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 determine_ext
   8
   9
  10 class ThisAVIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
  12     _TEST = {
  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
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26
  27         video_id = mobj.group('id')
  28         webpage = self._download_webpage(url, video_id)
  29         title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title')
  30         video_url = self._html_search_regex(
  31             r"addVariable\('file','([^']+)'\);", webpage, 'video url')
  32         uploader = self._html_search_regex(
  33             r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
  34             webpage, 'uploader name', fatal=False)
  35         uploader_id = self._html_search_regex(
  36             r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
  37             webpage, 'uploader id', fatal=False)
  38         ext = determine_ext(video_url)
  39
  40         return {
  41             'id':          video_id,
  42             'url':         video_url,
  43             'uploader':    uploader,
  44             'uploader_id': uploader_id,
  45             'title':       title,
  46             'ext':         ext,
  47         }