Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/thisav.py

   1 #coding: utf-8
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8 )
   9
  10 class ThisAVIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
  12     _TEST = {
  13         u"url": u"http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html",
  14         u"file": u"47734.flv",
  15         u"md5": u"0480f1ef3932d901f0e0e719f188f19b",
  16         u"info_dict": {
  17             u"title": u"高樹マリア - Just fit",
  18             u"uploader": u"dj7970",
  19             u"uploader_id": u"dj7970"
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25
  26         video_id = mobj.group('id')
  27         webpage = self._download_webpage(url, video_id)
  28         title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, u'title')
  29         video_url = self._html_search_regex(
  30             r"addVariable\('file','([^']+)'\);", webpage, u'video url')
  31         uploader = self._html_search_regex(
  32             r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
  33             webpage, u'uploader name', fatal=False)
  34         uploader_id = self._html_search_regex(
  35             r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
  36             webpage, u'uploader id', fatal=False)
  37         ext = determine_ext(video_url)
  38
  39         return {
  40             '_type':       'video',
  41             'id':          video_id,
  42             'url':         video_url,
  43             'uploader':    uploader,
  44             'uploader_id': uploader_id,
  45             'title':       title,
  46             'ext':         ext,
  47         }