yt-dlp/yt_dlp/extractor/cbs.py

231 lines
9.6 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
from .common import InfoExtractor
from .theplatform import ThePlatformFeedIE
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
from ..utils import (
ExtractorError,
2016-04-01 06:33:37 +00:00
int_or_none,
find_xpath_attr,
xpath_element,
xpath_text,
update_url_query,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
)
2013-12-16 02:53:43 +00:00
class CBSBaseIE(ThePlatformFeedIE):
2016-04-01 09:12:29 +00:00
def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
2019-04-13 16:00:24 +00:00
subtitles = {}
for k, ext in [('sMPTE-TTCCURL', 'tt'), ('ClosedCaptionURL', 'ttml'), ('webVTTCaptionURL', 'vtt')]:
cc_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', k)
if cc_e is not None:
cc_url = cc_e.get('value')
if cc_url:
subtitles.setdefault(subtitles_lang, []).append({
'ext': ext,
'url': cc_url,
})
return subtitles
2016-04-01 09:12:29 +00:00
class CBSIE(CBSBaseIE):
_VALID_URL = r'''(?x)
(?:
cbs:|
https?://(?:www\.)?(?:
(?:cbs|paramountplus)\.com/(?:shows/[^/]+/video|movies/[^/]+)/|
colbertlateshow\.com/(?:video|podcasts)/)
)(?P<id>[\w-]+)'''
2013-12-16 02:53:43 +00:00
_TESTS = [{
'url': 'https://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
'info_dict': {
2016-04-01 06:33:37 +00:00
'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
'ext': 'mp4',
'title': 'Connect Chat feat. Garth Brooks',
'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
'duration': 1495,
'timestamp': 1385585425,
'upload_date': '20131127',
'uploader': 'CBSI-NEW',
2013-12-16 02:53:43 +00:00
},
'params': {
# m3u8 download
'skip_download': True,
},
'_skip': 'Blocked outside the US',
}, {
'url': 'https://www.paramountplus.com/shows/catdog/video/Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k/catdog-climb-every-catdog-the-canine-mutiny/',
'info_dict': {
'id': 'Oe44g5_NrlgiZE3aQVONleD6vXc8kP0k',
'ext': 'mp4',
'title': 'CatDog - Climb Every CatDog/The Canine Mutiny',
'description': 'md5:7ac835000645a69933df226940e3c859',
'duration': 1418,
'timestamp': 920264400,
'upload_date': '19990301',
'uploader': 'CBSI-NEW',
},
'params': {
'skip_download': 'm3u8',
},
'_skip': 'Blocked outside the US',
}, {
'url': 'https://www.paramountplus.com/shows/tooning-out-the-news/video/6hSWYWRrR9EUTz7IEe5fJKBhYvSUfexd/7-23-21-week-in-review-rep-jahana-hayes-howard-fineman-sen-michael-bennet-sheera-frenkel-cecilia-kang-/',
'info_dict': {
'id': '6hSWYWRrR9EUTz7IEe5fJKBhYvSUfexd',
'ext': 'mp4',
'title': '7/23/21 WEEK IN REVIEW (Rep. Jahana Hayes/Howard Fineman/Sen. Michael Bennet/Sheera Frenkel & Cecilia Kang)',
'description': 'md5:f4adcea3e8b106192022e121f1565bae',
'duration': 2506,
'timestamp': 1627063200,
'upload_date': '20210723',
'uploader': 'CBSI-NEW',
},
'params': {
'skip_download': 'm3u8',
},
'_skip': 'Blocked outside the US',
}, {
'url': 'https://www.cbs.com/shows/the-late-show-with-stephen-colbert/video/60icOhMb9NcjbcWnF_gub9XXHdeBcNk2/the-late-show-6-23-21-christine-baranski-joy-oladokun-',
'info_dict': {
'id': '60icOhMb9NcjbcWnF_gub9XXHdeBcNk2',
'title': 'The Late Show - 6/23/21 (Christine Baranski, Joy Oladokun)',
'timestamp': 1624507140,
'description': 'md5:e01af24e95c74d55e8775aef86117b95',
'uploader': 'CBSI-NEW',
'upload_date': '20210624',
},
'params': {
'ignore_no_formats_error': True,
'skip_download': True,
},
'expected_warnings': [
'This content expired on', 'No video formats found', 'Requested format is not available'],
}, {
'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
'only_matching': True,
}, {
2015-06-09 15:39:45 +00:00
'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
'only_matching': True,
}, {
'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/',
'only_matching': True,
}, {
'url': 'https://www.paramountplus.com/movies/million-dollar-american-princesses-meghan-and-harry/C0LpgNwXYeB8txxycdWdR9TjxpJOsdCq',
'only_matching': True,
}]
def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
items_data = self._download_xml(
'https://can.cbs.com/thunder/player/videoPlayerService.php',
content_id, query={'partner': site, 'contentId': content_id})
video_data = xpath_element(items_data, './/item')
title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
tp_release_url = 'https://link.theplatform.com/s/' + tp_path
asset_types = []
subtitles = {}
formats = []
useXMLmetadata = True
last_e = None
for item in items_data.findall('.//item'):
asset_type = xpath_text(item, 'assetType')
query = {
'mbr': 'true',
'assetTypes': asset_type,
}
if not asset_type:
# fallback for content_ids that videoPlayerService doesn't return anything for
useXMLmetadata = False
asset_type = 'fallback'
query['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3'
del query['assetTypes']
elif asset_type in asset_types:
continue
elif any(excluded in asset_type for excluded in ('HLS_FPS', 'DASH_CENC', 'OnceURL')):
continue
asset_types.append(asset_type)
if asset_type.startswith('HLS') or 'StreamPack' in asset_type:
query['formats'] = 'MPEG4,M3U'
elif asset_type in ('RTMP', 'WIFI', '3G'):
query['formats'] = 'MPEG4,FLV'
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query(tp_release_url, query), content_id,
'Downloading %s SMIL data' % asset_type)
except ExtractorError as e:
last_e = e
if useXMLmetadata:
continue
query['formats'] = '' # blank query to check if expired
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query(tp_release_url, query), content_id,
'Downloading %s SMIL data, trying again with another format' % asset_type)
except ExtractorError as e:
last_e = e
continue
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
if last_e and not formats:
self.raise_no_formats(last_e, True, content_id)
self._sort_formats(formats)
info = self._extract_theplatform_metadata(tp_path, content_id)
info.update({
'formats': formats,
'subtitles': subtitles,
'id': content_id
})
if useXMLmetadata:
info.update({
'title': title,
'series': xpath_text(video_data, 'seriesTitle'),
'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
'thumbnail': xpath_text(video_data, 'previewImageURL')
})
return info
2016-04-01 06:33:37 +00:00
2013-12-16 02:53:43 +00:00
def _real_extract(self, url):
content_id = self._match_id(url)
return self._extract_video_info(content_id)
class ParamountPlusSeriesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?paramountplus\.com/shows/(?P<id>[a-zA-Z0-9-_]+)/?(?:[#?]|$)'
_TESTS = [{
'url': 'https://www.paramountplus.com/shows/drake-josh',
'playlist_mincount': 50,
'info_dict': {
'id': 'drake-josh',
}
}, {
'url': 'https://www.paramountplus.com/shows/hawaii_five_0/',
'playlist_mincount': 240,
'info_dict': {
'id': 'hawaii_five_0',
}
}, {
'url': 'https://www.paramountplus.com/shows/spongebob-squarepants/',
'playlist_mincount': 248,
'info_dict': {
'id': 'spongebob-squarepants',
}
}]
_API_URL = 'https://www.paramountplus.com/shows/{}/xhr/episodes/page/0/size/100000/xs/0/season/0/'
def _entries(self, show_name):
show_json = self._download_json(self._API_URL.format(show_name), video_id=show_name)
if show_json.get('success'):
for episode in show_json['result']['data']:
yield self.url_result(
'https://www.paramountplus.com%s' % episode['url'],
ie=CBSIE.ie_key(), video_id=episode['content_id'])
def _real_extract(self, url):
show_name = self._match_id(url)
return self.playlist_result(self._entries(show_name), playlist_id=show_name)