youtube_dl/extractor/dump.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9 )
  10
  11 class DumpIE(InfoExtractor):
  12     _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/'
  13
  14     _TEST = {
  15         u'url': u'http://www.dump.com/oneus/',
  16         u'file': u'oneus.flv',
  17         u'md5': u'ad71704d1e67dfd9e81e3e8b42d69d99',
  18         u'info_dict': {
  19             u"title": u"He's one of us.",
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         m = re.match(self._VALID_URL, url)
  25         video_id = m.group('id')
  26
  27         # Note: There is an easier-to-parse configuration at
  28         # http://www.aparat.com/video/video/config/videohash/%video_id
  29         # but the URL in there does not work
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         try:
  34             video_url = re.findall(r'file","(.+?.flv)"', webpage)[-1]
  35         except IndexError:
  36             raise ExtractorError(u'No video URL found')
  37
  38         thumb = re.findall('<meta property="og:image" content="(.+?)"',webpage)[0]
  39
  40         title = self._search_regex(r'<b>([^"]+)</b>', webpage, u'title')
  41
  42         return {
  43             'id': video_id,
  44             'title': title,
  45             'url': video_url,
  46             'ext': 'flv',
  47             'thumbnail': thumb,
  48         }