yt_dlp/extractor/thisav.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import remove_end
   7
   8
   9 class ThisAVIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
  11     _TESTS = [{
  12         # jwplayer
  13         'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
  14         'md5': '0480f1ef3932d901f0e0e719f188f19b',
  15         'info_dict': {
  16             'id': '47734',
  17             'ext': 'flv',
  18             'title': '高樹マリア - Just fit',
  19             'uploader': 'dj7970',
  20             'uploader_id': 'dj7970'
  21         }
  22     }, {
  23         # html5 media
  24         'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html',
  25         'md5': 'ba90c076bd0f80203679e5b60bf523ee',
  26         'info_dict': {
  27             'id': '242352',
  28             'ext': 'mp4',
  29             'title': 'Nerdy 18yo Big Ass Tattoos and Glasses',
  30             'uploader': 'cybersluts',
  31             'uploader_id': 'cybersluts',
  32         },
  33     }]
  34
  35     def _real_extract(self, url):
  36         mobj = self._match_valid_url(url)
  37
  38         video_id = mobj.group('id')
  39         webpage = self._download_webpage(url, video_id)
  40         title = remove_end(self._html_search_regex(
  41             r'<title>([^<]+)</title>', webpage, 'title'),
  42             ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站')
  43         video_url = self._html_search_regex(
  44             r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
  45         if video_url:
  46             info_dict = {
  47                 'formats': [{
  48                     'url': video_url,
  49                 }],
  50             }
  51         else:
  52             entries = self._parse_html5_media_entries(url, webpage, video_id)
  53             if entries:
  54                 info_dict = entries[0]
  55             else:
  56                 info_dict = self._extract_jwplayer_data(
  57                     webpage, video_id, require_title=False)
  58         uploader = self._html_search_regex(
  59             r': <a href="http://www\.thisav\.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
  60             webpage, 'uploader name', fatal=False)
  61         uploader_id = self._html_search_regex(
  62             r': <a href="http://www\.thisav\.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
  63             webpage, 'uploader id', fatal=False)
  64
  65         info_dict.update({
  66             'id': video_id,
  67             'uploader': uploader,
  68             'uploader_id': uploader_id,
  69             'title': title,
  70         })
  71
  72         return info_dict