yt_dlp/extractor/zattoo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 from uuid import uuid4
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_HTTPError,
  10     compat_str,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     int_or_none,
  15     join_nonempty,
  16     try_get,
  17     url_or_none,
  18     urlencode_postdata,
  19 )
  20
  21
  22 class ZattooPlatformBaseIE(InfoExtractor):
  23     _power_guide_hash = None
  24
  25     def _host_url(self):
  26         return 'https://%s' % (self._API_HOST if hasattr(self, '_API_HOST') else self._HOST)
  27
  28     def _login(self):
  29         username, password = self._get_login_info()
  30         if not username or not password:
  31             self.raise_login_required(
  32                 'A valid %s account is needed to access this media.'
  33                 % self._NETRC_MACHINE)
  34
  35         try:
  36             data = self._download_json(
  37                 '%s/zapi/v2/account/login' % self._host_url(), None, 'Logging in',
  38                 data=urlencode_postdata({
  39                     'login': username,
  40                     'password': password,
  41                     'remember': 'true',
  42                 }), headers={
  43                     'Referer': '%s/login' % self._host_url(),
  44                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
  45                 })
  46         except ExtractorError as e:
  47             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
  48                 raise ExtractorError(
  49                     'Unable to login: incorrect username and/or password',
  50                     expected=True)
  51             raise
  52
  53         self._power_guide_hash = data['session']['power_guide_hash']
  54
  55     def _real_initialize(self):
  56         webpage = self._download_webpage(
  57             self._host_url(), None, 'Downloading app token')
  58         app_token = self._html_search_regex(
  59             r'appToken\s*=\s*(["\'])(?P<token>(?:(?!\1).)+?)\1',
  60             webpage, 'app token', group='token')
  61         app_version = self._html_search_regex(
  62             r'<!--\w+-(.+?)-', webpage, 'app version', default='2.8.2')
  63
  64         # Will setup appropriate cookies
  65         self._request_webpage(
  66             '%s/zapi/v2/session/hello' % self._host_url(), None,
  67             'Opening session', data=urlencode_postdata({
  68                 'client_app_token': app_token,
  69                 'uuid': compat_str(uuid4()),
  70                 'lang': 'en',
  71                 'app_version': app_version,
  72                 'format': 'json',
  73             }))
  74
  75         self._login()
  76
  77     def _extract_cid(self, video_id, channel_name):
  78         channel_groups = self._download_json(
  79             '%s/zapi/v2/cached/channels/%s' % (self._host_url(),
  80                                                self._power_guide_hash),
  81             video_id, 'Downloading channel list',
  82             query={'details': False})['channel_groups']
  83         channel_list = []
  84         for chgrp in channel_groups:
  85             channel_list.extend(chgrp['channels'])
  86         try:
  87             return next(
  88                 chan['cid'] for chan in channel_list
  89                 if chan.get('cid') and (
  90                     chan.get('display_alias') == channel_name
  91                     or chan.get('cid') == channel_name))
  92         except StopIteration:
  93             raise ExtractorError('Could not extract channel id')
  94
  95     def _extract_cid_and_video_info(self, video_id):
  96         data = self._download_json(
  97             '%s/zapi/v2/cached/program/power_details/%s' % (
  98                 self._host_url(), self._power_guide_hash),
  99             video_id,
 100             'Downloading video information',
 101             query={
 102                 'program_ids': video_id,
 103                 'complete': True,
 104             })
 105
 106         p = data['programs'][0]
 107         cid = p['cid']
 108
 109         info_dict = {
 110             'id': video_id,
 111             'title': p.get('t') or p['et'],
 112             'description': p.get('d'),
 113             'thumbnail': p.get('i_url'),
 114             'creator': p.get('channel_name'),
 115             'episode': p.get('et'),
 116             'episode_number': int_or_none(p.get('e_no')),
 117             'season_number': int_or_none(p.get('s_no')),
 118             'release_year': int_or_none(p.get('year')),
 119             'categories': try_get(p, lambda x: x['c'], list),
 120             'tags': try_get(p, lambda x: x['g'], list)
 121         }
 122
 123         return cid, info_dict
 124
 125     def _extract_formats(self, cid, video_id, record_id=None, is_live=False):
 126         postdata_common = {
 127             'https_watch_urls': True,
 128         }
 129
 130         if is_live:
 131             postdata_common.update({'timeshift': 10800})
 132             url = '%s/zapi/watch/live/%s' % (self._host_url(), cid)
 133         elif record_id:
 134             url = '%s/zapi/watch/recording/%s' % (self._host_url(), record_id)
 135         else:
 136             url = '%s/zapi/watch/recall/%s/%s' % (self._host_url(), cid, video_id)
 137
 138         formats = []
 139         for stream_type in ('dash', 'hls', 'hls5', 'hds'):
 140             postdata = postdata_common.copy()
 141             postdata['stream_type'] = stream_type
 142
 143             data = self._download_json(
 144                 url, video_id, 'Downloading %s formats' % stream_type.upper(),
 145                 data=urlencode_postdata(postdata), fatal=False)
 146             if not data:
 147                 continue
 148
 149             watch_urls = try_get(
 150                 data, lambda x: x['stream']['watch_urls'], list)
 151             if not watch_urls:
 152                 continue
 153
 154             for watch in watch_urls:
 155                 if not isinstance(watch, dict):
 156                     continue
 157                 watch_url = url_or_none(watch.get('url'))
 158                 if not watch_url:
 159                     continue
 160                 audio_channel = watch.get('audio_channel')
 161                 preference = 1 if audio_channel == 'A' else None
 162                 format_id = join_nonempty(stream_type, watch.get('maxrate'), audio_channel)
 163                 if stream_type in ('dash', 'dash_widevine', 'dash_playready'):
 164                     this_formats = self._extract_mpd_formats(
 165                         watch_url, video_id, mpd_id=format_id, fatal=False)
 166                 elif stream_type in ('hls', 'hls5', 'hls5_fairplay'):
 167                     this_formats = self._extract_m3u8_formats(
 168                         watch_url, video_id, 'mp4',
 169                         entry_protocol='m3u8_native', m3u8_id=format_id,
 170                         fatal=False)
 171                 elif stream_type == 'hds':
 172                     this_formats = self._extract_f4m_formats(
 173                         watch_url, video_id, f4m_id=format_id, fatal=False)
 174                 elif stream_type == 'smooth_playready':
 175                     this_formats = self._extract_ism_formats(
 176                         watch_url, video_id, ism_id=format_id, fatal=False)
 177                 else:
 178                     assert False
 179                 for this_format in this_formats:
 180                     this_format['quality'] = preference
 181                 formats.extend(this_formats)
 182         self._sort_formats(formats)
 183         return formats
 184
 185     def _extract_video(self, channel_name, video_id, record_id=None, is_live=False):
 186         if is_live:
 187             cid = self._extract_cid(video_id, channel_name)
 188             info_dict = {
 189                 'id': channel_name,
 190                 'title': self._live_title(channel_name),
 191                 'is_live': True,
 192             }
 193         else:
 194             cid, info_dict = self._extract_cid_and_video_info(video_id)
 195         formats = self._extract_formats(
 196             cid, video_id, record_id=record_id, is_live=is_live)
 197         info_dict['formats'] = formats
 198         return info_dict
 199
 200
 201 class QuicklineBaseIE(ZattooPlatformBaseIE):
 202     _NETRC_MACHINE = 'quickline'
 203     _HOST = 'mobiltv.quickline.com'
 204
 205
 206 class QuicklineIE(QuicklineBaseIE):
 207     _VALID_URL = r'https?://(?:www\.)?%s/watch/(?P<channel>[^/]+)/(?P<id>[0-9]+)' % re.escape(QuicklineBaseIE._HOST)
 208
 209     _TEST = {
 210         'url': 'https://mobiltv.quickline.com/watch/prosieben/130671867-maze-runner-die-auserwaehlten-in-der-brandwueste',
 211         'only_matching': True,
 212     }
 213
 214     def _real_extract(self, url):
 215         channel_name, video_id = self._match_valid_url(url).groups()
 216         return self._extract_video(channel_name, video_id)
 217
 218
 219 class QuicklineLiveIE(QuicklineBaseIE):
 220     _VALID_URL = r'https?://(?:www\.)?%s/watch/(?P<id>[^/]+)' % re.escape(QuicklineBaseIE._HOST)
 221
 222     _TEST = {
 223         'url': 'https://mobiltv.quickline.com/watch/srf1',
 224         'only_matching': True,
 225     }
 226
 227     @classmethod
 228     def suitable(cls, url):
 229         return False if QuicklineIE.suitable(url) else super(QuicklineLiveIE, cls).suitable(url)
 230
 231     def _real_extract(self, url):
 232         channel_name = video_id = self._match_id(url)
 233         return self._extract_video(channel_name, video_id, is_live=True)
 234
 235
 236 class ZattooBaseIE(ZattooPlatformBaseIE):
 237     _NETRC_MACHINE = 'zattoo'
 238     _HOST = 'zattoo.com'
 239
 240
 241 def _make_valid_url(tmpl, host):
 242     return tmpl % re.escape(host)
 243
 244
 245 class ZattooIE(ZattooBaseIE):
 246     _VALID_URL_TEMPLATE = r'https?://(?:www\.)?%s/watch/(?P<channel>[^/]+?)/(?P<id>[0-9]+)[^/]+(?:/(?P<recid>[0-9]+))?'
 247     _VALID_URL = _make_valid_url(_VALID_URL_TEMPLATE, ZattooBaseIE._HOST)
 248
 249     # Since regular videos are only available for 7 days and recorded videos
 250     # are only available for a specific user, we cannot have detailed tests.
 251     _TESTS = [{
 252         'url': 'https://zattoo.com/watch/prosieben/130671867-maze-runner-die-auserwaehlten-in-der-brandwueste',
 253         'only_matching': True,
 254     }, {
 255         'url': 'https://zattoo.com/watch/srf_zwei/132905652-eishockey-spengler-cup/102791477/1512211800000/1514433500000/92000',
 256         'only_matching': True,
 257     }]
 258
 259     def _real_extract(self, url):
 260         channel_name, video_id, record_id = self._match_valid_url(url).groups()
 261         return self._extract_video(channel_name, video_id, record_id)
 262
 263
 264 class ZattooLiveIE(ZattooBaseIE):
 265     _VALID_URL = r'https?://(?:www\.)?zattoo\.com/watch/(?P<id>[^/]+)'
 266
 267     _TEST = {
 268         'url': 'https://zattoo.com/watch/srf1',
 269         'only_matching': True,
 270     }
 271
 272     @classmethod
 273     def suitable(cls, url):
 274         return False if ZattooIE.suitable(url) else super(ZattooLiveIE, cls).suitable(url)
 275
 276     def _real_extract(self, url):
 277         channel_name = video_id = self._match_id(url)
 278         return self._extract_video(channel_name, video_id, is_live=True)
 279
 280
 281 class NetPlusIE(ZattooIE):
 282     _NETRC_MACHINE = 'netplus'
 283     _HOST = 'netplus.tv'
 284     _API_HOST = 'www.%s' % _HOST
 285     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 286
 287     _TESTS = [{
 288         'url': 'https://www.netplus.tv/watch/abc/123-abc',
 289         'only_matching': True,
 290     }]
 291
 292
 293 class MNetTVIE(ZattooIE):
 294     _NETRC_MACHINE = 'mnettv'
 295     _HOST = 'tvplus.m-net.de'
 296     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 297
 298     _TESTS = [{
 299         'url': 'https://tvplus.m-net.de/watch/abc/123-abc',
 300         'only_matching': True,
 301     }]
 302
 303
 304 class WalyTVIE(ZattooIE):
 305     _NETRC_MACHINE = 'walytv'
 306     _HOST = 'player.waly.tv'
 307     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 308
 309     _TESTS = [{
 310         'url': 'https://player.waly.tv/watch/abc/123-abc',
 311         'only_matching': True,
 312     }]
 313
 314
 315 class BBVTVIE(ZattooIE):
 316     _NETRC_MACHINE = 'bbvtv'
 317     _HOST = 'bbv-tv.net'
 318     _API_HOST = 'www.%s' % _HOST
 319     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 320
 321     _TESTS = [{
 322         'url': 'https://www.bbv-tv.net/watch/abc/123-abc',
 323         'only_matching': True,
 324     }]
 325
 326
 327 class VTXTVIE(ZattooIE):
 328     _NETRC_MACHINE = 'vtxtv'
 329     _HOST = 'vtxtv.ch'
 330     _API_HOST = 'www.%s' % _HOST
 331     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 332
 333     _TESTS = [{
 334         'url': 'https://www.vtxtv.ch/watch/abc/123-abc',
 335         'only_matching': True,
 336     }]
 337
 338
 339 class MyVisionTVIE(ZattooIE):
 340     _NETRC_MACHINE = 'myvisiontv'
 341     _HOST = 'myvisiontv.ch'
 342     _API_HOST = 'www.%s' % _HOST
 343     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 344
 345     _TESTS = [{
 346         'url': 'https://www.myvisiontv.ch/watch/abc/123-abc',
 347         'only_matching': True,
 348     }]
 349
 350
 351 class GlattvisionTVIE(ZattooIE):
 352     _NETRC_MACHINE = 'glattvisiontv'
 353     _HOST = 'iptv.glattvision.ch'
 354     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 355
 356     _TESTS = [{
 357         'url': 'https://iptv.glattvision.ch/watch/abc/123-abc',
 358         'only_matching': True,
 359     }]
 360
 361
 362 class SAKTVIE(ZattooIE):
 363     _NETRC_MACHINE = 'saktv'
 364     _HOST = 'saktv.ch'
 365     _API_HOST = 'www.%s' % _HOST
 366     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 367
 368     _TESTS = [{
 369         'url': 'https://www.saktv.ch/watch/abc/123-abc',
 370         'only_matching': True,
 371     }]
 372
 373
 374 class EWETVIE(ZattooIE):
 375     _NETRC_MACHINE = 'ewetv'
 376     _HOST = 'tvonline.ewe.de'
 377     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 378
 379     _TESTS = [{
 380         'url': 'https://tvonline.ewe.de/watch/abc/123-abc',
 381         'only_matching': True,
 382     }]
 383
 384
 385 class QuantumTVIE(ZattooIE):
 386     _NETRC_MACHINE = 'quantumtv'
 387     _HOST = 'quantum-tv.com'
 388     _API_HOST = 'www.%s' % _HOST
 389     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 390
 391     _TESTS = [{
 392         'url': 'https://www.quantum-tv.com/watch/abc/123-abc',
 393         'only_matching': True,
 394     }]
 395
 396
 397 class OsnatelTVIE(ZattooIE):
 398     _NETRC_MACHINE = 'osnateltv'
 399     _HOST = 'tvonline.osnatel.de'
 400     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 401
 402     _TESTS = [{
 403         'url': 'https://tvonline.osnatel.de/watch/abc/123-abc',
 404         'only_matching': True,
 405     }]
 406
 407
 408 class EinsUndEinsTVIE(ZattooIE):
 409     _NETRC_MACHINE = '1und1tv'
 410     _HOST = '1und1.tv'
 411     _API_HOST = 'www.%s' % _HOST
 412     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 413
 414     _TESTS = [{
 415         'url': 'https://www.1und1.tv/watch/abc/123-abc',
 416         'only_matching': True,
 417     }]
 418
 419
 420 class SaltTVIE(ZattooIE):
 421     _NETRC_MACHINE = 'salttv'
 422     _HOST = 'tv.salt.ch'
 423     _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST)
 424
 425     _TESTS = [{
 426         'url': 'https://tv.salt.ch/watch/abc/123-abc',
 427         'only_matching': True,
 428     }]