yt_dlp/extractor/go.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .adobepass import AdobePassIE
   7 from ..compat import compat_str
   8 from ..utils import (
   9     int_or_none,
  10     determine_ext,
  11     parse_age_limit,
  12     remove_start,
  13     remove_end,
  14     try_get,
  15     urlencode_postdata,
  16     ExtractorError,
  17 )
  18
  19
  20 class GoIE(AdobePassIE):
  21     _SITE_INFO = {
  22         'abc': {
  23             'brand': '001',
  24             'requestor_id': 'ABC',
  25         },
  26         'freeform': {
  27             'brand': '002',
  28             'requestor_id': 'ABCFamily',
  29         },
  30         'watchdisneychannel': {
  31             'brand': '004',
  32             'resource_id': 'Disney',
  33         },
  34         'watchdisneyjunior': {
  35             'brand': '008',
  36             'resource_id': 'DisneyJunior',
  37         },
  38         'watchdisneyxd': {
  39             'brand': '009',
  40             'resource_id': 'DisneyXD',
  41         },
  42         'disneynow': {
  43             'brand': '011',
  44             'resource_id': 'Disney',
  45         },
  46         'fxnow.fxnetworks': {
  47             'brand': '025',
  48             'requestor_id': 'dtci',
  49         },
  50     }
  51     _VALID_URL = r'''(?x)
  52                     https?://
  53                         (?P<sub_domain>
  54                             (?:%s\.)?go|fxnow\.fxnetworks|
  55                             (?:www\.)?(?:abc|freeform|disneynow)
  56                         )\.com/
  57                         (?:
  58                             (?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
  59                             (?:[^/]+/)*(?P<display_id>[^/?\#]+)
  60                         )
  61                     ''' % r'\.|'.join(list(_SITE_INFO.keys()))
  62     _TESTS = [{
  63         'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
  64         'info_dict': {
  65             'id': 'VDKA3807643',
  66             'ext': 'mp4',
  67             'title': 'The Traitor in the White House',
  68             'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
  69         },
  70         'params': {
  71             # m3u8 download
  72             'skip_download': True,
  73         },
  74         'skip': 'This content is no longer available.',
  75     }, {
  76         'url': 'http://watchdisneyxd.go.com/doraemon',
  77         'info_dict': {
  78             'title': 'Doraemon',
  79             'id': 'SH55574025',
  80         },
  81         'playlist_mincount': 51,
  82     }, {
  83         'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
  84         'info_dict': {
  85             'id': 'VDKA3609139',
  86             'ext': 'mp4',
  87             'title': 'This Guilty Blood',
  88             'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
  89             'age_limit': 14,
  90         },
  91         'params': {
  92             'geo_bypass_ip_block': '3.244.239.0/24',
  93             # m3u8 download
  94             'skip_download': True,
  95         },
  96     }, {
  97         'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet',
  98         'info_dict': {
  99             'id': 'VDKA13435179',
 100             'ext': 'mp4',
 101             'title': 'The Bet',
 102             'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404',
 103             'age_limit': 14,
 104         },
 105         'params': {
 106             'geo_bypass_ip_block': '3.244.239.0/24',
 107             # m3u8 download
 108             'skip_download': True,
 109         },
 110     }, {
 111         'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
 112         'info_dict': {
 113             'id': 'VDKA12782841',
 114             'ext': 'mp4',
 115             'title': 'First Look: Better Things - Season 2',
 116             'description': 'md5:fa73584a95761c605d9d54904e35b407',
 117         },
 118         'params': {
 119             'geo_bypass_ip_block': '3.244.239.0/24',
 120             # m3u8 download
 121             'skip_download': True,
 122         },
 123     }, {
 124         'url': 'https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot',
 125         'info_dict': {
 126             'id': 'VDKA22600213',
 127             'ext': 'mp4',
 128             'title': 'Pilot',
 129             'description': 'md5:74306df917cfc199d76d061d66bebdb4',
 130         },
 131         'params': {
 132             # m3u8 download
 133             'skip_download': True,
 134         },
 135     }, {
 136         'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
 137         'only_matching': True,
 138     }, {
 139         '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',
 140         'only_matching': True,
 141     }, {
 142         # brand 004
 143         'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
 144         'only_matching': True,
 145     }, {
 146         # brand 008
 147         'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
 148         'only_matching': True,
 149     }, {
 150         'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
 151         'only_matching': True,
 152     }, {
 153         'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
 154         'only_matching': True,
 155     }]
 156
 157     def _extract_videos(self, brand, video_id='-1', show_id='-1'):
 158         display_id = video_id if video_id != '-1' else show_id
 159         return self._download_json(
 160             '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),
 161             display_id)['video']
 162
 163     def _real_extract(self, url):
 164         mobj = re.match(self._VALID_URL, url)
 165         sub_domain = remove_start(remove_end(mobj.group('sub_domain') or '', '.go'), 'www.')
 166         video_id, display_id = mobj.group('id', 'display_id')
 167         site_info = self._SITE_INFO.get(sub_domain, {})
 168         brand = site_info.get('brand')
 169         if not video_id or not site_info:
 170             webpage = self._download_webpage(url, display_id or video_id)
 171             data = self._parse_json(
 172                 self._search_regex(
 173                     r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
 174                     'data', default='{}'),
 175                 display_id or video_id, fatal=False)
 176             # https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
 177             layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
 178             video_id = None
 179             if layout:
 180                 video_id = try_get(
 181                     layout,
 182                     (lambda x: x['videoid'], lambda x: x['video']['id']),
 183                     compat_str)
 184             if not video_id:
 185                 video_id = self._search_regex(
 186                     (
 187                         # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
 188                         # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
 189                         r'data-video-id=["\']*(VDKA\w+)',
 190                         # page.analytics.videoIdCode
 191                         r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
 192                         # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
 193                         r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
 194                     ), webpage, 'video id', default=video_id)
 195             if not site_info:
 196                 brand = self._search_regex(
 197                     (r'data-brand=\s*["\']\s*(\d+)',
 198                      r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
 199                     default='004')
 200                 site_info = next(
 201                     si for _, si in self._SITE_INFO.items()
 202                     if si.get('brand') == brand)
 203             if not video_id:
 204                 # show extraction works for Disney, DisneyJunior and DisneyXD
 205                 # ABC and Freeform has different layout
 206                 show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
 207                 videos = self._extract_videos(brand, show_id=show_id)
 208                 show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
 209                 entries = []
 210                 for video in videos:
 211                     entries.append(self.url_result(
 212                         video['url'], 'Go', video.get('id'), video.get('title')))
 213                 entries.reverse()
 214                 return self.playlist_result(entries, show_id, show_title)
 215         video_data = self._extract_videos(brand, video_id)[0]
 216         video_id = video_data['id']
 217         title = video_data['title']
 218
 219         formats = []
 220         for asset in video_data.get('assets', {}).get('asset', []):
 221             asset_url = asset.get('value')
 222             if not asset_url:
 223                 continue
 224             format_id = asset.get('format')
 225             ext = determine_ext(asset_url)
 226             if ext == 'm3u8':
 227                 video_type = video_data.get('type')
 228                 data = {
 229                     'video_id': video_data['id'],
 230                     'video_type': video_type,
 231                     'brand': brand,
 232                     'device': '001',
 233                 }
 234                 if video_data.get('accesslevel') == '1':
 235                     requestor_id = site_info.get('requestor_id', 'DisneyChannels')
 236                     resource = site_info.get('resource_id') or self._get_mvpd_resource(
 237                         requestor_id, title, video_id, None)
 238                     auth = self._extract_mvpd_auth(
 239                         url, video_id, requestor_id, resource)
 240                     data.update({
 241                         'token': auth,
 242                         'token_type': 'ap',
 243                         'adobe_requestor_id': requestor_id,
 244                     })
 245                 else:
 246                     self._initialize_geo_bypass({'countries': ['US']})
 247                 entitlement = self._download_json(
 248                     'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
 249                     video_id, data=urlencode_postdata(data))
 250                 errors = entitlement.get('errors', {}).get('errors', [])
 251                 if errors:
 252                     for error in errors:
 253                         if error.get('code') == 1002:
 254                             self.raise_geo_restricted(
 255                                 error['message'], countries=['US'])
 256                     error_message = ', '.join([error['message'] for error in errors])
 257                     raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
 258                 asset_url += '?' + entitlement['uplynkData']['sessionKey']
 259                 formats.extend(self._extract_m3u8_formats(
 260                     asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
 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         subtitles = {}
 285         for cc in video_data.get('closedcaption', {}).get('src', []):
 286             cc_url = cc.get('value')
 287             if not cc_url:
 288                 continue
 289             ext = determine_ext(cc_url)
 290             if ext == 'xml':
 291                 ext = 'ttml'
 292             subtitles.setdefault(cc.get('lang'), []).append({
 293                 'url': cc_url,
 294                 'ext': ext,
 295             })
 296
 297         thumbnails = []
 298         for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []):
 299             thumbnail_url = thumbnail.get('value')
 300             if not thumbnail_url:
 301                 continue
 302             thumbnails.append({
 303                 'url': thumbnail_url,
 304                 'width': int_or_none(thumbnail.get('width')),
 305                 'height': int_or_none(thumbnail.get('height')),
 306             })
 307
 308         return {
 309             'id': video_id,
 310             'title': title,
 311             'description': video_data.get('longdescription') or video_data.get('description'),
 312             'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000),
 313             'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')),
 314             'episode_number': int_or_none(video_data.get('episodenumber')),
 315             'series': video_data.get('show', {}).get('title'),
 316             'season_number': int_or_none(video_data.get('season', {}).get('num')),
 317             'thumbnails': thumbnails,
 318             'formats': formats,
 319             'subtitles': subtitles,
 320         }