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