1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
6 from ..compat
import compat_urlparse
16 class NovaMovIE(InfoExtractor
):
20 _VALID_URL_TEMPLATE
= r
'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
21 _VALID_URL
= _VALID_URL_TEMPLATE
% {'host': 'novamov\.com'}
23 _HOST
= 'www.novamov.com'
25 _FILE_DELETED_REGEX
= r
'This file no longer exists on our servers!</h2>'
26 _FILEKEY_REGEX
= r
'flashvars\.filekey="(?P<filekey>[^"]+)";'
27 _TITLE_REGEX
= r
'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
28 _DESCRIPTION_REGEX
= r
'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
31 'url': 'http://www.novamov.com/video/4rurhn9x446jj',
32 'md5': '7205f346a52bbeba427603ba10d4b935',
34 'id': '4rurhn9x446jj',
36 'title': 'search engine optimization',
37 'description': 'search engine optimization is used to rank the web page in the google search engine'
39 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
42 def _real_extract(self
, url
):
43 video_id
= self
._match
_id
(url
)
45 url
= 'http://%s/video/%s' % (self
._HOST
, video_id
)
47 webpage
= self
._download
_webpage
(
48 url
, video_id
, 'Downloading video page')
50 if re
.search(self
._FILE
_DELETED
_REGEX
, webpage
) is not None:
51 raise ExtractorError('Video %s does not exist' % video_id
, expected
=True)
53 def extract_filekey(default
=NO_DEFAULT
):
54 return self
._search
_regex
(
55 self
._FILEKEY
_REGEX
, webpage
, 'filekey', default
=default
)
57 filekey
= extract_filekey(default
=None)
60 fields
= self
._hidden
_inputs
(webpage
)
61 post_url
= self
._search
_regex
(
62 r
'<form[^>]+action=(["\'])(?P
<url
>.+?
)\
1', webpage,
63 'post url
', default=url, group='url
')
64 if not post_url.startswith('http
'):
65 post_url = compat_urlparse.urljoin(url, post_url)
66 request = sanitized_Request(
67 post_url, urlencode_postdata(encode_dict(fields)))
68 request.add_header('Content
-Type
', 'application
/x
-www
-form
-urlencoded
')
69 request.add_header('Referer
', post_url)
70 webpage = self._download_webpage(
71 request, video_id, 'Downloading
continue to the video page
')
73 filekey = extract_filekey()
75 title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title
', fatal=False)
76 description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description
', default='', fatal=False)
78 api_response = self._download_webpage(
79 'http
://%s/api
/player
.api
.php?key
=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
80 'Downloading video api response
')
82 response = compat_urlparse.parse_qs(api_response)
84 if 'error_msg
' in response:
85 raise ExtractorError('%s returned error
: %s' % (self.IE_NAME, response['error_msg
'][0]), expected=True)
87 video_url = response['url
'][0]
93 'description
': description
97 class WholeCloudIE(NovaMovIE):
98 IE_NAME = 'wholecloud
'
99 IE_DESC = 'WholeCloud
'
101 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
103 _HOST = 'www
.wholecloud
.net
'
105 _FILE_DELETED_REGEX = r'>This
file no longer exists on our servers
.<'
106 _TITLE_REGEX = r'<strong
>Title
:</strong
> ([^
<]+)</p
>'
107 _DESCRIPTION_REGEX = r'<strong
>Description
:</strong
> ([^
<]+)</p
>'
110 'url
': 'http
://www
.wholecloud
.net
/video
/559e28be54d96
',
111 'md5
': 'abd31a2132947262c50429e1d16c1bfd
',
113 'id': '559e28be54d96
',
115 'title
': 'dissapeared image
',
116 'description
': 'optical illusion dissapeared image magic illusion
',
121 class NowVideoIE(NovaMovIE):
125 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
127 _HOST = 'www
.nowvideo
.to
'
129 _FILE_DELETED_REGEX = r'>This
file no longer exists on our servers
.<'
130 _FILEKEY_REGEX = r'var fkzd
="([^"]+)";'
131 _TITLE_REGEX = r'<h4>([^<]+)</h4>'
132 _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
135 'url': 'http://www.nowvideo.to/video/0mw0yow7b6dxa',
136 'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
138 'id': '0mw0yow7b6dxa',
140 'title': 'youtubedl test video _BaW_jenozKc.mp4',
141 'description': 'Description',
146 class VideoWeedIE(NovaMovIE):
147 IE_NAME = 'videoweed'
148 IE_DESC = 'VideoWeed'
150 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
152 _HOST = 'www.videoweed.es'
154 _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
155 _TITLE_REGEX = r'<h1 class="text_shadow
">([^<]+)</h1>'
158 'url': 'http://www.videoweed.es/file/b42178afbea14',
159 'md5': 'abd31a2132947262c50429e1d16c1bfd',
161 'id': 'b42178afbea14',
163 'title': 'optical illusion dissapeared image magic illusion',
169 class CloudTimeIE(NovaMovIE):
170 IE_NAME = 'cloudtime'
171 IE_DESC = 'CloudTime'
173 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'}
175 _HOST = 'www.cloudtime.to'
177 _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
178 _TITLE_REGEX = r'<div[^>]+class=["\']video_det
["\'][^>]*>\s*<strong>([^<]+)</strong>'