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>'
29 _URL_TEMPLATE = 'http://%s/video/%s'
32 'url': 'http://www.novamov.com/video/4rurhn9x446jj',
33 'md5': '7205f346a52bbeba427603ba10d4b935',
35 'id': '4rurhn9x446jj',
37 'title': 'search engine optimization',
38 'description': 'search engine optimization is used to rank the web page in the google search engine'
40 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
43 def _real_extract(self, url):
44 video_id = self._match_id(url)
46 url = self._URL_TEMPLATE % (self._HOST, video_id)
48 webpage = self._download_webpage(
49 url, video_id, 'Downloading video page')
51 if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
52 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
54 def extract_filekey(default=NO_DEFAULT):
55 filekey = self._search_regex(
56 self._FILEKEY_REGEX, webpage, 'filekey', default=default)
57 if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
58 return self._search_regex(
59 r'var\s*%s\s*=\s*"([^"]+)"', webpage, 'filekey', default=default)
63 filekey = extract_filekey(default=None)
66 fields = self._hidden_inputs(webpage)
67 post_url = self._search_regex(
68 r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
69 'post url', default=url, group='url')
70 if not post_url.startswith('http'):
71 post_url = compat_urlparse.urljoin(url, post_url)
72 request = sanitized_Request(
73 post_url, urlencode_postdata(encode_dict(fields)))
74 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
75 request.add_header('Referer', post_url)
76 webpage = self._download_webpage(
77 request, video_id, 'Downloading continue to the video page')
79 filekey = extract_filekey()
81 title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
82 description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
84 api_response = self._download_webpage(
85 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
86 'Downloading video api response')
88 response = compat_urlparse.parse_qs(api_response)
90 if 'error_msg' in response:
91 raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
93 video_url = response['url'][0]
99 'description': description
103 class WholeCloudIE(NovaMovIE):
104 IE_NAME = 'wholecloud'
105 IE_DESC = 'WholeCloud'
107 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
109 _HOST = 'www.wholecloud.net'
111 _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
112 _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
113 _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
116 'url': 'http://www.wholecloud.net/video/559e28be54d96',
117 'md5': 'abd31a2132947262c50429e1d16c1bfd',
119 'id': '559e28be54d96',
121 'title': 'dissapeared image',
122 'description': 'optical illusion dissapeared image magic illusion',
127 class NowVideoIE(NovaMovIE):
131 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
133 _HOST = 'www.nowvideo.to'
135 _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
136 _TITLE_REGEX = r'<h4>([^<]+)</h4>'
137 _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
140 'url': 'http://www.nowvideo.to/video/0mw0yow7b6dxa',
141 'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
143 'id': '0mw0yow7b6dxa',
145 'title': 'youtubedl test video _BaW_jenozKc.mp4',
146 'description': 'Description',
151 class VideoWeedIE(NovaMovIE):
152 IE_NAME = 'videoweed'
153 IE_DESC = 'VideoWeed'
155 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
157 _HOST = 'www.videoweed.es'
159 _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
160 _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
161 _URL_TEMPLATE = 'http://%s/file/%s'
164 'url': 'http://www.videoweed.es/file/b42178afbea14',
165 'md5': 'abd31a2132947262c50429e1d16c1bfd',
167 'id': 'b42178afbea14',
169 'title': 'optical illusion dissapeared image magic illusion',
175 class CloudTimeIE(NovaMovIE):
176 IE_NAME = 'cloudtime'
177 IE_DESC = 'CloudTime'
179 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'}
181 _HOST = 'www.cloudtime.to'
183 _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
184 _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'