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     _IE_DESC = 'cloudy.ec and videoraj.ch'
  17     _VALID_URL = r'''(?x)
  18         https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/
  19         (?:v/|embed\.php\?id=)
  20         (?P<id>[A-Za-z0-9]+)
  21         '''
  22     _EMBED_URL = 'http://www.%s/embed.php?id=%s'
  23     _API_URL = 'http://www.%s/api/player.api.php?%s'
  24     _TESTS = [
  25         {
  26             'url': 'https://www.cloudy.ec/v/af511e2527aac',
  27             'md5': '5cb253ace826a42f35b4740539bedf07',
  28             'info_dict': {
  29                 'id': 'af511e2527aac',
  30                 'ext': 'flv',
  31                 'title': 'Funny Cats and Animals Compilation june 2013',
  32             }
  33         },
  34         {
  35             'url': 'http://www.videoraj.ch/v/47f399fd8bb60',
  36             'md5': '7d0f8799d91efd4eda26587421c3c3b0',
  37             'info_dict': {
  38                 'id': '47f399fd8bb60',
  39                 'ext': 'flv',
  40                 'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?',
  41             }
  42         }
  43     ]
  44
  45     def _real_extract(self, url):
  46         mobj = re.match(self._VALID_URL, url)
  47         video_host = mobj.group('host')
  48         video_id = mobj.group('id')
  49
  50         url = self._EMBED_URL % (video_host, video_id)
  51         webpage = self._download_webpage(url, video_id)
  52
  53         file_key = self._search_regex(
  54             r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
  55         data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode({
  56             'file': video_id,
  57             'key': file_key,
  58         }))
  59         player_data = self._download_webpage(
  60             data_url, video_id, 'Downloading player data')
  61         data = compat_parse_qs(player_data)
  62
  63         if 'error' in data:
  64             raise ExtractorError(
  65                 '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
  66                 expected=True)
  67
  68         title = data.get('title', [None])[0]
  69         if title:
  70             title = remove_end(title, '&asdasdas').strip()
  71
  72         formats = []
  73         video_url = data.get('url', [None])[0]
  74         if video_url:
  75             formats.append({
  76                 'format_id': 'sd',
  77                 'url': video_url,
  78             })
  79
  80         return {
  81             'id': video_id,
  82             'title': title,
  83             'formats': formats,
  84         }