yt_dlp/extractor/wetv.py

   1 import functools
   2 import re
   3 import time
   4
   5 from .common import InfoExtractor
   6 from ..aes import aes_cbc_encrypt_bytes
   7 from ..utils import determine_ext, int_or_none, traverse_obj, urljoin
   8
   9
  10 class WeTvBaseIE(InfoExtractor):
  11     _VALID_URL_BASE = r'https?://(?:www\.)?wetv\.vip/(?:[^?#]+/)?play'
  12
  13     def _get_ckey(self, video_id, url, app_version, platform):
  14         ua = self.get_param('http_headers')['User-Agent']
  15
  16         payload = (f'{video_id}|{int(time.time())}|mg3c3b04ba|{app_version}|0000000000000000|'
  17                    f'{platform}|{url[:48]}|{ua.lower()[:48]}||Mozilla|Netscape|Win32|00|')
  18
  19         return aes_cbc_encrypt_bytes(
  20             bytes(f'|{sum(map(ord, payload))}|{payload}', 'utf-8'),
  21             b'Ok\xda\xa3\x9e/\x8c\xb0\x7f^r-\x9e\xde\xf3\x14',
  22             b'\x01PJ\xf3V\xe6\x19\xcf.B\xbb\xa6\x8c?p\xf9',
  23             padding_mode='whitespace').hex()
  24
  25     def _get_video_api_response(self, video_url, video_id, series_id, subtitle_format, video_format, video_quality):
  26         app_version = '3.5.57'
  27         platform = '4830201'
  28
  29         ckey = self._get_ckey(video_id, video_url, app_version, platform)
  30         query = {
  31             'vid': video_id,
  32             'cid': series_id,
  33             'cKey': ckey,
  34             'encryptVer': '8.1',
  35             'spcaptiontype': '1' if subtitle_format == 'vtt' else '0',  # 0 - SRT, 1 - VTT
  36             'sphls': '1' if video_format == 'hls' else '0',  # 0 - MP4, 1 - HLS
  37             'defn': video_quality,  # '': 480p, 'shd': 720p, 'fhd': 1080p
  38             'spsrt': '1',  # Enable subtitles
  39             'sphttps': '1',  # Enable HTTPS
  40             'otype': 'json',  # Response format: xml, json,
  41             'dtype': '1',
  42             'spwm': '1',
  43             'host': 'wetv.vip',  # These three values are needed for SHD
  44             'referer': 'wetv.vip',
  45             'ehost': video_url,
  46             'appVer': app_version,
  47             'platform': platform,
  48         }
  49
  50         return self._search_json(r'QZOutputJson=', self._download_webpage(
  51             'https://play.wetv.vip/getvinfo', video_id, query=query), 'api_response', video_id)
  52
  53     def _get_webpage_metadata(self, webpage, video_id):
  54         return self._parse_json(
  55             traverse_obj(self._search_nextjs_data(webpage, video_id), ('props', 'pageProps', 'data')),
  56             video_id, fatal=False)
  57
  58
  59 class WeTvEpisodeIE(WeTvBaseIE):
  60     IE_NAME = 'wetv:episode'
  61     _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'
  62
  63     _TESTS = [{
  64         'url': 'https://wetv.vip/en/play/air11ooo2rdsdi3-Cute-Programmer/v0040pr89t9-EP1-Cute-Programmer',
  65         'md5': 'a046f565c9dce9b263a0465a422cd7bf',
  66         'info_dict': {
  67             'id': 'v0040pr89t9',
  68             'ext': 'mp4',
  69             'title': 'EP1: Cute Programmer',
  70             'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
  71             'thumbnail': r're:^https?://[^?#]+air11ooo2rdsdi3',
  72             'series': 'Cute Programmer',
  73             'episode': 'Episode 1',
  74             'episode_number': 1,
  75             'duration': 2835,
  76         },
  77     }, {
  78         'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu/p0039b9nvik',
  79         'md5': '4d9d69bcfd11da61f4aae64fc6b316b3',
  80         'info_dict': {
  81             'id': 'p0039b9nvik',
  82             'ext': 'mp4',
  83             'title': 'EP1: You Are My Glory',
  84             'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
  85             'thumbnail': r're:^https?://[^?#]+u37kgfnfzs73kiu',
  86             'series': 'You Are My Glory',
  87             'episode': 'Episode 1',
  88             'episode_number': 1,
  89             'duration': 2454,
  90         },
  91     }, {
  92         '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',
  93         'md5': '71133f5c2d5d6cad3427e1b010488280',
  94         'info_dict': {
  95             'id': 'i0042y00lxp',
  96             'ext': 'mp4',
  97             'title': 'md5:f7a0857dbe5fbbe2e7ad630b92b54e6a',
  98             'description': 'md5:76260cb9cdc0ef76826d7ca9d92fadfa',
  99             'thumbnail': r're:^https?://[^?#]+lcxgwod5hapghvw',
 100             'series': 'WeTV PICK-A-BOO',
 101             'episode': 'Episode 0',
 102             'episode_number': 0,
 103             'duration': 442,
 104         },
 105     }]
 106
 107     def _extract_video_formats_and_subtitles(self, api_response, video_id, video_quality):
 108         video_response = api_response['vl']['vi'][0]
 109         video_width = video_response.get('vw')
 110         video_height = video_response.get('vh')
 111
 112         formats, subtitles = [], {}
 113         for video_format in video_response['ul']['ui']:
 114             if video_format.get('hls'):
 115                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
 116                     video_format['url'] + video_format['hls']['pname'], video_id, 'mp4', fatal=False)
 117                 for f in fmts:
 118                     f['width'] = video_width
 119                     f['height'] = video_height
 120
 121                 formats.extend(fmts)
 122                 self._merge_subtitles(subs, target=subtitles)
 123             else:
 124                 formats.append({
 125                     'url': f'{video_format["url"]}{video_response["fn"]}?vkey={video_response["fvkey"]}',
 126                     'width': video_width,
 127                     'height': video_height,
 128                     'ext': 'mp4',
 129                 })
 130
 131         return formats, subtitles
 132
 133     def _extract_video_subtitles(self, api_response, subtitles_format):
 134         subtitles = {}
 135         for subtitle in traverse_obj(api_response, ('sfl', 'fi')):
 136             subtitles.setdefault(subtitle['lang'].lower(), []).append({
 137                 'url': subtitle['url'],
 138                 'ext': subtitles_format,
 139                 'protocol': 'm3u8_native' if determine_ext(subtitle['url']) == 'm3u8' else 'http',
 140             })
 141
 142         return subtitles
 143
 144     def _real_extract(self, url):
 145         video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
 146         webpage = self._download_webpage(url, video_id)
 147
 148         formats, subtitles = [], {}
 149         for video_format, subtitle_format, video_quality in (('mp4', 'srt', ''), ('hls', 'vtt', 'shd'), ('hls', 'vtt', 'fhd')):
 150             api_response = self._get_video_api_response(url, video_id, series_id, subtitle_format, video_format, video_quality)
 151
 152             fmts, subs = self._extract_video_formats_and_subtitles(api_response, video_id, video_quality)
 153             native_subtitles = self._extract_video_subtitles(api_response, subtitle_format)
 154
 155             formats.extend(fmts)
 156             self._merge_subtitles(subs, native_subtitles, target=subtitles)
 157
 158         self._sort_formats(formats)
 159         webpage_metadata = self._get_webpage_metadata(webpage, video_id)
 160
 161         return {
 162             'id': video_id,
 163             'title': (self._og_search_title(webpage)
 164                       or traverse_obj(webpage_metadata, ('coverInfo', 'description'))),
 165             'description': (self._og_search_description(webpage)
 166                             or traverse_obj(webpage_metadata, ('coverInfo', 'description'))),
 167             'formats': formats,
 168             'subtitles': subtitles,
 169             'thumbnail': self._og_search_thumbnail(webpage),
 170             'duration': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'duration'))),
 171             'series': traverse_obj(webpage_metadata, ('coverInfo', 'title')),
 172             'episode_number': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'episode'))),
 173         }
 174
 175
 176 class WeTvSeriesIE(WeTvBaseIE):
 177     _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]|$)'
 178
 179     _TESTS = [{
 180         'url': 'https://wetv.vip/play/air11ooo2rdsdi3-Cute-Programmer',
 181         'info_dict': {
 182             'id': 'air11ooo2rdsdi3',
 183             'title': 'Cute Programmer',
 184             'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
 185         },
 186         'playlist_count': 30,
 187     }, {
 188         'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu-You-Are-My-Glory',
 189         'info_dict': {
 190             'id': 'u37kgfnfzs73kiu',
 191             'title': 'You Are My Glory',
 192             'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
 193         },
 194         'playlist_count': 32,
 195     }]
 196
 197     def _real_extract(self, url):
 198         series_id = self._match_id(url)
 199         webpage = self._download_webpage(url, series_id)
 200         webpage_metadata = self._get_webpage_metadata(webpage, series_id)
 201
 202         episode_paths = (re.findall(r'<a[^>]+class="play-video__link"[^>]+href="(?P<path>[^"]+)', webpage)
 203                          or [f'/{series_id}/{episode["vid"]}' for episode in webpage_metadata.get('videoList')])
 204
 205         return self.playlist_from_matches(
 206             episode_paths, series_id, ie=WeTvEpisodeIE, getter=functools.partial(urljoin, url),
 207             title=traverse_obj(webpage_metadata, ('coverInfo', 'title')) or self._og_search_title(webpage),
 208             description=traverse_obj(webpage_metadata, ('coverInfo', 'description')) or self._og_search_description(webpage))