youtube_dl/extractor/thisav.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .jwplatform import JWPlatformBaseIE
   7 from ..utils import remove_end
   8
   9
  10 class ThisAVIE(JWPlatformBaseIE):
  11     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
  12     _TESTS = [{
  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         'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html',
  24         'md5': 'ba90c076bd0f80203679e5b60bf523ee',
  25         'info_dict': {
  26             'id': '242352',
  27             'ext': 'mp4',
  28             'title': 'Nerdy 18yo Big Ass Tattoos and Glasses',
  29             'uploader': 'cybersluts',
  30             'uploader_id': 'cybersluts',
  31         },
  32     }]
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36
  37         video_id = mobj.group('id')
  38         webpage = self._download_webpage(url, video_id)
  39         title = remove_end(self._html_search_regex(
  40             r'<title>([^<]+)</title>', webpage, 'title'),
  41             ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站')
  42         video_url = self._html_search_regex(
  43             r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
  44         if video_url:
  45             info_dict = {
  46                 'formats': [{
  47                     'url': video_url,
  48                 }],
  49             }
  50         else:
  51             info_dict = self._extract_jwplayer_data(
  52                 webpage, video_id, require_title=False)
  53         uploader = self._html_search_regex(
  54             r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
  55             webpage, 'uploader name', fatal=False)
  56         uploader_id = self._html_search_regex(
  57             r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
  58             webpage, 'uploader id', fatal=False)
  59
  60         info_dict.update({
  61             'id': video_id,
  62             'uploader': uploader,
  63             'uploader_id': uploader_id,
  64             'title': title,
  65         })
  66
  67         return info_dict