]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/novamov.py
Fix extraction from youtube.
[youtubedl] / youtube_dl / extractor / novamov.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..compat import compat_urlparse
7 from ..utils import (
8 ExtractorError,
9 NO_DEFAULT,
10 sanitized_Request,
11 urlencode_postdata,
12 )
13
14
15 class NovaMovIE(InfoExtractor):
16 IE_NAME = 'novamov'
17 IE_DESC = 'NovaMov'
18
19 _VALID_URL_TEMPLATE = r'''(?x)
20 http://
21 (?:
22 (?:www\.)?%(host)s/(?:file|video|mobile/\#/videos)/|
23 (?:(?:embed|www)\.)%(host)s/embed(?:\.php|/)?\?(?:.*?&)?\bv=
24 )
25 (?P<id>[a-z\d]{13})
26 '''
27 _VALID_URL = _VALID_URL_TEMPLATE % {'host': r'novamov\.com'}
28
29 _HOST = 'www.novamov.com'
30
31 _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
32 _FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);'
33 _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
34 _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
35 _URL_TEMPLATE = 'http://%s/video/%s'
36
37 _TEST = None
38
39 def _check_existence(self, webpage, video_id):
40 if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
41 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
42
43 def _real_extract(self, url):
44 video_id = self._match_id(url)
45
46 url = self._URL_TEMPLATE % (self._HOST, video_id)
47
48 webpage = self._download_webpage(
49 url, video_id, 'Downloading video page')
50
51 self._check_existence(webpage, video_id)
52
53 def extract_filekey(default=NO_DEFAULT):
54 filekey = self._search_regex(
55 self._FILEKEY_REGEX, webpage, 'filekey', default=default)
56 if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
57 return self._search_regex(
58 r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default)
59 else:
60 return filekey
61
62 filekey = extract_filekey(default=None)
63
64 if not filekey:
65 fields = self._hidden_inputs(webpage)
66 post_url = self._search_regex(
67 r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
68 'post url', default=url, group='url')
69 if not post_url.startswith('http'):
70 post_url = compat_urlparse.urljoin(url, post_url)
71 request = sanitized_Request(
72 post_url, urlencode_postdata(fields))
73 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
74 request.add_header('Referer', post_url)
75 webpage = self._download_webpage(
76 request, video_id, 'Downloading continue to the video page')
77 self._check_existence(webpage, video_id)
78
79 filekey = extract_filekey()
80
81 title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title')
82 description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
83
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')
87
88 response = compat_urlparse.parse_qs(api_response)
89
90 if 'error_msg' in response:
91 raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
92
93 video_url = response['url'][0]
94
95 return {
96 'id': video_id,
97 'url': video_url,
98 'title': title,
99 'description': description
100 }
101
102
103 class WholeCloudIE(NovaMovIE):
104 IE_NAME = 'wholecloud'
105 IE_DESC = 'WholeCloud'
106
107 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
108
109 _HOST = 'www.wholecloud.net'
110
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>'
114
115 _TEST = {
116 'url': 'http://www.wholecloud.net/video/559e28be54d96',
117 'md5': 'abd31a2132947262c50429e1d16c1bfd',
118 'info_dict': {
119 'id': '559e28be54d96',
120 'ext': 'flv',
121 'title': 'dissapeared image',
122 'description': 'optical illusion dissapeared image magic illusion',
123 }
124 }
125
126
127 class NowVideoIE(NovaMovIE):
128 IE_NAME = 'nowvideo'
129 IE_DESC = 'NowVideo'
130
131 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
132
133 _HOST = 'www.nowvideo.to'
134
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>'
138
139 _TEST = {
140 'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b',
141 'md5': '12c82cad4f2084881d8bc60ee29df092',
142 'info_dict': {
143 'id': 'f1d6fce9a968b',
144 'ext': 'flv',
145 'title': 'youtubedl test video BaWjenozKc',
146 'description': 'Description',
147 },
148 }
149
150
151 class VideoWeedIE(NovaMovIE):
152 IE_NAME = 'videoweed'
153 IE_DESC = 'VideoWeed'
154
155 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'videoweed\.(?:es|com)'}
156
157 _HOST = 'www.videoweed.es'
158
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'
162
163 _TEST = {
164 'url': 'http://www.videoweed.es/file/b42178afbea14',
165 'md5': 'abd31a2132947262c50429e1d16c1bfd',
166 'info_dict': {
167 'id': 'b42178afbea14',
168 'ext': 'flv',
169 'title': 'optical illusion dissapeared image magic illusion',
170 'description': ''
171 },
172 }
173
174
175 class CloudTimeIE(NovaMovIE):
176 IE_NAME = 'cloudtime'
177 IE_DESC = 'CloudTime'
178
179 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'cloudtime\.to'}
180
181 _HOST = 'www.cloudtime.to'
182
183 _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
184 _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
185
186 _TEST = None
187
188
189 class AuroraVidIE(NovaMovIE):
190 IE_NAME = 'auroravid'
191 IE_DESC = 'AuroraVid'
192
193 _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': r'auroravid\.to'}
194
195 _HOST = 'www.auroravid.to'
196
197 _FILE_DELETED_REGEX = r'This file no longer exists on our servers!<'
198
199 _TESTS = [{
200 'url': 'http://www.auroravid.to/video/4rurhn9x446jj',
201 'md5': '7205f346a52bbeba427603ba10d4b935',
202 'info_dict': {
203 'id': '4rurhn9x446jj',
204 'ext': 'flv',
205 'title': 'search engine optimization',
206 'description': 'search engine optimization is used to rank the web page in the google search engine'
207 },
208 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
209 }, {
210 'url': 'http://www.auroravid.to/embed/?v=4rurhn9x446jj',
211 'only_matching': True,
212 }]