]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/novamov.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
12 class NovaMovIE(InfoExtractor
):
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'}
19 _HOST
= 'www.novamov.com'
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>'
27 'url': 'http://www.novamov.com/video/4rurhn9x446jj',
28 'md5': '7205f346a52bbeba427603ba10d4b935',
30 'id': '4rurhn9x446jj',
32 'title': 'search engine optimization',
33 'description': 'search engine optimization is used to rank the web page in the google search engine'
35 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
38 def _real_extract(self
, url
):
39 mobj
= re
.match(self
._VALID
_URL
, url
)
40 video_id
= mobj
.group('id')
42 page
= self
._download
_webpage
(
43 'http://%s/video/%s' % (self
._HOST
, video_id
), video_id
, 'Downloading video page')
45 if re
.search(self
._FILE
_DELETED
_REGEX
, page
) is not None:
46 raise ExtractorError('Video %s does not exist' % video_id
, expected
=True)
48 filekey
= self
._search
_regex
(self
._FILEKEY
_REGEX
, page
, 'filekey')
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)
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