1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-29 19:47:54 +01:00

Merge remote-tracking branch 'upstream/master' into fix-zing-mp3

This commit is contained in:
Thinh Nguyen 2019-07-10 15:26:10 +07:00
commit fdf6405f03
No known key found for this signature in database
GPG Key ID: C565BDA2570826DE
43 changed files with 2310 additions and 2312 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 2019.06.08. 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 Issues with outdated version will be REJECTED.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 2019.07.02. 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 Issues with outdated version will be REJECTED.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 **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.07.02**
- [ ] 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 2019.06.08
[debug] youtube-dl version 2019.07.02
[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 2019.06.08. 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 2019.07.02. 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 **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.07.02**
- [ ] 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 2019.06.08. 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 2019.07.02. 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 **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.07.02**
- [ ] 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 2019.06.08. 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 2019.07.02. 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 **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.07.02**
- [ ] 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 2019.06.08
[debug] youtube-dl version 2019.07.02
[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 2019.06.08. 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 2019.07.02. 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 **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.07.02**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

View File

@ -1,3 +1,56 @@
version 2019.07.02
Core
+ [utils] Introduce random_user_agent and use as default User-Agent (#21546)
Extractors
+ [vevo] Add support for embed.vevo.com URLs (#21565)
+ [openload] Add support for oload.biz (#21574)
* [xiami] Update API base URL (#21575)
* [yourporn] Fix extraction (#21585)
+ [acast] Add support for URLs with episode id (#21444)
+ [dailymotion] Add support for DM.player embeds
* [soundcloud] Update client id
version 2019.06.27
Extractors
+ [go] Add support for disneynow.com (#21528)
* [mixer:vod] Relax URL regular expression (#21531, #21536)
* [drtv] Relax URL regular expression
* [fusion] Fix extraction (#17775, #21269)
- [nfb] Remove extractor (#21518)
+ [beeg] Add support for api/v6 v2 URLs (#21511)
+ [brightcove:new] Add support for playlists (#21331)
+ [openload] Add support for oload.life (#21495)
* [vimeo:channel,group] Make title extraction non fatal
* [vimeo:likes] Implement extrator in terms of channel extractor (#21493)
+ [pornhub] Add support for more paged video sources
+ [pornhub] Add support for downloading single pages and search pages (#15570)
* [pornhub] Rework extractors (#11922, #16078, #17454, #17936)
+ [youtube] Add another signature function pattern
* [tf1] Fix extraction (#21365, #21372)
* [crunchyroll] Move Accept-Language workaround to video extractor since
it causes playlists not to list any videos
* [crunchyroll:playlist] Fix and relax title extraction (#21291, #21443)
version 2019.06.21
Core
* [utils] Restrict parse_codecs and add theora as known vcodec (#21381)
Extractors
* [youtube] Update signature function patterns (#21469, #21476)
* [youtube] Make --write-annotations non fatal (#21452)
+ [sixplay] Add support for rtlmost.hu (#21405)
* [youtube] Hardcode codec metadata for av01 video only formats (#21381)
* [toutv] Update client key (#21370)
+ [biqle] Add support for new embed domain
* [cbs] Improve DRM protected videos detection (#21339)
version 2019.06.08
Core

View File

@ -581,7 +581,6 @@
- **NextTV**: 壹電視
- **Nexx**
- **NexxEmbed**
- **nfb**: National Film Board of Canada
- **nfl.com**
- **NhkVod**
- **nhl.com**
@ -692,8 +691,9 @@
- **PornerBros**
- **PornHd**
- **PornHub**: PornHub and Thumbzilla
- **PornHubPlaylist**
- **PornHubUserVideos**
- **PornHubPagedVideoList**
- **PornHubUser**
- **PornHubUserVideosUpload**
- **Pornotube**
- **PornoVoisines**
- **PornoXO**

View File

@ -822,6 +822,15 @@ class TestUtil(unittest.TestCase):
'vcodec': 'av01.0.05M.08',
'acodec': 'none',
})
self.assertEqual(parse_codecs('theora, vorbis'), {
'vcodec': 'theora',
'acodec': 'vorbis',
})
self.assertEqual(parse_codecs('unknownvcodec, unknownacodec'), {
'vcodec': 'unknownvcodec',
'acodec': 'unknownacodec',
})
self.assertEqual(parse_codecs('unknown'), {})
def test_escape_rfc3986(self):
reserved = "!*'();:@&=+$,/?#[]"

View File

@ -7,6 +7,7 @@ import functools
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
float_or_none,
int_or_none,
try_get,
@ -27,7 +28,7 @@ class ACastIE(InfoExtractor):
'''
_TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
'md5': '16d936099ec5ca2d5869e3a813ee8dc4',
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
@ -46,28 +47,37 @@ class ACastIE(InfoExtractor):
}, {
'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True,
}]
def _real_extract(self, url):
channel, display_id = re.match(self._VALID_URL, url).groups()
s = self._download_json(
'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
display_id)['result']
'https://feeder.acast.com/api/v1/shows/%s/episodes/%s' % (channel, display_id),
display_id)
media_url = s['url']
if re.search(r'[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}', display_id):
episode_url = s.get('episodeUrl')
if episode_url:
display_id = episode_url
else:
channel, display_id = re.match(self._VALID_URL, s['link']).groups()
cast_data = self._download_json(
'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
display_id)['result']
e = cast_data['episode']
title = e['name']
title = e.get('name') or s['title']
return {
'id': compat_str(e['id']),
'display_id': display_id,
'url': media_url,
'title': title,
'description': e.get('description') or e.get('summary'),
'description': e.get('summary') or clean_html(e.get('description') or s.get('description')),
'thumbnail': e.get('image'),
'timestamp': unified_timestamp(e.get('publishingDate')),
'duration': float_or_none(s.get('duration') or e.get('duration')),
'timestamp': unified_timestamp(e.get('publishingDate') or s.get('publishDate')),
'duration': float_or_none(e.get('duration') or s.get('duration')),
'filesize': int_or_none(e.get('contentLength')),
'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),

View File

@ -25,6 +25,11 @@ MSO_INFO = {
'username_field': 'username',
'password_field': 'password',
},
'ATT': {
'name': 'AT&T U-verse',
'username_field': 'userid',
'password_field': 'password',
},
'ATTOTT': {
'name': 'DIRECTV NOW',
'username_field': 'email',

View File

@ -4,17 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlparse,
)
from ..compat import compat_str
from ..utils import (
ExtractorError,
find_xpath_attr,
get_element_by_attribute,
int_or_none,
NO_DEFAULT,
qualities,
try_get,
unified_strdate,
@ -25,59 +18,7 @@ from ..utils import (
# add tests.
class ArteTvIE(InfoExtractor):
_VALID_URL = r'https?://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
IE_NAME = 'arte.tv'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
lang = mobj.group('lang')
video_id = mobj.group('id')
ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
ref_xml_doc = self._download_xml(
ref_xml_url, video_id, note='Downloading metadata')
config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
config_xml_url = config_node.attrib['ref']
config = self._download_xml(
config_xml_url, video_id, note='Downloading configuration')
formats = [{
'format_id': q.attrib['quality'],
# The playpath starts at 'mp4:', if we don't manually
# split the url, rtmpdump will incorrectly parse them
'url': q.text.split('mp4:', 1)[0],
'play_path': 'mp4:' + q.text.split('mp4:', 1)[1],
'ext': 'flv',
'quality': 2 if q.attrib['quality'] == 'hd' else 1,
} for q in config.findall('./urls/url')]
self._sort_formats(formats)
title = config.find('.//name').text
thumbnail = config.find('.//firstThumbnailUrl').text
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}
class ArteTVBaseIE(InfoExtractor):
@classmethod
def _extract_url_info(cls, url):
mobj = re.match(cls._VALID_URL, url)
lang = mobj.group('lang')
query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
if 'vid' in query:
video_id = query['vid'][0]
else:
# This is not a real id, it can be for example AJT for the news
# http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
video_id = mobj.group('id')
return video_id, lang
def _extract_from_json_url(self, json_url, video_id, lang, title=None):
info = self._download_json(json_url, video_id)
player_info = info['videoJsonPlayer']
@ -108,13 +49,15 @@ class ArteTVBaseIE(InfoExtractor):
'upload_date': unified_strdate(upload_date_str),
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
}
qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
qfunc = qualities(['MQ', 'HQ', 'EQ', 'SQ'])
LANGS = {
'fr': 'F',
'de': 'A',
'en': 'E[ANG]',
'es': 'E[ESP]',
'it': 'E[ITA]',
'pl': 'E[POL]',
}
langcode = LANGS.get(lang, lang)
@ -126,8 +69,8 @@ class ArteTVBaseIE(InfoExtractor):
l = re.escape(langcode)
# Language preference from most to least priority
# Reference: section 5.6.3 of
# http://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-05.pdf
# Reference: section 6.8 of
# https://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-07-1.pdf
PREFERENCES = (
# original version in requested language, without subtitles
r'VO{0}$'.format(l),
@ -193,274 +136,59 @@ class ArteTVBaseIE(InfoExtractor):
class ArteTVPlus7IE(ArteTVBaseIE):
IE_NAME = 'arte.tv:+7'
_VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>\d{6}-\d{3}-[AF])'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
'only_matching': True,
}, {
'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
'only_matching': True,
}, {
'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn',
'only_matching': True,
'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
'info_dict': {
'id': '088501-000-A',
'ext': 'mp4',
'title': 'Mexico: Stealing Petrol to Survive',
'upload_date': '20190628',
},
}]
@classmethod
def suitable(cls, url):
return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url)
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, video_id)
return self._extract_from_webpage(webpage, video_id, lang)
def _extract_from_webpage(self, webpage, video_id, lang):
patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
ids = (video_id, '')
# some pages contain multiple videos (like
# http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
# so we first try to look for json URLs that contain the video id from
# the 'vid' parameter.
patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
json_url = self._html_search_regex(
patterns, webpage, 'json vp url', default=None)
if not json_url:
def find_iframe_url(webpage, default=NO_DEFAULT):
return self._html_search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
webpage, 'iframe url', group='url', default=default)
iframe_url = find_iframe_url(webpage, None)
if not iframe_url:
embed_url = self._html_search_regex(
r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
if embed_url:
player = self._download_json(
embed_url, video_id, 'Downloading player page')
iframe_url = find_iframe_url(player['html'])
# en and es URLs produce react-based pages with different layout (e.g.
# http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
if not iframe_url:
program = self._search_regex(
r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
webpage, 'program', default=None)
if program:
embed_html = self._parse_json(program, video_id)
if embed_html:
iframe_url = find_iframe_url(embed_html['embed_html'])
if iframe_url:
json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
if json_url:
title = self._search_regex(
r'<h3[^>]+title=(["\'])(?P<title>.+?)\1',
webpage, 'title', default=None, group='title')
return self._extract_from_json_url(json_url, video_id, lang, title=title)
# Different kind of embed URL (e.g.
# http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
entries = [
self.url_result(url)
for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)]
return self.playlist_result(entries)
# It also uses the arte_vp_url url from the webpage to extract the information
class ArteTVCreativeIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:creative'
_VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1',
'info_dict': {
'id': '057405-001-A',
'ext': 'mp4',
'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)',
'upload_date': '20150716',
},
}, {
'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
'playlist_count': 11,
'add_ie': ['Youtube'],
}, {
'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde',
'only_matching': True,
}]
class ArteTVInfoIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:info'
_VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere',
'info_dict': {
'id': '067528-000-A',
'ext': 'mp4',
'title': 'Service civique, un cache misère ?',
'upload_date': '20160403',
},
}]
class ArteTVFutureIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:future'
_VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses',
'info_dict': {
'id': '050940-028-A',
'ext': 'mp4',
'title': 'Les écrevisses aussi peuvent être anxieuses',
'upload_date': '20140902',
},
}, {
'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable',
'only_matching': True,
}]
class ArteTVDDCIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:ddc'
_VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
_TESTS = []
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
if lang == 'folge':
lang = 'de'
elif lang == 'emission':
lang = 'fr'
webpage = self._download_webpage(url, video_id)
scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
return self._extract_from_json_url(json_url, video_id, lang)
class ArteTVConcertIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:concert'
_VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
'md5': '9ea035b7bd69696b67aa2ccaaa218161',
'info_dict': {
'id': '186',
'ext': 'mp4',
'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
'upload_date': '20140128',
'description': 'md5:486eb08f991552ade77439fe6d82c305',
},
}]
class ArteTVCinemaIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:cinema'
_VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
_TESTS = [{
'url': 'http://cinema.arte.tv/fr/article/les-ailes-du-desir-de-julia-reck',
'md5': 'a5b9dd5575a11d93daf0e3f404f45438',
'info_dict': {
'id': '062494-000-A',
'ext': 'mp4',
'title': 'Film lauréat du concours web - "Les ailes du désir" de Julia Reck',
'upload_date': '20150807',
},
}]
class ArteTVMagazineIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:magazine'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/magazine/[^/]+/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
# Embedded via <iframe src="http://www.arte.tv/arte_vp/index.php?json_url=..."
'url': 'http://www.arte.tv/magazine/trepalium/fr/entretien-avec-le-realisateur-vincent-lannoo-trepalium',
'md5': '2a9369bcccf847d1c741e51416299f25',
'info_dict': {
'id': '065965-000-A',
'ext': 'mp4',
'title': 'Trepalium - Extrait Ep.01',
'upload_date': '20160121',
},
}, {
# Embedded via <iframe src="http://www.arte.tv/guide/fr/embed/054813-004-A/medium"
'url': 'http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium',
'md5': 'fedc64fc7a946110fe311634e79782ca',
'info_dict': {
'id': '054813-004_PLUS7-F',
'ext': 'mp4',
'title': 'Trepalium (4/6)',
'description': 'md5:10057003c34d54e95350be4f9b05cb40',
'upload_date': '20160218',
},
}, {
'url': 'http://www.arte.tv/magazine/metropolis/de/frank-woeste-german-paris-metropolis',
'only_matching': True,
}]
lang, video_id = re.match(self._VALID_URL, url).groups()
return self._extract_from_json_url(
'https://api.arte.tv/api/player/v1/config/%s/%s' % (lang, video_id),
video_id, lang)
class ArteTVEmbedIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:embed'
_VALID_URL = r'''(?x)
http://www\.arte\.tv
/(?:playerv2/embed|arte_vp/index)\.php\?json_url=
https://www\.arte\.tv
/player/v3/index\.php\?json_url=
(?P<json_url>
http://arte\.tv/papi/tvguide/videos/stream/player/
(?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*
https?://api\.arte\.tv/api/player/v1/config/
(?P<lang>[^/]+)/(?P<id>\d{6}-\d{3}-[AF])
)
'''
_TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
lang = mobj.group('lang')
json_url = mobj.group('json_url')
json_url, lang, video_id = re.match(self._VALID_URL, url).groups()
return self._extract_from_json_url(json_url, video_id, lang)
class TheOperaPlatformIE(ArteTVPlus7IE):
IE_NAME = 'theoperaplatform'
_VALID_URL = r'https?://(?:www\.)?theoperaplatform\.eu/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.theoperaplatform.eu/de/opera/verdi-otello',
'md5': '970655901fa2e82e04c00b955e9afe7b',
'info_dict': {
'id': '060338-009-A',
'ext': 'mp4',
'title': 'Verdi - OTELLO',
'upload_date': '20160927',
},
}]
class ArteTVPlaylistIE(ArteTVBaseIE):
IE_NAME = 'arte.tv:playlist'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>RC-\d{6})'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/plus7/?country=DE#collection/PL-013263/ARTETV',
'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
'info_dict': {
'id': 'PL-013263',
'title': 'Areva & Uramin',
'description': 'md5:a1dc0312ce357c262259139cfd48c9bf',
'id': 'RC-016954',
'title': 'Earn a Living',
'description': 'md5:d322c55011514b3a7241f7fb80d494c2',
},
'playlist_mincount': 6,
}, {
'url': 'http://www.arte.tv/guide/de/playlists?country=DE#collection/PL-013190/ARTETV',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id, lang = self._extract_url_info(url)
lang, playlist_id = re.match(self._VALID_URL, url).groups()
collection = self._download_json(
'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos'
% (lang, playlist_id), playlist_id)

View File

@ -99,8 +99,8 @@ class BeamProLiveIE(BeamProBaseIE):
class BeamProVodIE(BeamProBaseIE):
IE_NAME = 'Mixer:vod'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>\d+)'
_TEST = {
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>[^?#&]+)'
_TESTS = [{
'url': 'https://mixer.com/willow8714?vod=2259830',
'md5': 'b2431e6e8347dc92ebafb565d368b76b',
'info_dict': {
@ -119,7 +119,13 @@ class BeamProVodIE(BeamProBaseIE):
'params': {
'skip_download': True,
},
}
}, {
'url': 'https://mixer.com/streamer?vod=IxFno1rqC0S_XJ1a2yGgNw',
'only_matching': True,
}, {
'url': 'https://mixer.com/streamer?vod=Rh3LY0VAqkGpEQUe2pN-ig',
'only_matching': True,
}]
@staticmethod
def _extract_format(vod, vod_type):

View File

@ -1,7 +1,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
int_or_none,
unified_timestamp,
@ -11,6 +14,7 @@ from ..utils import (
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
_TESTS = [{
# api/v6 v1
'url': 'http://beeg.com/5416503',
'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
'info_dict': {
@ -24,6 +28,10 @@ class BeegIE(InfoExtractor):
'tags': list,
'age_limit': 18,
}
}, {
# api/v6 v2
'url': 'https://beeg.com/1941093077?t=911-1391',
'only_matching': True,
}, {
'url': 'https://beeg.porn/video/5416503',
'only_matching': True,
@ -41,11 +49,22 @@ class BeegIE(InfoExtractor):
r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
default='1546225636701')
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
t = qs.get('t', [''])[0].split('-')
if len(t) > 1:
query = {
'v': 2,
's': t[0],
'e': t[1],
}
else:
query = {'v': 1}
for api_path in ('', 'api.'):
video = self._download_json(
'https://%sbeeg.com/api/v6/%s/video/%s'
% (api_path, beeg_version, video_id), video_id,
fatal=api_path == 'api.')
fatal=api_path == 'api.', query=query)
if video:
break

View File

@ -483,7 +483,7 @@ class BrightcoveLegacyIE(InfoExtractor):
class BrightcoveNewIE(AdobePassIE):
IE_NAME = 'brightcove:new'
_VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+|ref:[^&]+)'
_VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*(?P<content_type>video|playlist)Id=(?P<video_id>\d+|ref:[^&]+)'
_TESTS = [{
'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001',
'md5': 'c8100925723840d4b0d243f7025703be',
@ -516,6 +516,21 @@ class BrightcoveNewIE(AdobePassIE):
# m3u8 download
'skip_download': True,
}
}, {
# playlist stream
'url': 'https://players.brightcove.net/1752604059001/S13cJdUBz_default/index.html?playlistId=5718313430001',
'info_dict': {
'id': '5718313430001',
'title': 'No Audio Playlist',
},
'playlist_count': 7,
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=5743160747001',
'only_matching': True,
}, {
# ref: prefixed video id
'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442',
@ -715,7 +730,7 @@ class BrightcoveNewIE(AdobePassIE):
'ip_blocks': smuggled_data.get('geo_ip_blocks'),
})
account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
account_id, player_id, embed, content_type, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(
'http://players.brightcove.net/%s/%s_%s/index.min.js'
@ -736,7 +751,7 @@ class BrightcoveNewIE(AdobePassIE):
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id)
api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/%ss/%s' % (account_id, content_type, video_id)
headers = {
'Accept': 'application/json;pk=%s' % policy_key,
}
@ -771,5 +786,12 @@ class BrightcoveNewIE(AdobePassIE):
'tveToken': tve_token,
})
if content_type == 'playlist':
return self.playlist_result(
[self._parse_brightcove_metadata(vid, vid.get('id'), headers)
for vid in json_data.get('videos', []) if vid.get('id')],
json_data.get('id'), json_data.get('name'),
json_data.get('description'))
return self._parse_brightcove_metadata(
json_data, video_id, headers=headers)

View File

@ -103,19 +103,6 @@ class CrunchyrollBaseIE(InfoExtractor):
def _real_initialize(self):
self._login()
def _download_webpage(self, url_or_request, *args, **kwargs):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
else sanitized_Request(url_or_request))
# Accept-Language must be set explicitly to accept any language to avoid issues
# similar to https://github.com/ytdl-org/youtube-dl/issues/6797.
# Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
# should be imposed or not (from what I can see it just takes the first language
# ignoring the priority and requires it to correspond the IP). By the way this causes
# Crunchyroll to not work in georestriction cases in some browsers that don't place
# the locale lang first in header. However allowing any language seems to workaround the issue.
request.add_header('Accept-Language', '*')
return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
@staticmethod
def _add_skip_wall(url):
parsed_url = compat_urlparse.urlparse(url)
@ -269,6 +256,19 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
'1080': ('80', '108'),
}
def _download_webpage(self, url_or_request, *args, **kwargs):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
else sanitized_Request(url_or_request))
# Accept-Language must be set explicitly to accept any language to avoid issues
# similar to https://github.com/ytdl-org/youtube-dl/issues/6797.
# Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
# should be imposed or not (from what I can see it just takes the first language
# ignoring the priority and requires it to correspond the IP). By the way this causes
# Crunchyroll to not work in georestriction cases in some browsers that don't place
# the locale lang first in header. However allowing any language seems to workaround the issue.
request.add_header('Accept-Language', '*')
return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(compat_b64decode(data))
iv = bytes_to_intlist(compat_b64decode(iv))
@ -661,9 +661,8 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
webpage = self._download_webpage(
self._add_skip_wall(url), show_id,
headers=self.geo_verification_headers())
title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title')
title = self._html_search_meta('name', webpage, default=None)
episode_paths = re.findall(
r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"',
webpage)

View File

@ -137,10 +137,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
@staticmethod
def _extract_urls(webpage):
urls = []
# Look for embedded Dailymotion player
matches = re.findall(
r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
return list(map(lambda m: unescapeHTML(m[1]), matches))
# https://developer.dailymotion.com/player#player-parameters
for mobj in re.finditer(
r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage):
urls.append(unescapeHTML(mobj.group('url')))
for mobj in re.finditer(
r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
urls.append('https://www.dailymotion.com/embed/video/' + mobj.group('id'))
return urls
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@ -24,7 +24,7 @@ from ..utils import (
class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_GEO_BYPASS = False
_GEO_COUNTRIES = ['DK']
IE_NAME = 'drtv'
@ -80,6 +80,9 @@ class DRTVIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -58,17 +58,8 @@ from .ard import (
ARDMediathekIE,
)
from .arte import (
ArteTvIE,
ArteTVPlus7IE,
ArteTVCreativeIE,
ArteTVConcertIE,
ArteTVInfoIE,
ArteTVFutureIE,
ArteTVCinemaIE,
ArteTVDDCIE,
ArteTVMagazineIE,
ArteTVEmbedIE,
TheOperaPlatformIE,
ArteTVPlaylistIE,
)
from .asiancrush import (
@ -745,7 +736,6 @@ from .nexx import (
NexxIE,
NexxEmbedIE,
)
from .nfb import NFBIE
from .nfl import NFLIE
from .nhk import NhkVodIE
from .nhl import NHLIE
@ -892,8 +882,9 @@ from .porncom import PornComIE
from .pornhd import PornHdIE
from .pornhub import (
PornHubIE,
PornHubPlaylistIE,
PornHubUserVideosIE,
PornHubUserIE,
PornHubPagedVideoListIE,
PornHubUserVideosUploadIE,
)
from .pornotube import PornotubeIE
from .pornovoisines import PornoVoisinesIE

View File

@ -1,35 +1,84 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..utils import (
determine_ext,
int_or_none,
mimetype2ext,
parse_iso8601,
)
class FusionIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fusion\.(?:net|tv)/video/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?fusion\.(?:net|tv)/(?:video/|show/.+?\bvideo=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://fusion.tv/video/201781/u-s-and-panamanian-forces-work-together-to-stop-a-vessel-smuggling-drugs/',
'info_dict': {
'id': 'ZpcWNoMTE6x6uVIIWYpHh0qQDjxBuq5P',
'id': '3145868',
'ext': 'mp4',
'title': 'U.S. and Panamanian forces work together to stop a vessel smuggling drugs',
'description': 'md5:0cc84a9943c064c0f46b128b41b1b0d7',
'duration': 140.0,
'timestamp': 1442589635,
'uploader': 'UNIVISON',
'upload_date': '20150918',
},
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
'add_ie': ['Anvato'],
}, {
'url': 'http://fusion.tv/video/201781',
'only_matching': True,
}, {
'url': 'https://fusion.tv/show/food-exposed-with-nelufar-hedayat/?ancla=full-episodes&video=588644',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._match_id(url)
video = self._download_json(
'https://platform.fusion.net/wp-json/fusiondotnet/v1/video/' + video_id, video_id)
ooyala_code = self._search_regex(
r'data-ooyala-id=(["\'])(?P<code>(?:(?!\1).)+)\1',
webpage, 'ooyala code', group='code')
info = {
'id': video_id,
'title': video['title'],
'description': video.get('excerpt'),
'timestamp': parse_iso8601(video.get('published')),
'series': video.get('show'),
}
return OoyalaIE._build_url_result(ooyala_code)
formats = []
src = video.get('src') or {}
for f_id, f in src.items():
for q_id, q in f.items():
q_url = q.get('url')
if not q_url:
continue
ext = determine_ext(q_url, mimetype2ext(q.get('type')))
if ext == 'smil':
formats.extend(self._extract_smil_formats(q_url, video_id, fatal=False))
elif f_id == 'm3u8-variant' or (ext == 'm3u8' and q_id == 'Variant'):
formats.extend(self._extract_m3u8_formats(
q_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': '-'.join([f_id, q_id]),
'url': q_url,
'width': int_or_none(q.get('width')),
'height': int_or_none(q.get('height')),
'tbr': int_or_none(self._search_regex(r'_(\d+)\.m(?:p4|3u8)', q_url, 'bitrate')),
'ext': 'mp4' if ext == 'm3u8' else ext,
'protocol': 'm3u8_native' if ext == 'm3u8' else 'https',
})
if formats:
self._sort_formats(formats)
info['formats'] = formats
else:
info.update({
'_type': 'url',
'url': 'anvato:uni:' + video['video_ids']['anvato'],
'ie_key': 'Anvato',
})
return info

View File

@ -2104,6 +2104,23 @@ class GenericIE(InfoExtractor):
},
'expected_warnings': ['Failed to download MPD manifest'],
},
{
# DailyMotion embed with DM.player
'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
'info_dict': {
'id': 'k6aKkGHd9FJs4mtJN39',
'ext': 'mp4',
'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
'description': 'This video is private.',
'uploader_id': 'x1jf30l',
'uploader': 'beIN SPORTS USA',
'upload_date': '20190528',
'timestamp': 1559062971,
},
'params': {
'skip_download': True,
},
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject

View File

@ -34,9 +34,13 @@ class GoIE(AdobePassIE):
'watchdisneyxd': {
'brand': '009',
'resource_id': 'DisneyXD',
},
'disneynow': {
'brand': '011',
'resource_id': 'Disney',
}
}
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
_VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|(?P<sub_domain_2>disneynow))\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
% '|'.join(list(_SITE_INFO.keys()) + ['disneynow'])
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
@ -71,6 +75,9 @@ class GoIE(AdobePassIE):
# brand 008
'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}]
def _extract_videos(self, brand, video_id='-1', show_id='-1'):
@ -80,7 +87,9 @@ class GoIE(AdobePassIE):
display_id)['video']
def _real_extract(self, url):
sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
mobj = re.match(self._VALID_URL, url)
sub_domain = mobj.group('sub_domain') or mobj.group('sub_domain_2')
video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand')
if not video_id or not site_info:
@ -89,7 +98,7 @@ class GoIE(AdobePassIE):
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id',
default=None)
default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',

View File

@ -6,8 +6,8 @@ import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
determine_ext,
extract_attributes,
ExtractorError,
float_or_none,
int_or_none,
@ -19,6 +19,7 @@ from ..utils import (
class LecturioBaseIE(InfoExtractor):
_API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
_LOGIN_URL = 'https://app.lecturio.com/en/login'
_NETRC_MACHINE = 'lecturio'
@ -67,51 +68,56 @@ class LecturioIE(LecturioBaseIE):
_VALID_URL = r'''(?x)
https://
(?:
app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture|
(?:www\.)?lecturio\.de/[^/]+/(?P<id_de>[^/?#&]+)\.vortrag
app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
(?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
)
'''
_TESTS = [{
'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
'md5': '9a42cf1d8282a6311bf7211bbde26fde',
'info_dict': {
'id': '39634',
'ext': 'mp4',
'title': 'Important Concepts and Terms Introduction to Microbiology',
'title': 'Important Concepts and Terms Introduction to Microbiology',
},
'skip': 'Requires lecturio account credentials',
}, {
'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
'only_matching': True,
}, {
'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
'only_matching': True,
}]
_CC_LANGS = {
'Arabic': 'ar',
'Bulgarian': 'bg',
'German': 'de',
'English': 'en',
'Spanish': 'es',
'Persian': 'fa',
'French': 'fr',
'Japanese': 'ja',
'Polish': 'pl',
'Pashto': 'ps',
'Russian': 'ru',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id') or mobj.group('id_de')
webpage = self._download_webpage(
'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
display_id)
lecture_id = self._search_regex(
r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id')
api_url = self._search_regex(
r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'api url', group='url')
video = self._download_json(api_url, display_id)
nt = mobj.group('nt') or mobj.group('nt_de')
lecture_id = mobj.group('id')
display_id = nt or lecture_id
api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
video = self._download_json(
self._API_BASE_URL + api_path, display_id)
title = video['title'].strip()
if not lecture_id:
pid = video.get('productId') or video.get('uid')
if pid:
spid = pid.split('_')
if spid and len(spid) == 2:
lecture_id = spid[1]
formats = []
for format_ in video['content']['media']:
@ -129,24 +135,30 @@ class LecturioIE(LecturioBaseIE):
continue
label = str_or_none(format_.get('label'))
filesize = int_or_none(format_.get('fileSize'))
formats.append({
f = {
'url': file_url,
'format_id': label,
'filesize': float_or_none(filesize, invscale=1000)
})
}
if label:
mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
if mobj:
f.update({
'format_id': mobj.group(2),
'height': int(mobj.group(1)),
})
formats.append(f)
self._sort_formats(formats)
subtitles = {}
automatic_captions = {}
cc = self._parse_json(
self._search_regex(
r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles',
default='{}'), display_id, fatal=False)
for cc_label, cc_url in cc.items():
cc_url = url_or_none(cc_url)
captions = video.get('captions') or []
for cc in captions:
cc_url = cc.get('url')
if not cc_url:
continue
lang = self._search_regex(
cc_label = cc.get('translatedCode')
lang = cc.get('languageCode') or self._search_regex(
r'/([a-z]{2})_', cc_url, 'lang',
default=cc_label.split()[0] if cc_label else 'en')
original_lang = self._search_regex(
@ -160,7 +172,7 @@ class LecturioIE(LecturioBaseIE):
})
return {
'id': lecture_id,
'id': lecture_id or nt,
'title': title,
'formats': formats,
'subtitles': subtitles,
@ -169,37 +181,40 @@ class LecturioIE(LecturioBaseIE):
class LecturioCourseIE(LecturioBaseIE):
_VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course'
_TEST = {
_VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
_TESTS = [{
'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
'info_dict': {
'id': 'microbiology-introduction',
'title': 'Microbiology: Introduction',
'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
},
'playlist_count': 45,
'skip': 'Requires lecturio account credentials',
}
}, {
'url': 'https://app.lecturio.com/#/course/c/6434',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nt, course_id = re.match(self._VALID_URL, url).groups()
display_id = nt or course_id
api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
course = self._download_json(
self._API_BASE_URL + api_path, display_id)
entries = []
for mobj in re.finditer(
r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>',
webpage):
params = extract_attributes(mobj.group(0))
lecture_url = urljoin(url, params.get('data-url'))
lecture_id = params.get('data-id')
for lecture in course.get('lectures', []):
lecture_id = str_or_none(lecture.get('id'))
lecture_url = lecture.get('url')
if lecture_url:
lecture_url = urljoin(url, lecture_url)
else:
lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
entries.append(self.url_result(
lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
title = self._search_regex(
r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage,
'title', default=None)
return self.playlist_result(entries, display_id, title)
return self.playlist_result(
entries, display_id, course.get('title'),
clean_html(course.get('description')))
class LecturioDeCourseIE(LecturioBaseIE):

View File

@ -1,112 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
int_or_none,
qualities,
urlencode_postdata,
xpath_text,
)
class NFBIE(InfoExtractor):
IE_NAME = 'nfb'
IE_DESC = 'National Film Board of Canada'
_VALID_URL = r'https?://(?:www\.)?(?:nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
_TEST = {
'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
'info_dict': {
'id': 'qallunaat_why_white_people_are_funny',
'ext': 'flv',
'title': 'Qallunaat! Why White People Are Funny ',
'description': 'md5:6b8e32dde3abf91e58857b174916620c',
'duration': 3128,
'creator': 'Mark Sandiford',
'uploader': 'Mark Sandiford',
},
'params': {
# rtmp download
'skip_download': True,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
config = self._download_xml(
'https://www.nfb.ca/film/%s/player_config' % video_id,
video_id, 'Downloading player config XML',
data=urlencode_postdata({'getConfig': 'true'}),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'X-NFB-Referer': 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf'
})
title, description, thumbnail, duration, uploader, author = [None] * 6
thumbnails, formats = [[]] * 2
subtitles = {}
for media in config.findall('./player/stream/media'):
if media.get('type') == 'posterImage':
quality_key = qualities(('low', 'high'))
thumbnails = []
for asset in media.findall('assets/asset'):
asset_url = xpath_text(asset, 'default/url', default=None)
if not asset_url:
continue
quality = asset.get('quality')
thumbnails.append({
'url': asset_url,
'id': quality,
'preference': quality_key(quality),
})
elif media.get('type') == 'video':
title = xpath_text(media, 'title', fatal=True)
for asset in media.findall('assets/asset'):
quality = asset.get('quality')
height = int_or_none(self._search_regex(
r'^(\d+)[pP]$', quality or '', 'height', default=None))
for node in asset:
streamer = xpath_text(node, 'streamerURI', default=None)
if not streamer:
continue
play_path = xpath_text(node, 'url', default=None)
if not play_path:
continue
formats.append({
'url': streamer,
'app': streamer.split('/', 3)[3],
'play_path': play_path,
'rtmp_live': False,
'ext': 'flv',
'format_id': '%s-%s' % (node.tag, quality) if quality else node.tag,
'height': height,
})
self._sort_formats(formats)
description = clean_html(xpath_text(media, 'description'))
uploader = xpath_text(media, 'author')
duration = int_or_none(media.get('duration'))
for subtitle in media.findall('./subtitles/subtitle'):
subtitle_url = xpath_text(subtitle, 'url', default=None)
if not subtitle_url:
continue
lang = xpath_text(subtitle, 'lang', default='en')
subtitles.setdefault(lang, []).append({
'url': subtitle_url,
'ext': (subtitle.get('format') or determine_ext(subtitle_url)).lower(),
})
return {
'id': video_id,
'title': title,
'description': description,
'thumbnails': thumbnails,
'duration': duration,
'creator': uploader,
'uploader': uploader,
'formats': formats,
'subtitles': subtitles,
}

File diff suppressed because it is too large Load Diff

View File

@ -5,26 +5,27 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_str,
# compat_str,
compat_HTTPError,
)
from ..utils import (
clean_html,
ExtractorError,
remove_end,
# remove_end,
str_or_none,
strip_or_none,
unified_timestamp,
urljoin,
# urljoin,
)
class PacktPubBaseIE(InfoExtractor):
_PACKT_BASE = 'https://www.packtpub.com'
_MAPT_REST = '%s/mapt-rest' % _PACKT_BASE
# _PACKT_BASE = 'https://www.packtpub.com'
_STATIC_PRODUCTS_BASE = 'https://static.packt-cdn.com/products/'
class PacktPubIE(PacktPubBaseIE):
_VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>[^/]+)/(?P<id>[^/]+)(?:/(?P<display_id>[^/?&#]+))?'
_TESTS = [{
'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
@ -40,6 +41,9 @@ class PacktPubIE(PacktPubBaseIE):
}, {
'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro',
'only_matching': True,
}, {
'url': 'https://subscription.packtpub.com/video/programming/9781838988906/p1/video1_1/business-card-project',
'only_matching': True,
}]
_NETRC_MACHINE = 'packtpub'
_TOKEN = None
@ -50,9 +54,9 @@ class PacktPubIE(PacktPubBaseIE):
return
try:
self._TOKEN = self._download_json(
self._MAPT_REST + '/users/tokens', None,
'https://services.packtpub.com/auth-v1/users/tokens', None,
'Downloading Authorization Token', data=json.dumps({
'email': username,
'username': username,
'password': password,
}).encode())['data']['access']
except ExtractorError as e:
@ -61,54 +65,40 @@ class PacktPubIE(PacktPubBaseIE):
raise ExtractorError(message, expected=True)
raise
def _handle_error(self, response):
if response.get('status') != 'success':
raise ExtractorError(
'% said: %s' % (self.IE_NAME, response['message']),
expected=True)
def _download_json(self, *args, **kwargs):
response = super(PacktPubIE, self)._download_json(*args, **kwargs)
self._handle_error(response)
return response
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
course_id, chapter_id, video_id = mobj.group(
'course_id', 'chapter_id', 'id')
course_id, chapter_id, video_id, display_id = re.match(self._VALID_URL, url).groups()
headers = {}
if self._TOKEN:
headers['Authorization'] = 'Bearer ' + self._TOKEN
video = self._download_json(
'%s/users/me/products/%s/chapters/%s/sections/%s'
% (self._MAPT_REST, course_id, chapter_id, video_id), video_id,
'Downloading JSON video', headers=headers)['data']
try:
video_url = self._download_json(
'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id,
'Downloading JSON video', headers=headers)['data']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
self.raise_login_required('This video is locked')
raise
content = video.get('content')
if not content:
self.raise_login_required('This video is locked')
# TODO: find a better way to avoid duplicating course requests
# metadata = self._download_json(
# '%s/products/%s/chapters/%s/sections/%s/metadata'
# % (self._MAPT_REST, course_id, chapter_id, video_id),
# video_id)['data']
video_url = content['file']
metadata = self._download_json(
'%s/products/%s/chapters/%s/sections/%s/metadata'
% (self._MAPT_REST, course_id, chapter_id, video_id),
video_id)['data']
title = metadata['pageTitle']
course_title = metadata.get('title')
if course_title:
title = remove_end(title, ' - %s' % course_title)
timestamp = unified_timestamp(metadata.get('publicationDate'))
thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
# title = metadata['pageTitle']
# course_title = metadata.get('title')
# if course_title:
# title = remove_end(title, ' - %s' % course_title)
# timestamp = unified_timestamp(metadata.get('publicationDate'))
# thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'timestamp': timestamp,
'title': display_id or video_id, # title,
# 'thumbnail': thumbnail,
# 'timestamp': timestamp,
}
@ -119,6 +109,7 @@ class PacktPubCourseIE(PacktPubBaseIE):
'info_dict': {
'id': '9781787122215',
'title': 'Learn Nodejs by building 12 projects [Video]',
'description': 'md5:489da8d953f416e51927b60a1c7db0aa',
},
'playlist_count': 90,
}, {
@ -136,35 +127,38 @@ class PacktPubCourseIE(PacktPubBaseIE):
url, course_id = mobj.group('url', 'id')
course = self._download_json(
'%s/products/%s/metadata' % (self._MAPT_REST, course_id),
course_id)['data']
self._STATIC_PRODUCTS_BASE + '%s/toc' % course_id, course_id)
metadata = self._download_json(
self._STATIC_PRODUCTS_BASE + '%s/summary' % course_id,
course_id, fatal=False) or {}
entries = []
for chapter_num, chapter in enumerate(course['tableOfContents'], 1):
if chapter.get('type') != 'chapter':
continue
children = chapter.get('children')
if not isinstance(children, list):
for chapter_num, chapter in enumerate(course['chapters'], 1):
chapter_id = str_or_none(chapter.get('id'))
sections = chapter.get('sections')
if not chapter_id or not isinstance(sections, list):
continue
chapter_info = {
'chapter': chapter.get('title'),
'chapter_number': chapter_num,
'chapter_id': chapter.get('id'),
'chapter_id': chapter_id,
}
for section in children:
if section.get('type') != 'section':
continue
section_url = section.get('seoUrl')
if not isinstance(section_url, compat_str):
for section in sections:
section_id = str_or_none(section.get('id'))
if not section_id or section.get('contentType') != 'video':
continue
entry = {
'_type': 'url_transparent',
'url': urljoin(url + '/', section_url),
'url': '/'.join([url, chapter_id, section_id]),
'title': strip_or_none(section.get('title')),
'description': clean_html(section.get('summary')),
'thumbnail': metadata.get('coverImage'),
'timestamp': unified_timestamp(metadata.get('publicationDate')),
'ie_key': PacktPubIE.ie_key(),
}
entry.update(chapter_info)
entries.append(entry)
return self.playlist_result(entries, course_id, course.get('title'))
return self.playlist_result(
entries, course_id, metadata.get('title'),
clean_html(metadata.get('about')))

View File

@ -168,7 +168,7 @@ class PeerTubeIE(InfoExtractor):
@staticmethod
def _extract_peertube_url(webpage, source_url):
mobj = re.match(
r'https?://(?P<host>[^/]+)/videos/watch/(?P<id>%s)'
r'https?://(?P<host>[^/]+)/videos/(?:watch|embed)/(?P<id>%s)'
% PeerTubeIE._UUID_RE, source_url)
if mobj and any(p in webpage for p in (
'<title>PeerTube<',

View File

@ -14,7 +14,7 @@ class PhilharmonieDeParisIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)|
live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|embed(?:app)?/|misc/Playlist\.ashx\?id=)|
pad\.philharmoniedeparis\.fr/doc/CIMU/
)
(?P<id>\d+)
@ -40,6 +40,12 @@ class PhilharmonieDeParisIE(InfoExtractor):
}, {
'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
'only_matching': True,
}, {
'url': 'https://live.philharmoniedeparis.fr/embedapp/1098406/berlioz-fantastique-lelio-les-siecles-national-youth-choir-of.html?lang=fr-FR',
'only_matching': True,
}, {
'url': 'https://live.philharmoniedeparis.fr/embed/1098406/berlioz-fantastique-lelio-les-siecles-national-youth-choir-of.html?lang=fr-FR',
'only_matching': True,
}]
_LIVE_URL = 'https://live.philharmoniedeparis.fr'

View File

@ -372,37 +372,92 @@ class PornHubPlaylistBaseIE(PornHubBaseIE):
entries, playlist_id, title, playlist.get('description'))
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
class PornHubUserIE(PornHubPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_TESTS = [{
'url': 'http://www.pornhub.com/playlist/4667351',
'info_dict': {
'id': '4667351',
'title': 'Nataly Hot',
},
'playlist_mincount': 2,
'url': 'https://www.pornhub.com/model/zoe_ph',
'playlist_mincount': 118,
}, {
'url': 'https://de.pornhub.com/playlist/4667351',
'url': 'https://www.pornhub.com/pornstar/liz-vicious',
'info_dict': {
'id': 'liz-vicious',
},
'playlist_mincount': 118,
}, {
'url': 'https://www.pornhub.com/users/russianveet69',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/channels/povd',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('id')
return self.url_result(
'%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
video_id=user_id)
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
item_id = mobj.group('id')
page = int_or_none(self._search_regex(
r'\bpage=(\d+)', url, 'page', default=None))
page_url = self._make_page_url(url)
entries = []
for page_num in (page, ) if page is not None else itertools.count(1):
try:
webpage = self._download_webpage(
page_url, item_id, 'Downloading page %d' % page_num,
query={'page': page_num})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break
raise
page_entries = self._extract_entries(webpage, host)
if not page_entries:
break
entries.extend(page_entries)
if not self._has_more(webpage):
break
return self.playlist_result(orderedSet(entries), item_id)
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'info_dict': {
'id': 'zoe_ph',
},
'playlist_mincount': 171,
'url': 'https://www.pornhub.com/model/zoe_ph/videos',
'only_matching': True,
}, {
'url': 'http://www.pornhub.com/users/rushandlia/videos',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
'info_dict': {
'id': 'pornstar/jenny-blighe/videos',
},
'playlist_mincount': 149,
}, {
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
'info_dict': {
'id': 'pornstar/jenny-blighe/videos',
},
'playlist_mincount': 40,
}, {
# default sorting as Top Rated Videos
'url': 'https://www.pornhub.com/channels/povd/videos',
'info_dict': {
'id': 'povd',
'id': 'channels/povd/videos',
},
'playlist_mincount': 293,
}, {
@ -421,31 +476,107 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
# Most Viewed Videos
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
# Top Rated Videos
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
'only_matching': True,
}, {
# Longest Videos
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
'only_matching': True,
}, {
# Newest Videos
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video/search?search=123',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/categories/teen',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/categories/teen?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/hd',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/hd?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/described-video',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/described-video?page=2',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/playlist/44121572',
'info_dict': {
'id': 'playlist/44121572',
},
'playlist_mincount': 132,
}, {
'url': 'https://www.pornhub.com/playlist/4667351',
'only_matching': True,
}, {
'url': 'https://de.pornhub.com/playlist/4667351',
'only_matching': True,
}]
def _real_extract(self, url):
@classmethod
def suitable(cls, url):
return (False
if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
else super(PornHubPagedVideoListIE, cls).suitable(url))
def _make_page_url(self, url):
return url
@staticmethod
def _has_more(webpage):
return re.search(
r'''(?x)
<li[^>]+\bclass=["\']page_next|
<link[^>]+\brel=["\']next|
<button[^>]+\bid=["\']moreDataBtn
''', webpage) is not None
class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
_TESTS = [{
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
'info_dict': {
'id': 'jenny-blighe',
},
'playlist_mincount': 129,
}, {
'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
'only_matching': True,
}]
def _make_page_url(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
user_id = mobj.group('id')
return '%s/ajax' % mobj.group('url')
entries = []
for page_num in itertools.count(1):
try:
webpage = self._download_webpage(
url, user_id, 'Downloading page %d' % page_num,
query={'page': page_num})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break
raise
page_entries = self._extract_entries(webpage, host)
if not page_entries:
break
entries.extend(page_entries)
return self.playlist_result(entries, user_id)
@staticmethod
def _has_more(webpage):
return True

View File

@ -19,7 +19,7 @@ from ..utils import (
class SixPlayIE(InfoExtractor):
IE_NAME = '6play'
_VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr)/.+?-c_)(?P<id>[0-9]+)'
_VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr|rtlmost\.hu)/.+?-c_)(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
@ -35,6 +35,9 @@ class SixPlayIE(InfoExtractor):
}, {
'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989',
'only_matching': True,
}, {
'url': 'https://www.rtlmost.hu/megtorve-p_14167/megtorve-6-resz-c_12397787',
'only_matching': True,
}]
def _real_extract(self, url):
@ -43,6 +46,7 @@ class SixPlayIE(InfoExtractor):
'6play.fr': ('6play', 'm6web'),
'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'),
'rtlmost.hu': ('rtlhu_rtl_most', 'rtlhu'),
}.get(domain, ('6play', 'm6web'))
data = self._download_json(

View File

@ -221,7 +221,7 @@ class SoundcloudIE(InfoExtractor):
}
]
_CLIENT_ID = 'FweeGBOOEOYJWLJN3oEyToGLKhmSz0I7'
_CLIENT_ID = 'BeGVhOrGmfboy1LtiHTQF6Ejpt9ULJCI'
@staticmethod
def _extract_urls(webpage):

View File

@ -133,7 +133,7 @@ class TEDIE(InfoExtractor):
def _extract_info(self, webpage):
info_json = self._search_regex(
r'(?s)q\(\s*"\w+.init"\s*,\s*({.+})\)\s*</script>',
r'(?s)q\(\s*"\w+.init"\s*,\s*({.+?})\)\s*</script>',
webpage, 'info json')
return json.loads(info_json)

View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
class TF1IE(InfoExtractor):
@ -43,12 +44,49 @@ class TF1IE(InfoExtractor):
}, {
'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
'only_matching': True,
}, {
'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
'info_dict': {
'id': '13641379',
'ext': 'mp4',
'title': 'md5:f392bc52245dc5ad43771650c96fb620',
'description': 'md5:44bc54f0a21322f5b91d68e76a544eae',
'upload_date': '20190611',
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
wat_id = self._html_search_regex(
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
webpage, 'wat id', group='id')
wat_id = None
data = self._parse_json(
self._search_regex(
r'__APOLLO_STATE__\s*=\s*({.+?})\s*(?:;|</script>)', webpage,
'data', default='{}'), video_id, fatal=False)
if data:
try:
wat_id = next(
video.get('streamId')
for key, video in data.items()
if isinstance(video, dict)
and video.get('slug') == video_id)
if not isinstance(wat_id, compat_str) or not wat_id.isdigit():
wat_id = None
except StopIteration:
pass
if not wat_id:
wat_id = self._html_search_regex(
(r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
r'(["\']?)streamId\1\s*:\s*(["\']?)(?P<id>\d+)\2'),
webpage, 'wat id', group='id')
return self.url_result('wat:%s' % wat_id, 'Wat')

View File

@ -38,7 +38,7 @@ class TouTvIE(RadioCanadaIE):
'url': 'https://ici.tou.tv/l-age-adulte/S01C501',
'only_matching': True,
}]
_CLIENT_KEY = '4dd36440-09d5-4468-8923-b6d91174ad36'
_CLIENT_KEY = '90505c8d-9c34-4f34-8da1-3a85bdc6d4f4'
def _real_initialize(self):
email, password = self._get_login_info()

View File

@ -1,32 +1,35 @@
# coding: utf-8
from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
from .spike import ParamountNetworkIE
class TVLandIE(MTVServicesInfoExtractor):
class TVLandIE(ParamountNetworkIE):
IE_NAME = 'tvland.com'
_VALID_URL = r'https?://(?:www\.)?tvland\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
_FEED_URL = 'http://www.tvland.com/feeds/mrss/'
_TESTS = [{
# Geo-restricted. Without a proxy metadata are still there. With a
# proxy it redirects to http://m.tvland.com/app/
'url': 'http://www.tvland.com/episodes/hqhps2/everybody-loves-raymond-the-invasion-ep-048',
'url': 'https://www.tvland.com/episodes/s04pzf/everybody-loves-raymond-the-dog-season-1-ep-19',
'info_dict': {
'description': 'md5:80973e81b916a324e05c14a3fb506d29',
'title': 'The Invasion',
'description': 'md5:84928e7a8ad6649371fbf5da5e1ad75a',
'title': 'The Dog',
},
'playlist': [],
'playlist_mincount': 5,
}, {
'url': 'http://www.tvland.com/video-clips/zea2ev/younger-younger--hilary-duff---little-lies',
'url': 'https://www.tvland.com/video-clips/4n87f2/younger-a-first-look-at-younger-season-6',
'md5': 'e2c6389401cf485df26c79c247b08713',
'info_dict': {
'id': 'b8697515-4bbe-4e01-83d5-fa705ce5fa88',
'id': '891f7d3c-5b5b-4753-b879-b7ba1a601757',
'ext': 'mp4',
'title': 'Younger|December 28, 2015|2|NO-EPISODE#|Younger: Hilary Duff - Little Lies',
'description': 'md5:7d192f56ca8d958645c83f0de8ef0269',
'upload_date': '20151228',
'timestamp': 1451289600,
'title': 'Younger|April 30, 2019|6|NO-EPISODE#|A First Look at Younger Season 6',
'description': 'md5:595ea74578d3a888ae878dfd1c7d4ab2',
'upload_date': '20190430',
'timestamp': 1556658000,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.tvland.com/full-episodes/iu0hz6/younger-a-kiss-is-just-a-kiss-season-3-ep-301',

View File

@ -317,7 +317,7 @@ class TwitchVodIE(TwitchItemBaseIE):
'Downloading %s access token' % self._ITEM_TYPE)
formats = self._extract_m3u8_formats(
'%s/vod/%s?%s' % (
'%s/vod/%s.m3u8?%s' % (
self._USHER_BASE, item_id,
compat_urllib_parse_urlencode({
'allow_source': 'true',

View File

@ -34,6 +34,7 @@ class VevoIE(VevoBaseIE):
(?:https?://(?:www\.)?vevo\.com/watch/(?!playlist|genre)(?:[^/]+/(?:[^/]+/)?)?|
https?://cache\.vevo\.com/m/html/embed\.html\?video=|
https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|
https?://embed\.vevo\.com/.*?[?&]isrc=|
vevo:)
(?P<id>[^&?#]+)'''
@ -144,6 +145,9 @@ class VevoIE(VevoBaseIE):
# Geo-restricted to Netherlands/Germany
'url': 'http://www.vevo.com/watch/boostee/pop-corn-clip-officiel/FR1A91600909',
'only_matching': True,
}, {
'url': 'https://embed.vevo.com/?isrc=USH5V1923499&partnerId=4d61b777-8023-4191-9ede-497ed6c24647&partnerAdCode=',
'only_matching': True,
}]
_VERSIONS = {
0: 'youtube', # only in AuthenticateVideo videoVersions

View File

@ -16,7 +16,6 @@ from ..utils import (
determine_ext,
ExtractorError,
js_to_json,
InAdvancePagedList,
int_or_none,
merge_dicts,
NO_DEFAULT,
@ -814,7 +813,8 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
return '%s/videos/page:%d/' % (base_url, pagenum)
def _extract_list_title(self, webpage):
return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
return self._TITLE or self._html_search_regex(
self._TITLE_RE, webpage, 'list title', fatal=False)
def _login_list_password(self, page_url, list_id, webpage):
login_form = self._search_regex(
@ -955,7 +955,7 @@ class VimeoGroupsIE(VimeoAlbumIE):
}]
def _extract_list_title(self, webpage):
return self._og_search_title(webpage)
return self._og_search_title(webpage, fatal=False)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -1065,7 +1065,7 @@ class VimeoWatchLaterIE(VimeoChannelIE):
return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
class VimeoLikesIE(InfoExtractor):
class VimeoLikesIE(VimeoChannelIE):
_VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
IE_NAME = 'vimeo:likes'
IE_DESC = 'Vimeo user likes'
@ -1073,55 +1073,20 @@ class VimeoLikesIE(InfoExtractor):
'url': 'https://vimeo.com/user755559/likes/',
'playlist_mincount': 293,
'info_dict': {
'id': 'user755559_likes',
'description': 'See all the videos urza likes',
'title': 'Videos urza likes',
'id': 'user755559',
'title': 'urzas Likes',
},
}, {
'url': 'https://vimeo.com/stormlapse/likes',
'only_matching': True,
}]
def _page_url(self, base_url, pagenum):
return '%s/page:%d/' % (base_url, pagenum)
def _real_extract(self, url):
user_id = self._match_id(url)
webpage = self._download_webpage(url, user_id)
page_count = self._int(
self._search_regex(
r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
.*?</a></li>\s*<li\s+class="pagination_next">
''', webpage, 'page count', default=1),
'page count', fatal=True)
PAGE_SIZE = 12
title = self._html_search_regex(
r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
description = self._html_search_meta('description', webpage)
def _get_page(idx):
page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % (
user_id, idx + 1)
webpage = self._download_webpage(
page_url, user_id,
note='Downloading page %d/%d' % (idx + 1, page_count))
video_list = self._search_regex(
r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
webpage, 'video content')
paths = re.findall(
r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
for path in paths:
yield {
'_type': 'url',
'url': compat_urlparse.urljoin(page_url, path),
}
pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
return {
'_type': 'playlist',
'id': '%s_likes' % user_id,
'title': title,
'description': description,
'entries': pl,
}
return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
class VHXEmbedIE(InfoExtractor):

View File

@ -32,6 +32,10 @@ class VzaarIE(InfoExtractor):
'ext': 'mp3',
'title': 'MP3',
},
}, {
# with null videoTitle
'url': 'https://view.vzaar.com/20313539/download',
'only_matching': True,
}]
@staticmethod
@ -45,7 +49,7 @@ class VzaarIE(InfoExtractor):
video_data = self._download_json(
'http://view.vzaar.com/v2/%s/video' % video_id, video_id)
title = video_data['videoTitle']
title = video_data.get('videoTitle') or video_id
formats = []

View File

@ -7,7 +7,7 @@ from ..utils import int_or_none
class XiamiBaseIE(InfoExtractor):
_API_BASE_URL = 'http://www.xiami.com/song/playlist/cat/json/id'
_API_BASE_URL = 'https://emumo.xiami.com/song/playlist/cat/json/id'
def _download_webpage_handle(self, *args, **kwargs):
webpage = super(XiamiBaseIE, self)._download_webpage_handle(*args, **kwargs)

View File

@ -37,7 +37,7 @@ class YourPornIE(InfoExtractor):
self._search_regex(
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
group='data'),
video_id)[video_id]).replace('/cdn/', '/cdn4/')
video_id)[video_id]).replace('/cdn/', '/cdn5/')
title = (self._search_regex(
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',

View File

@ -500,6 +500,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# RTMP (unnamed)
'_rtmp': {'protocol': 'rtmp'},
# av01 video only formats sometimes served with "unknown" codecs
'394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
'395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
'396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
'397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
}
_SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
@ -1306,11 +1312,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _parse_sig_js(self, jscode):
funcname = self._search_regex(
(r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
(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'(?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$]+)\(',
r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
jscode, 'Initial JS player signature function name', group='sig')
jsi = JSInterpreter(jscode)
@ -1575,8 +1588,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return video_id
def _extract_annotations(self, video_id):
url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
return self._download_webpage(
'https://www.youtube.com/annotations_invideo', video_id,
note='Downloading annotations',
errnote='Unable to download video annotations', fatal=False,
query={
'features': 1,
'legacy': 1,
'video_id': video_id,
})
@staticmethod
def _extract_chapters(description, duration):

File diff suppressed because it is too large Load Diff

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2019.06.08'
__version__ = '2019.07.02'