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     _VALID_URL = r'http://(?:(?:www\.)?novamov\.com/video/|(?:(?:embed|www)\.)novamov\.com/embed\.php\?v=)(?P<videoid>[a-z\d]{13})'
  14
  15     _TEST = {
  16         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
  17         'file': '4rurhn9x446jj.flv',
  18         'md5': '7205f346a52bbeba427603ba10d4b935',
  19         'info_dict': {
  20             'title': 'search engine optimization',
  21             'description': 'search engine optimization is used to rank the web page in the google search engine'
  22         },
  23         'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('videoid')
  29
  30         page = self._download_webpage('http://www.novamov.com/video/%s' % video_id,
  31                                       video_id, 'Downloading video page')
  32
  33         if re.search(r'This file no longer exists on our servers!</h2>', page) is not None:
  34             raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
  35
  36         filekey = self._search_regex(
  37             r'flashvars\.filekey="(?P<filekey>[^"]+)";', page, 'filekey')
  38
  39         title = self._html_search_regex(
  40             r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>',
  41             page, 'title', fatal=False)
  42
  43         description = self._html_search_regex(
  44             r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>',
  45             page, 'description', fatal=False)
  46
  47         api_response = self._download_webpage(
  48             'http://www.novamov.com/api/player.api.php?key=%s&file=%s' % (filekey, video_id),
  49             video_id, 'Downloading video api response')
  50
  51         response = compat_urlparse.parse_qs(api_response)
  52
  53         if 'error_msg' in response:
  54             raise ExtractorError('novamov returned error: %s' % response['error_msg'][0], expected=True)
  55
  56         video_url = response['url'][0]
  57
  58         return {
  59             'id': video_id,
  60             'url': video_url,
  61             'title': title,
  62             'description': description
  63         }