1 from __future__ import unicode_literals
5 from .common import InfoExtractor
12 class NovaMovIE(InfoExtractor):
16 _VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'novamov\.com'}
18 _HOST = 'www.novamov.com'
20 _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
21 _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
22 _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
23 _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
26 'url': 'http://www.novamov.com/video/4rurhn9x446jj',
27 'md5': '7205f346a52bbeba427603ba10d4b935',
29 'id': '4rurhn9x446jj',
31 'title': 'search engine optimization',
32 'description': 'search engine optimization is used to rank the web page in the google search engine'
34 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
37 def _real_extract(self, url):
38 mobj = re.match(self._VALID_URL, url)
39 video_id = mobj.group('videoid')
41 page = self._download_webpage(
42 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
44 if re.search(self._FILE_DELETED_REGEX, page) is not None:
45 raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
47 filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
49 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)
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')
57 response = compat_urlparse.parse_qs(api_response)
59 if 'error_msg' in response:
60 raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
62 video_url = response['url'][0]
68 'description': description