youtube_dl/extractor/thisav.py

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