx)
(<video\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
(<video(?:-js)?\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
(?:.*?
(<script[^>]+
src=["\'](?:https?:)?//players\.brightcove\.net/

View File

@@ -1229,14 +1229,11 @@ from .twentymin import TwentyMinutenIE
from .twentythreevideo import TwentyThreeVideoIE
from .twitcasting import TwitCastingIE
from .twitch import (
TwitchVideoIE,
TwitchChapterIE,
TwitchVodIE,
TwitchProfileIE,
TwitchAllVideosIE,
TwitchUploadsIE,
TwitchPastBroadcastsIE,
TwitchHighlightsIE,
TwitchCollectionIE,
TwitchVideosIE,
TwitchVideosClipsIE,
TwitchVideosCollectionsIE,
TwitchStreamIE,
TwitchClipsIE,
)

View File

@@ -466,15 +466,18 @@ class FacebookIE(InfoExtractor):
return info_dict
if '/posts/' in url:
entries = [
self.url_result('facebook:%s' % vid, FacebookIE.ie_key())
for vid in self._parse_json(
self._search_regex(
r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])',
webpage, 'video ids', group='ids'),
video_id)]
video_id_json = self._search_regex(
r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', webpage, 'video ids', group='ids',
default='')
if video_id_json:
entries = [
self.url_result('facebook:%s' % vid, FacebookIE.ie_key())
for vid in self._parse_json(video_id_json, video_id)]
return self.playlist_result(entries, video_id)
return self.playlist_result(entries, video_id)
# Single Video?
video_id = self._search_regex(r'video_id:\s*"([0-9]+)"', webpage, 'single video id')
return self.url_result('facebook:%s' % video_id, FacebookIE.ie_key())
else:
_, info_dict = self._extract_from_url(
self._VIDEO_PAGE_TEMPLATE % video_id,

View File

@@ -1708,6 +1708,15 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['Kaltura'],
},
{
# multiple kaltura embeds, nsfw
'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
'info_dict': {
'id': 'kamila-avec-video-jaime-sadomie',
'title': "Kamila avec vídeo “J'aime sadomie”",
},
'playlist_count': 8,
},
{
# Non-standard Vimeo embed
'url': 'https://openclassrooms.com/courses/understanding-the-web',
@@ -2844,9 +2853,12 @@ class GenericIE(InfoExtractor):
return self.url_result(mobj.group('url'), 'Zapiks')
# Look for Kaltura embeds
kaltura_url = KalturaIE._extract_url(webpage)
if kaltura_url:
return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
kaltura_urls = KalturaIE._extract_urls(webpage)
if kaltura_urls:
return self.playlist_from_matches(
kaltura_urls, video_id, video_title,
getter=lambda x: smuggle_url(x, {'source_url': url}),
ie=KalturaIE.ie_key())
# Look for EaglePlatform embeds
eagleplatform_url = EaglePlatformIE._extract_url(webpage)

View File

@@ -113,9 +113,14 @@ class KalturaIE(InfoExtractor):
@staticmethod
def _extract_url(webpage):
urls = KalturaIE._extract_urls(webpage)
return urls[0] if urls else None
@staticmethod
def _extract_urls(webpage):
# Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
mobj = (
re.search(
finditer = (
re.finditer(
r"""(?xs)
kWidget\.(?:thumb)?[Ee]mbed\(
\{.*?
@@ -124,7 +129,7 @@ class KalturaIE(InfoExtractor):
(?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
(?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
""", webpage)
or re.search(
or re.finditer(
r'''(?xs)
(?P<q1>["'])
(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
@@ -138,7 +143,7 @@ class KalturaIE(InfoExtractor):
)
(?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
''', webpage)
or re.search(
or re.finditer(
r'''(?xs)
<(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
(?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
@@ -148,7 +153,8 @@ class KalturaIE(InfoExtractor):
(?P=q1)
''', webpage)
)
if mobj:
urls = []
for mobj in finditer:
embed_info = mobj.groupdict()
for k, v in embed_info.items():
if v:
@@ -160,7 +166,8 @@ class KalturaIE(InfoExtractor):
webpage)
if service_mobj:
url = smuggle_url(url, {'service_url': service_mobj.group('id')})
return url
urls.append(url)
return urls
def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs):
params = actions[0]

View File

@@ -11,7 +11,6 @@ from ..compat import (
from ..utils import (
ExtractorError,
int_or_none,
JSON_LD_RE,
js_to_json,
NO_DEFAULT,
parse_age_limit,
@@ -425,13 +424,20 @@ class NRKTVEpisodeIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
nrk_id = self._parse_json(
self._search_regex(JSON_LD_RE, webpage, 'JSON-LD', group='json_ld'),
display_id)['@id']
info = self._search_json_ld(webpage, display_id, default={})
nrk_id = info.get('@id') or self._html_search_meta(
'nrk:program-id', webpage, default=None) or self._search_regex(
r'data-program-id=["\'](%s)' % NRKTVIE._EPISODE_RE, webpage,
'nrk id')
assert re.match(NRKTVIE._EPISODE_RE, nrk_id)
return self.url_result(
'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id)
info.update({
'_type': 'url_transparent',
'id': nrk_id,
'url': 'nrk:%s' % nrk_id,
'ie_key': NRKIE.ie_key(),
})
return info
class NRKTVSerieBaseIE(InfoExtractor):

View File

@@ -224,9 +224,15 @@ class SVTPlayIE(SVTPlayBaseIE):
self._adjust_title(info_dict)
return info_dict
svt_id = self._search_regex(
r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
webpage, 'video id')
svt_id = try_get(
data, lambda x: x['statistics']['dataLake']['content']['id'],
compat_str)
if not svt_id:
svt_id = self._search_regex(
(r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"'),
webpage, 'video id')
return self._extract_by_video_id(svt_id, webpage)

View File

@@ -1,24 +1,26 @@
# coding: utf-8
from __future__ import unicode_literals
import collections
import itertools
import re
import random
import json
import random
import re
from .common import InfoExtractor
from ..compat import (
compat_kwargs,
compat_parse_qs,
compat_str,
compat_urlparse,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
)
from ..utils import (
clean_html,
ExtractorError,
float_or_none,
int_or_none,
orderedSet,
parse_duration,
parse_iso8601,
qualities,
@@ -150,120 +152,16 @@ class TwitchBaseIE(InfoExtractor):
})
self._sort_formats(formats)
def _download_access_token(self, channel_name):
return self._call_api(
'api/channels/%s/access_token' % channel_name, channel_name,
'Downloading access token JSON')
class TwitchItemBaseIE(TwitchBaseIE):
def _download_info(self, item, item_id):
return self._extract_info(self._call_api(
'kraken/videos/%s%s' % (item, item_id), item_id,
'Downloading %s info JSON' % self._ITEM_TYPE))
def _extract_media(self, item_id):
info = self._download_info(self._ITEM_SHORTCUT, item_id)
response = self._call_api(
'api/videos/%s%s' % (self._ITEM_SHORTCUT, item_id), item_id,
'Downloading %s playlist JSON' % self._ITEM_TYPE)
entries = []
chunks = response['chunks']
qualities = list(chunks.keys())
for num, fragment in enumerate(zip(*chunks.values()), start=1):
formats = []
for fmt_num, fragment_fmt in enumerate(fragment):
format_id = qualities[fmt_num]
fmt = {
'url': fragment_fmt['url'],
'format_id': format_id,
'quality': 1 if format_id == 'live' else 0,
}
m = re.search(r'^(?P<height>\d+)[Pp]', format_id)
if m:
fmt['height'] = int(m.group('height'))
formats.append(fmt)
self._sort_formats(formats)
entry = dict(info)
entry['id'] = '%s_%d' % (entry['id'], num)
entry['title'] = '%s part %d' % (entry['title'], num)
entry['formats'] = formats
entries.append(entry)
return self.playlist_result(entries, info['id'], info['title'])
def _extract_info(self, info):
status = info.get('status')
if status == 'recording':
is_live = True
elif status == 'recorded':
is_live = False
else:
is_live = None
_QUALITIES = ('small', 'medium', 'large')
quality_key = qualities(_QUALITIES)
thumbnails = []
preview = info.get('preview')
if isinstance(preview, dict):
for thumbnail_id, thumbnail_url in preview.items():
thumbnail_url = url_or_none(thumbnail_url)
if not thumbnail_url:
continue
if thumbnail_id not in _QUALITIES:
continue
thumbnails.append({
'url': thumbnail_url,
'preference': quality_key(thumbnail_id),
})
return {
'id': info['_id'],
'title': info.get('title') or 'Untitled Broadcast',
'description': info.get('description'),
'duration': int_or_none(info.get('length')),
'thumbnails': thumbnails,
'uploader': info.get('channel', {}).get('display_name'),
'uploader_id': info.get('channel', {}).get('name'),
'timestamp': parse_iso8601(info.get('recorded_at')),
'view_count': int_or_none(info.get('views')),
'is_live': is_live,
}
def _real_extract(self, url):
return self._extract_media(self._match_id(url))
def _extract_channel_id(self, token, channel_name):
return compat_str(self._parse_json(token, channel_name)['channel_id'])
class TwitchVideoIE(TwitchItemBaseIE):
IE_NAME = 'twitch:video'
_VALID_URL = r'%s/[^/]+/b/(?P<id>\d+)' % TwitchBaseIE._VALID_URL_BASE
_ITEM_TYPE = 'video'
_ITEM_SHORTCUT = 'a'
_TEST = {
'url': 'http://www.twitch.tv/riotgames/b/577357806',
'info_dict': {
'id': 'a577357806',
'title': 'Worlds Semifinals - Star Horn Royal Club vs. OMG',
},
'playlist_mincount': 12,
'skip': 'HTTP Error 404: Not Found',
}
class TwitchChapterIE(TwitchItemBaseIE):
IE_NAME = 'twitch:chapter'
_VALID_URL = r'%s/[^/]+/c/(?P<id>\d+)' % TwitchBaseIE._VALID_URL_BASE
_ITEM_TYPE = 'chapter'
_ITEM_SHORTCUT = 'c'
_TESTS = [{
'url': 'http://www.twitch.tv/acracingleague/c/5285812',
'info_dict': {
'id': 'c5285812',
'title': 'ACRL Off Season - Sports Cars @ Nordschleife',
},
'playlist_mincount': 3,
'skip': 'HTTP Error 404: Not Found',
}, {
'url': 'http://www.twitch.tv/tsm_theoddone/c/2349361',
'only_matching': True,
}]
class TwitchVodIE(TwitchItemBaseIE):
class TwitchVodIE(TwitchBaseIE):
IE_NAME = 'twitch:vod'
_VALID_URL = r'''(?x)
https?://
@@ -332,17 +230,60 @@ class TwitchVodIE(TwitchItemBaseIE):
'only_matching': True,
}]
def _real_extract(self, url):
item_id = self._match_id(url)
def _download_info(self, item_id):
return self._extract_info(
self._call_api(
'kraken/videos/%s' % item_id, item_id,
'Downloading video info JSON'))
info = self._download_info(self._ITEM_SHORTCUT, item_id)
@staticmethod
def _extract_info(info):
status = info.get('status')
if status == 'recording':
is_live = True
elif status == 'recorded':
is_live = False
else:
is_live = None
_QUALITIES = ('small', 'medium', 'large')
quality_key = qualities(_QUALITIES)
thumbnails = []
preview = info.get('preview')
if isinstance(preview, dict):
for thumbnail_id, thumbnail_url in preview.items():
thumbnail_url = url_or_none(thumbnail_url)
if not thumbnail_url:
continue
if thumbnail_id not in _QUALITIES:
continue
thumbnails.append({
'url': thumbnail_url,
'preference': quality_key(thumbnail_id),
})
return {
'id': info['_id'],
'title': info.get('title') or 'Untitled Broadcast',
'description': info.get('description'),
'duration': int_or_none(info.get('length')),
'thumbnails': thumbnails,
'uploader': info.get('channel', {}).get('display_name'),
'uploader_id': info.get('channel', {}).get('name'),
'timestamp': parse_iso8601(info.get('recorded_at')),
'view_count': int_or_none(info.get('views')),
'is_live': is_live,
}
def _real_extract(self, url):
vod_id = self._match_id(url)
info = self._download_info(vod_id)
access_token = self._call_api(
'api/vods/%s/access_token' % item_id, item_id,
'api/vods/%s/access_token' % vod_id, vod_id,
'Downloading %s access token' % self._ITEM_TYPE)
formats = self._extract_m3u8_formats(
'%s/vod/%s.m3u8?%s' % (
self._USHER_BASE, item_id,
self._USHER_BASE, vod_id,
compat_urllib_parse_urlencode({
'allow_source': 'true',
'allow_audio_only': 'true',
@@ -352,7 +293,7 @@ class TwitchVodIE(TwitchItemBaseIE):
'nauth': access_token['token'],
'nauthsig': access_token['sig'],
})),
item_id, 'mp4', entry_protocol='m3u8_native')
vod_id, 'mp4', entry_protocol='m3u8_native')
self._prefer_source(formats)
info['formats'] = formats
@@ -366,7 +307,7 @@ class TwitchVodIE(TwitchItemBaseIE):
info['subtitles'] = {
'rechat': [{
'url': update_url_query(
'https://api.twitch.tv/v5/videos/%s/comments' % item_id, {
'https://api.twitch.tv/v5/videos/%s/comments' % vod_id, {
'client_id': self._CLIENT_ID,
}),
'ext': 'json',
@@ -376,164 +317,405 @@ class TwitchVodIE(TwitchItemBaseIE):
return info
class TwitchPlaylistBaseIE(TwitchBaseIE):
_PLAYLIST_PATH = 'kraken/channels/%s/videos/?offset=%d&limit=%d'
def _make_video_result(node):
assert isinstance(node, dict)
video_id = node.get('id')
if not video_id:
return
return {
'_type': 'url_transparent',
'ie_key': TwitchVodIE.ie_key(),
'id': video_id,
'url': 'https://www.twitch.tv/videos/%s' % video_id,
'title': node.get('title'),
'thumbnail': node.get('previewThumbnailURL'),
'duration': float_or_none(node.get('lengthSeconds')),
'view_count': int_or_none(node.get('viewCount')),
}
class TwitchGraphQLBaseIE(TwitchBaseIE):
_PAGE_LIMIT = 100
def _extract_playlist(self, channel_id):
info = self._call_api(
'kraken/channels/%s' % channel_id,
channel_id, 'Downloading channel info JSON')
channel_name = info.get('display_name') or info.get('name')
def _download_gql(self, video_id, op, variables, sha256_hash, note, fatal=True):
return self._download_json(
'https://gql.twitch.tv/gql', video_id, note,
data=json.dumps({
'operationName': op,
'variables': variables,
'extensions': {
'persistedQuery': {
'version': 1,
'sha256Hash': sha256_hash,
}
}
}).encode(),
headers={
'Content-Type': 'text/plain;charset=UTF-8',
'Client-ID': self._CLIENT_ID,
}, fatal=fatal)
class TwitchCollectionIE(TwitchGraphQLBaseIE):
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/collections/(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://www.twitch.tv/collections/wlDCoH0zEBZZbQ',
'info_dict': {
'id': 'wlDCoH0zEBZZbQ',
'title': 'Overthrow Nook, capitalism for children',
},
'playlist_mincount': 13,
}]
_OPERATION_NAME = 'CollectionSideBar'
_SHA256_HASH = '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14'
def _real_extract(self, url):
collection_id = self._match_id(url)
collection = self._download_gql(
collection_id, self._OPERATION_NAME,
{'collectionID': collection_id}, self._SHA256_HASH,
'Downloading collection GraphQL')['data']['collection']
title = collection.get('title')
entries = []
for edge in collection['items']['edges']:
if not isinstance(edge, dict):
continue
node = edge.get('node')
if not isinstance(node, dict):
continue
video = _make_video_result(node)
if video:
entries.append(video)
return self.playlist_result(
entries, playlist_id=collection_id, playlist_title=title)
class TwitchPlaylistBaseIE(TwitchGraphQLBaseIE):
def _entries(self, channel_name, *args):
cursor = None
variables_common = self._make_variables(channel_name, *args)
entries_key = '%ss' % self._ENTRY_KIND
for page_num in itertools.count(1):
variables = variables_common.copy()
variables['limit'] = self._PAGE_LIMIT
if cursor:
variables['cursor'] = cursor
page = self._download_gql(
channel_name, self._OPERATION_NAME, variables,
self._SHA256_HASH,
'Downloading %ss GraphQL page %s' % (self._NODE_KIND, page_num),
fatal=False)
if not page:
break
edges = try_get(
page, lambda x: x['data']['user'][entries_key]['edges'], list)
if not edges:
break
for edge in edges:
if not isinstance(edge, dict):
continue
if edge.get('__typename') != self._EDGE_KIND:
continue
node = edge.get('node')
if not isinstance(node, dict):
continue
if node.get('__typename') != self._NODE_KIND:
continue
entry = self._extract_entry(node)
if entry:
cursor = edge.get('cursor')
yield entry
if not cursor or not isinstance(cursor, compat_str):
break
# Deprecated kraken v5 API
def _entries_kraken(self, channel_name, broadcast_type, sort):
access_token = self._download_access_token(channel_name)
channel_id = self._extract_channel_id(access_token['token'], channel_name)
offset = 0
limit = self._PAGE_LIMIT
broken_paging_detected = False
counter_override = None
for counter in itertools.count(1):
response = self._call_api(
self._PLAYLIST_PATH % (channel_id, offset, limit),
'kraken/channels/%s/videos/' % channel_id,
channel_id,
'Downloading %s JSON page %s'
% (self._PLAYLIST_TYPE, counter_override or counter))
page_entries = self._extract_playlist_page(response)
if not page_entries:
'Downloading video JSON page %s' % (counter_override or counter),
query={
'offset': offset,
'limit': self._PAGE_LIMIT,
'broadcast_type': broadcast_type,
'sort': sort,
})
videos = response.get('videos')
if not isinstance(videos, list):
break
for video in videos:
if not isinstance(video, dict):
continue
video_url = url_or_none(video.get('url'))
if not video_url:
continue
yield {
'_type': 'url_transparent',
'ie_key': TwitchVodIE.ie_key(),
'id': video.get('_id'),
'url': video_url,
'title': video.get('title'),
'description': video.get('description'),
'timestamp': unified_timestamp(video.get('published_at')),
'duration': float_or_none(video.get('length')),
'view_count': int_or_none(video.get('views')),
'language': video.get('language'),
}
offset += self._PAGE_LIMIT
total = int_or_none(response.get('_total'))
# Since the beginning of March 2016 twitch's paging mechanism
# is completely broken on the twitch side. It simply ignores
# a limit and returns the whole offset number of videos.
# Working around by just requesting all videos at once.
# Upd: pagination bug was fixed by twitch on 15.03.2016.
if not broken_paging_detected and total and len(page_entries) > limit:
self.report_warning(
'Twitch pagination is broken on twitch side, requesting all videos at once',
channel_id)
broken_paging_detected = True
offset = total
counter_override = '(all at once)'
continue
entries.extend(page_entries)
if broken_paging_detected or total and len(page_entries) >= total:
if total and offset >= total:
break
offset += limit
return self.playlist_result(
[self._make_url_result(entry) for entry in orderedSet(entries)],
channel_id, channel_name)
def _make_url_result(self, url):
try:
video_id = 'v%s' % TwitchVodIE._match_id(url)
return self.url_result(url, TwitchVodIE.ie_key(), video_id=video_id)
except AssertionError:
return self.url_result(url)
def _extract_playlist_page(self, response):
videos = response.get('videos')
return [video['url'] for video in videos] if videos else []
def _real_extract(self, url):
return self._extract_playlist(self._match_id(url))
class TwitchProfileIE(TwitchPlaylistBaseIE):
IE_NAME = 'twitch:profile'
_VALID_URL = r'%s/(?P<id>[^/]+)/profile/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE
_PLAYLIST_TYPE = 'profile'
class TwitchVideosIE(TwitchPlaylistBaseIE):
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/(?:videos|profile)'
_TESTS = [{
'url': 'http://www.twitch.tv/vanillatv/profile',
'info_dict': {
'id': 'vanillatv',
'title': 'VanillaTV',
},
'playlist_mincount': 412,
}, {
'url': 'http://m.twitch.tv/vanillatv/profile',
'only_matching': True,
}]
class TwitchVideosBaseIE(TwitchPlaylistBaseIE):
_VALID_URL_VIDEOS_BASE = r'%s/(?P<id>[^/]+)/videos' % TwitchBaseIE._VALID_URL_BASE
_PLAYLIST_PATH = TwitchPlaylistBaseIE._PLAYLIST_PATH + '&broadcast_type='
class TwitchAllVideosIE(TwitchVideosBaseIE):
IE_NAME = 'twitch:videos:all'
_VALID_URL = r'%s/all' % TwitchVideosBaseIE._VALID_URL_VIDEOS_BASE
_PLAYLIST_PATH = TwitchVideosBaseIE._PLAYLIST_PATH + 'archive,upload,highlight'
_PLAYLIST_TYPE = 'all videos'
_TESTS = [{
'url': 'https://www.twitch.tv/spamfish/videos/all',
# All Videos sorted by Date
'url': 'https://www.twitch.tv/spamfish/videos?filter=all',
'info_dict': {
'id': 'spamfish',
'title': 'Spamfish',
'title': 'spamfish - All Videos sorted by Date',
},
'playlist_mincount': 869,
'playlist_mincount': 924,
}, {
# All Videos sorted by Popular
'url': 'https://www.twitch.tv/spamfish/videos?filter=all&sort=views',
'info_dict': {
'id': 'spamfish',
'title': 'spamfish - All Videos sorted by Popular',
},
'playlist_mincount': 931,
}, {
# Past Broadcasts sorted by Date
'url': 'https://www.twitch.tv/spamfish/videos?filter=archives',
'info_dict': {
'id': 'spamfish',
'title': 'spamfish - Past Broadcasts sorted by Date',
},
'playlist_mincount': 27,
}, {
# Highlights sorted by Date
'url': 'https://www.twitch.tv/spamfish/videos?filter=highlights',
'info_dict': {
'id': 'spamfish',
'title': 'spamfish - Highlights sorted by Date',
},
'playlist_mincount': 901,
}, {
# Uploads sorted by Date
'url': 'https://www.twitch.tv/esl_csgo/videos?filter=uploads&sort=time',
'info_dict': {
'id': 'esl_csgo',
'title': 'esl_csgo - Uploads sorted by Date',
},
'playlist_mincount': 5,
}, {
# Past Premieres sorted by Date
'url': 'https://www.twitch.tv/spamfish/videos?filter=past_premieres',
'info_dict': {
'id': 'spamfish',
'title': 'spamfish - Past Premieres sorted by Date',
},
'playlist_mincount': 1,
}, {
'url': 'https://www.twitch.tv/spamfish/videos/all',
'only_matching': True,
}, {
'url': 'https://m.twitch.tv/spamfish/videos/all',
'only_matching': True,
}]
class TwitchUploadsIE(TwitchVideosBaseIE):
IE_NAME = 'twitch:videos:uploads'
_VALID_URL = r'%s/uploads' % TwitchVideosBaseIE._VALID_URL_VIDEOS_BASE
_PLAYLIST_PATH = TwitchVideosBaseIE._PLAYLIST_PATH + 'upload'
_PLAYLIST_TYPE = 'uploads'
_TESTS = [{
'url': 'https://www.twitch.tv/spamfish/videos/uploads',
'info_dict': {
'id': 'spamfish',
'title': 'Spamfish',
},
'playlist_mincount': 0,
}, {
'url': 'https://m.twitch.tv/spamfish/videos/uploads',
'url': 'https://www.twitch.tv/spamfish/videos',
'only_matching': True,
}]
Broadcast = collections.namedtuple('Broadcast', ['type', 'label'])
class TwitchPastBroadcastsIE(TwitchVideosBaseIE):
IE_NAME = 'twitch:videos:past-broadcasts'
_VALID_URL = r'%s/past-broadcasts' % TwitchVideosBaseIE._VALID_URL_VIDEOS_BASE
_PLAYLIST_PATH = TwitchVideosBaseIE._PLAYLIST_PATH + 'archive'
_PLAYLIST_TYPE = 'past broadcasts'
_DEFAULT_BROADCAST = Broadcast(None, 'All Videos')
_BROADCASTS = {
'archives': Broadcast('ARCHIVE', 'Past Broadcasts'),
'highlights': Broadcast('HIGHLIGHT', 'Highlights'),
'uploads': Broadcast('UPLOAD', 'Uploads'),
'past_premieres': Broadcast('PAST_PREMIERE', 'Past Premieres'),
'all': _DEFAULT_BROADCAST,
}
_DEFAULT_SORTED_BY = 'Date'
_SORTED_BY = {
'time': _DEFAULT_SORTED_BY,
'views': 'Popular',
}
_SHA256_HASH = 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb'
_OPERATION_NAME = 'FilterableVideoTower_Videos'
_ENTRY_KIND = 'video'
_EDGE_KIND = 'VideoEdge'
_NODE_KIND = 'Video'
@classmethod
def suitable(cls, url):
return (False
if any(ie.suitable(url) for ie in (
TwitchVideosClipsIE,
TwitchVideosCollectionsIE))
else super(TwitchVideosIE, cls).suitable(url))
@staticmethod
def _make_variables(channel_name, broadcast_type, sort):
return {
'channelOwnerLogin': channel_name,
'broadcastType': broadcast_type,
'videoSort': sort.upper(),
}
@staticmethod
def _extract_entry(node):
return _make_video_result(node)
def _real_extract(self, url):
channel_name = self._match_id(url)
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
filter = qs.get('filter', ['all'])[0]
sort = qs.get('sort', ['time'])[0]
broadcast = self._BROADCASTS.get(filter, self._DEFAULT_BROADCAST)
return self.playlist_result(
self._entries(channel_name, broadcast.type, sort),
playlist_id=channel_name,
playlist_title='%s - %s sorted by %s'
% (channel_name, broadcast.label,
self._SORTED_BY.get(sort, self._DEFAULT_SORTED_BY)))
class TwitchVideosClipsIE(TwitchPlaylistBaseIE):
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/(?:clips|videos/*?\?.*?\bfilter=clips)'
_TESTS = [{
'url': 'https://www.twitch.tv/spamfish/videos/past-broadcasts',
# Clips
'url': 'https://www.twitch.tv/vanillatv/clips?filter=clips&range=all',
'info_dict': {
'id': 'spamfish',
'title': 'Spamfish',
'id': 'vanillatv',
'title': 'vanillatv - Clips Top All',
},
'playlist_mincount': 0,
'playlist_mincount': 1,
}, {
'url': 'https://m.twitch.tv/spamfish/videos/past-broadcasts',
'url': 'https://www.twitch.tv/dota2ruhub/videos?filter=clips&range=7d',
'only_matching': True,
}]
Clip = collections.namedtuple('Clip', ['filter', 'label'])
class TwitchHighlightsIE(TwitchVideosBaseIE):
IE_NAME = 'twitch:videos:highlights'
_VALID_URL = r'%s/highlights' % TwitchVideosBaseIE._VALID_URL_VIDEOS_BASE
_PLAYLIST_PATH = TwitchVideosBaseIE._PLAYLIST_PATH + 'highlight'
_PLAYLIST_TYPE = 'highlights'
_DEFAULT_CLIP = Clip('LAST_WEEK', 'Top 7D')
_RANGE = {
'24hr': Clip('LAST_DAY', 'Top 24H'),
'7d': _DEFAULT_CLIP,
'30d': Clip('LAST_MONTH', 'Top 30D'),
'all': Clip('ALL_TIME', 'Top All'),
}
# NB: values other than 20 result in skipped videos
_PAGE_LIMIT = 20
_SHA256_HASH = 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777'
_OPERATION_NAME = 'ClipsCards__User'
_ENTRY_KIND = 'clip'
_EDGE_KIND = 'ClipEdge'
_NODE_KIND = 'Clip'
@staticmethod
def _make_variables(channel_name, filter):
return {
'login': channel_name,
'criteria': {
'filter': filter,
},
}
@staticmethod
def _extract_entry(node):
assert isinstance(node, dict)
clip_url = url_or_none(node.get('url'))
if not clip_url:
return
return {
'_type': 'url_transparent',
'ie_key': TwitchClipsIE.ie_key(),
'id': node.get('id'),
'url': clip_url,
'title': node.get('title'),
'thumbnail': node.get('thumbnailURL'),
'duration': float_or_none(node.get('durationSeconds')),
'timestamp': unified_timestamp(node.get('createdAt')),
'view_count': int_or_none(node.get('viewCount')),
'language': node.get('language'),
}
def _real_extract(self, url):
channel_name = self._match_id(url)
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
range = qs.get('range', ['7d'])[0]
clip = self._RANGE.get(range, self._DEFAULT_CLIP)
return self.playlist_result(
self._entries(channel_name, clip.filter),
playlist_id=channel_name,
playlist_title='%s - Clips %s' % (channel_name, clip.label))
class TwitchVideosCollectionsIE(TwitchPlaylistBaseIE):
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/videos/*?\?.*?\bfilter=collections'
_TESTS = [{
'url': 'https://www.twitch.tv/spamfish/videos/highlights',
# Collections
'url': 'https://www.twitch.tv/spamfish/videos?filter=collections',
'info_dict': {
'id': 'spamfish',
'title': 'Spamfish',
'title': 'spamfish - Collections',
},
'playlist_mincount': 805,
}, {
'url': 'https://m.twitch.tv/spamfish/videos/highlights',
'only_matching': True,
'playlist_mincount': 3,
}]
_SHA256_HASH = '07e3691a1bad77a36aba590c351180439a40baefc1c275356f40fc7082419a84'
_OPERATION_NAME = 'ChannelCollectionsContent'
_ENTRY_KIND = 'collection'
_EDGE_KIND = 'CollectionsItemEdge'
_NODE_KIND = 'Collection'
@staticmethod
def _make_variables(channel_name):
return {
'ownerLogin': channel_name,
}
@staticmethod
def _extract_entry(node):
assert isinstance(node, dict)
collection_id = node.get('id')
if not collection_id:
return
return {
'_type': 'url_transparent',
'ie_key': TwitchCollectionIE.ie_key(),
'id': collection_id,
'url': 'https://www.twitch.tv/collections/%s' % collection_id,
'title': node.get('title'),
'thumbnail': node.get('thumbnailURL'),
'duration': float_or_none(node.get('lengthSeconds')),
'timestamp': unified_timestamp(node.get('updatedAt')),
'view_count': int_or_none(node.get('viewCount')),
}
def _real_extract(self, url):
channel_name = self._match_id(url)
return self.playlist_result(
self._entries(channel_name), playlist_id=channel_name,
playlist_title='%s - Collections' % channel_name)
class TwitchStreamIE(TwitchBaseIE):
IE_NAME = 'twitch:stream'
@@ -583,27 +765,21 @@ class TwitchStreamIE(TwitchBaseIE):
def suitable(cls, url):
return (False
if any(ie.suitable(url) for ie in (
TwitchVideoIE,
TwitchChapterIE,
TwitchVodIE,
TwitchProfileIE,
TwitchAllVideosIE,
TwitchUploadsIE,
TwitchPastBroadcastsIE,
TwitchHighlightsIE,
TwitchCollectionIE,
TwitchVideosIE,
TwitchVideosClipsIE,
TwitchVideosCollectionsIE,
TwitchClipsIE))
else super(TwitchStreamIE, cls).suitable(url))
def _real_extract(self, url):
channel_name = self._match_id(url)
access_token = self._call_api(
'api/channels/%s/access_token' % channel_name, channel_name,
'Downloading access token JSON')
access_token = self._download_access_token(channel_name)
token = access_token['token']
channel_id = compat_str(self._parse_json(
token, channel_name)['channel_id'])
channel_id = self._extract_channel_id(token, channel_name)
stream = self._call_api(
'kraken/streams/%s?stream_type=all' % channel_id,

View File

@@ -56,7 +56,7 @@ class WistiaIE(InfoExtractor):
urls.append(unescapeHTML(match.group('url')))
for match in re.finditer(
r'''(?sx)
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
<div[^>]+class=(["'])(?:(?!\1).)*?\bwistia_async_(?P<id>[a-z0-9]{10})\b(?:(?!\1).)*?\1
''', webpage):
urls.append('wistia:%s' % match.group('id'))
for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):

View File

@@ -20,13 +20,13 @@ from ..utils import (
class XHamsterIE(InfoExtractor):
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)'
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)'
_VALID_URL = r'''(?x)
https?://
(?:.+?\.)?%s/
(?:
movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
)
''' % _DOMAINS
_TESTS = [{
@@ -99,12 +99,21 @@ class XHamsterIE(InfoExtractor):
}, {
'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
'only_matching': True,
}, {
'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
'only_matching': True,
}, {
'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
'only_matching': True,
}, {
'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
'only_matching': True,
}, {
'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
'only_matching': True,
}, {
'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -129,7 +138,8 @@ class XHamsterIE(InfoExtractor):
initials = self._parse_json(
self._search_regex(
r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
(r'window\.initials\s*=\s*({.+?})\s*;\s*</script>',
r'window\.initials\s*=\s*({.+?})\s*;'), webpage, 'initials',
default='{}'),
video_id, fatal=False)
if initials:

View File

@@ -70,9 +70,14 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
_PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}'
_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&hl=en',
'.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en',
# YouTube sets the expire time to about two months
expire_time=time.time() + 2 * 30 * 24 * 3600)
@@ -298,10 +303,11 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
# Downloading page may result in intermittent 5xx HTTP error
# that is usually worked around with a retry
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
'https://www.youtube.com/%s' % mobj.group('more'), playlist_id,
'Downloading page #%s%s'
% (page_num, ' (retry #%d)' % count if count else ''),
transform_source=uppercase_escape)
transform_source=uppercase_escape,
headers=self._YOUTUBE_CLIENT_HEADERS)
break
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
@@ -1378,7 +1384,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
funcname = self._search_regex(
(r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
# Obsolete patterns
r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
@@ -1652,8 +1658,63 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
video_id = mobj.group(2)
return video_id
def _extract_chapters_from_json(self, webpage, video_id, duration):
if not webpage:
return
player = self._parse_json(
self._search_regex(
r'RELATED_PLAYER_ARGS["\']\s*:\s*({.+})\s*,?\s*\n', webpage,
'player args', default='{}'),
video_id, fatal=False)
if not player or not isinstance(player, dict):
return
watch_next_response = player.get('watch_next_response')
if not isinstance(watch_next_response, compat_str):
return
response = self._parse_json(watch_next_response, video_id, fatal=False)
if not response or not isinstance(response, dict):
return
chapters_list = try_get(
response,
lambda x: x['playerOverlays']
['playerOverlayRenderer']
['decoratedPlayerBarRenderer']
['decoratedPlayerBarRenderer']
['playerBar']
['chapteredPlayerBarRenderer']
['chapters'],
list)
if not chapters_list:
return
def chapter_time(chapter):
return float_or_none(
try_get(
chapter,
lambda x: x['chapterRenderer']['timeRangeStartMillis'],
int),
scale=1000)
chapters = []
for next_num, chapter in enumerate(chapters_list, start=1):
start_time = chapter_time(chapter)
if start_time is None:
continue
end_time = (chapter_time(chapters_list[next_num])
if next_num < len(chapters_list) else duration)
if end_time is None:
continue
title = try_get(
chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
compat_str)
chapters.append({
'start_time': start_time,
'end_time': end_time,
'title': title,
})
return chapters
@staticmethod
def _extract_chapters(description, duration):
def _extract_chapters_from_description(description, duration):
if not description:
return None
chapter_lines = re.findall(
@@ -1687,6 +1748,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
})
return chapters
def _extract_chapters(self, webpage, description, video_id, duration):
return (self._extract_chapters_from_json(webpage, video_id, duration)
or self._extract_chapters_from_description(description, duration))
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
@@ -1760,7 +1825,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# Get video info
video_info = {}
embed_webpage = None
if re.search(r'player-age-gate-content">', video_webpage) is not None:
if (self._og_search_property('restrictions:age', video_webpage, default=None) == '18+'
or re.search(r'player-age-gate-content">', video_webpage) is not None):
age_gate = True
# We simulate the access to the video from www.youtube.com/v/{video_id}
# this can be viewed without login into Youtube
@@ -1833,6 +1899,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
video_details = try_get(
player_response, lambda x: x['videoDetails'], dict) or {}
microformat = try_get(
player_response, lambda x: x['microformat']['playerMicroformatRenderer'], dict) or {}
video_title = video_info.get('title', [None])[0] or video_details.get('title')
if not video_title:
self._downloader.report_warning('Unable to extract video title')
@@ -1862,7 +1931,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
''', replace_url, video_description)
video_description = clean_html(video_description)
else:
video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
video_description = video_details.get('shortDescription') or self._html_search_meta('description', video_webpage)
if not smuggled_data.get('force_singlefeed', False):
if not self._downloader.params.get('noplaylist'):
@@ -1910,6 +1979,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
view_count = extract_view_count(video_info)
if view_count is None and video_details:
view_count = int_or_none(video_details.get('viewCount'))
if view_count is None and microformat:
view_count = int_or_none(microformat.get('viewCount'))
if is_live is None:
is_live = bool_or_none(video_details.get('isLive'))
@@ -2161,7 +2232,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
video_uploader_id = mobj.group('uploader_id')
video_uploader_url = mobj.group('uploader_url')
else:
self._downloader.report_warning('unable to extract uploader nickname')
owner_profile_url = url_or_none(microformat.get('ownerProfileUrl'))
if owner_profile_url:
video_uploader_id = self._search_regex(
r'(?:user|channel)/([^/]+)', owner_profile_url, 'uploader id',
default=None)
video_uploader_url = owner_profile_url
channel_id = (
str_or_none(video_details.get('channelId'))
@@ -2172,17 +2248,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
video_webpage, 'channel id', default=None, group='id'))
channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
# thumbnail image
# We try first to get a high quality image:
m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
video_webpage, re.DOTALL)
if m_thumb is not None:
video_thumbnail = m_thumb.group(1)
elif 'thumbnail_url' not in video_info:
self._downloader.report_warning('unable to extract video thumbnail')
thumbnails = []
thumbnails_list = try_get(
video_details, lambda x: x['thumbnail']['thumbnails'], list) or []
for t in thumbnails_list:
if not isinstance(t, dict):
continue
thumbnail_url = url_or_none(t.get('url'))
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
'width': int_or_none(t.get('width')),
'height': int_or_none(t.get('height')),
})
if not thumbnails:
video_thumbnail = None
else: # don't panic if we can't find it
video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
# We try first to get a high quality image:
m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
video_webpage, re.DOTALL)
if m_thumb is not None:
video_thumbnail = m_thumb.group(1)
thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url'][0], compat_str)
if thumbnail_url:
video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url)
if video_thumbnail:
thumbnails.append({'url': video_thumbnail})
# upload date
upload_date = self._html_search_meta(
@@ -2192,6 +2284,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
[r'(?s)id="eow-date.*?>(.*?)</span>',
r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
video_webpage, 'upload date', default=None)
if not upload_date:
upload_date = microformat.get('publishDate') or microformat.get('uploadDate')
upload_date = unified_strdate(upload_date)
video_license = self._html_search_regex(
@@ -2263,17 +2357,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
m_cat_container = self._search_regex(
r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
video_webpage, 'categories', default=None)
category = None
if m_cat_container:
category = self._html_search_regex(
r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
default=None)
video_categories = None if category is None else [category]
else:
video_categories = None
if not category:
category = try_get(
microformat, lambda x: x['category'], compat_str)
video_categories = None if category is None else [category]
video_tags = [
unescapeHTML(m.group('content'))
for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
if not video_tags:
video_tags = try_get(video_details, lambda x: x['keywords'], list)
def _extract_count(count_name):
return str_to_int(self._search_regex(
@@ -2324,7 +2422,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
errnote='Unable to download video annotations', fatal=False,
data=urlencode_postdata({xsrf_field_name: xsrf_token}))
chapters = self._extract_chapters(description_original, video_duration)
chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration)
# Look for the DASH manifest
if self._downloader.params.get('youtube_include_dash_manifest', True):
@@ -2415,7 +2513,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'creator': video_creator or artist,
'title': video_title,
'alt_title': video_alt_title or track,
'thumbnail': video_thumbnail,
'thumbnails': thumbnails,
'description': video_description,
'categories': video_categories,
'tags': video_tags,
@@ -2679,7 +2777,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
ids = []
last_id = playlist_id[-11:]
for n in itertools.count(1):
url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
webpage = self._download_webpage(
url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
new_ids = orderedSet(re.findall(
@@ -2911,7 +3009,7 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
class YoutubeUserIE(YoutubeChannelIE):
IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
_VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
_VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9%-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_%-]+)'
_TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
IE_NAME = 'youtube:user'
@@ -2941,6 +3039,9 @@ class YoutubeUserIE(YoutubeChannelIE):
}, {
'url': 'https://www.youtube.com/c/gametrailers',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/c/Pawe%C5%82Zadro%C5%BCniak',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/gametrailers',
'only_matching': True,
@@ -3019,7 +3120,7 @@ class YoutubeLiveIE(YoutubeBaseInfoExtractor):
class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
IE_DESC = 'YouTube.com user/channel playlists'
_VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
_VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists'
IE_NAME = 'youtube:playlists'
_TESTS = [{
@@ -3045,6 +3146,9 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
'title': 'Chem Player',
},
'skip': 'Blocked',
}, {
'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
'only_matching': True,
}]
@@ -3189,9 +3293,10 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
'https://www.youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
'Downloading page #%s' % page_num,
transform_source=uppercase_escape)
transform_source=uppercase_escape,
headers=self._YOUTUBE_CLIENT_HEADERS)
content_html = more['content_html']
more_widget_html = more['load_more_widget_html']

View File

@@ -4198,6 +4198,7 @@ def mimetype2ext(mt):
'vnd.ms-sstr+xml': 'ism',
'quicktime': 'mov',
'mp2t': 'ts',
'x-wav': 'wav',
}.get(res, res)

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2020.06.06'
__version__ = '2020.09.06'