yt_dlp/extractor/wetv.py

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