yt_dlp/extractor/tencent.py

   1 import random
   2 import re
   3 import string
   4 import time
   5
   6 from .common import InfoExtractor
   7 from ..aes import aes_cbc_encrypt_bytes
   8 from ..utils import (
   9     ExtractorError,
  10     determine_ext,
  11     float_or_none,
  12     int_or_none,
  13     js_to_json,
  14     traverse_obj,
  15     urljoin,
  16 )
  17
  18
  19 class TencentBaseIE(InfoExtractor):
  20     """Subclasses must set _API_URL, _APP_VERSION, _PLATFORM, _HOST, _REFERER"""
  21
  22     def _check_api_response(self, api_response):
  23         msg = api_response.get('msg')
  24         if api_response.get('code') != '0.0' and msg is not None:
  25             if msg in (
  26                 '您所在区域暂无此内容版权（如设置VPN请关闭后重试）',
  27                 'This content is not available in your area due to copyright restrictions. Please choose other videos.',
  28             ):
  29                 self.raise_geo_restricted()
  30             raise ExtractorError(f'Tencent said: {msg}')
  31
  32     def _get_ckey(self, video_id, url, guid):
  33         ua = self.get_param('http_headers')['User-Agent']
  34
  35         payload = (f'{video_id}|{int(time.time())}|mg3c3b04ba|{self._APP_VERSION}|{guid}|'
  36                    f'{self._PLATFORM}|{url[:48]}|{ua.lower()[:48]}||Mozilla|Netscape|Windows x86_64|00|')
  37
  38         return aes_cbc_encrypt_bytes(
  39             bytes(f'|{sum(map(ord, payload))}|{payload}', 'utf-8'),
  40             b'Ok\xda\xa3\x9e/\x8c\xb0\x7f^r-\x9e\xde\xf3\x14',
  41             b'\x01PJ\xf3V\xe6\x19\xcf.B\xbb\xa6\x8c?p\xf9',
  42             padding_mode='whitespace').hex().upper()
  43
  44     def _get_video_api_response(self, video_url, video_id, series_id, subtitle_format, video_format, video_quality):
  45         guid = ''.join(random.choices(string.digits + string.ascii_lowercase, k=16))
  46         ckey = self._get_ckey(video_id, video_url, guid)
  47         query = {
  48             'vid': video_id,
  49             'cid': series_id,
  50             'cKey': ckey,
  51             'encryptVer': '8.1',
  52             'spcaptiontype': '1' if subtitle_format == 'vtt' else '0',
  53             'sphls': '2' if video_format == 'hls' else '0',
  54             'dtype': '3' if video_format == 'hls' else '0',
  55             'defn': video_quality,
  56             'spsrt': '2',  # Enable subtitles
  57             'sphttps': '1',  # Enable HTTPS
  58             'otype': 'json',
  59             'spwm': '1',
  60             'hevclv': '28',  # Enable HEVC
  61             'drm': '40',  # Enable DRM
  62             # For HDR
  63             'spvideo': '4',
  64             'spsfrhdr': '100',
  65             # For SHD
  66             'host': self._HOST,
  67             'referer': self._REFERER,
  68             'ehost': video_url,
  69             'appVer': self._APP_VERSION,
  70             'platform': self._PLATFORM,
  71             # For VQQ
  72             'guid': guid,
  73             'flowid': ''.join(random.choices(string.digits + string.ascii_lowercase, k=32)),
  74         }
  75
  76         return self._search_json(r'QZOutputJson=', self._download_webpage(
  77             self._API_URL, video_id, query=query), 'api_response', video_id)
  78
  79     def _extract_video_formats_and_subtitles(self, api_response, video_id):
  80         video_response = api_response['vl']['vi'][0]
  81
  82         formats, subtitles = [], {}
  83         for video_format in video_response['ul']['ui']:
  84             if video_format.get('hls') or determine_ext(video_format['url']) == 'm3u8':
  85                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
  86                     video_format['url'] + traverse_obj(video_format, ('hls', 'pt'), default=''),
  87                     video_id, 'mp4', fatal=False)
  88
  89                 formats.extend(fmts)
  90                 self._merge_subtitles(subs, target=subtitles)
  91             else:
  92                 formats.append({
  93                     'url': f'{video_format["url"]}{video_response["fn"]}?vkey={video_response["fvkey"]}',
  94                     'ext': 'mp4',
  95                 })
  96
  97         identifier = video_response.get('br')
  98         format_response = traverse_obj(
  99             api_response, ('fl', 'fi', lambda _, v: v['br'] == identifier),
 100             expected_type=dict, get_all=False) or {}
 101         common_info = {
 102             'width': video_response.get('vw'),
 103             'height': video_response.get('vh'),
 104             'abr': float_or_none(format_response.get('audiobandwidth'), scale=1000),
 105             'vbr': float_or_none(format_response.get('bandwidth'), scale=1000),
 106             'fps': format_response.get('vfps'),
 107             'format': format_response.get('sname'),
 108             'format_id': format_response.get('name'),
 109             'format_note': format_response.get('resolution'),
 110             'dynamic_range': {'hdr10': 'hdr10'}.get(format_response.get('name'), 'sdr'),
 111             'has_drm': format_response.get('drm', 0) != 0,
 112         }
 113         for f in formats:
 114             f.update(common_info)
 115
 116         return formats, subtitles
 117
 118     def _extract_video_native_subtitles(self, api_response):
 119         subtitles = {}
 120         for subtitle in traverse_obj(api_response, ('sfl', 'fi')) or ():
 121             subtitles.setdefault(subtitle['lang'].lower(), []).append({
 122                 'url': subtitle['url'],
 123                 'ext': 'srt' if subtitle.get('captionType') == 1 else 'vtt',
 124                 'protocol': 'm3u8_native' if determine_ext(subtitle['url']) == 'm3u8' else 'http',
 125             })
 126
 127         return subtitles
 128
 129     def _extract_all_video_formats_and_subtitles(self, url, video_id, series_id):
 130         api_responses = [self._get_video_api_response(url, video_id, series_id, 'srt', 'hls', 'hd')]
 131         self._check_api_response(api_responses[0])
 132         qualities = traverse_obj(api_responses, (0, 'fl', 'fi', ..., 'name')) or ('shd', 'fhd')
 133         for q in qualities:
 134             if q not in ('ld', 'sd', 'hd'):
 135                 api_responses.append(self._get_video_api_response(
 136                     url, video_id, series_id, 'vtt', 'hls', q))
 137                 self._check_api_response(api_responses[-1])
 138
 139         formats, subtitles = [], {}
 140         for api_response in api_responses:
 141             fmts, subs = self._extract_video_formats_and_subtitles(api_response, video_id)
 142             native_subtitles = self._extract_video_native_subtitles(api_response)
 143
 144             formats.extend(fmts)
 145             self._merge_subtitles(subs, native_subtitles, target=subtitles)
 146
 147         return formats, subtitles
 148
 149     def _get_clean_title(self, title):
 150         return re.sub(
 151             r'\s*[_\-]\s*(?:Watch online|Watch HD Video Online|WeTV|腾讯视频|(?:高清)?1080P在线观看平台).*?$',
 152             '', title or '').strip() or None
 153
 154
 155 class VQQBaseIE(TencentBaseIE):
 156     _VALID_URL_BASE = r'https?://v\.qq\.com'
 157
 158     _API_URL = 'https://h5vv6.video.qq.com/getvinfo'
 159     _APP_VERSION = '3.5.57'
 160     _PLATFORM = '10901'
 161     _HOST = 'v.qq.com'
 162     _REFERER = 'v.qq.com'
 163
 164     def _get_webpage_metadata(self, webpage, video_id):
 165         return self._search_json(
 166             r'<script[^>]*>[^<]*window\.__(?:pinia|PINIA__)\s*=',
 167             webpage, 'pinia data', video_id, transform_source=js_to_json, fatal=False)
 168
 169
 170 class VQQVideoIE(VQQBaseIE):
 171     IE_NAME = 'vqq:video'
 172     _VALID_URL = VQQBaseIE._VALID_URL_BASE + r'/x/(?:page|cover/(?P<series_id>\w+))/(?P<id>\w+)'
 173
 174     _TESTS = [{
 175         'url': 'https://v.qq.com/x/page/q326831cny0.html',
 176         'md5': 'b11c9cb781df710d686b950376676e2a',
 177         'info_dict': {
 178             'id': 'q326831cny0',
 179             'ext': 'mp4',
 180             'title': '我是选手：雷霆裂阵，终极时刻',
 181             'description': 'md5:e7ed70be89244017dac2a835a10aeb1e',
 182             'thumbnail': r're:^https?://[^?#]+q326831cny0',
 183             'format_id': r're:^shd',
 184         },
 185     }, {
 186         'url': 'https://v.qq.com/x/page/o3013za7cse.html',
 187         'md5': 'a1bcf42c6d28c189bd2fe2d468abb287',
 188         'info_dict': {
 189             'id': 'o3013za7cse',
 190             'ext': 'mp4',
 191             'title': '欧阳娜娜VLOG',
 192             'description': 'md5:29fe847497a98e04a8c3826e499edd2e',
 193             'thumbnail': r're:^https?://[^?#]+o3013za7cse',
 194             'format_id': r're:^shd',
 195         },
 196     }, {
 197         'url': 'https://v.qq.com/x/cover/7ce5noezvafma27/a00269ix3l8.html',
 198         'md5': '87968df6238a65d2478f19c25adf850b',
 199         'info_dict': {
 200             'id': 'a00269ix3l8',
 201             'ext': 'mp4',
 202             'title': '鸡毛飞上天 第01集',
 203             'description': 'md5:8cae3534327315b3872fbef5e51b5c5b',
 204             'thumbnail': r're:^https?://[^?#]+7ce5noezvafma27',
 205             'series': '鸡毛飞上天',
 206             'format_id': r're:^shd',
 207         },
 208         'skip': '404',
 209     }, {
 210         'url': 'https://v.qq.com/x/cover/mzc00200p29k31e/s0043cwsgj0.html',
 211         'md5': 'fadd10bf88aec3420f06f19ee1d24c5b',
 212         'info_dict': {
 213             'id': 's0043cwsgj0',
 214             'ext': 'mp4',
 215             'title': '第1集：如何快乐吃糖？',
 216             'description': 'md5:1d8c3a0b8729ae3827fa5b2d3ebd5213',
 217             'thumbnail': r're:^https?://[^?#]+s0043cwsgj0',
 218             'series': '青年理工工作者生活研究所',
 219             'format_id': r're:^shd',
 220         },
 221         'params': {'skip_download': 'm3u8'},
 222     }, {
 223         # Geo-restricted to China
 224         'url': 'https://v.qq.com/x/cover/mcv8hkc8zk8lnov/x0036x5qqsr.html',
 225         'only_matching': True,
 226     }]
 227
 228     def _real_extract(self, url):
 229         video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
 230         webpage = self._download_webpage(url, video_id)
 231         webpage_metadata = self._get_webpage_metadata(webpage, video_id)
 232
 233         formats, subtitles = self._extract_all_video_formats_and_subtitles(url, video_id, series_id)
 234         return {
 235             'id': video_id,
 236             'title': self._get_clean_title(self._og_search_title(webpage)
 237                                            or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'title'))),
 238             'description': (self._og_search_description(webpage)
 239                             or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'desc'))),
 240             'formats': formats,
 241             'subtitles': subtitles,
 242             'thumbnail': (self._og_search_thumbnail(webpage)
 243                           or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'pic160x90'))),
 244             'series': traverse_obj(webpage_metadata, ('global', 'coverInfo', 'title')),
 245         }
 246
 247
 248 class VQQSeriesIE(VQQBaseIE):
 249     IE_NAME = 'vqq:series'
 250     _VALID_URL = VQQBaseIE._VALID_URL_BASE + r'/x/cover/(?P<id>\w+)\.html/?(?:[?#]|$)'
 251
 252     _TESTS = [{
 253         'url': 'https://v.qq.com/x/cover/7ce5noezvafma27.html',
 254         'info_dict': {
 255             'id': '7ce5noezvafma27',
 256             'title': '鸡毛飞上天',
 257             'description': 'md5:8cae3534327315b3872fbef5e51b5c5b',
 258         },
 259         'playlist_count': 55,
 260     }, {
 261         'url': 'https://v.qq.com/x/cover/oshd7r0vy9sfq8e.html',
 262         'info_dict': {
 263             'id': 'oshd7r0vy9sfq8e',
 264             'title': '恋爱细胞2',
 265             'description': 'md5:9d8a2245679f71ca828534b0f95d2a03',
 266         },
 267         'playlist_count': 12,
 268     }]
 269
 270     def _real_extract(self, url):
 271         series_id = self._match_id(url)
 272         webpage = self._download_webpage(url, series_id)
 273         webpage_metadata = self._get_webpage_metadata(webpage, series_id)
 274
 275         episode_paths = [f'/x/cover/{series_id}/{video_id}.html' for video_id in re.findall(
 276             r'<div[^>]+data-vid="(?P<video_id>[^"]+)"[^>]+class="[^"]+episode-item-rect--number',
 277             webpage)]
 278
 279         return self.playlist_from_matches(
 280             episode_paths, series_id, ie=VQQVideoIE, getter=urljoin(url),
 281             title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
 282                                         or self._og_search_title(webpage)),
 283             description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
 284                          or self._og_search_description(webpage)))
 285
 286
 287 class WeTvBaseIE(TencentBaseIE):
 288     _VALID_URL_BASE = r'https?://(?:www\.)?wetv\.vip/(?:[^?#]+/)?play'
 289
 290     _API_URL = 'https://play.wetv.vip/getvinfo'
 291     _APP_VERSION = '3.5.57'
 292     _PLATFORM = '4830201'
 293     _HOST = 'wetv.vip'
 294     _REFERER = 'wetv.vip'
 295
 296     def _get_webpage_metadata(self, webpage, video_id):
 297         return self._parse_json(
 298             traverse_obj(self._search_nextjs_data(webpage, video_id), ('props', 'pageProps', 'data')),
 299             video_id, fatal=False)
 300
 301     def _extract_episode(self, url):
 302         video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
 303         webpage = self._download_webpage(url, video_id)
 304         webpage_metadata = self._get_webpage_metadata(webpage, video_id)
 305
 306         formats, subtitles = self._extract_all_video_formats_and_subtitles(url, video_id, series_id)
 307         return {
 308             'id': video_id,
 309             'title': self._get_clean_title(self._og_search_title(webpage)
 310                                            or traverse_obj(webpage_metadata, ('coverInfo', 'title'))),
 311             'description': (traverse_obj(webpage_metadata, ('coverInfo', 'description'))
 312                             or self._og_search_description(webpage)),
 313             'formats': formats,
 314             'subtitles': subtitles,
 315             'thumbnail': self._og_search_thumbnail(webpage),
 316             'duration': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'duration'))),
 317             'series': traverse_obj(webpage_metadata, ('coverInfo', 'title')),
 318             'episode_number': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'episode'))),
 319         }
 320
 321     def _extract_series(self, url, ie):
 322         series_id = self._match_id(url)
 323         webpage = self._download_webpage(url, series_id)
 324         webpage_metadata = self._get_webpage_metadata(webpage, series_id)
 325
 326         episode_paths = ([f'/play/{series_id}/{episode["vid"]}' for episode in webpage_metadata.get('videoList')]
 327                          or re.findall(r'<a[^>]+class="play-video__link"[^>]+href="(?P<path>[^"]+)', webpage))
 328
 329         return self.playlist_from_matches(
 330             episode_paths, series_id, ie=ie, getter=urljoin(url),
 331             title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
 332                                         or self._og_search_title(webpage)),
 333             description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
 334                          or self._og_search_description(webpage)))
 335
 336
 337 class WeTvEpisodeIE(WeTvBaseIE):
 338     IE_NAME = 'wetv:episode'
 339     _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'
 340
 341     _TESTS = [{
 342         'url': 'https://wetv.vip/en/play/air11ooo2rdsdi3-Cute-Programmer/v0040pr89t9-EP1-Cute-Programmer',
 343         'md5': '0c70fdfaa5011ab022eebc598e64bbbe',
 344         'info_dict': {
 345             'id': 'v0040pr89t9',
 346             'ext': 'mp4',
 347             'title': 'EP1: Cute Programmer',
 348             'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
 349             'thumbnail': r're:^https?://[^?#]+air11ooo2rdsdi3',
 350             'series': 'Cute Programmer',
 351             'episode': 'Episode 1',
 352             'episode_number': 1,
 353             'duration': 2835,
 354             'format_id': r're:^shd',
 355         },
 356     }, {
 357         'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu/p0039b9nvik',
 358         'md5': '3b3c15ca4b9a158d8d28d5aa9d7c0a49',
 359         'info_dict': {
 360             'id': 'p0039b9nvik',
 361             'ext': 'mp4',
 362             'title': 'EP1: You Are My Glory',
 363             'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
 364             'thumbnail': r're:^https?://[^?#]+u37kgfnfzs73kiu',
 365             'series': 'You Are My Glory',
 366             'episode': 'Episode 1',
 367             'episode_number': 1,
 368             'duration': 2454,
 369             'format_id': r're:^shd',
 370         },
 371     }, {
 372         'url': 'https://wetv.vip/en/play/lcxgwod5hapghvw-WeTV-PICK-A-BOO/i0042y00lxp-Zhao-Lusi-Describes-The-First-Experiences-She-Had-In-Who-Rules-The-World-%7C-WeTV-PICK-A-BOO',
 373         'md5': '71133f5c2d5d6cad3427e1b010488280',
 374         'info_dict': {
 375             'id': 'i0042y00lxp',
 376             'ext': 'mp4',
 377             'title': 'md5:f7a0857dbe5fbbe2e7ad630b92b54e6a',
 378             'description': 'md5:76260cb9cdc0ef76826d7ca9d92fadfa',
 379             'thumbnail': r're:^https?://[^?#]+i0042y00lxp',
 380             'series': 'WeTV PICK-A-BOO',
 381             'episode': 'Episode 0',
 382             'episode_number': 0,
 383             'duration': 442,
 384             'format_id': r're:^shd',
 385         },
 386     }]
 387
 388     def _real_extract(self, url):
 389         return self._extract_episode(url)
 390
 391
 392 class WeTvSeriesIE(WeTvBaseIE):
 393     _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]|$)'
 394
 395     _TESTS = [{
 396         'url': 'https://wetv.vip/play/air11ooo2rdsdi3-Cute-Programmer',
 397         'info_dict': {
 398             'id': 'air11ooo2rdsdi3',
 399             'title': 'Cute Programmer',
 400             'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
 401         },
 402         'playlist_count': 30,
 403     }, {
 404         'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu-You-Are-My-Glory',
 405         'info_dict': {
 406             'id': 'u37kgfnfzs73kiu',
 407             'title': 'You Are My Glory',
 408             'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
 409         },
 410         'playlist_count': 32,
 411     }]
 412
 413     def _real_extract(self, url):
 414         return self._extract_series(url, WeTvEpisodeIE)
 415
 416
 417 class IflixBaseIE(WeTvBaseIE):
 418     _VALID_URL_BASE = r'https?://(?:www\.)?iflix\.com/(?:[^?#]+/)?play'
 419
 420     _API_URL = 'https://vplay.iflix.com/getvinfo'
 421     _APP_VERSION = '3.5.57'
 422     _PLATFORM = '330201'
 423     _HOST = 'www.iflix.com'
 424     _REFERER = 'www.iflix.com'
 425
 426
 427 class IflixEpisodeIE(IflixBaseIE):
 428     IE_NAME = 'iflix:episode'
 429     _VALID_URL = IflixBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'
 430
 431     _TESTS = [{
 432         'url': 'https://www.iflix.com/en/play/daijrxu03yypu0s/a0040kvgaza',
 433         'md5': '9740f9338c3a2105290d16b68fb3262f',
 434         'info_dict': {
 435             'id': 'a0040kvgaza',
 436             'ext': 'mp4',
 437             'title': 'EP1: Put Your Head On My Shoulder 2021',
 438             'description': 'md5:c095a742d3b7da6dfedd0c8170727a42',
 439             'thumbnail': r're:^https?://[^?#]+daijrxu03yypu0s',
 440             'series': 'Put Your Head On My Shoulder 2021',
 441             'episode': 'Episode 1',
 442             'episode_number': 1,
 443             'duration': 2639,
 444             'format_id': r're:^shd',
 445         },
 446     }, {
 447         'url': 'https://www.iflix.com/en/play/fvvrcc3ra9lbtt1-Take-My-Brother-Away/i0029sd3gm1-EP1%EF%BC%9ATake-My-Brother-Away',
 448         'md5': '375c9b8478fdedca062274b2c2f53681',
 449         'info_dict': {
 450             'id': 'i0029sd3gm1',
 451             'ext': 'mp4',
 452             'title': 'EP1：Take My Brother Away',
 453             'description': 'md5:f0f7be1606af51cd94d5627de96b0c76',
 454             'thumbnail': r're:^https?://[^?#]+fvvrcc3ra9lbtt1',
 455             'series': 'Take My Brother Away',
 456             'episode': 'Episode 1',
 457             'episode_number': 1,
 458             'duration': 228,
 459             'format_id': r're:^shd',
 460         },
 461     }]
 462
 463     def _real_extract(self, url):
 464         return self._extract_episode(url)
 465
 466
 467 class IflixSeriesIE(IflixBaseIE):
 468     _VALID_URL = IflixBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]|$)'
 469
 470     _TESTS = [{
 471         'url': 'https://www.iflix.com/en/play/g21a6qk4u1s9x22-You-Are-My-Hero',
 472         'info_dict': {
 473             'id': 'g21a6qk4u1s9x22',
 474             'title': 'You Are My Hero',
 475             'description': 'md5:9c4d844bc0799cd3d2b5aed758a2050a',
 476         },
 477         'playlist_count': 40,
 478     }, {
 479         'url': 'https://www.iflix.com/play/0s682hc45t0ohll',
 480         'info_dict': {
 481             'id': '0s682hc45t0ohll',
 482             'title': 'Miss Gu Who Is Silent',
 483             'description': 'md5:a9651d0236f25af06435e845fa2f8c78',
 484         },
 485         'playlist_count': 20,
 486     }]
 487
 488     def _real_extract(self, url):
 489         return self._extract_series(url, IflixEpisodeIE)