1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
NO_DEFAULT,
encode_dict,
sanitized_Request,
urlencode_postdata,
)
class NovaMovIE(InfoExtractor):
IE_NAME = 'novamov'
IE_DESC = 'NovaMov'
_VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video|mobile/#/videos)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
_VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
_HOST = 'www.novamov.com'
_FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
_FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);'
_TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
_DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
_URL_TEMPLATE = 'http://%s/video/%s'
_TEST = {
'url': 'http://www.novamov.com/video/4rurhn9x446jj',
'md5': '7205f346a52bbeba427603ba10d4b935',
'info_dict': {
'id': '4rurhn9x446jj',
'ext': 'flv',
'title': 'search engine optimization',
'description': 'search engine optimization is used to rank the web page in the google search engine'
},
'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
}
def _check_existence(self, webpage, video_id):
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
url = self._URL_TEMPLATE % (self._HOST, video_id)
webpage = self._download_webpage(
url, video_id, 'Downloading video page')
self._check_existence(webpage, video_id)
def extract_filekey(default=NO_DEFAULT):
filekey = self._search_regex(
self._FILEKEY_REGEX, webpage, 'filekey', default=default)
if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
return self._search_regex(
r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default)
else:
return filekey
filekey = extract_filekey(default=None)
if not filekey:
fields = self._hidden_inputs(webpage)
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
'post url', default=url, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(url, post_url)
request = sanitized_Request(
post_url, urlencode_postdata(encode_dict(fields)))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
request.add_header('Referer', post_url)
webpage = self._download_webpage(
request, video_id, 'Downloading continue to the video page')
self._check_existence(webpage, video_id)
filekey = extract_filekey()
title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
api_response = self._download_webpage(
'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
'Downloading video api response')
response = compat_urlparse.parse_qs(api_response)
if 'error_msg' in response:
raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
video_url = response['url'][0]
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description
}
class WholeCloudIE(NovaMovIE):
IE_NAME = 'wholecloud'
IE_DESC = 'WholeCloud'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
_HOST = 'www.wholecloud.net'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
_DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
_TEST = {
'url': 'http://www.wholecloud.net/video/559e28be54d96',
'md5': 'abd31a2132947262c50429e1d16c1bfd',
'info_dict': {
'id': '559e28be54d96',
'ext': 'flv',
'title': 'dissapeared image',
'description': 'optical illusion dissapeared image magic illusion',
}
}
class NowVideoIE(NovaMovIE):
IE_NAME = 'nowvideo'
IE_DESC = 'NowVideo'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
_HOST = 'www.nowvideo.to'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<h4>([^<]+)</h4>'
_DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
_TEST = {
'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b',
'md5': '12c82cad4f2084881d8bc60ee29df092',
'info_dict': {
'id': 'f1d6fce9a968b',
'ext': 'flv',
'title': 'youtubedl test video BaWjenozKc',
'description': 'Description',
},
}
class VideoWeedIE(NovaMovIE):
IE_NAME = 'videoweed'
IE_DESC = 'VideoWeed'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
_HOST = 'www.videoweed.es'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
_URL_TEMPLATE = 'http://%s/file/%s'
_TEST = {
'url': 'http://www.videoweed.es/file/b42178afbea14',
'md5': 'abd31a2132947262c50429e1d16c1bfd',
'info_dict': {
'id': 'b42178afbea14',
'ext': 'flv',
'title': 'optical illusion dissapeared image magic illusion',
'description': ''
},
}
class CloudTimeIE(NovaMovIE):
IE_NAME = 'cloudtime'
IE_DESC = 'CloudTime'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'}
_HOST = 'www.cloudtime.to'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
_TEST = None
|
