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     join_nonempty,
   9     parse_age_limit,
  10     traverse_obj,
  11 )
  12
  13
  14 class ViewLiftBaseIE(InfoExtractor):
  15     _API_BASE = 'https://prod-api.viewlift.com/'
  16     _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'
  17     _SITE_MAP = {
  18         'ftfnext': 'lax',
  19         'funnyforfree': 'snagfilms',
  20         'hoichoi': 'hoichoitv',
  21         'kiddovid': 'snagfilms',
  22         'laxsportsnetwork': 'lax',
  23         'legapallacanestro': 'lnp',
  24         'marquee': 'marquee-tv',
  25         'monumentalsportsnetwork': 'monumental-network',
  26         'moviespree': 'bingeflix',
  27         'pflmma': 'pfl',
  28         'snagxtreme': 'snagfilms',
  29         'theidentitytb': 'tampabay',
  30         'vayafilm': 'snagfilms',
  31         'chorki': 'prothomalo',
  32     }
  33     _TOKENS = {}
  34
  35     def _fetch_token(self, site, url):
  36         if self._TOKENS.get(site):
  37             return
  38
  39         cookies = self._get_cookies(url)
  40         if cookies and cookies.get('token'):
  41             self._TOKENS[site] = self._search_regex(r'22authorizationToken\%22:\%22([^\%]+)\%22', cookies['token'].value, 'token')
  42         if not self._TOKENS.get(site):
  43             self.raise_login_required('Cookies (not necessarily logged in) are needed to download from this website', method='cookies')
  44
  45     def _call_api(self, site, path, video_id, url, query):
  46         self._fetch_token(site, url)
  47         try:
  48             return self._download_json(
  49                 self._API_BASE + path, video_id, headers={'Authorization': self._TOKENS.get(site)}, query=query)
  50         except ExtractorError as e:
  51             if isinstance(e.cause, HTTPError) and e.cause.status == 403:
  52                 webpage = e.cause.response.read().decode()
  53                 try:
  54                     error_message = traverse_obj(json.loads(webpage), 'errorMessage', 'message')
  55                 except json.JSONDecodeError:
  56                     raise ExtractorError(f'{site} said: {webpage}', cause=e.cause)
  57                 if error_message:
  58                     if 'has not purchased' in error_message:
  59                         self.raise_login_required(method='cookies')
  60                     raise ExtractorError(error_message, expected=True)
  61             raise
  62
  63
  64 class ViewLiftEmbedIE(ViewLiftBaseIE):
  65     IE_NAME = 'viewlift:embed'
  66     _VALID_URL = rf'https?://(?:(?:www|embed)\.)?(?P<domain>{ViewLiftBaseIE._DOMAINS_REGEX})/embed/player\?.*\bfilmId=(?P<id>[\da-f]{{8}}-(?:[\da-f]{{4}}-){{3}}[\da-f]{{12}})'
  67     _EMBED_REGEX = [rf'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?(?:{ViewLiftBaseIE._DOMAINS_REGEX})/embed/player.+?)\1']
  68     _TESTS = [{
  69         'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
  70         'md5': '2924e9215c6eff7a55ed35b72276bd93',
  71         'info_dict': {
  72             'id': '74849a00-85a9-11e1-9660-123139220831',
  73             'ext': 'mp4',
  74             'title': '#whilewewatch',
  75             'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8',
  76             'timestamp': 1334350096,
  77             'upload_date': '20120413',
  78         },
  79     }, {
  80         # invalid labels, 360p is better that 480p
  81         'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
  82         'md5': '882fca19b9eb27ef865efeeaed376a48',
  83         'info_dict': {
  84             'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
  85             'ext': 'mp4',
  86             'title': 'Life in Limbo',
  87         },
  88         'skip': 'The video does not exist',
  89     }, {
  90         'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
  91         'only_matching': True,
  92     }]
  93
  94     def _real_extract(self, url):
  95         domain, film_id = self._match_valid_url(url).groups()
  96         site = domain.split('.')[-2]
  97         if site in self._SITE_MAP:
  98             site = self._SITE_MAP[site]
  99
 100         content_data = self._call_api(
 101             site, 'entitlement/video/status', film_id, url, {
 102                 'id': film_id,
 103             })['video']
 104         gist = content_data['gist']
 105         title = gist['title']
 106         video_assets = content_data['streamingInfo']['videoAssets']
 107
 108         hls_url = video_assets.get('hls')
 109         formats, subtitles = [], {}
 110         if hls_url:
 111             formats, subtitles = self._extract_m3u8_formats_and_subtitles(
 112                 hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
 113
 114         for video_asset in video_assets.get('mpeg') or []:
 115             video_asset_url = video_asset.get('url')
 116             if not video_asset_url:
 117                 continue
 118             bitrate = int_or_none(video_asset.get('bitrate'))
 119             height = int_or_none(self._search_regex(
 120                 r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
 121                 'height', default=None))
 122             formats.append({
 123                 'url': video_asset_url,
 124                 'format_id': join_nonempty('http', bitrate),
 125                 'tbr': bitrate,
 126                 'height': height,
 127                 'vcodec': video_asset.get('codec'),
 128             })
 129
 130         subs = {}
 131         for sub in traverse_obj(content_data, ('contentDetails', 'closedCaptions')) or []:
 132             sub_url = sub.get('url')
 133             if not sub_url:
 134                 continue
 135             subs.setdefault(sub.get('language', 'English'), []).append({
 136                 'url': sub_url,
 137             })
 138
 139         return {
 140             'id': film_id,
 141             'title': title,
 142             'description': gist.get('description'),
 143             'thumbnail': gist.get('videoImageUrl'),
 144             'duration': int_or_none(gist.get('runtime')),
 145             'age_limit': parse_age_limit(content_data.get('parentalRating')),
 146             'timestamp': int_or_none(gist.get('publishDate'), 1000),
 147             'formats': formats,
 148             'subtitles': self._merge_subtitles(subs, subtitles),
 149             'categories': traverse_obj(content_data, ('categories', ..., 'title')),
 150             'tags': traverse_obj(content_data, ('tags', ..., 'title')),
 151         }
 152
 153
 154 class ViewLiftIE(ViewLiftBaseIE):
 155     IE_NAME = 'viewlift'
 156     _API_BASE = 'https://prod-api-cached-2.viewlift.com/'
 157     _VALID_URL = rf'https?://(?:www\.)?(?P<domain>{ViewLiftBaseIE._DOMAINS_REGEX})(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))'
 158     _TESTS = [{
 159         'url': 'http://www.snagfilms.com/films/title/lost_for_life',
 160         'md5': '19844f897b35af219773fd63bdec2942',
 161         'info_dict': {
 162             'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
 163             'display_id': 'lost_for_life',
 164             'ext': 'mp4',
 165             'title': 'Lost for Life',
 166             'description': 'md5:ea10b5a50405ae1f7b5269a6ec594102',
 167             'thumbnail': r're:^https?://.*\.jpg',
 168             'duration': 4489,
 169             'categories': 'mincount:3',
 170             'age_limit': 14,
 171             'upload_date': '20150421',
 172             'timestamp': 1429656820,
 173         },
 174     }, {
 175         'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
 176         'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
 177         'info_dict': {
 178             'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
 179             'display_id': 'the_world_cut_project/india',
 180             'ext': 'mp4',
 181             'title': 'India',
 182             'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
 183             'thumbnail': r're:^https?://.*\.jpg',
 184             'duration': 979,
 185             'timestamp': 1399478279,
 186             'upload_date': '20140507',
 187         },
 188     }, {
 189         'url': 'http://main.snagfilms.com/augie_alone/s_2_ep_12_love',
 190         'info_dict': {
 191             'id': '00000148-7b53-de26-a9fb-fbf306f70020',
 192             'display_id': 'augie_alone/s_2_ep_12_love',
 193             'ext': 'mp4',
 194             'title': 'S. 2 Ep. 12 - Love',
 195             'description': 'Augie finds love.',
 196             'thumbnail': r're:^https?://.*\.jpg',
 197             'duration': 107,
 198             'upload_date': '20141012',
 199             'timestamp': 1413129540,
 200             'age_limit': 17,
 201         },
 202         'params': {
 203             'skip_download': True,
 204         },
 205     }, {
 206         'url': 'http://main.snagfilms.com/films/title/the_freebie',
 207         'only_matching': True,
 208     }, {
 209         # Film is not playable in your area.
 210         'url': 'http://www.snagfilms.com/films/title/inside_mecca',
 211         'only_matching': True,
 212     }, {
 213         # Film is not available.
 214         'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
 215         'only_matching': True,
 216     }, {
 217         'url': 'http://www.winnersview.com/videos/the-good-son',
 218         'only_matching': True,
 219     }, {
 220         # Was once Kaltura embed
 221         'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
 222         'only_matching': True,
 223     }, {
 224         'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters',
 225         'only_matching': True,
 226     }, {  # Free film with langauge code
 227         'url': 'https://www.hoichoi.tv/bn/films/title/shuyopoka',
 228         'info_dict': {
 229             'id': '7a7a9d33-1f4c-4771-9173-ee4fb6dbf196',
 230             'ext': 'mp4',
 231             'title': 'Shuyopoka',
 232             'description': 'md5:e28f2fb8680096a69c944d37c1fa5ffc',
 233             'thumbnail': r're:^https?://.*\.jpg$',
 234             'upload_date': '20211006',
 235         },
 236         'params': {'skip_download': True},
 237     }, {  # Free film
 238         'url': 'https://www.hoichoi.tv/films/title/dadu-no1',
 239         'info_dict': {
 240             'id': '0000015b-b009-d126-a1db-b81ff3780000',
 241             'ext': 'mp4',
 242             'title': 'Dadu No.1',
 243             'description': 'md5:605cba408e51a79dafcb824bdeded51e',
 244             'thumbnail': r're:^https?://.*\.jpg$',
 245             'upload_date': '20210827',
 246         },
 247         'params': {'skip_download': True},
 248     }, {  # Free episode
 249         'url': 'https://www.hoichoi.tv/webseries/case-jaundice-s01-e01',
 250         'info_dict': {
 251             'id': 'f779e07c-30c8-459c-8612-5a834ab5e5ba',
 252             'ext': 'mp4',
 253             'title': 'Humans Vs. Corona',
 254             'description': 'md5:ca30a682b4528d02a3eb6d0427dd0f87',
 255             'thumbnail': r're:^https?://.*\.jpg$',
 256             'upload_date': '20210830',
 257             'series': 'Case Jaundice',
 258         },
 259         'params': {'skip_download': True},
 260     }, {  # Free video
 261         'url': 'https://www.hoichoi.tv/videos/1549072415320-six-episode-02-hindi',
 262         'info_dict': {
 263             'id': 'b41fa1ce-aca6-47b6-b208-283ff0a2de30',
 264             'ext': 'mp4',
 265             'title': 'Woman in red - Hindi',
 266             'description': 'md5:9d21edc1827d32f8633eb67c2054fc31',
 267             'thumbnail': r're:^https?://.*\.jpg$',
 268             'upload_date': '20211006',
 269             'series': 'Six (Hindi)',
 270         },
 271         'params': {'skip_download': True},
 272     }, {  # Free episode
 273         'url': 'https://www.hoichoi.tv/shows/watch-asian-paints-moner-thikana-online-season-1-episode-1',
 274         'info_dict': {
 275             'id': '1f45d185-8500-455c-b88d-13252307c3eb',
 276             'ext': 'mp4',
 277             'title': 'Jisshu Sengupta',
 278             'description': 'md5:ef6ffae01a3d83438597367400f824ed',
 279             'thumbnail': r're:^https?://.*\.jpg$',
 280             'upload_date': '20211004',
 281             'series': 'Asian Paints Moner Thikana',
 282         },
 283         'params': {'skip_download': True},
 284     }, {  # Free series
 285         'url': 'https://www.hoichoi.tv/shows/watch-moner-thikana-bengali-web-series-online',
 286         'playlist_mincount': 5,
 287         'info_dict': {
 288             'id': 'watch-moner-thikana-bengali-web-series-online',
 289         },
 290     }, {  # Premium series
 291         'url': 'https://www.hoichoi.tv/shows/watch-byomkesh-bengali-web-series-online',
 292         'playlist_mincount': 14,
 293         'info_dict': {
 294             'id': 'watch-byomkesh-bengali-web-series-online',
 295         },
 296     }, {  # Premium movie
 297         'url': 'https://www.hoichoi.tv/movies/detective-2020',
 298         'only_matching': True,
 299     }, {  # Chorki Premium series
 300         'url': 'https://www.chorki.com/bn/series/sinpaat',
 301         'playlist_mincount': 7,
 302         'info_dict': {
 303             'id': 'bn/series/sinpaat',
 304         },
 305     }, {  # Chorki free movie
 306         'url': 'https://www.chorki.com/bn/videos/bangla-movie-bikkhov',
 307         'info_dict': {
 308             'id': '564e755b-f5c7-4515-aee6-8959bee18c93',
 309             'title': 'Bikkhov',
 310             'ext': 'mp4',
 311             'upload_date': '20230824',
 312             'timestamp': 1692860553,
 313             'categories': ['Action Movies', 'Salman Special'],
 314             'tags': 'count:14',
 315             'thumbnail': 'https://snagfilms-a.akamaihd.net/dd078ff5-b16e-45e4-9723-501b56b9df0a/images/2023/08/24/1692860450729_1920x1080_16x9Images.jpg',
 316             'display_id': 'bn/videos/bangla-movie-bikkhov',
 317             'description': 'md5:71492b086450625f4374a3eb824f27dc',
 318             'duration': 8002,
 319         },
 320         'params': {
 321             'skip_download': True,
 322         },
 323     }, {  # Chorki Premium movie
 324         'url': 'https://www.chorki.com/bn/videos/something-like-an-autobiography',
 325         'only_matching': True,
 326     }]
 327
 328     @classmethod
 329     def suitable(cls, url):
 330         return False if ViewLiftEmbedIE.suitable(url) else super().suitable(url)
 331
 332     def _show_entries(self, domain, seasons):
 333         for season in seasons:
 334             for episode in season.get('episodes') or []:
 335                 path = traverse_obj(episode, ('gist', 'permalink'))
 336                 if path:
 337                     yield self.url_result(f'https://www.{domain}{path}', ie=self.ie_key())
 338
 339     def _real_extract(self, url):
 340         domain, path, display_id = self._match_valid_url(url).groups()
 341         site = domain.split('.')[-2]
 342         if site in self._SITE_MAP:
 343             site = self._SITE_MAP[site]
 344         modules = self._call_api(
 345             site, 'content/pages', display_id, url, {
 346                 'includeContent': 'true',
 347                 'moduleOffset': 1,
 348                 'path': path,
 349                 'site': site,
 350             })['modules']
 351
 352         seasons = next((m['contentData'][0]['seasons'] for m in modules if m.get('moduleType') == 'ShowDetailModule'), None)
 353         if seasons:
 354             return self.playlist_result(self._show_entries(domain, seasons), display_id)
 355
 356         film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule')
 357         return {
 358             '_type': 'url_transparent',
 359             'url': f'http://{domain}/embed/player?filmId={film_id}',
 360             'id': film_id,
 361             'display_id': display_id,
 362             'ie_key': 'ViewLiftEmbed',
 363         }