yt_dlp/extractor/thisav.py

   1 from .common import InfoExtractor
   2 from ..utils import remove_end
   3
   4
   5 class ThisAVIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
   7     _TESTS = [{
   8         # jwplayer
   9         'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
  10         'md5': '0480f1ef3932d901f0e0e719f188f19b',
  11         'info_dict': {
  12             'id': '47734',
  13             'ext': 'flv',
  14             'title': '高樹マリア - Just fit',
  15             'uploader': 'dj7970',
  16             'uploader_id': 'dj7970'
  17         }
  18     }, {
  19         # html5 media
  20         'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html',
  21         'md5': 'ba90c076bd0f80203679e5b60bf523ee',
  22         'info_dict': {
  23             'id': '242352',
  24             'ext': 'mp4',
  25             'title': 'Nerdy 18yo Big Ass Tattoos and Glasses',
  26             'uploader': 'cybersluts',
  27             'uploader_id': 'cybersluts',
  28         },
  29     }]
  30
  31     def _real_extract(self, url):
  32         mobj = self._match_valid_url(url)
  33
  34         video_id = mobj.group('id')
  35         webpage = self._download_webpage(url, video_id)
  36         title = remove_end(self._html_extract_title(webpage), ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站')
  37         video_url = self._html_search_regex(
  38             r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
  39         if video_url:
  40             info_dict = {
  41                 'formats': [{
  42                     'url': video_url,
  43                 }],
  44             }
  45         else:
  46             entries = self._parse_html5_media_entries(url, webpage, video_id)
  47             if entries:
  48                 info_dict = entries[0]
  49             else:
  50                 info_dict = self._extract_jwplayer_data(
  51                     webpage, video_id, require_title=False)
  52         uploader = self._html_search_regex(
  53             r': <a href="http://www\.thisav\.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
  54             webpage, 'uploader name', fatal=False)
  55         uploader_id = self._html_search_regex(
  56             r': <a href="http://www\.thisav\.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
  57             webpage, 'uploader id', fatal=False)
  58
  59         info_dict.update({
  60             'id': video_id,
  61             'uploader': uploader,
  62             'uploader_id': uploader_id,
  63             'title': title,
  64         })
  65
  66         return info_dict