yt_dlp/extractor/go.py

   1 import re
   2
   3 from .adobepass import AdobePassIE
   4 from ..compat import compat_str
   5 from ..utils import (
   6     int_or_none,
   7     determine_ext,
   8     parse_age_limit,
   9     remove_start,
  10     remove_end,
  11     try_get,
  12     urlencode_postdata,
  13     ExtractorError,
  14 )
  15
  16
  17 class GoIE(AdobePassIE):
  18     _SITE_INFO = {
  19         'abc': {
  20             'brand': '001',
  21             'requestor_id': 'ABC',
  22         },
  23         'freeform': {
  24             'brand': '002',
  25             'requestor_id': 'ABCFamily',
  26         },
  27         'watchdisneychannel': {
  28             'brand': '004',
  29             'resource_id': 'Disney',
  30         },
  31         'watchdisneyjunior': {
  32             'brand': '008',
  33             'resource_id': 'DisneyJunior',
  34         },
  35         'watchdisneyxd': {
  36             'brand': '009',
  37             'resource_id': 'DisneyXD',
  38         },
  39         'disneynow': {
  40             'brand': '011',
  41             'resource_id': 'Disney',
  42         },
  43         'fxnow.fxnetworks': {
  44             'brand': '025',
  45             'requestor_id': 'dtci',
  46         },
  47     }
  48     _VALID_URL = r'''(?x)
  49                     https?://
  50                         (?P<sub_domain>
  51                             (?:%s\.)?go|fxnow\.fxnetworks|
  52                             (?:www\.)?(?:abc|freeform|disneynow)
  53                         )\.com/
  54                         (?:
  55                             (?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
  56                             (?:[^/]+/)*(?P<display_id>[^/?\#]+)
  57                         )
  58                     ''' % r'\.|'.join(list(_SITE_INFO.keys()))
  59     _TESTS = [{
  60         'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
  61         'info_dict': {
  62             'id': 'VDKA3807643',
  63             'ext': 'mp4',
  64             'title': 'The Traitor in the White House',
  65             'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
  66         },
  67         'params': {
  68             # m3u8 download
  69             'skip_download': True,
  70         },
  71         'skip': 'This content is no longer available.',
  72     }, {
  73         'url': 'http://watchdisneyxd.go.com/doraemon',
  74         'info_dict': {
  75             'title': 'Doraemon',
  76             'id': 'SH55574025',
  77         },
  78         'playlist_mincount': 51,
  79     }, {
  80         'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
  81         'info_dict': {
  82             'id': 'VDKA3609139',
  83             'ext': 'mp4',
  84             'title': 'This Guilty Blood',
  85             'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
  86             'age_limit': 14,
  87         },
  88         'params': {
  89             'geo_bypass_ip_block': '3.244.239.0/24',
  90             # m3u8 download
  91             'skip_download': True,
  92         },
  93     }, {
  94         'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet',
  95         'info_dict': {
  96             'id': 'VDKA13435179',
  97             'ext': 'mp4',
  98             'title': 'The Bet',
  99             'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404',
 100             'age_limit': 14,
 101         },
 102         'params': {
 103             'geo_bypass_ip_block': '3.244.239.0/24',
 104             # m3u8 download
 105             'skip_download': True,
 106         },
 107     }, {
 108         'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
 109         'info_dict': {
 110             'id': 'VDKA12782841',
 111             'ext': 'mp4',
 112             'title': 'First Look: Better Things - Season 2',
 113             'description': 'md5:fa73584a95761c605d9d54904e35b407',
 114         },
 115         'params': {
 116             'geo_bypass_ip_block': '3.244.239.0/24',
 117             # m3u8 download
 118             'skip_download': True,
 119         },
 120     }, {
 121         'url': 'https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot',
 122         'info_dict': {
 123             'id': 'VDKA22600213',
 124             'ext': 'mp4',
 125             'title': 'Pilot',
 126             'description': 'md5:74306df917cfc199d76d061d66bebdb4',
 127         },
 128         'params': {
 129             # m3u8 download
 130             'skip_download': True,
 131         },
 132     }, {
 133         'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
 134         'only_matching': True,
 135     }, {
 136         'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
 137         'only_matching': True,
 138     }, {
 139         # brand 004
 140         'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
 141         'only_matching': True,
 142     }, {
 143         # brand 008
 144         'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
 145         'only_matching': True,
 146     }, {
 147         'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
 148         'only_matching': True,
 149     }, {
 150         'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
 151         'only_matching': True,
 152     }]
 153
 154     def _extract_videos(self, brand, video_id='-1', show_id='-1'):
 155         display_id = video_id if video_id != '-1' else show_id
 156         return self._download_json(
 157             'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id),
 158             display_id)['video']
 159
 160     def _real_extract(self, url):
 161         mobj = self._match_valid_url(url)
 162         sub_domain = remove_start(remove_end(mobj.group('sub_domain') or '', '.go'), 'www.')
 163         video_id, display_id = mobj.group('id', 'display_id')
 164         site_info = self._SITE_INFO.get(sub_domain, {})
 165         brand = site_info.get('brand')
 166         if not video_id or not site_info:
 167             webpage = self._download_webpage(url, display_id or video_id)
 168             data = self._parse_json(
 169                 self._search_regex(
 170                     r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
 171                     'data', default='{}'),
 172                 display_id or video_id, fatal=False)
 173             # https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
 174             layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
 175             video_id = None
 176             if layout:
 177                 video_id = try_get(
 178                     layout,
 179                     (lambda x: x['videoid'], lambda x: x['video']['id']),
 180                     compat_str)
 181             if not video_id:
 182                 video_id = self._search_regex(
 183                     (
 184                         # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
 185                         # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
 186                         r'data-video-id=["\']*(VDKA\w+)',
 187                         # page.analytics.videoIdCode
 188                         r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
 189                         # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
 190                         r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
 191                     ), webpage, 'video id', default=video_id)
 192             if not site_info:
 193                 brand = self._search_regex(
 194                     (r'data-brand=\s*["\']\s*(\d+)',
 195                      r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
 196                     default='004')
 197                 site_info = next(
 198                     si for _, si in self._SITE_INFO.items()
 199                     if si.get('brand') == brand)
 200             if not video_id:
 201                 # show extraction works for Disney, DisneyJunior and DisneyXD
 202                 # ABC and Freeform has different layout
 203                 show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
 204                 videos = self._extract_videos(brand, show_id=show_id)
 205                 show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
 206                 entries = []
 207                 for video in videos:
 208                     entries.append(self.url_result(
 209                         video['url'], 'Go', video.get('id'), video.get('title')))
 210                 entries.reverse()
 211                 return self.playlist_result(entries, show_id, show_title)
 212         video_data = self._extract_videos(brand, video_id)[0]
 213         video_id = video_data['id']
 214         title = video_data['title']
 215
 216         formats = []
 217         subtitles = {}
 218         for asset in video_data.get('assets', {}).get('asset', []):
 219             asset_url = asset.get('value')
 220             if not asset_url:
 221                 continue
 222             format_id = asset.get('format')
 223             ext = determine_ext(asset_url)
 224             if ext == 'm3u8':
 225                 video_type = video_data.get('type')
 226                 data = {
 227                     'video_id': video_data['id'],
 228                     'video_type': video_type,
 229                     'brand': brand,
 230                     'device': '001',
 231                 }
 232                 if video_data.get('accesslevel') == '1':
 233                     requestor_id = site_info.get('requestor_id', 'DisneyChannels')
 234                     resource = site_info.get('resource_id') or self._get_mvpd_resource(
 235                         requestor_id, title, video_id, None)
 236                     auth = self._extract_mvpd_auth(
 237                         url, video_id, requestor_id, resource)
 238                     data.update({
 239                         'token': auth,
 240                         'token_type': 'ap',
 241                         'adobe_requestor_id': requestor_id,
 242                     })
 243                 else:
 244                     self._initialize_geo_bypass({'countries': ['US']})
 245                 entitlement = self._download_json(
 246                     'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
 247                     video_id, data=urlencode_postdata(data))
 248                 errors = entitlement.get('errors', {}).get('errors', [])
 249                 if errors:
 250                     for error in errors:
 251                         if error.get('code') == 1002:
 252                             self.raise_geo_restricted(
 253                                 error['message'], countries=['US'])
 254                     error_message = ', '.join([error['message'] for error in errors])
 255                     raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
 256                 asset_url += '?' + entitlement['uplynkData']['sessionKey']
 257                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
 258                     asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)
 259                 formats.extend(fmts)
 260                 self._merge_subtitles(subs, target=subtitles)
 261             else:
 262                 f = {
 263                     'format_id': format_id,
 264                     'url': asset_url,
 265                     'ext': ext,
 266                 }
 267                 if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url):
 268                     f.update({
 269                         'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE',
 270                         'quality': 1,
 271                     })
 272                 else:
 273                     mobj = re.search(r'/(\d+)x(\d+)/', asset_url)
 274                     if mobj:
 275                         height = int(mobj.group(2))
 276                         f.update({
 277                             'format_id': ('%s-' % format_id if format_id else '') + '%dP' % height,
 278                             'width': int(mobj.group(1)),
 279                             'height': height,
 280                         })
 281                 formats.append(f)
 282         self._sort_formats(formats)
 283
 284         for cc in video_data.get('closedcaption', {}).get('src', []):
 285             cc_url = cc.get('value')
 286             if not cc_url:
 287                 continue
 288             ext = determine_ext(cc_url)
 289             if ext == 'xml':
 290                 ext = 'ttml'
 291             subtitles.setdefault(cc.get('lang'), []).append({
 292                 'url': cc_url,
 293                 'ext': ext,
 294             })
 295
 296         thumbnails = []
 297         for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []):
 298             thumbnail_url = thumbnail.get('value')
 299             if not thumbnail_url:
 300                 continue
 301             thumbnails.append({
 302                 'url': thumbnail_url,
 303                 'width': int_or_none(thumbnail.get('width')),
 304                 'height': int_or_none(thumbnail.get('height')),
 305             })
 306
 307         return {
 308             'id': video_id,
 309             'title': title,
 310             'description': video_data.get('longdescription') or video_data.get('description'),
 311             'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000),
 312             'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')),
 313             'episode_number': int_or_none(video_data.get('episodenumber')),
 314             'series': video_data.get('show', {}).get('title'),
 315             'season_number': int_or_none(video_data.get('season', {}).get('num')),
 316             'thumbnails': thumbnails,
 317             'formats': formats,
 318             'subtitles': subtitles,
 319         }