yt_dlp/extractor/viewlift.py

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