Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/novamov.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 NovaMovIE(InfoExtractor):
  13     IE_NAME = 'novamov'
  14     IE_DESC = 'NovaMov'
  15
  16     _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
  17     _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
  18
  19     _HOST = 'www.novamov.com'
  20
  21     _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
  22     _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
  23     _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
  24     _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
  25
  26     _TEST = {
  27         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
  28         'md5': '7205f346a52bbeba427603ba10d4b935',
  29         'info_dict': {
  30             'id': '4rurhn9x446jj',
  31             'ext': 'flv',
  32             'title': 'search engine optimization',
  33             'description': 'search engine optimization is used to rank the web page in the google search engine'
  34         },
  35         'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
  36     }
  37
  38     def _real_extract(self, url):
  39         mobj = re.match(self._VALID_URL, url)
  40         video_id = mobj.group('id')
  41
  42         page = self._download_webpage(
  43             'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
  44
  45         if re.search(self._FILE_DELETED_REGEX, page) is not None:
  46             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  47
  48         filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
  49
  50         title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
  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         }