_ Git - youtube-dl/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 class NovamovIE(InfoExtractor):
  12     IE_NAME = 'novamov'
  13     IE_DESC = 'novamov.com videos'
  14     _VALID_URL = r'http://(?:www\.novamov\.com/video/|embed\.novamov\.com/embed\.php\?v=)(?P<videoid>[a-z\d]{13})'
  15
  16     _TEST = {
  17         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
  18         'file': '4rurhn9x446jj.flv',
  19         'md5': '7205f346a52bbeba427603ba10d4b935',
  20         'info_dict': {
  21             'title': 'search engine optimization',
  22             'description': 'search engine optimization is used to rank the web page in the google search engine'
  23         }
  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         mobj= re.search(r'flashvars\.filekey="(?P<filekey>[^"]+)";', page)
  37         if mobj is None:
  38             raise ExtractorError('Unable to extract filekey', expected=True)
  39
  40         filekey = mobj.group('filekey')
  41
  42         title = self._html_search_regex(
  43             r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>',
  44             page, 'title', fatal=False)
  45
  46         description = self._html_search_regex(
  47             r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>',
  48             page, 'description', fatal=False)
  49
  50         api_response = self._download_webpage('http://www.novamov.com/api/player.api.php?key=%s&file=%s' % (filekey, video_id),
  51                                               video_id, 'Downloading video api response')
  52
  53         response = compat_urlparse.parse_qs(api_response)
  54
  55         if 'error_msg' in response:
  56             raise ExtractorError('novamov returned error: %s' % response['error_msg'][0], expected=True)
  57
  58         video_url = response['url'][0]
  59
  60         return {
  61             'id': video_id,
  62             'url': video_url,
  63             'title': title,
  64             'description': description
  65         }