Merge branch 'master' of https://git.hpkg.tv/df/youtube-dl into Hummy
This commit is contained in:
commit
2d714ecb56
|
@ -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 **2021.04.26**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.06.06**
|
||||
- [ ] 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 2021.04.26
|
||||
[debug] youtube-dl version 2021.06.06
|
||||
[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: {}
|
||||
|
|
|
@ -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 **2021.04.26**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.06.06**
|
||||
- [ ] 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
|
||||
|
|
|
@ -24,7 +24,7 @@ Carefully read and work through this check list in order to prevent the most com
|
|||
-->
|
||||
|
||||
- [ ] I'm reporting a site feature request
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.04.26**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.06.06**
|
||||
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
|
||||
|
||||
|
||||
|
|
|
@ -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 **2021.04.26**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.06.06**
|
||||
- [ ] 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 2021.04.26
|
||||
[debug] youtube-dl version 2021.06.06
|
||||
[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: {}
|
||||
|
|
|
@ -25,7 +25,7 @@ Carefully read and work through this check list in order to prevent the most com
|
|||
-->
|
||||
|
||||
- [ ] I'm reporting a feature request
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.04.26**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.06.06**
|
||||
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
||||
|
||||
|
||||
|
|
49
ChangeLog
49
ChangeLog
|
@ -1,3 +1,52 @@
|
|||
version 2021.06.06
|
||||
|
||||
Extractors
|
||||
* [facebook] Improve login required detection
|
||||
* [youporn] Fix formats and view count extraction (#29216)
|
||||
* [orf:tvthek] Fix thumbnails extraction (#29217)
|
||||
* [formula1] Fix extraction (#29206)
|
||||
* [ard] Relax URL regular expression and fix video ids (#22724, #29091)
|
||||
+ [ustream] Detect https embeds (#29133)
|
||||
* [ted] Prefer own formats over external sources (#29142)
|
||||
* [twitch:clips] Improve extraction (#29149)
|
||||
+ [twitch:clips] Add access token query to download URLs (#29136)
|
||||
* [youtube] Fix get_video_info request (#29086, #29165)
|
||||
* [vimeo] Fix vimeo pro embed extraction (#29126)
|
||||
* [redbulltv] Fix embed data extraction (#28770)
|
||||
* [shahid] Relax URL regular expression (#28772, #28930)
|
||||
|
||||
|
||||
version 2021.05.16
|
||||
|
||||
Core
|
||||
* [options] Fix thumbnail option group name (#29042)
|
||||
* [YoutubeDL] Improve extract_info doc (#28946)
|
||||
|
||||
Extractors
|
||||
+ [playstuff] Add support for play.stuff.co.nz (#28901, #28931)
|
||||
* [eroprofile] Fix extraction (#23200, #23626, #29008)
|
||||
+ [vivo] Add support for vivo.st (#29009)
|
||||
+ [generic] Add support for og:audio (#28311, #29015)
|
||||
* [phoenix] Fix extraction (#29057)
|
||||
+ [generic] Add support for sibnet embeds
|
||||
+ [vk] Add support for sibnet embeds (#9500)
|
||||
+ [generic] Add Referer header for direct videojs download URLs (#2879,
|
||||
#20217, #29053)
|
||||
* [orf:radio] Switch download URLs to HTTPS (#29012, #29046)
|
||||
- [blinkx] Remove extractor (#28941)
|
||||
* [medaltv] Relax URL regular expression (#28884)
|
||||
+ [funimation] Add support for optional lang code in URLs (#28950)
|
||||
+ [gdcvault] Add support for HTML5 videos
|
||||
* [dispeak] Improve FLV extraction (#13513, #28970)
|
||||
* [kaltura] Improve iframe extraction (#28969)
|
||||
* [kaltura] Make embed code alternatives actually work
|
||||
* [cda] Improve extraction (#28709, #28937)
|
||||
* [twitter] Improve formats extraction from vmap URL (#28909)
|
||||
* [xtube] Fix formats extraction (#28870)
|
||||
* [svtplay] Improve extraction (#28507, #28876)
|
||||
* [tv2dk] Fix extraction (#28888)
|
||||
|
||||
|
||||
version 2021.04.26
|
||||
|
||||
Extractors
|
||||
|
|
|
@ -287,7 +287,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
|
|||
--no-cache-dir Disable filesystem caching
|
||||
--rm-cache-dir Delete all filesystem cache files
|
||||
|
||||
## Thumbnail images:
|
||||
## Thumbnail Options:
|
||||
--write-thumbnail Write thumbnail image to disk
|
||||
--write-all-thumbnails Write all thumbnail image formats to
|
||||
disk
|
||||
|
@ -893,7 +893,7 @@ Since June 2012 ([#342](https://github.com/ytdl-org/youtube-dl/issues/342)) yout
|
|||
|
||||
### The exe throws an error due to missing `MSVCR100.dll`
|
||||
|
||||
To run the exe you need to install first the [Microsoft Visual C++ 2010 Redistributable Package (x86)](https://www.microsoft.com/en-US/download/details.aspx?id=5555).
|
||||
To run the exe you need to install first the [Microsoft Visual C++ 2010 Service Pack 1 Redistributable Package (x86)](https://download.microsoft.com/download/1/6/5/165255E7-1014-4D0A-B094-B6A430A6BFFC/vcredist_x86.exe).
|
||||
|
||||
### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?
|
||||
|
||||
|
|
|
@ -119,7 +119,6 @@
|
|||
- **BitChuteChannel**
|
||||
- **BleacherReport**
|
||||
- **BleacherReportCMS**
|
||||
- **blinkx**
|
||||
- **Bloomberg**
|
||||
- **BokeCC**
|
||||
- **BongaCams**
|
||||
|
@ -713,6 +712,7 @@
|
|||
- **play.fm**
|
||||
- **player.sky.it**
|
||||
- **PlayPlusTV**
|
||||
- **PlayStuff**
|
||||
- **PlaysTV**
|
||||
- **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
|
||||
- **Playvid**
|
||||
|
|
|
@ -773,11 +773,20 @@ class YoutubeDL(object):
|
|||
|
||||
def extract_info(self, url, download=True, ie_key=None, extra_info={},
|
||||
process=True, force_generic_extractor=False):
|
||||
'''
|
||||
Returns a list with a dictionary for each video we find.
|
||||
If 'download', also downloads the videos.
|
||||
extra_info is a dict containing the extra values to add to each result
|
||||
'''
|
||||
"""
|
||||
Return a list with a dictionary for each video extracted.
|
||||
|
||||
Arguments:
|
||||
url -- URL to extract
|
||||
|
||||
Keyword arguments:
|
||||
download -- whether to download videos during extraction
|
||||
ie_key -- extractor key hint
|
||||
extra_info -- dictionary containing the extra values to add to each result
|
||||
process -- whether to resolve all unresolved references (URLs, playlist items),
|
||||
must be True for download to work.
|
||||
force_generic_extractor -- force using the generic extractor
|
||||
"""
|
||||
|
||||
if not ie_key and force_generic_extractor:
|
||||
ie_key = 'Generic'
|
||||
|
|
|
@ -249,14 +249,14 @@ class ARDMediathekIE(ARDMediathekBaseIE):
|
|||
|
||||
|
||||
class ARDIE(InfoExtractor):
|
||||
_VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?:video-?)?(?P<id>[0-9]+))\.html'
|
||||
_VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/(?:[^/?#&]+/)+(?P<id>[^/?#&]+))\.html'
|
||||
_TESTS = [{
|
||||
# available till 7.01.2022
|
||||
'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-die-woche-video100.html',
|
||||
'md5': '867d8aa39eeaf6d76407c5ad1bb0d4c1',
|
||||
'info_dict': {
|
||||
'display_id': 'maischberger-die-woche',
|
||||
'id': '100',
|
||||
'id': 'maischberger-die-woche-video100',
|
||||
'display_id': 'maischberger-die-woche-video100',
|
||||
'ext': 'mp4',
|
||||
'duration': 3687.0,
|
||||
'title': 'maischberger. die woche vom 7. Januar 2021',
|
||||
|
@ -264,16 +264,25 @@ class ARDIE(InfoExtractor):
|
|||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.daserste.de/information/reportage-dokumentation/erlebnis-erde/videosextern/woelfe-und-herdenschutzhunde-ungleiche-brueder-102.html',
|
||||
'url': 'https://www.daserste.de/information/politik-weltgeschehen/morgenmagazin/videosextern/dominik-kahun-aus-der-nhl-direkt-zur-weltmeisterschaft-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.daserste.de/information/nachrichten-wetter/tagesthemen/videosextern/tagesthemen-17736.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.daserste.de/unterhaltung/serie/in-aller-freundschaft-die-jungen-aerzte/Drehpause-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.daserste.de/unterhaltung/film/filmmittwoch-im-ersten/videos/making-ofwendezeit-video-100.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
display_id = mobj.group('display_id')
|
||||
display_id = mobj.group('id')
|
||||
|
||||
player_url = mobj.group('mainurl') + '~playerXml.xml'
|
||||
doc = self._download_xml(player_url, display_id)
|
||||
|
@ -324,7 +333,7 @@ class ARDIE(InfoExtractor):
|
|||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': mobj.group('id'),
|
||||
'id': xpath_text(video_node, './videoId', default=display_id),
|
||||
'formats': formats,
|
||||
'display_id': display_id,
|
||||
'title': video_node.find('./title').text,
|
||||
|
|
|
@ -1,86 +0,0 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
remove_start,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class BlinkxIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
|
||||
IE_NAME = 'blinkx'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.blinkx.com/ce/Da0Gw3xc5ucpNduzLuDDlv4WC9PuI4fDi1-t6Y3LyfdY2SZS5Urbvn-UPJvrvbo8LTKTc67Wu2rPKSQDJyZeeORCR8bYkhs8lI7eqddznH2ofh5WEEdjYXnoRtj7ByQwt7atMErmXIeYKPsSDuMAAqJDlQZ-3Ff4HJVeH_s3Gh8oQ',
|
||||
'md5': '337cf7a344663ec79bf93a526a2e06c7',
|
||||
'info_dict': {
|
||||
'id': 'Da0Gw3xc',
|
||||
'ext': 'mp4',
|
||||
'title': 'No Daily Show for John Oliver; HBO Show Renewed - IGN News',
|
||||
'uploader': 'IGN News',
|
||||
'upload_date': '20150217',
|
||||
'timestamp': 1424215740,
|
||||
'description': 'HBO has renewed Last Week Tonight With John Oliver for two more seasons.',
|
||||
'duration': 47.743333,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
display_id = video_id[:8]
|
||||
|
||||
api_url = ('https://apib4.blinkx.com/api.php?action=play_video&'
|
||||
+ 'video=%s' % video_id)
|
||||
data_json = self._download_webpage(api_url, display_id)
|
||||
data = json.loads(data_json)['api']['results'][0]
|
||||
duration = None
|
||||
thumbnails = []
|
||||
formats = []
|
||||
for m in data['media']:
|
||||
if m['type'] == 'jpg':
|
||||
thumbnails.append({
|
||||
'url': m['link'],
|
||||
'width': int(m['w']),
|
||||
'height': int(m['h']),
|
||||
})
|
||||
elif m['type'] == 'original':
|
||||
duration = float(m['d'])
|
||||
elif m['type'] == 'youtube':
|
||||
yt_id = m['link']
|
||||
self.to_screen('Youtube video detected: %s' % yt_id)
|
||||
return self.url_result(yt_id, 'Youtube', video_id=yt_id)
|
||||
elif m['type'] in ('flv', 'mp4'):
|
||||
vcodec = remove_start(m['vcodec'], 'ff')
|
||||
acodec = remove_start(m['acodec'], 'ff')
|
||||
vbr = int_or_none(m.get('vbr') or m.get('vbitrate'), 1000)
|
||||
abr = int_or_none(m.get('abr') or m.get('abitrate'), 1000)
|
||||
tbr = vbr + abr if vbr and abr else None
|
||||
format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': m['link'],
|
||||
'vcodec': vcodec,
|
||||
'acodec': acodec,
|
||||
'abr': abr,
|
||||
'vbr': vbr,
|
||||
'tbr': tbr,
|
||||
'width': int_or_none(m.get('w')),
|
||||
'height': int_or_none(m.get('h')),
|
||||
})
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': display_id,
|
||||
'fullid': video_id,
|
||||
'title': data['title'],
|
||||
'formats': formats,
|
||||
'uploader': data['channel_name'],
|
||||
'timestamp': data['pubdate_epoch'],
|
||||
'description': data.get('description'),
|
||||
'thumbnails': thumbnails,
|
||||
'duration': duration,
|
||||
}
|
|
@ -133,6 +133,8 @@ class CDAIE(InfoExtractor):
|
|||
'age_limit': 18 if need_confirm_age else 0,
|
||||
}
|
||||
|
||||
info = self._search_json_ld(webpage, video_id, default={})
|
||||
|
||||
# Source: https://www.cda.pl/js/player.js?t=1606154898
|
||||
def decrypt_file(a):
|
||||
for p in ('_XDDD', '_CDA', '_ADC', '_CXD', '_QWE', '_Q5', '_IKSDE'):
|
||||
|
@ -197,7 +199,7 @@ class CDAIE(InfoExtractor):
|
|||
handler = self._download_webpage
|
||||
|
||||
webpage = handler(
|
||||
self._BASE_URL + href, video_id,
|
||||
urljoin(self._BASE_URL, href), video_id,
|
||||
'Downloading %s version information' % resolution, fatal=False)
|
||||
if not webpage:
|
||||
# Manually report warning because empty page is returned when
|
||||
|
@ -209,6 +211,4 @@ class CDAIE(InfoExtractor):
|
|||
|
||||
self._sort_formats(formats)
|
||||
|
||||
info = self._search_json_ld(webpage, video_id, default={})
|
||||
|
||||
return merge_dicts(info_dict, info)
|
||||
|
|
|
@ -32,6 +32,18 @@ class DigitallySpeakingIE(InfoExtractor):
|
|||
# From http://www.gdcvault.com/play/1013700/Advanced-Material
|
||||
'url': 'http://sevt.dispeak.com/ubm/gdc/eur10/xml/11256_1282118587281VNIT.xml',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# From https://gdcvault.com/play/1016624, empty speakerVideo
|
||||
'url': 'https://sevt.dispeak.com/ubm/gdc/online12/xml/201210-822101_1349794556671DDDD.xml',
|
||||
'info_dict': {
|
||||
'id': '201210-822101_1349794556671DDDD',
|
||||
'ext': 'flv',
|
||||
'title': 'Pre-launch - Preparing to Take the Plunge',
|
||||
},
|
||||
}, {
|
||||
# From http://www.gdcvault.com/play/1014846/Conference-Keynote-Shigeru, empty slideVideo
|
||||
'url': 'http://events.digitallyspeaking.com/gdc/project25/xml/p25-miyamoto1999_1282467389849HSVB.xml',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _parse_mp4(self, metadata):
|
||||
|
@ -84,26 +96,20 @@ class DigitallySpeakingIE(InfoExtractor):
|
|||
'vcodec': 'none',
|
||||
'format_id': audio.get('code'),
|
||||
})
|
||||
slide_video_path = xpath_text(metadata, './slideVideo', fatal=True)
|
||||
formats.append({
|
||||
'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
|
||||
'play_path': remove_end(slide_video_path, '.flv'),
|
||||
'ext': 'flv',
|
||||
'format_note': 'slide deck video',
|
||||
'quality': -2,
|
||||
'preference': -2,
|
||||
'format_id': 'slides',
|
||||
})
|
||||
speaker_video_path = xpath_text(metadata, './speakerVideo', fatal=True)
|
||||
formats.append({
|
||||
'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
|
||||
'play_path': remove_end(speaker_video_path, '.flv'),
|
||||
'ext': 'flv',
|
||||
'format_note': 'speaker video',
|
||||
'quality': -1,
|
||||
'preference': -1,
|
||||
'format_id': 'speaker',
|
||||
})
|
||||
for video_key, format_id, preference in (
|
||||
('slide', 'slides', -2), ('speaker', 'speaker', -1)):
|
||||
video_path = xpath_text(metadata, './%sVideo' % video_key)
|
||||
if not video_path:
|
||||
continue
|
||||
formats.append({
|
||||
'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
|
||||
'play_path': remove_end(video_path, '.flv'),
|
||||
'ext': 'flv',
|
||||
'format_note': '%s video' % video_key,
|
||||
'quality': preference,
|
||||
'preference': preference,
|
||||
'format_id': format_id,
|
||||
})
|
||||
return formats
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
|
|
@ -6,7 +6,7 @@ from .common import InfoExtractor
|
|||
from ..compat import compat_urllib_parse_urlencode
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
unescapeHTML
|
||||
merge_dicts,
|
||||
)
|
||||
|
||||
|
||||
|
@ -24,7 +24,8 @@ class EroProfileIE(InfoExtractor):
|
|||
'title': 'sexy babe softcore',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'age_limit': 18,
|
||||
}
|
||||
},
|
||||
'skip': 'Video not found',
|
||||
}, {
|
||||
'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
|
||||
'md5': '1baa9602ede46ce904c431f5418d8916',
|
||||
|
@ -77,19 +78,15 @@ class EroProfileIE(InfoExtractor):
|
|||
[r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
|
||||
webpage, 'video id', default=None)
|
||||
|
||||
video_url = unescapeHTML(self._search_regex(
|
||||
r'<source src="([^"]+)', webpage, 'video url'))
|
||||
title = self._html_search_regex(
|
||||
r'Title:</th><td>([^<]+)</td>', webpage, 'title')
|
||||
thumbnail = self._search_regex(
|
||||
r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
|
||||
webpage, 'thumbnail', fatal=False)
|
||||
(r'Title:</th><td>([^<]+)</td>', r'<h1[^>]*>(.+?)</h1>'),
|
||||
webpage, 'title')
|
||||
|
||||
return {
|
||||
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
|
||||
|
||||
return merge_dicts(info, {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'age_limit': 18,
|
||||
}
|
||||
})
|
||||
|
|
|
@ -132,7 +132,6 @@ from .bleacherreport import (
|
|||
BleacherReportIE,
|
||||
BleacherReportCMSIE,
|
||||
)
|
||||
from .blinkx import BlinkxIE
|
||||
from .bloomberg import BloombergIE
|
||||
from .bokecc import BokeCCIE
|
||||
from .bongacams import BongaCamsIE
|
||||
|
@ -926,6 +925,7 @@ from .platzi import (
|
|||
from .playfm import PlayFMIE
|
||||
from .playplustv import PlayPlusTVIE
|
||||
from .plays import PlaysTVIE
|
||||
from .playstuff import PlayStuffIE
|
||||
from .playtvak import PlaytvakIE
|
||||
from .playvid import PlayvidIE
|
||||
from .playwire import PlaywireIE
|
||||
|
|
|
@ -521,7 +521,10 @@ class FacebookIE(InfoExtractor):
|
|||
raise ExtractorError(
|
||||
'The video is not available, Facebook said: "%s"' % m_msg.group(1),
|
||||
expected=True)
|
||||
elif '>You must log in to continue' in webpage:
|
||||
elif any(p in webpage for p in (
|
||||
'>You must log in to continue',
|
||||
'id="login_form"',
|
||||
'id="loginbutton"')):
|
||||
self.raise_login_required()
|
||||
|
||||
if not video_data and '/watchparty/' in url:
|
||||
|
|
|
@ -5,29 +5,23 @@ from .common import InfoExtractor
|
|||
|
||||
|
||||
class Formula1IE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?formula1\.com/(?:content/fom-website/)?en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.formula1.com/content/fom-website/en/video/2016/5/Race_highlights_-_Spain_2016.html',
|
||||
'md5': '8c79e54be72078b26b89e0e111c0502b',
|
||||
_VALID_URL = r'https?://(?:www\.)?formula1\.com/en/latest/video\.[^.]+\.(?P<id>\d+)\.html'
|
||||
_TEST = {
|
||||
'url': 'https://www.formula1.com/en/latest/video.race-highlights-spain-2016.6060988138001.html',
|
||||
'md5': 'be7d3a8c2f804eb2ab2aa5d941c359f8',
|
||||
'info_dict': {
|
||||
'id': 'JvYXJpMzE6pArfHWm5ARp5AiUmD-gibV',
|
||||
'id': '6060988138001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Race highlights - Spain 2016',
|
||||
'timestamp': 1463332814,
|
||||
'upload_date': '20160515',
|
||||
'uploader_id': '6057949432001',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': ['Ooyala'],
|
||||
}, {
|
||||
'url': 'http://www.formula1.com/en/video/2016/5/Race_highlights_-_Spain_2016.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
'add_ie': ['BrightcoveNew'],
|
||||
}
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/6057949432001/S1WMrhjlh_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
ooyala_embed_code = self._search_regex(
|
||||
r'data-videoid="([^"]+)"', webpage, 'ooyala embed code')
|
||||
bc_id = self._match_id(url)
|
||||
return self.url_result(
|
||||
'ooyala:%s' % ooyala_embed_code, 'Ooyala', ooyala_embed_code)
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % bc_id, 'BrightcoveNew', bc_id)
|
||||
|
|
|
@ -16,7 +16,7 @@ from ..utils import (
|
|||
|
||||
|
||||
class FunimationIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:[^/]+/)?shows/[^/]+/(?P<id>[^/?#&]+)'
|
||||
|
||||
_NETRC_MACHINE = 'funimation'
|
||||
_TOKEN = None
|
||||
|
@ -51,6 +51,10 @@ class FunimationIE(InfoExtractor):
|
|||
}, {
|
||||
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# with lang code
|
||||
'url': 'https://www.funimation.com/en/shows/hacksign/role-play/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _login(self):
|
||||
|
|
|
@ -6,6 +6,7 @@ from .common import InfoExtractor
|
|||
from .kaltura import KalturaIE
|
||||
from ..utils import (
|
||||
HEADRequest,
|
||||
remove_start,
|
||||
sanitized_Request,
|
||||
smuggle_url,
|
||||
urlencode_postdata,
|
||||
|
@ -102,6 +103,26 @@ class GDCVaultIE(InfoExtractor):
|
|||
'format': 'mp4-408',
|
||||
},
|
||||
},
|
||||
{
|
||||
# Kaltura embed, whitespace between quote and embedded URL in iframe's src
|
||||
'url': 'https://www.gdcvault.com/play/1025699',
|
||||
'info_dict': {
|
||||
'id': '0_zagynv0a',
|
||||
'ext': 'mp4',
|
||||
'title': 'Tech Toolbox',
|
||||
'upload_date': '20190408',
|
||||
'uploader_id': 'joe@blazestreaming.com',
|
||||
'timestamp': 1554764629,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
# HTML5 video
|
||||
'url': 'http://www.gdcvault.com/play/1014846/Conference-Keynote-Shigeru',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
def _login(self, webpage_url, display_id):
|
||||
|
@ -175,7 +196,18 @@ class GDCVaultIE(InfoExtractor):
|
|||
|
||||
xml_name = self._html_search_regex(
|
||||
r'<iframe src=".*?\?xml(?:=|URL=xml/)(.+?\.xml).*?".*?</iframe>',
|
||||
start_page, 'xml filename')
|
||||
start_page, 'xml filename', default=None)
|
||||
if not xml_name:
|
||||
info = self._parse_html5_media_entries(url, start_page, video_id)[0]
|
||||
info.update({
|
||||
'title': remove_start(self._search_regex(
|
||||
r'>Session Name:\s*<.*?>\s*<td>(.+?)</td>', start_page,
|
||||
'title', default=None) or self._og_search_title(
|
||||
start_page, default=None), 'GDC Vault - '),
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
})
|
||||
return info
|
||||
embed_url = '%s/xml/%s' % (xml_root, xml_name)
|
||||
ie_key = 'DigitallySpeaking'
|
||||
|
||||
|
|
|
@ -126,6 +126,7 @@ from .viqeo import ViqeoIE
|
|||
from .expressen import ExpressenIE
|
||||
from .zype import ZypeIE
|
||||
from .odnoklassniki import OdnoklassnikiIE
|
||||
from .vk import VKIE
|
||||
from .kinja import KinjaEmbedIE
|
||||
from .arcpublishing import ArcPublishingIE
|
||||
from .medialaan import MedialaanIE
|
||||
|
@ -2248,6 +2249,11 @@ class GenericIE(InfoExtractor):
|
|||
},
|
||||
'playlist_mincount': 52,
|
||||
},
|
||||
{
|
||||
# Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
|
||||
'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
def report_following_redirect(self, new_url):
|
||||
|
@ -2777,6 +2783,11 @@ class GenericIE(InfoExtractor):
|
|||
if odnoklassniki_url:
|
||||
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
|
||||
|
||||
# Look for sibnet embedded player
|
||||
sibnet_urls = VKIE._extract_sibnet_urls(webpage)
|
||||
if sibnet_urls:
|
||||
return self.playlist_from_matches(sibnet_urls, video_id, video_title)
|
||||
|
||||
# Look for embedded ivi player
|
||||
mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
|
||||
if mobj is not None:
|
||||
|
@ -3400,6 +3411,9 @@ class GenericIE(InfoExtractor):
|
|||
'url': src,
|
||||
'ext': (mimetype2ext(src_type)
|
||||
or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
|
||||
'http_headers': {
|
||||
'Referer': full_response.geturl(),
|
||||
},
|
||||
})
|
||||
if formats:
|
||||
self._sort_formats(formats)
|
||||
|
@ -3468,7 +3482,7 @@ class GenericIE(InfoExtractor):
|
|||
m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
|
||||
# We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
|
||||
if m_video_type is not None:
|
||||
found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
|
||||
found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
|
||||
if not found:
|
||||
REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
|
||||
found = re.search(
|
||||
|
|
|
@ -120,7 +120,7 @@ class KalturaIE(InfoExtractor):
|
|||
def _extract_urls(webpage):
|
||||
# Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
|
||||
finditer = (
|
||||
re.finditer(
|
||||
list(re.finditer(
|
||||
r"""(?xs)
|
||||
kWidget\.(?:thumb)?[Ee]mbed\(
|
||||
\{.*?
|
||||
|
@ -128,8 +128,8 @@ class KalturaIE(InfoExtractor):
|
|||
(?P<q2>['"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
|
||||
(?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
|
||||
(?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
|
||||
""", webpage)
|
||||
or re.finditer(
|
||||
""", webpage))
|
||||
or list(re.finditer(
|
||||
r'''(?xs)
|
||||
(?P<q1>["'])
|
||||
(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
|
||||
|
@ -142,16 +142,16 @@ class KalturaIE(InfoExtractor):
|
|||
\[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s*
|
||||
)
|
||||
(?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
|
||||
''', webpage)
|
||||
or re.finditer(
|
||||
''', webpage))
|
||||
or list(re.finditer(
|
||||
r'''(?xs)
|
||||
<(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
|
||||
<(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])\s*
|
||||
(?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
|
||||
(?:(?!(?P=q1)).)*
|
||||
[?&;]entry_id=(?P<id>(?:(?!(?P=q1))[^&])+)
|
||||
(?:(?!(?P=q1)).)*
|
||||
(?P=q1)
|
||||
''', webpage)
|
||||
''', webpage))
|
||||
)
|
||||
urls = []
|
||||
for mobj in finditer:
|
||||
|
|
|
@ -15,7 +15,7 @@ from ..utils import (
|
|||
|
||||
|
||||
class MedalTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?medal\.tv/clips/(?P<id>[a-zA-Z0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?medal\.tv/clips/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://medal.tv/clips/2mA60jWAGQCBH',
|
||||
'md5': '7b07b064331b1cf9e8e5c52a06ae68fa',
|
||||
|
@ -42,6 +42,12 @@ class MedalTVIE(InfoExtractor):
|
|||
'upload_date': '20201117',
|
||||
'uploader_id': '5156321',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://medal.tv/clips/37rMeFpryCC-9',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://medal.tv/clips/2WRj40tpY_EU9',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
|
|
@ -140,6 +140,25 @@ class ORFTVthekIE(InfoExtractor):
|
|||
})
|
||||
|
||||
upload_date = unified_strdate(sd.get('created_date'))
|
||||
|
||||
thumbnails = []
|
||||
preview = sd.get('preview_image_url')
|
||||
if preview:
|
||||
thumbnails.append({
|
||||
'id': 'preview',
|
||||
'url': preview,
|
||||
'preference': 0,
|
||||
})
|
||||
image = sd.get('image_full_url')
|
||||
if not image and len(data_jsb) == 1:
|
||||
image = self._og_search_thumbnail(webpage)
|
||||
if image:
|
||||
thumbnails.append({
|
||||
'id': 'full',
|
||||
'url': image,
|
||||
'preference': 1,
|
||||
})
|
||||
|
||||
entries.append({
|
||||
'_type': 'video',
|
||||
'id': video_id,
|
||||
|
@ -149,7 +168,7 @@ class ORFTVthekIE(InfoExtractor):
|
|||
'description': sd.get('description'),
|
||||
'duration': int_or_none(sd.get('duration_in_seconds')),
|
||||
'upload_date': upload_date,
|
||||
'thumbnail': sd.get('image_full_url'),
|
||||
'thumbnails': thumbnails,
|
||||
})
|
||||
|
||||
return {
|
||||
|
@ -182,7 +201,7 @@ class ORFRadioIE(InfoExtractor):
|
|||
duration = end - start if end and start else None
|
||||
entries.append({
|
||||
'id': loop_stream_id.replace('.mp3', ''),
|
||||
'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
|
||||
'url': 'https://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
|
||||
'title': title,
|
||||
'description': clean_html(data.get('subtitle')),
|
||||
'duration': duration,
|
||||
|
|
|
@ -9,8 +9,9 @@ from ..compat import compat_str
|
|||
from ..utils import (
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
xpath_text,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
|
@ -27,10 +28,11 @@ class PhoenixIE(ZDFBaseIE):
|
|||
'title': 'Wohin führt der Protest in der Pandemie?',
|
||||
'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
|
||||
'duration': 1691,
|
||||
'timestamp': 1613906100,
|
||||
'timestamp': 1613902500,
|
||||
'upload_date': '20210221',
|
||||
'uploader': 'Phoenix',
|
||||
'channel': 'corona nachgehakt',
|
||||
'series': 'corona nachgehakt',
|
||||
'episode': 'Wohin führt der Protest in der Pandemie?',
|
||||
},
|
||||
}, {
|
||||
# Youtube embed
|
||||
|
@ -79,50 +81,53 @@ class PhoenixIE(ZDFBaseIE):
|
|||
|
||||
video_id = compat_str(video.get('basename') or video.get('content'))
|
||||
|
||||
details = self._download_xml(
|
||||
details = self._download_json(
|
||||
'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
|
||||
video_id, 'Downloading details XML', query={
|
||||
video_id, 'Downloading details JSON', query={
|
||||
'ak': 'web',
|
||||
'ptmd': 'true',
|
||||
'id': video_id,
|
||||
'profile': 'player2',
|
||||
})
|
||||
|
||||
title = title or xpath_text(
|
||||
details, './/information/title', 'title', fatal=True)
|
||||
content_id = xpath_text(
|
||||
details, './/video/details/basename', 'content id', fatal=True)
|
||||
title = title or details['title']
|
||||
content_id = details['tracking']['nielsen']['content']['assetid']
|
||||
|
||||
info = self._extract_ptmd(
|
||||
'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
|
||||
content_id, None, url)
|
||||
|
||||
timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
|
||||
duration = int_or_none(try_get(
|
||||
details, lambda x: x['tracking']['nielsen']['content']['length']))
|
||||
timestamp = unified_timestamp(details.get('editorialDate'))
|
||||
series = try_get(
|
||||
details, lambda x: x['tracking']['nielsen']['content']['program'],
|
||||
compat_str)
|
||||
episode = title if details.get('contentType') == 'episode' else None
|
||||
|
||||
thumbnails = []
|
||||
for node in details.findall('.//teaserimages/teaserimage'):
|
||||
thumbnail_url = node.text
|
||||
teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
|
||||
for thumbnail_key, thumbnail_url in teaser_images.items():
|
||||
thumbnail_url = urljoin(url, thumbnail_url)
|
||||
if not thumbnail_url:
|
||||
continue
|
||||
thumbnail = {
|
||||
'url': thumbnail_url,
|
||||
}
|
||||
thumbnail_key = node.get('key')
|
||||
if thumbnail_key:
|
||||
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
|
||||
if m:
|
||||
thumbnail['width'] = int(m.group(1))
|
||||
thumbnail['height'] = int(m.group(2))
|
||||
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
|
||||
if m:
|
||||
thumbnail['width'] = int(m.group(1))
|
||||
thumbnail['height'] = int(m.group(2))
|
||||
thumbnails.append(thumbnail)
|
||||
|
||||
return merge_dicts(info, {
|
||||
'id': content_id,
|
||||
'title': title,
|
||||
'description': xpath_text(details, './/information/detail'),
|
||||
'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
|
||||
'description': details.get('leadParagraph'),
|
||||
'duration': duration,
|
||||
'thumbnails': thumbnails,
|
||||
'timestamp': timestamp,
|
||||
'uploader': xpath_text(details, './/details/channel'),
|
||||
'uploader_id': xpath_text(details, './/details/originChannelId'),
|
||||
'channel': xpath_text(details, './/details/originChannelTitle'),
|
||||
'uploader': details.get('tvService'),
|
||||
'series': series,
|
||||
'episode': episode,
|
||||
})
|
||||
|
|
|
@ -0,0 +1,65 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
smuggle_url,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class PlayStuffIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?play\.stuff\.co\.nz/details/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://play.stuff.co.nz/details/608778ac1de1c4001a3fa09a',
|
||||
'md5': 'c82d3669e5247c64bc382577843e5bd0',
|
||||
'info_dict': {
|
||||
'id': '6250584958001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Episode 1: Rotorua/Mt Maunganui/Tauranga',
|
||||
'description': 'md5:c154bafb9f0dd02d01fd4100fb1c1913',
|
||||
'uploader_id': '6005208634001',
|
||||
'timestamp': 1619491027,
|
||||
'upload_date': '20210427',
|
||||
},
|
||||
'add_ie': ['BrightcoveNew'],
|
||||
}, {
|
||||
# geo restricted, bypassable
|
||||
'url': 'https://play.stuff.co.nz/details/_6155660351001',
|
||||
'only_matching': True,
|
||||
}]
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
state = self._parse_json(
|
||||
self._search_regex(
|
||||
r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'state'),
|
||||
video_id)
|
||||
|
||||
account_id = try_get(
|
||||
state, lambda x: x['configurations']['accountId'],
|
||||
compat_str) or '6005208634001'
|
||||
player_id = try_get(
|
||||
state, lambda x: x['configurations']['playerId'],
|
||||
compat_str) or 'default'
|
||||
|
||||
entries = []
|
||||
for item_id, video in state['items'].items():
|
||||
if not isinstance(video, dict):
|
||||
continue
|
||||
asset_id = try_get(
|
||||
video, lambda x: x['content']['attributes']['assetId'],
|
||||
compat_str)
|
||||
if not asset_id:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
smuggle_url(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, asset_id),
|
||||
{'geo_countries': ['NZ']}),
|
||||
'BrightcoveNew', video_id))
|
||||
|
||||
return self.playlist_result(entries, video_id)
|
|
@ -133,8 +133,10 @@ class RedBullEmbedIE(RedBullTVIE):
|
|||
rrn_id = self._match_id(url)
|
||||
asset_id = self._download_json(
|
||||
'https://edge-graphql.crepo-production.redbullaws.com/v1/graphql',
|
||||
rrn_id, headers={'API-KEY': 'e90a1ff11335423998b100c929ecc866'},
|
||||
query={
|
||||
rrn_id, headers={
|
||||
'Accept': 'application/json',
|
||||
'API-KEY': 'e90a1ff11335423998b100c929ecc866',
|
||||
}, query={
|
||||
'query': '''{
|
||||
resource(id: "%s", enforceGeoBlocking: false) {
|
||||
%s
|
||||
|
|
|
@ -21,6 +21,7 @@ from ..utils import (
|
|||
class ShahidBaseIE(AWSIE):
|
||||
_AWS_PROXY_HOST = 'api2.shahid.net'
|
||||
_AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
|
||||
_VALID_URL_BASE = r'https?://shahid\.mbc\.net/[a-z]{2}/'
|
||||
|
||||
def _handle_error(self, e):
|
||||
fail_data = self._parse_json(
|
||||
|
@ -49,7 +50,7 @@ class ShahidBaseIE(AWSIE):
|
|||
|
||||
class ShahidIE(ShahidBaseIE):
|
||||
_NETRC_MACHINE = 'shahid'
|
||||
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
|
||||
_VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
|
||||
'info_dict': {
|
||||
|
@ -73,6 +74,9 @@ class ShahidIE(ShahidBaseIE):
|
|||
# shahid plus subscriber only
|
||||
'url': 'https://shahid.mbc.net/ar/series/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/episode-90511',
|
||||
'only_matching': True
|
||||
}, {
|
||||
'url': 'https://shahid.mbc.net/en/shows/Ramez-Fi-Al-Shallal-season-1-episode-1/episode-359319',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
|
@ -168,7 +172,7 @@ class ShahidIE(ShahidBaseIE):
|
|||
|
||||
|
||||
class ShahidShowIE(ShahidBaseIE):
|
||||
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
|
||||
_VALID_URL = ShahidBaseIE._VALID_URL_BASE + r'(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
|
||||
'info_dict': {
|
||||
|
|
|
@ -86,10 +86,10 @@ class SharedIE(SharedBaseIE):
|
|||
|
||||
class VivoIE(SharedBaseIE):
|
||||
IE_DESC = 'vivo.sx'
|
||||
_VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
|
||||
_VALID_URL = r'https?://vivo\.s[xt]/(?P<id>[\da-z]{10})'
|
||||
_FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://vivo.sx/d7ddda0e78',
|
||||
'md5': '15b3af41be0b4fe01f4df075c2678b2c',
|
||||
'info_dict': {
|
||||
|
@ -98,7 +98,10 @@ class VivoIE(SharedBaseIE):
|
|||
'title': 'Chicken',
|
||||
'filesize': 515659,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'http://vivo.st/d7ddda0e78',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_title(self, webpage):
|
||||
title = self._html_search_regex(
|
||||
|
|
|
@ -146,7 +146,7 @@ class SVTPlayIE(SVTPlayBaseIE):
|
|||
)
|
||||
(?P<svt_id>[^/?#&]+)|
|
||||
https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)
|
||||
(?:.*?modalId=(?P<modal_id>[\da-zA-Z-]+))?
|
||||
(?:.*?(?:modalId|id)=(?P<modal_id>[\da-zA-Z-]+))?
|
||||
)
|
||||
'''
|
||||
_TESTS = [{
|
||||
|
@ -177,6 +177,9 @@ class SVTPlayIE(SVTPlayBaseIE):
|
|||
}, {
|
||||
'url': 'https://www.svtplay.se/video/30479064/husdrommar/husdrommar-sasong-8-designdrommar-i-stenungsund?modalId=8zVbDPA',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.svtplay.se/video/30684086/rapport/rapport-24-apr-18-00-7?id=e72gVpa',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# geo restricted to Sweden
|
||||
'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
|
||||
|
@ -259,7 +262,7 @@ class SVTPlayIE(SVTPlayBaseIE):
|
|||
if not svt_id:
|
||||
svt_id = self._search_regex(
|
||||
(r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
|
||||
r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/%s/[^"\']*\bmodalId=([\da-zA-Z-]+)' % re.escape(video_id),
|
||||
r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/%s/[^"\']*\b(?:modalId|id)=([\da-zA-Z-]+)' % re.escape(video_id),
|
||||
r'["\']videoSvtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
|
||||
r'["\']videoSvtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)',
|
||||
r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"',
|
||||
|
|
|
@ -123,6 +123,10 @@ class TEDIE(InfoExtractor):
|
|||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# with own formats and private Youtube external
|
||||
'url': 'https://www.ted.com/talks/spencer_wells_a_family_tree_for_humanity',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_NATIVE_FORMATS = {
|
||||
|
@ -210,16 +214,6 @@ class TEDIE(InfoExtractor):
|
|||
|
||||
player_talk = talk_info['player_talks'][0]
|
||||
|
||||
external = player_talk.get('external')
|
||||
if isinstance(external, dict):
|
||||
service = external.get('service')
|
||||
if isinstance(service, compat_str):
|
||||
ext_url = None
|
||||
if service.lower() == 'youtube':
|
||||
ext_url = external.get('code')
|
||||
|
||||
return self.url_result(ext_url or external['uri'])
|
||||
|
||||
resources_ = player_talk.get('resources') or talk_info.get('resources')
|
||||
|
||||
http_url = None
|
||||
|
@ -294,6 +288,16 @@ class TEDIE(InfoExtractor):
|
|||
'vcodec': 'none',
|
||||
})
|
||||
|
||||
if not formats:
|
||||
external = player_talk.get('external')
|
||||
if isinstance(external, dict):
|
||||
service = external.get('service')
|
||||
if isinstance(service, compat_str):
|
||||
ext_url = None
|
||||
if service.lower() == 'youtube':
|
||||
ext_url = external.get('code')
|
||||
return self.url_result(ext_url or external['uri'])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
video_id = compat_str(talk_info['id'])
|
||||
|
|
|
@ -74,6 +74,12 @@ class TV2DKIE(InfoExtractor):
|
|||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
entries = []
|
||||
|
||||
def add_entry(partner_id, kaltura_id):
|
||||
entries.append(self.url_result(
|
||||
'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
|
||||
video_id=kaltura_id))
|
||||
|
||||
for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage):
|
||||
video = extract_attributes(video_el)
|
||||
kaltura_id = video.get('data-entryid')
|
||||
|
@ -82,9 +88,14 @@ class TV2DKIE(InfoExtractor):
|
|||
partner_id = video.get('data-partnerid')
|
||||
if not partner_id:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
|
||||
video_id=kaltura_id))
|
||||
add_entry(partner_id, kaltura_id)
|
||||
if not entries:
|
||||
kaltura_id = self._search_regex(
|
||||
r'entry_id\s*:\s*["\']([0-9a-z_]+)', webpage, 'kaltura id')
|
||||
partner_id = self._search_regex(
|
||||
(r'\\u002Fp\\u002F(\d+)\\u002F', r'/p/(\d+)/'), webpage,
|
||||
'partner id')
|
||||
add_entry(partner_id, kaltura_id)
|
||||
return self.playlist_result(entries)
|
||||
|
||||
|
||||
|
|
|
@ -49,6 +49,7 @@ class TwitchBaseIE(InfoExtractor):
|
|||
'ChannelCollectionsContent': '07e3691a1bad77a36aba590c351180439a40baefc1c275356f40fc7082419a84',
|
||||
'StreamMetadata': '1c719a40e481453e5c48d9bb585d971b8b372f8ebb105b17076722264dfa5b3e',
|
||||
'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
|
||||
'VideoAccessToken_Clip': '36b89d2507fce29e5ca551df756d27c1cfe079e2609642b4390aa4c35796eb11',
|
||||
'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
|
||||
'VideoMetadata': '226edb3e692509f727fd56821f5653c05740242c82b0388883e0c0e75dcbf687',
|
||||
}
|
||||
|
@ -893,7 +894,25 @@ class TwitchClipsIE(TwitchBaseIE):
|
|||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
clip = self._download_base_gql(
|
||||
clip = self._download_gql(
|
||||
video_id, [{
|
||||
'operationName': 'VideoAccessToken_Clip',
|
||||
'variables': {
|
||||
'slug': video_id,
|
||||
},
|
||||
}],
|
||||
'Downloading clip access token GraphQL')[0]['data']['clip']
|
||||
|
||||
if not clip:
|
||||
raise ExtractorError(
|
||||
'This clip is no longer available', expected=True)
|
||||
|
||||
access_query = {
|
||||
'sig': clip['playbackAccessToken']['signature'],
|
||||
'token': clip['playbackAccessToken']['value'],
|
||||
}
|
||||
|
||||
data = self._download_base_gql(
|
||||
video_id, {
|
||||
'query': '''{
|
||||
clip(slug: "%s") {
|
||||
|
@ -918,11 +937,10 @@ class TwitchClipsIE(TwitchBaseIE):
|
|||
}
|
||||
viewCount
|
||||
}
|
||||
}''' % video_id}, 'Downloading clip GraphQL')['data']['clip']
|
||||
}''' % video_id}, 'Downloading clip GraphQL', fatal=False)
|
||||
|
||||
if not clip:
|
||||
raise ExtractorError(
|
||||
'This clip is no longer available', expected=True)
|
||||
if data:
|
||||
clip = try_get(data, lambda x: x['data']['clip'], dict) or clip
|
||||
|
||||
formats = []
|
||||
for option in clip.get('videoQualities', []):
|
||||
|
@ -932,7 +950,7 @@ class TwitchClipsIE(TwitchBaseIE):
|
|||
if not source:
|
||||
continue
|
||||
formats.append({
|
||||
'url': source,
|
||||
'url': update_url_query(source, access_query),
|
||||
'format_id': option.get('quality'),
|
||||
'height': int_or_none(option.get('quality')),
|
||||
'fps': int_or_none(option.get('frameRate')),
|
||||
|
|
|
@ -19,6 +19,7 @@ from ..utils import (
|
|||
strip_or_none,
|
||||
unified_timestamp,
|
||||
update_url_query,
|
||||
url_or_none,
|
||||
xpath_text,
|
||||
)
|
||||
|
||||
|
@ -52,6 +53,9 @@ class TwitterBaseIE(InfoExtractor):
|
|||
return [f]
|
||||
|
||||
def _extract_formats_from_vmap_url(self, vmap_url, video_id):
|
||||
vmap_url = url_or_none(vmap_url)
|
||||
if not vmap_url:
|
||||
return []
|
||||
vmap_data = self._download_xml(vmap_url, video_id)
|
||||
formats = []
|
||||
urls = []
|
||||
|
|
|
@ -75,7 +75,7 @@ class UstreamIE(InfoExtractor):
|
|||
@staticmethod
|
||||
def _extract_url(webpage):
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>http://(?:www\.)?(?:ustream\.tv|video\.ibm\.com)/embed/.+?)\1', webpage)
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?(?:ustream\.tv|video\.ibm\.com)/embed/.+?)\1', webpage)
|
||||
if mobj is not None:
|
||||
return mobj.group('url')
|
||||
|
||||
|
|
|
@ -647,7 +647,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
|||
expected=True)
|
||||
raise
|
||||
|
||||
if '://player.vimeo.com/video/' in url:
|
||||
if '//player.vimeo.com/video/' in url:
|
||||
config = self._parse_json(self._search_regex(
|
||||
r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
|
||||
if config.get('view') == 4:
|
||||
|
|
|
@ -300,6 +300,13 @@ class VKIE(VKBaseIE):
|
|||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_sibnet_urls(webpage):
|
||||
# https://help.sibnet.ru/?sibnet_video_embed
|
||||
return [unescapeHTML(mobj.group('url')) for mobj in re.finditer(
|
||||
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.sibnet\.ru/shell\.php\?.*?\bvideoid=\d+.*?)\1',
|
||||
webpage)]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('videoid')
|
||||
|
@ -408,6 +415,10 @@ class VKIE(VKBaseIE):
|
|||
if odnoklassniki_url:
|
||||
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
|
||||
|
||||
sibnet_urls = self._extract_sibnet_urls(info_page)
|
||||
if sibnet_urls:
|
||||
return self.url_result(sibnet_urls[0])
|
||||
|
||||
m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
|
||||
if m_opts:
|
||||
m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
|
||||
|
|
|
@ -11,6 +11,7 @@ from ..utils import (
|
|||
parse_duration,
|
||||
sanitized_Request,
|
||||
str_to_int,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
|
@ -87,10 +88,10 @@ class XTubeIE(InfoExtractor):
|
|||
'Cookie': 'age_verified=1; cookiesAccepted=1',
|
||||
})
|
||||
|
||||
title, thumbnail, duration = [None] * 3
|
||||
title, thumbnail, duration, sources, media_definition = [None] * 5
|
||||
|
||||
config = self._parse_json(self._search_regex(
|
||||
r'playerConf\s*=\s*({.+?})\s*,\s*(?:\n|loaderConf)', webpage, 'config',
|
||||
r'playerConf\s*=\s*({.+?})\s*,\s*(?:\n|loaderConf|playerWrapper)', webpage, 'config',
|
||||
default='{}'), video_id, transform_source=js_to_json, fatal=False)
|
||||
if config:
|
||||
config = config.get('mainRoll')
|
||||
|
@ -99,20 +100,52 @@ class XTubeIE(InfoExtractor):
|
|||
thumbnail = config.get('poster')
|
||||
duration = int_or_none(config.get('duration'))
|
||||
sources = config.get('sources') or config.get('format')
|
||||
media_definition = config.get('mediaDefinition')
|
||||
|
||||
if not isinstance(sources, dict):
|
||||
if not isinstance(sources, dict) and not media_definition:
|
||||
sources = self._parse_json(self._search_regex(
|
||||
r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
|
||||
webpage, 'sources', group='sources'), video_id,
|
||||
transform_source=js_to_json)
|
||||
|
||||
formats = []
|
||||
for format_id, format_url in sources.items():
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': format_id,
|
||||
'height': int_or_none(format_id),
|
||||
})
|
||||
format_urls = set()
|
||||
|
||||
if isinstance(sources, dict):
|
||||
for format_id, format_url in sources.items():
|
||||
format_url = url_or_none(format_url)
|
||||
if not format_url:
|
||||
continue
|
||||
if format_url in format_urls:
|
||||
continue
|
||||
format_urls.add(format_url)
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': format_id,
|
||||
'height': int_or_none(format_id),
|
||||
})
|
||||
|
||||
if isinstance(media_definition, list):
|
||||
for media in media_definition:
|
||||
video_url = url_or_none(media.get('videoUrl'))
|
||||
if not video_url:
|
||||
continue
|
||||
if video_url in format_urls:
|
||||
continue
|
||||
format_urls.add(video_url)
|
||||
format_id = media.get('format')
|
||||
if format_id == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
elif format_id == 'mp4':
|
||||
height = int_or_none(media.get('quality'))
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': '%s-%d' % (format_id, height) if height else format_id,
|
||||
'height': height,
|
||||
})
|
||||
|
||||
self._remove_duplicate_formats(formats)
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
|
|
@ -4,13 +4,12 @@ import re
|
|||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
int_or_none,
|
||||
str_to_int,
|
||||
unescapeHTML,
|
||||
unified_strdate,
|
||||
url_or_none,
|
||||
)
|
||||
from ..aes import aes_decrypt_text
|
||||
|
||||
|
||||
class YouPornIE(InfoExtractor):
|
||||
|
@ -34,6 +33,7 @@ class YouPornIE(InfoExtractor):
|
|||
'tags': list,
|
||||
'age_limit': 18,
|
||||
},
|
||||
'skip': 'This video has been disabled',
|
||||
}, {
|
||||
# Unknown uploader
|
||||
'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
|
||||
|
@ -78,6 +78,40 @@ class YouPornIE(InfoExtractor):
|
|||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
|
||||
definitions = self._download_json(
|
||||
'https://www.youporn.com/api/video/media_definitions/%s/' % video_id,
|
||||
display_id)
|
||||
|
||||
formats = []
|
||||
for definition in definitions:
|
||||
if not isinstance(definition, dict):
|
||||
continue
|
||||
video_url = url_or_none(definition.get('videoUrl'))
|
||||
if not video_url:
|
||||
continue
|
||||
f = {
|
||||
'url': video_url,
|
||||
'filesize': int_or_none(definition.get('videoSize')),
|
||||
}
|
||||
height = int_or_none(definition.get('quality'))
|
||||
# Video URL's path looks like this:
|
||||
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /videos/201703/11/109285532/1080P_4000K_109285532.mp4
|
||||
# We will benefit from it by extracting some metadata
|
||||
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
|
||||
if mobj:
|
||||
if not height:
|
||||
height = int(mobj.group('height'))
|
||||
bitrate = int(mobj.group('bitrate'))
|
||||
f.update({
|
||||
'format_id': '%dp-%dk' % (height, bitrate),
|
||||
'tbr': bitrate,
|
||||
})
|
||||
f['height'] = height
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'http://www.youporn.com/watch/%s' % video_id, display_id,
|
||||
headers={'Cookie': 'age_verified=1'})
|
||||
|
@ -88,65 +122,6 @@ class YouPornIE(InfoExtractor):
|
|||
webpage, default=None) or self._html_search_meta(
|
||||
'title', webpage, fatal=True)
|
||||
|
||||
links = []
|
||||
|
||||
# Main source
|
||||
definitions = self._parse_json(
|
||||
self._search_regex(
|
||||
r'mediaDefinition\s*[=:]\s*(\[.+?\])\s*[;,]', webpage,
|
||||
'media definitions', default='[]'),
|
||||
video_id, fatal=False)
|
||||
if definitions:
|
||||
for definition in definitions:
|
||||
if not isinstance(definition, dict):
|
||||
continue
|
||||
video_url = url_or_none(definition.get('videoUrl'))
|
||||
if video_url:
|
||||
links.append(video_url)
|
||||
|
||||
# Fallback #1, this also contains extra low quality 180p format
|
||||
for _, link in re.findall(r'<a[^>]+href=(["\'])(http(?:(?!\1).)+\.mp4(?:(?!\1).)*)\1[^>]+title=["\']Download [Vv]ideo', webpage):
|
||||
links.append(link)
|
||||
|
||||
# Fallback #2 (unavailable as at 22.06.2017)
|
||||
sources = self._search_regex(
|
||||
r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
|
||||
if sources:
|
||||
for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
|
||||
links.append(link)
|
||||
|
||||
# Fallback #3 (unavailable as at 22.06.2017)
|
||||
for _, link in re.findall(
|
||||
r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
|
||||
links.append(link)
|
||||
|
||||
# Fallback #4, encrypted links (unavailable as at 22.06.2017)
|
||||
for _, encrypted_link in re.findall(
|
||||
r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
|
||||
links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
|
||||
|
||||
formats = []
|
||||
for video_url in set(unescapeHTML(link) for link in links):
|
||||
f = {
|
||||
'url': video_url,
|
||||
}
|
||||
# Video URL's path looks like this:
|
||||
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /videos/201703/11/109285532/1080P_4000K_109285532.mp4
|
||||
# We will benefit from it by extracting some metadata
|
||||
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
|
||||
if mobj:
|
||||
height = int(mobj.group('height'))
|
||||
bitrate = int(mobj.group('bitrate'))
|
||||
f.update({
|
||||
'format_id': '%dp-%dk' % (height, bitrate),
|
||||
'height': height,
|
||||
'tbr': bitrate,
|
||||
})
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
|
||||
webpage, 'description',
|
||||
|
@ -169,13 +144,12 @@ class YouPornIE(InfoExtractor):
|
|||
|
||||
age_limit = self._rta_search(webpage)
|
||||
|
||||
average_rating = int_or_none(self._search_regex(
|
||||
r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
|
||||
webpage, 'average rating', fatal=False))
|
||||
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
|
||||
webpage, 'view count', fatal=False, group='count'))
|
||||
view_count = None
|
||||
views = self._search_regex(
|
||||
r'(<div[^>]+\bclass=["\']js_videoInfoViews["\']>)', webpage,
|
||||
'views', default=None)
|
||||
if views:
|
||||
view_count = str_to_int(extract_attributes(views).get('data-value'))
|
||||
comment_count = str_to_int(self._search_regex(
|
||||
r'>All [Cc]omments? \(([\d,.]+)\)',
|
||||
webpage, 'comment count', default=None))
|
||||
|
@ -201,7 +175,6 @@ class YouPornIE(InfoExtractor):
|
|||
'duration': duration,
|
||||
'uploader': uploader,
|
||||
'upload_date': upload_date,
|
||||
'average_rating': average_rating,
|
||||
'view_count': view_count,
|
||||
'comment_count': comment_count,
|
||||
'categories': categories,
|
||||
|
|
|
@ -1499,6 +1499,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'unable to download video info webpage', query={
|
||||
'video_id': video_id,
|
||||
'eurl': 'https://youtube.googleapis.com/v/' + video_id,
|
||||
'html5': 1,
|
||||
}, fatal=False)),
|
||||
lambda x: x['player_response'][0],
|
||||
compat_str) or '{}', video_id)
|
||||
|
|
|
@ -768,7 +768,7 @@ def parseOpts(overrideArguments=None):
|
|||
action='store_true', dest='rm_cachedir',
|
||||
help='Delete all filesystem cache files')
|
||||
|
||||
thumbnail = optparse.OptionGroup(parser, 'Thumbnail images')
|
||||
thumbnail = optparse.OptionGroup(parser, 'Thumbnail Options')
|
||||
thumbnail.add_option(
|
||||
'--write-thumbnail',
|
||||
action='store_true', dest='writethumbnail', default=False,
|
||||
|
|
|
@ -1,3 +1,3 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2021.04.26'
|
||||
__version__ = '2021.06.06'
|
||||
|
|
Loading…
Reference in New Issue