[comedycentral] fix extraction(closes #27905)

This commit is contained in:
Remita Amine 2021-01-21 23:53:09 +01:00
parent 3bb7769c40
commit fa8f6d8580
4 changed files with 37 additions and 145 deletions

View File

@ -1,142 +1,51 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor from .mtv import MTVServicesInfoExtractor
from .common import InfoExtractor
class ComedyCentralIE(MTVServicesInfoExtractor): class ComedyCentralIE(MTVServicesInfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ _VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})'
(video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
/(?P<title>.*)'''
_FEED_URL = 'http://comedycentral.com/feeds/mrss/' _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
_TESTS = [{ _TESTS = [{
'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', 'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
'md5': 'c4f48e9eda1b16dd10add0744344b6d8', 'md5': 'b8acb347177c680ff18a292aa2166f80',
'info_dict': { 'info_dict': {
'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', 'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
'ext': 'mp4', 'ext': 'mp4',
'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother', 'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike',
'description': 'After a certain point, breastfeeding becomes c**kblocking.', 'description': 'md5:5334307c433892b85f4f5e5ac9ef7498',
'timestamp': 1376798400, 'timestamp': 1598670000,
'upload_date': '20130818', 'upload_date': '20200829',
}, },
}, { }, {
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview', 'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
'only_matching': True, 'only_matching': True,
}]
class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
(?:full-episodes|shows(?=/[^/]+/full-episodes))
/(?P<id>[^?]+)'''
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
_TESTS = [{
'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
'info_dict': {
'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
'title': 'November 28, 2016 - Ryan Speedo Green',
},
'playlist_count': 4,
}, { }, {
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', 'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1')
videos_info = self._get_videos_info(mgid)
return videos_info
class ToshIE(MTVServicesInfoExtractor):
IE_DESC = 'Tosh.0'
_VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
_FEED_URL = 'http://tosh.cc.com/feeds/mrss'
_TESTS = [{
'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
'info_dict': {
'description': 'Tosh asked fans to share their summer plans.',
'title': 'Twitter Users Share Summer Plans',
},
'playlist': [{
'md5': 'f269e88114c1805bb6d7653fecea9e06',
'info_dict': {
'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
'ext': 'mp4',
'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
'description': 'Tosh asked fans to share their summer plans.',
'thumbnail': r're:^https?://.*\.jpg',
# It's really reported to be published on year 2077
'upload_date': '20770610',
'timestamp': 3390510600,
'subtitles': {
'en': 'mincount:3',
},
},
}]
}, {
'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
'only_matching': True, 'only_matching': True,
}] }]
class ComedyCentralTVIE(MTVServicesInfoExtractor): class ComedyCentralTVIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/folgen/(?P<id>[0-9a-z]{6})'
_TESTS = [{ _TESTS = [{
'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4', 'url': 'https://www.comedycentral.tv/folgen/pxdpec/josh-investigates-klimawandel-staffel-1-ep-1',
'info_dict': { 'info_dict': {
'id': 'local_playlist-f99b626bdfe13568579a', 'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285',
'ext': 'flv', 'ext': 'mp4',
'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1', 'title': 'Josh Investigates',
'description': 'Steht uns das Ende der Welt bevor?',
}, },
'params': {
# rtmp download
'skip_download': True,
},
}, {
'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
'only_matching': True,
}, {
'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
'only_matching': True,
}] }]
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
_GEO_COUNTRIES = ['DE']
def _real_extract(self, url): def _get_feed_query(self, uri):
video_id = self._match_id(url) return {
'accountOverride': 'intl.mtvi.com',
webpage = self._download_webpage(url, video_id) 'arcEp': 'web.cc.tv',
'ep': 'b9032c3a',
mrss_url = self._search_regex( 'imageEp': 'web.cc.tv',
r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1', 'mgid': uri,
webpage, 'mrss url', group='url')
return self._get_videos_info_from_url(mrss_url, video_id)
class ComedyCentralShortnameIE(InfoExtractor):
_VALID_URL = r'^:(?P<id>tds|thedailyshow|theopposition)$'
_TESTS = [{
'url': ':tds',
'only_matching': True,
}, {
'url': ':thedailyshow',
'only_matching': True,
}, {
'url': ':theopposition',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
shortcut_map = {
'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
'theopposition': 'http://www.cc.com/shows/the-opposition-with-jordan-klepper/full-episodes',
} }
return self.url_result(shortcut_map[video_id])

View File

@ -235,11 +235,8 @@ from .cnn import (
) )
from .coub import CoubIE from .coub import CoubIE
from .comedycentral import ( from .comedycentral import (
ComedyCentralFullEpisodesIE,
ComedyCentralIE, ComedyCentralIE,
ComedyCentralShortnameIE,
ComedyCentralTVIE, ComedyCentralTVIE,
ToshIE,
) )
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .commonprotocols import ( from .commonprotocols import (

View File

@ -253,6 +253,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
return try_get(feed, lambda x: x['result']['data']['id'], compat_str) return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
@staticmethod
def _extract_child_with_type(parent, t):
return next(c for c in parent['children'] if c.get('type') == t)
def _extract_mgid(self, webpage): def _extract_mgid(self, webpage):
try: try:
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
@ -278,6 +282,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
if not mgid: if not mgid:
mgid = self._extract_triforce_mgid(webpage) mgid = self._extract_triforce_mgid(webpage)
if not mgid:
data = self._parse_json(self._search_regex(
r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
main_container = self._extract_child_with_type(data, 'MainContainer')
video_player = self._extract_child_with_type(main_container, 'VideoPlayer')
mgid = video_player['props']['media']['video']['config']['uri']
return mgid return mgid
def _real_extract(self, url): def _real_extract(self, url):
@ -349,18 +360,6 @@ class MTVIE(MTVServicesInfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
@staticmethod
def extract_child_with_type(parent, t):
children = parent['children']
return next(c for c in children if c.get('type') == t)
def _extract_mgid(self, webpage):
data = self._parse_json(self._search_regex(
r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
main_container = self.extract_child_with_type(data, 'MainContainer')
video_player = self.extract_child_with_type(main_container, 'VideoPlayer')
return video_player['props']['media']['video']['config']['uri']
class MTVJapanIE(MTVServicesInfoExtractor): class MTVJapanIE(MTVServicesInfoExtractor):
IE_NAME = 'mtvjapan' IE_NAME = 'mtvjapan'

View File

@ -20,9 +20,6 @@ class BellatorIE(MTVServicesInfoExtractor):
_FEED_URL = 'http://www.bellator.com/feeds/mrss/' _FEED_URL = 'http://www.bellator.com/feeds/mrss/'
_GEO_COUNTRIES = ['US'] _GEO_COUNTRIES = ['US']
def _extract_mgid(self, webpage):
return self._extract_triforce_mgid(webpage)
class ParamountNetworkIE(MTVServicesInfoExtractor): class ParamountNetworkIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)' _VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)'
@ -46,16 +43,6 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
def _get_feed_query(self, uri): def _get_feed_query(self, uri):
return { return {
'arcEp': 'paramountnetwork.com', 'arcEp': 'paramountnetwork.com',
'imageEp': 'paramountnetwork.com',
'mgid': uri, 'mgid': uri,
} }
def _extract_mgid(self, webpage):
root_data = self._parse_json(self._search_regex(
r'window\.__DATA__\s*=\s*({.+})',
webpage, 'data'), None)
def find_sub_data(data, data_type):
return next(c for c in data['children'] if c.get('type') == data_type)
c = find_sub_data(find_sub_data(root_data, 'MainContainer'), 'VideoPlayer')
return c['props']['media']['video']['config']['uri']