yt-dlp/yt_dlp/extractor/tubitv.py

169 lines
6.5 KiB
Python
Raw Normal View History

import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
js_to_json,
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 11:18:17 -05:00
sanitized_Request,
urlencode_postdata,
traverse_obj,
)
class TubiTvIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
tubitv:|
https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows)/
)
(?P<id>[0-9]+)'''
_LOGIN_URL = 'http://tubitv.com/login'
_NETRC_MACHINE = 'tubitv'
2017-02-24 06:27:56 -05:00
_GEO_COUNTRIES = ['US']
_TESTS = [{
'url': 'https://tubitv.com/movies/383676/tracker',
'md5': '566fa0f76870302d11af0de89511d3f0',
'info_dict': {
'id': '383676',
'ext': 'mp4',
'title': 'Tracker',
'description': 'md5:ff320baf43d0ad2655e538c1d5cd9706',
'uploader_id': 'f866e2677ea2f0dff719788e4f7f9195',
'release_year': 2010,
'thumbnail': r're:^https?://.+\.(jpe?g|png)$',
'duration': 6122,
},
}, {
2016-04-21 15:29:42 -04:00
'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
2016-11-03 04:04:20 -04:00
'md5': '43ac06be9326f41912dc64ccf7a80320',
'info_dict': {
2016-04-21 15:29:42 -04:00
'id': '283829',
'ext': 'mp4',
2016-04-21 15:29:42 -04:00
'title': 'The Comedian at The Friday',
'description': 'A stand up comedian is forced to look at the decisions in his life while on a one week trip to the west coast.',
2016-11-03 04:04:20 -04:00
'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434',
},
'skip': 'Content Unavailable'
}, {
'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories',
'only_matching': True,
2021-01-01 07:26:37 -05:00
}, {
'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
'info_dict': {
'id': '560057',
'ext': 'mp4',
'title': 'Penitentiary',
'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
'release_year': 1979,
},
'skip': 'Content Unavailable'
}]
# DRM formats are included only to raise appropriate error
_UNPLAYABLE_FORMATS = ('hlsv6_widevine', 'hlsv6_widevine_nonclearlead', 'hlsv6_playready_psshv0',
'hlsv6_fairplay', 'dash_widevine', 'dash_widevine_nonclearlead')
def _perform_login(self, username, password):
self.report_login()
form_data = {
'username': username,
'password': password,
}
payload = urlencode_postdata(form_data)
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 11:18:17 -05:00
request = sanitized_Request(self._LOGIN_URL, payload)
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
login_page = self._download_webpage(
request, None, False, 'Wrong login info')
if not re.search(r'id="tubi-logout"', login_page):
raise ExtractorError(
'Login failed (invalid username/password)', expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(f'https://tubitv.com/oz/videos/{video_id}/content', video_id, query={
'video_resources': ['dash', 'hlsv3', 'hlsv6', *self._UNPLAYABLE_FORMATS],
})
2016-11-03 04:04:20 -04:00
title = video_data['title']
formats = []
drm_formats = False
for resource in video_data['video_resources']:
if resource['type'] in ('dash', ):
formats += self._extract_mpd_formats(resource['manifest']['url'], video_id, mpd_id=resource['type'], fatal=False)
elif resource['type'] in ('hlsv3', 'hlsv6'):
formats += self._extract_m3u8_formats(resource['manifest']['url'], video_id, 'mp4', m3u8_id=resource['type'], fatal=False)
elif resource['type'] in self._UNPLAYABLE_FORMATS:
drm_formats = True
if not formats and drm_formats:
self.report_drm(video_id)
elif not formats and not video_data.get('policy_match'): # policy_match is False if content was removed
raise ExtractorError('This content is currently unavailable', expected=True)
2016-11-03 04:04:20 -04:00
thumbnails = []
for thumbnail_url in video_data.get('thumbnails', []):
if not thumbnail_url:
continue
thumbnails.append({
'url': self._proto_relative_url(thumbnail_url),
})
2016-04-21 15:29:42 -04:00
subtitles = {}
2016-11-03 04:04:20 -04:00
for sub in video_data.get('subtitles', []):
sub_url = sub.get('url')
2016-04-21 15:29:42 -04:00
if not sub_url:
continue
2016-11-03 04:04:20 -04:00
subtitles.setdefault(sub.get('lang', 'English'), []).append({
'url': self._proto_relative_url(sub_url),
2016-04-21 15:29:42 -04:00
})
season_number, episode_number, episode_title = self._search_regex(
r'^S(\d+):E(\d+) - (.+)', title, 'episode info', fatal=False, group=(1, 2, 3), default=(None, None, None))
return {
'id': video_id,
'title': title,
'formats': formats,
2016-04-21 15:29:42 -04:00
'subtitles': subtitles,
2016-11-03 04:04:20 -04:00
'thumbnails': thumbnails,
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'uploader_id': video_data.get('publisher_id'),
2021-01-01 07:26:37 -05:00
'release_year': int_or_none(video_data.get('year')),
'season_number': int_or_none(season_number),
'episode_number': int_or_none(episode_number),
'episode_title': episode_title
}
class TubiTvShowIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/[0-9]+/(?P<show_name>[^/?#]+)'
_TESTS = [{
'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true',
'playlist_mincount': 390,
'info_dict': {
'id': 'the-joy-of-painting-with-bob-ross',
}
}]
def _entries(self, show_url, show_name):
show_webpage = self._download_webpage(show_url, show_name)
show_json = self._parse_json(self._search_regex(
r'window\.__data\s*=\s*({[^<]+});\s*</script>',
show_webpage, 'data'), show_name, transform_source=js_to_json)['video']
for episode_id in show_json['fullContentById'].keys():
if traverse_obj(show_json, ('byId', episode_id, 'type')) == 's':
continue
yield self.url_result(
'tubitv:%s' % episode_id,
ie=TubiTvIE.ie_key(), video_id=episode_id)
def _real_extract(self, url):
show_name = self._match_valid_url(url).group('show_name')
return self.playlist_result(self._entries(url, show_name), playlist_id=show_name)