youtube_dl/extractor/videoweed.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     compat_urlparse
   9 )
  10
  11
  12 class VideoweedIE(InfoExtractor):
  13     IE_NAME = 'videoweed'
  14     IE_DESC = 'VideoWEED'
  15
  16     #_VALID_URL = r'http://(?:(?:www\.)?%(host)s/file/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'videoweed\.com'}
  17     _VALID_URL =r'http://(?:www\.)videoweed\.es/file/(?P<id>[^"]+)'
  18     _HOST = 'www.videoweed.es'
  19
  20     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.</'
  21     _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
  22     _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
  23     _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
  24
  25     _TEST = {
  26         'url': 'http://www.videoweed.es/file/89868b4aa3bdf',
  27         'md5': '7205f346a52bbeba427603ba10d4b935',
  28         'info_dict': {
  29             'id': '89868b4aa3bdf',
  30             'ext': 'flv',
  31             'title': 'law and order svu 103 dvdrip',
  32             'description': ''
  33         },
  34         'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
  35     }
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         video_id = mobj.group('id')
  40         print "itworks"
  41         page = self._download_webpage(
  42             'http://%s/file/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
  43
  44         if re.search(self._FILE_DELETED_REGEX, page) is not None:
  45             raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
  46
  47         filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
  48
  49         title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
  50
  51         description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
  52
  53         api_response = self._download_webpage(
  54             'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
  55             'Downloading video api response')
  56
  57         response = compat_urlparse.parse_qs(api_response)
  58
  59         if 'error_msg' in response:
  60             raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
  61
  62         video_url = response['url'][0]
  63
  64         return {
  65             'id': video_id,
  66             'url': video_url,
  67             'title': title,
  68             'description': description
  69         }