yt_dlp/extractor/viewlift.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..networking.exceptions import HTTPError
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     parse_age_limit,
   9     traverse_obj,
  10 )
  11
  12
  13 class ViewLiftBaseIE(InfoExtractor):
  14     _API_BASE = 'https://prod-api.viewlift.com/'
  15     _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm|failarmy|ftfnext|lnppass\.legapallacanestro|moviespree|app\.myoutdoortv|neoufitness|pflmma|theidentitytb|chorki)\.com|(?:hoichoi|app\.horseandcountry|kronon|marquee|supercrosslive)\.tv'
  16     _SITE_MAP = {
  17         'ftfnext': 'lax',
  18         'funnyforfree': 'snagfilms',
  19         'hoichoi': 'hoichoitv',
  20         'kiddovid': 'snagfilms',
  21         'laxsportsnetwork': 'lax',
  22         'legapallacanestro': 'lnp',
  23         'marquee': 'marquee-tv',
  24         'monumentalsportsnetwork': 'monumental-network',
  25         'moviespree': 'bingeflix',
  26         'pflmma': 'pfl',
  27         'snagxtreme': 'snagfilms',
  28         'theidentitytb': 'tampabay',
  29         'vayafilm': 'snagfilms',
  30         'chorki': 'prothomalo',
  31     }
  32     _TOKENS = {}
  33
  34     def _fetch_token(self, site, url):
  35         if self._TOKENS.get(site):
  36             return
  37
  38         cookies = self._get_cookies(url)
  39         if cookies and cookies.get('token'):
  40             self._TOKENS[site] = self._search_regex(r'22authorizationToken\%22:\%22([^\%]+)\%22', cookies['token'].value, 'token')
  41         if not self._TOKENS.get(site):
  42             self.raise_login_required('Cookies (not necessarily logged in) are needed to download from this website', method='cookies')
  43
  44     def _call_api(self, site, path, video_id, url, query):
  45         self._fetch_token(site, url)
  46         try:
  47             return self._download_json(
  48                 self._API_BASE + path, video_id, headers={'Authorization': self._TOKENS.get(site)}, query=query)
  49         except ExtractorError as e:
  50             if isinstance(e.cause, HTTPError) and e.cause.status == 403:
  51                 webpage = e.cause.response.read().decode()
  52                 try:
  53                     error_message = traverse_obj(json.loads(webpage), 'errorMessage', 'message')
  54                 except json.JSONDecodeError:
  55                     raise ExtractorError(f'{site} said: {webpage}', cause=e.cause)
  56                 if error_message:
  57                     if 'has not purchased' in error_message:
  58                         self.raise_login_required(method='cookies')
  59                     raise ExtractorError(error_message, expected=True)
  60             raise
  61
  62
  63 class ViewLiftEmbedIE(ViewLiftBaseIE):
  64     IE_NAME = 'viewlift:embed'
  65     _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
  66     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?(?:%s)/embed/player.+?)\1' % ViewLiftBaseIE._DOMAINS_REGEX]
  67     _TESTS = [{
  68         'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
  69         'md5': '2924e9215c6eff7a55ed35b72276bd93',
  70         'info_dict': {
  71             'id': '74849a00-85a9-11e1-9660-123139220831',
  72             'ext': 'mp4',
  73             'title': '#whilewewatch',
  74             'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8',
  75             'timestamp': 1334350096,
  76             'upload_date': '20120413',
  77         }
  78     }, {
  79         # invalid labels, 360p is better that 480p
  80         'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
  81         'md5': '882fca19b9eb27ef865efeeaed376a48',
  82         'info_dict': {
  83             'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
  84             'ext': 'mp4',
  85             'title': 'Life in Limbo',
  86         },
  87         'skip': 'The video does not exist',
  88     }, {
  89         'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
  90         'only_matching': True,
  91     }]
  92
  93     def _real_extract(self, url):
  94         domain, film_id = self._match_valid_url(url).groups()
  95         site = domain.split('.')[-2]
  96         if site in self._SITE_MAP:
  97             site = self._SITE_MAP[site]
  98
  99         content_data = self._call_api(
 100             site, 'entitlement/video/status', film_id, url, {
 101                 'id': film_id
 102             })['video']
 103         gist = content_data['gist']
 104         title = gist['title']
 105         video_assets = content_data['streamingInfo']['videoAssets']
 106
 107         hls_url = video_assets.get('hls')
 108         formats, subtitles = [], {}
 109         if hls_url:
 110             formats, subtitles = self._extract_m3u8_formats_and_subtitles(
 111                 hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
 112
 113         for video_asset in video_assets.get('mpeg') or []:
 114             video_asset_url = video_asset.get('url')
 115             if not video_asset_url:
 116                 continue
 117             bitrate = int_or_none(video_asset.get('bitrate'))
 118             height = int_or_none(self._search_regex(
 119                 r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
 120                 'height', default=None))
 121             formats.append({
 122                 'url': video_asset_url,
 123                 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
 124                 'tbr': bitrate,
 125                 'height': height,
 126                 'vcodec': video_asset.get('codec'),
 127             })
 128
 129         subs = {}
 130         for sub in traverse_obj(content_data, ('contentDetails', 'closedCaptions')) or []:
 131             sub_url = sub.get('url')
 132             if not sub_url:
 133                 continue
 134             subs.setdefault(sub.get('language', 'English'), []).append({
 135                 'url': sub_url,
 136             })
 137
 138         return {
 139             'id': film_id,
 140             'title': title,
 141             'description': gist.get('description'),
 142             'thumbnail': gist.get('videoImageUrl'),
 143             'duration': int_or_none(gist.get('runtime')),
 144             'age_limit': parse_age_limit(content_data.get('parentalRating')),
 145             'timestamp': int_or_none(gist.get('publishDate'), 1000),
 146             'formats': formats,
 147             'subtitles': self._merge_subtitles(subs, subtitles),
 148             'categories': traverse_obj(content_data, ('categories', ..., 'title')),
 149             'tags': traverse_obj(content_data, ('tags', ..., 'title')),
 150         }
 151
 152
 153 class ViewLiftIE(ViewLiftBaseIE):
 154     IE_NAME = 'viewlift'
 155     _API_BASE = 'https://prod-api-cached-2.viewlift.com/'
 156     _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX
 157     _TESTS = [{
 158         'url': 'http://www.snagfilms.com/films/title/lost_for_life',
 159         'md5': '19844f897b35af219773fd63bdec2942',
 160         'info_dict': {
 161             'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
 162             'display_id': 'lost_for_life',
 163             'ext': 'mp4',
 164             'title': 'Lost for Life',
 165             'description': 'md5:ea10b5a50405ae1f7b5269a6ec594102',
 166             'thumbnail': r're:^https?://.*\.jpg',
 167             'duration': 4489,
 168             'categories': 'mincount:3',
 169             'age_limit': 14,
 170             'upload_date': '20150421',
 171             'timestamp': 1429656820,
 172         }
 173     }, {
 174         'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
 175         'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
 176         'info_dict': {
 177             'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
 178             'display_id': 'the_world_cut_project/india',
 179             'ext': 'mp4',
 180             'title': 'India',
 181             'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
 182             'thumbnail': r're:^https?://.*\.jpg',
 183             'duration': 979,
 184             'timestamp': 1399478279,
 185             'upload_date': '20140507',
 186         }
 187     }, {
 188         'url': 'http://main.snagfilms.com/augie_alone/s_2_ep_12_love',
 189         'info_dict': {
 190             'id': '00000148-7b53-de26-a9fb-fbf306f70020',
 191             'display_id': 'augie_alone/s_2_ep_12_love',
 192             'ext': 'mp4',
 193             'title': 'S. 2 Ep. 12 - Love',
 194             'description': 'Augie finds love.',
 195             'thumbnail': r're:^https?://.*\.jpg',
 196             'duration': 107,
 197             'upload_date': '20141012',
 198             'timestamp': 1413129540,
 199             'age_limit': 17,
 200         },
 201         'params': {
 202             'skip_download': True,
 203         },
 204     }, {
 205         'url': 'http://main.snagfilms.com/films/title/the_freebie',
 206         'only_matching': True,
 207     }, {
 208         # Film is not playable in your area.
 209         'url': 'http://www.snagfilms.com/films/title/inside_mecca',
 210         'only_matching': True,
 211     }, {
 212         # Film is not available.
 213         'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
 214         'only_matching': True,
 215     }, {
 216         'url': 'http://www.winnersview.com/videos/the-good-son',
 217         'only_matching': True,
 218     }, {
 219         # Was once Kaltura embed
 220         'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
 221         'only_matching': True,
 222     }, {
 223         'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters',
 224         'only_matching': True,
 225     }, {  # Free film with langauge code
 226         'url': 'https://www.hoichoi.tv/bn/films/title/shuyopoka',
 227         'info_dict': {
 228             'id': '7a7a9d33-1f4c-4771-9173-ee4fb6dbf196',
 229             'ext': 'mp4',
 230             'title': 'Shuyopoka',
 231             'description': 'md5:e28f2fb8680096a69c944d37c1fa5ffc',
 232             'thumbnail': r're:^https?://.*\.jpg$',
 233             'upload_date': '20211006',
 234         },
 235         'params': {'skip_download': True},
 236     }, {  # Free film
 237         'url': 'https://www.hoichoi.tv/films/title/dadu-no1',
 238         'info_dict': {
 239             'id': '0000015b-b009-d126-a1db-b81ff3780000',
 240             'ext': 'mp4',
 241             'title': 'Dadu No.1',
 242             'description': 'md5:605cba408e51a79dafcb824bdeded51e',
 243             'thumbnail': r're:^https?://.*\.jpg$',
 244             'upload_date': '20210827',
 245         },
 246         'params': {'skip_download': True},
 247     }, {  # Free episode
 248         'url': 'https://www.hoichoi.tv/webseries/case-jaundice-s01-e01',
 249         'info_dict': {
 250             'id': 'f779e07c-30c8-459c-8612-5a834ab5e5ba',
 251             'ext': 'mp4',
 252             'title': 'Humans Vs. Corona',
 253             'description': 'md5:ca30a682b4528d02a3eb6d0427dd0f87',
 254             'thumbnail': r're:^https?://.*\.jpg$',
 255             'upload_date': '20210830',
 256             'series': 'Case Jaundice'
 257         },
 258         'params': {'skip_download': True},
 259     }, {  # Free video
 260         'url': 'https://www.hoichoi.tv/videos/1549072415320-six-episode-02-hindi',
 261         'info_dict': {
 262             'id': 'b41fa1ce-aca6-47b6-b208-283ff0a2de30',
 263             'ext': 'mp4',
 264             'title': 'Woman in red - Hindi',
 265             'description': 'md5:9d21edc1827d32f8633eb67c2054fc31',
 266             'thumbnail': r're:^https?://.*\.jpg$',
 267             'upload_date': '20211006',
 268             'series': 'Six (Hindi)'
 269         },
 270         'params': {'skip_download': True},
 271     }, {  # Free episode
 272         'url': 'https://www.hoichoi.tv/shows/watch-asian-paints-moner-thikana-online-season-1-episode-1',
 273         'info_dict': {
 274             'id': '1f45d185-8500-455c-b88d-13252307c3eb',
 275             'ext': 'mp4',
 276             'title': 'Jisshu Sengupta',
 277             'description': 'md5:ef6ffae01a3d83438597367400f824ed',
 278             'thumbnail': r're:^https?://.*\.jpg$',
 279             'upload_date': '20211004',
 280             'series': 'Asian Paints Moner Thikana'
 281         },
 282         'params': {'skip_download': True},
 283     }, {  # Free series
 284         'url': 'https://www.hoichoi.tv/shows/watch-moner-thikana-bengali-web-series-online',
 285         'playlist_mincount': 5,
 286         'info_dict': {
 287             'id': 'watch-moner-thikana-bengali-web-series-online',
 288         },
 289     }, {  # Premium series
 290         'url': 'https://www.hoichoi.tv/shows/watch-byomkesh-bengali-web-series-online',
 291         'playlist_mincount': 14,
 292         'info_dict': {
 293             'id': 'watch-byomkesh-bengali-web-series-online',
 294         },
 295     }, {  # Premium movie
 296         'url': 'https://www.hoichoi.tv/movies/detective-2020',
 297         'only_matching': True
 298     }, {  # Chorki Premium series
 299         'url': 'https://www.chorki.com/bn/series/sinpaat',
 300         'playlist_mincount': 7,
 301         'info_dict': {
 302             'id': 'bn/series/sinpaat',
 303         },
 304     }, {  # Chorki free movie
 305         'url': 'https://www.chorki.com/bn/videos/bangla-movie-bikkhov',
 306         'info_dict': {
 307             'id': '564e755b-f5c7-4515-aee6-8959bee18c93',
 308             'title': 'Bikkhov',
 309             'ext': 'mp4',
 310             'upload_date': '20230824',
 311             'timestamp': 1692860553,
 312             'categories': ['Action Movies', 'Salman Special'],
 313             'tags': 'count:14',
 314             'thumbnail': 'https://snagfilms-a.akamaihd.net/dd078ff5-b16e-45e4-9723-501b56b9df0a/images/2023/08/24/1692860450729_1920x1080_16x9Images.jpg',
 315             'display_id': 'bn/videos/bangla-movie-bikkhov',
 316             'description': 'md5:71492b086450625f4374a3eb824f27dc',
 317             'duration': 8002,
 318         },
 319         'params': {
 320             'skip_download': True,
 321         },
 322     }, {  # Chorki Premium movie
 323         'url': 'https://www.chorki.com/bn/videos/something-like-an-autobiography',
 324         'only_matching': True,
 325     }]
 326
 327     @classmethod
 328     def suitable(cls, url):
 329         return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
 330
 331     def _show_entries(self, domain, seasons):
 332         for season in seasons:
 333             for episode in season.get('episodes') or []:
 334                 path = traverse_obj(episode, ('gist', 'permalink'))
 335                 if path:
 336                     yield self.url_result(f'https://www.{domain}{path}', ie=self.ie_key())
 337
 338     def _real_extract(self, url):
 339         domain, path, display_id = self._match_valid_url(url).groups()
 340         site = domain.split('.')[-2]
 341         if site in self._SITE_MAP:
 342             site = self._SITE_MAP[site]
 343         modules = self._call_api(
 344             site, 'content/pages', display_id, url, {
 345                 'includeContent': 'true',
 346                 'moduleOffset': 1,
 347                 'path': path,
 348                 'site': site,
 349             })['modules']
 350
 351         seasons = next((m['contentData'][0]['seasons'] for m in modules if m.get('moduleType') == 'ShowDetailModule'), None)
 352         if seasons:
 353             return self.playlist_result(self._show_entries(domain, seasons), display_id)
 354
 355         film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule')
 356         return {
 357             '_type': 'url_transparent',
 358             'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
 359             'id': film_id,
 360             'display_id': display_id,
 361             'ie_key': 'ViewLiftEmbed',
 362         }