yt_dlp/extractor/viewlift.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_HTTPError
   8 from ..utils import (
   9     ExtractorError,
  10     int_or_none,
  11     parse_age_limit,
  12     traverse_obj,
  13 )
  14
  15
  16 class ViewLiftBaseIE(InfoExtractor):
  17     _API_BASE = 'https://prod-api.viewlift.com/'
  18     _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm|failarmy|ftfnext|lnppass\.legapallacanestro|moviespree|app\.myoutdoortv|neoufitness|pflmma|theidentitytb)\.com|(?:hoichoi|app\.horseandcountry|kronon|marquee|supercrosslive)\.tv'
  19     _SITE_MAP = {
  20         'ftfnext': 'lax',
  21         'funnyforfree': 'snagfilms',
  22         'hoichoi': 'hoichoitv',
  23         'kiddovid': 'snagfilms',
  24         'laxsportsnetwork': 'lax',
  25         'legapallacanestro': 'lnp',
  26         'marquee': 'marquee-tv',
  27         'monumentalsportsnetwork': 'monumental-network',
  28         'moviespree': 'bingeflix',
  29         'pflmma': 'pfl',
  30         'snagxtreme': 'snagfilms',
  31         'theidentitytb': 'tampabay',
  32         'vayafilm': 'snagfilms',
  33     }
  34     _TOKENS = {}
  35
  36     def _fetch_token(self, site, url):
  37         if self._TOKENS.get(site):
  38             return
  39         email, password = self._get_login_info(netrc_machine=site)
  40         if email:
  41             self.report_warning('Logging in using username and password is broken. %s' % self._LOGIN_HINTS['cookies'])
  42
  43         cookies = self._get_cookies(url)
  44         if cookies and cookies.get('token'):
  45             self._TOKENS[site] = self._search_regex(r'22authorizationToken\%22:\%22([^\%]+)\%22', cookies['token'].value, 'token')
  46         if not self._TOKENS.get(site):
  47             self.raise_login_required('Cookies (not necessarily logged in) are needed to download from this website', method='cookies')
  48
  49     def _call_api(self, site, path, video_id, url, query):
  50         self._fetch_token(site, url)
  51         try:
  52             return self._download_json(
  53                 self._API_BASE + path, video_id, headers={'Authorization': self._TOKENS.get(site)}, query=query)
  54         except ExtractorError as e:
  55             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
  56                 webpage = e.cause.read().decode()
  57                 try:
  58                     error_message = traverse_obj(json.loads(webpage), 'errorMessage', 'message')
  59                 except json.JSONDecodeError:
  60                     raise ExtractorError(f'{site} said: {webpage}', cause=e.cause)
  61                 if error_message:
  62                     if 'has not purchased' in error_message:
  63                         self.raise_login_required(method='cookies')
  64                     raise ExtractorError(error_message, expected=True)
  65             raise
  66
  67
  68 class ViewLiftEmbedIE(ViewLiftBaseIE):
  69     IE_NAME = 'viewlift:embed'
  70     _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?P<domain>%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX
  71     _TESTS = [{
  72         'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
  73         'md5': '2924e9215c6eff7a55ed35b72276bd93',
  74         'info_dict': {
  75             'id': '74849a00-85a9-11e1-9660-123139220831',
  76             'ext': 'mp4',
  77             'title': '#whilewewatch',
  78             'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8',
  79             'timestamp': 1334350096,
  80             'upload_date': '20120413',
  81         }
  82     }, {
  83         # invalid labels, 360p is better that 480p
  84         'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
  85         'md5': '882fca19b9eb27ef865efeeaed376a48',
  86         'info_dict': {
  87             'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
  88             'ext': 'mp4',
  89             'title': 'Life in Limbo',
  90         },
  91         'skip': 'The video does not exist',
  92     }, {
  93         'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
  94         'only_matching': True,
  95     }]
  96
  97     @staticmethod
  98     def _extract_url(webpage):
  99         mobj = re.search(
 100             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?(?:%s)/embed/player.+?)\1' % ViewLiftBaseIE._DOMAINS_REGEX,
 101             webpage)
 102         if mobj:
 103             return mobj.group('url')
 104
 105     def _real_extract(self, url):
 106         domain, film_id = self._match_valid_url(url).groups()
 107         site = domain.split('.')[-2]
 108         if site in self._SITE_MAP:
 109             site = self._SITE_MAP[site]
 110
 111         content_data = self._call_api(
 112             site, 'entitlement/video/status', film_id, url, {
 113                 'id': film_id
 114             })['video']
 115         gist = content_data['gist']
 116         title = gist['title']
 117         video_assets = content_data['streamingInfo']['videoAssets']
 118
 119         hls_url = video_assets.get('hls')
 120         formats, subtitles = [], {}
 121         if hls_url:
 122             formats, subtitles = self._extract_m3u8_formats_and_subtitles(
 123                 hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
 124
 125         for video_asset in video_assets.get('mpeg') or []:
 126             video_asset_url = video_asset.get('url')
 127             if not video_asset_url:
 128                 continue
 129             bitrate = int_or_none(video_asset.get('bitrate'))
 130             height = int_or_none(self._search_regex(
 131                 r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
 132                 'height', default=None))
 133             formats.append({
 134                 'url': video_asset_url,
 135                 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
 136                 'tbr': bitrate,
 137                 'height': height,
 138                 'vcodec': video_asset.get('codec'),
 139             })
 140
 141         subs = {}
 142         for sub in traverse_obj(content_data, ('contentDetails', 'closedCaptions')) or []:
 143             sub_url = sub.get('url')
 144             if not sub_url:
 145                 continue
 146             subs.setdefault(sub.get('language', 'English'), []).append({
 147                 'url': sub_url,
 148             })
 149
 150         self._sort_formats(formats)
 151         return {
 152             'id': film_id,
 153             'title': title,
 154             'description': gist.get('description'),
 155             'thumbnail': gist.get('videoImageUrl'),
 156             'duration': int_or_none(gist.get('runtime')),
 157             'age_limit': parse_age_limit(content_data.get('parentalRating')),
 158             'timestamp': int_or_none(gist.get('publishDate'), 1000),
 159             'formats': formats,
 160             'subtitles': self._merge_subtitles(subs, subtitles),
 161             'categories': traverse_obj(content_data, ('categories', ..., 'title')),
 162             'tags': traverse_obj(content_data, ('tags', ..., 'title')),
 163         }
 164
 165
 166 class ViewLiftIE(ViewLiftBaseIE):
 167     IE_NAME = 'viewlift'
 168     _API_BASE = 'https://prod-api-cached-2.viewlift.com/'
 169     _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX
 170     _TESTS = [{
 171         'url': 'http://www.snagfilms.com/films/title/lost_for_life',
 172         'md5': '19844f897b35af219773fd63bdec2942',
 173         'info_dict': {
 174             'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
 175             'display_id': 'lost_for_life',
 176             'ext': 'mp4',
 177             'title': 'Lost for Life',
 178             'description': 'md5:ea10b5a50405ae1f7b5269a6ec594102',
 179             'thumbnail': r're:^https?://.*\.jpg',
 180             'duration': 4489,
 181             'categories': 'mincount:3',
 182             'age_limit': 14,
 183             'upload_date': '20150421',
 184             'timestamp': 1429656820,
 185         }
 186     }, {
 187         'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
 188         'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
 189         'info_dict': {
 190             'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
 191             'display_id': 'the_world_cut_project/india',
 192             'ext': 'mp4',
 193             'title': 'India',
 194             'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
 195             'thumbnail': r're:^https?://.*\.jpg',
 196             'duration': 979,
 197             'timestamp': 1399478279,
 198             'upload_date': '20140507',
 199         }
 200     }, {
 201         'url': 'http://main.snagfilms.com/augie_alone/s_2_ep_12_love',
 202         'info_dict': {
 203             'id': '00000148-7b53-de26-a9fb-fbf306f70020',
 204             'display_id': 'augie_alone/s_2_ep_12_love',
 205             'ext': 'mp4',
 206             'title': 'S. 2 Ep. 12 - Love',
 207             'description': 'Augie finds love.',
 208             'thumbnail': r're:^https?://.*\.jpg',
 209             'duration': 107,
 210             'upload_date': '20141012',
 211             'timestamp': 1413129540,
 212             'age_limit': 17,
 213         },
 214         'params': {
 215             'skip_download': True,
 216         },
 217     }, {
 218         'url': 'http://main.snagfilms.com/films/title/the_freebie',
 219         'only_matching': True,
 220     }, {
 221         # Film is not playable in your area.
 222         'url': 'http://www.snagfilms.com/films/title/inside_mecca',
 223         'only_matching': True,
 224     }, {
 225         # Film is not available.
 226         'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
 227         'only_matching': True,
 228     }, {
 229         'url': 'http://www.winnersview.com/videos/the-good-son',
 230         'only_matching': True,
 231     }, {
 232         # Was once Kaltura embed
 233         'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
 234         'only_matching': True,
 235     }, {
 236         'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters',
 237         'only_matching': True,
 238     }, {  # Free film with langauge code
 239         'url': 'https://www.hoichoi.tv/bn/films/title/shuyopoka',
 240         'info_dict': {
 241             'id': '7a7a9d33-1f4c-4771-9173-ee4fb6dbf196',
 242             'ext': 'mp4',
 243             'title': 'Shuyopoka',
 244             'description': 'md5:e28f2fb8680096a69c944d37c1fa5ffc',
 245             'thumbnail': r're:^https?://.*\.jpg$',
 246             'upload_date': '20211006',
 247             'series': None
 248         },
 249         'params': {'skip_download': True},
 250     }, {  # Free film
 251         'url': 'https://www.hoichoi.tv/films/title/dadu-no1',
 252         'info_dict': {
 253             'id': '0000015b-b009-d126-a1db-b81ff3780000',
 254             'ext': 'mp4',
 255             'title': 'Dadu No.1',
 256             'description': 'md5:605cba408e51a79dafcb824bdeded51e',
 257             'thumbnail': r're:^https?://.*\.jpg$',
 258             'upload_date': '20210827',
 259             'series': None
 260         },
 261         'params': {'skip_download': True},
 262     }, {  # Free episode
 263         'url': 'https://www.hoichoi.tv/webseries/case-jaundice-s01-e01',
 264         'info_dict': {
 265             'id': 'f779e07c-30c8-459c-8612-5a834ab5e5ba',
 266             'ext': 'mp4',
 267             'title': 'Humans Vs. Corona',
 268             'description': 'md5:ca30a682b4528d02a3eb6d0427dd0f87',
 269             'thumbnail': r're:^https?://.*\.jpg$',
 270             'upload_date': '20210830',
 271             'series': 'Case Jaundice'
 272         },
 273         'params': {'skip_download': True},
 274     }, {  # Free video
 275         'url': 'https://www.hoichoi.tv/videos/1549072415320-six-episode-02-hindi',
 276         'info_dict': {
 277             'id': 'b41fa1ce-aca6-47b6-b208-283ff0a2de30',
 278             'ext': 'mp4',
 279             'title': 'Woman in red - Hindi',
 280             'description': 'md5:9d21edc1827d32f8633eb67c2054fc31',
 281             'thumbnail': r're:^https?://.*\.jpg$',
 282             'upload_date': '20211006',
 283             'series': 'Six (Hindi)'
 284         },
 285         'params': {'skip_download': True},
 286     }, {  # Free episode
 287         'url': 'https://www.hoichoi.tv/shows/watch-asian-paints-moner-thikana-online-season-1-episode-1',
 288         'info_dict': {
 289             'id': '1f45d185-8500-455c-b88d-13252307c3eb',
 290             'ext': 'mp4',
 291             'title': 'Jisshu Sengupta',
 292             'description': 'md5:ef6ffae01a3d83438597367400f824ed',
 293             'thumbnail': r're:^https?://.*\.jpg$',
 294             'upload_date': '20211004',
 295             'series': 'Asian Paints Moner Thikana'
 296         },
 297         'params': {'skip_download': True},
 298     }, {  # Free series
 299         'url': 'https://www.hoichoi.tv/shows/watch-moner-thikana-bengali-web-series-online',
 300         'playlist_mincount': 5,
 301         'info_dict': {
 302             'id': 'watch-moner-thikana-bengali-web-series-online',
 303         },
 304     }, {  # Premium series
 305         'url': 'https://www.hoichoi.tv/shows/watch-byomkesh-bengali-web-series-online',
 306         'playlist_mincount': 14,
 307         'info_dict': {
 308             'id': 'watch-byomkesh-bengali-web-series-online',
 309         },
 310     }, {  # Premium movie
 311         'url': 'https://www.hoichoi.tv/movies/detective-2020',
 312         'only_matching': True
 313     }]
 314
 315     @classmethod
 316     def suitable(cls, url):
 317         return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
 318
 319     def _show_entries(self, domain, seasons):
 320         for season in seasons:
 321             for episode in season.get('episodes') or []:
 322                 path = traverse_obj(episode, ('gist', 'permalink'))
 323                 if path:
 324                     yield self.url_result(f'https://www.{domain}{path}', ie=self.ie_key())
 325
 326     def _real_extract(self, url):
 327         domain, path, display_id = self._match_valid_url(url).groups()
 328         site = domain.split('.')[-2]
 329         if site in self._SITE_MAP:
 330             site = self._SITE_MAP[site]
 331         modules = self._call_api(
 332             site, 'content/pages', display_id, url, {
 333                 'includeContent': 'true',
 334                 'moduleOffset': 1,
 335                 'path': path,
 336                 'site': site,
 337             })['modules']
 338
 339         seasons = next((m['contentData'][0]['seasons'] for m in modules if m.get('moduleType') == 'ShowDetailModule'), None)
 340         if seasons:
 341             return self.playlist_result(self._show_entries(domain, seasons), display_id)
 342
 343         film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule')
 344         return {
 345             '_type': 'url_transparent',
 346             'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
 347             'id': film_id,
 348             'display_id': display_id,
 349             'ie_key': 'ViewLiftEmbed',
 350         }