youtube_dl/extractor/cloudy.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 (
   8     ExtractorError,
   9     compat_parse_qs,
  10     compat_urllib_parse,
  11     remove_end,
  12 )
  13
  14
  15 class CloudyIE(InfoExtractor):
  16     _VALID_URL = r'''(?x)
  17         https?://(?:www\.)?cloudy\.ec/
  18         (?:v/|embed\.php\?id=)
  19         (?P<id>[A-Za-z0-9]+)
  20         '''
  21     _API_URL = 'http://www.cloudy.ec/api/player.api.php?%s'
  22     _TEST = {
  23         'url': 'https://www.cloudy.ec/v/af511e2527aac',
  24         'md5': '5cb253ace826a42f35b4740539bedf07',
  25         'info_dict': {
  26             'id': 'af511e2527aac',
  27             'ext': 'flv',
  28             'title': 'Funny Cats and Animals Compilation june 2013',
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35
  36         url = 'http://www.cloudy.ec/embed.php?id=%s' % video_id
  37         webpage = self._download_webpage(url, video_id)
  38
  39         file_key = self._search_regex(
  40             r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
  41         data_url = self._API_URL % compat_urllib_parse.urlencode({
  42             'file': video_id,
  43             'key': file_key,
  44         })
  45         player_data = self._download_webpage(
  46             data_url, video_id, 'Downloading player data')
  47         data = compat_parse_qs(player_data)
  48
  49         if 'error' in data:
  50             raise ExtractorError(
  51                 '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
  52                 expected=True)
  53
  54         title = data.get('title', [None])[0]
  55         if title:
  56             title = remove_end(title, '&asdasdas').strip()
  57
  58         formats = []
  59         video_url = data.get('url', [None])[0]
  60         if video_url:
  61             formats.append({
  62                 'format_id': 'sd',
  63                 'url': video_url,
  64             })
  65
  66         return {
  67             'id': video_id,
  68             'title': title,
  69             'formats': formats,
  70         }