Raphaël G. Git Repositories - youtubedl/blob - 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 ..compat import (
   8     compat_parse_qs,
   9     compat_urllib_parse,
  10     compat_HTTPError,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     HEADRequest,
  15     remove_end,
  16 )
  17
  18
  19 class CloudyIE(InfoExtractor):
  20     _IE_DESC = 'cloudy.ec and videoraj.ch'
  21     _VALID_URL = r'''(?x)
  22         https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/
  23         (?:v/|embed\.php\?id=)
  24         (?P<id>[A-Za-z0-9]+)
  25         '''
  26     _EMBED_URL = 'http://www.%s/embed.php?id=%s'
  27     _API_URL = 'http://www.%s/api/player.api.php?%s'
  28     _MAX_TRIES = 2
  29     _TESTS = [
  30         {
  31             'url': 'https://www.cloudy.ec/v/af511e2527aac',
  32             'md5': '5cb253ace826a42f35b4740539bedf07',
  33             'info_dict': {
  34                 'id': 'af511e2527aac',
  35                 'ext': 'flv',
  36                 'title': 'Funny Cats and Animals Compilation june 2013',
  37             }
  38         },
  39         {
  40             'url': 'http://www.videoraj.ch/v/47f399fd8bb60',
  41             'md5': '7d0f8799d91efd4eda26587421c3c3b0',
  42             'info_dict': {
  43                 'id': '47f399fd8bb60',
  44                 'ext': 'flv',
  45                 'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?',
  46             }
  47         }
  48     ]
  49
  50     def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0):
  51
  52         if try_num > self._MAX_TRIES - 1:
  53             raise ExtractorError('Unable to extract video URL', expected=True)
  54
  55         form = {
  56             'file': video_id,
  57             'key': file_key,
  58         }
  59
  60         if error_url:
  61             form.update({
  62                 'numOfErrors': try_num,
  63                 'errorCode': '404',
  64                 'errorUrl': error_url,
  65             })
  66
  67         data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode(form))
  68         player_data = self._download_webpage(
  69             data_url, video_id, 'Downloading player data')
  70         data = compat_parse_qs(player_data)
  71
  72         try_num += 1
  73
  74         if 'error' in data:
  75             raise ExtractorError(
  76                 '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
  77                 expected=True)
  78
  79         title = data.get('title', [None])[0]
  80         if title:
  81             title = remove_end(title, '&asdasdas').strip()
  82
  83         video_url = data.get('url', [None])[0]
  84
  85         if video_url:
  86             try:
  87                 self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL')
  88             except ExtractorError as e:
  89                 if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
  90                     self.report_warning('Invalid video URL, requesting another', video_id)
  91                     return self._extract_video(video_host, video_id, file_key, video_url, try_num)
  92
  93         return {
  94             'id': video_id,
  95             'url': video_url,
  96             'title': title,
  97         }
  98
  99     def _real_extract(self, url):
 100         mobj = re.match(self._VALID_URL, url)
 101         video_host = mobj.group('host')
 102         video_id = mobj.group('id')
 103
 104         url = self._EMBED_URL % (video_host, video_id)
 105         webpage = self._download_webpage(url, video_id)
 106
 107         file_key = self._search_regex(
 108             r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
 109
 110         return self._extract_video(video_host, video_id, file_key)