]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vk.py
Update changelog.
[youtubedl] / youtube_dl / extractor / vk.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5 import json
6
7 from .common import InfoExtractor
8 from ..compat import (
9 compat_str,
10 compat_urllib_parse,
11 compat_urllib_request,
12 )
13 from ..utils import (
14 ExtractorError,
15 orderedSet,
16 unescapeHTML,
17 unified_strdate,
18 )
19
20
21 class VKIE(InfoExtractor):
22 IE_NAME = 'vk.com'
23 _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))'
24 _NETRC_MACHINE = 'vk'
25
26 _TESTS = [
27 {
28 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
29 'md5': '0deae91935c54e00003c2a00646315f0',
30 'info_dict': {
31 'id': '162222515',
32 'ext': 'flv',
33 'title': 'ProtivoGunz - Хуёвая песня',
34 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
35 'duration': 195,
36 'upload_date': '20120212',
37 },
38 },
39 {
40 'url': 'http://vk.com/video205387401_165548505',
41 'md5': '6c0aeb2e90396ba97035b9cbde548700',
42 'info_dict': {
43 'id': '165548505',
44 'ext': 'mp4',
45 'uploader': 'Tom Cruise',
46 'title': 'No name',
47 'duration': 9,
48 'upload_date': '20130721'
49 }
50 },
51 {
52 'note': 'Embedded video',
53 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
54 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
55 'info_dict': {
56 'id': '162925554',
57 'ext': 'mp4',
58 'uploader': 'Vladimir Gavrin',
59 'title': 'Lin Dan',
60 'duration': 101,
61 'upload_date': '20120730',
62 }
63 },
64 {
65 # VIDEO NOW REMOVED
66 # please update if you find a video whose URL follows the same pattern
67 'url': 'http://vk.com/video-8871596_164049491',
68 'md5': 'a590bcaf3d543576c9bd162812387666',
69 'note': 'Only available for registered users',
70 'info_dict': {
71 'id': '164049491',
72 'ext': 'mp4',
73 'uploader': 'Триллеры',
74 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
75 'duration': 8352,
76 'upload_date': '20121218'
77 },
78 'skip': 'Requires vk account credentials',
79 },
80 {
81 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
82 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
83 'info_dict': {
84 'id': '168067957',
85 'ext': 'mp4',
86 'uploader': 'Киномания - лучшее из мира кино',
87 'title': ' ',
88 'duration': 7291,
89 'upload_date': '20140328',
90 },
91 'skip': 'Requires vk account credentials',
92 },
93 {
94 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
95 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
96 'note': 'ivi.ru embed',
97 'info_dict': {
98 'id': '60690',
99 'ext': 'mp4',
100 'title': 'Книга Илая',
101 'duration': 6771,
102 'upload_date': '20140626',
103 },
104 'skip': 'Only works from Russia',
105 },
106 {
107 # removed video, just testing that we match the pattern
108 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
109 'only_matching': True,
110 },
111 ]
112
113 def _login(self):
114 (username, password) = self._get_login_info()
115 if username is None:
116 return
117
118 login_form = {
119 'act': 'login',
120 'role': 'al_frame',
121 'expire': '1',
122 'email': username,
123 'pass': password,
124 }
125
126 request = compat_urllib_request.Request('https://login.vk.com/?act=login',
127 compat_urllib_parse.urlencode(login_form).encode('utf-8'))
128 login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
129
130 if re.search(r'onLoginFailed', login_page):
131 raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
132
133 def _real_initialize(self):
134 self._login()
135
136 def _real_extract(self, url):
137 mobj = re.match(self._VALID_URL, url)
138 video_id = mobj.group('videoid')
139
140 if not video_id:
141 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
142
143 info_url = 'http://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
144 info_page = self._download_webpage(info_url, video_id)
145
146 ERRORS = {
147 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
148 'Video %s has been removed from public access due to rightholder complaint.',
149
150 r'<!>Please log in or <':
151 'Video %s is only available for registered users, '
152 'use --username and --password options to provide account credentials.',
153
154 r'<!>Unknown error':
155 'Video %s does not exist.',
156
157 r'<!>Видео временно недоступно':
158 'Video %s is temporarily unavailable.',
159 }
160
161 for error_re, error_msg in ERRORS.items():
162 if re.search(error_re, info_page):
163 raise ExtractorError(error_msg % video_id, expected=True)
164
165 m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
166 if m_yt is not None:
167 self.to_screen('Youtube video detected')
168 return self.url_result(m_yt.group(1), 'Youtube')
169
170 m_rutube = re.search(
171 r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
172 if m_rutube is not None:
173 self.to_screen('rutube video detected')
174 rutube_url = self._proto_relative_url(
175 m_rutube.group(1).replace('\\', ''))
176 return self.url_result(rutube_url)
177
178 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
179 if m_opts:
180 m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))
181 if m_opts_url:
182 opts_url = m_opts_url.group(1)
183 if opts_url.startswith('//'):
184 opts_url = 'http:' + opts_url
185 return self.url_result(opts_url)
186
187 data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
188 data = json.loads(data_json)
189
190 # Extract upload date
191 upload_date = None
192 mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
193 if mobj is not None:
194 mobj.group(1) + ' ' + mobj.group(2)
195 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
196
197 formats = [{
198 'format_id': k,
199 'url': v,
200 'width': int(k[len('url'):]),
201 } for k, v in data.items()
202 if k.startswith('url')]
203 self._sort_formats(formats)
204
205 return {
206 'id': compat_str(data['vid']),
207 'formats': formats,
208 'title': unescapeHTML(data['md_title']),
209 'thumbnail': data.get('jpg'),
210 'uploader': data.get('md_author'),
211 'duration': data.get('duration'),
212 'upload_date': upload_date,
213 }
214
215
216 class VKUserVideosIE(InfoExtractor):
217 IE_NAME = 'vk.com:user-videos'
218 IE_DESC = 'vk.com:All of a user\'s videos'
219 _VALID_URL = r'https?://vk\.com/videos(?P<id>[0-9]+)(?:m\?.*)?'
220 _TEMPLATE_URL = 'https://vk.com/videos'
221 _TEST = {
222 'url': 'http://vk.com/videos205387401',
223 'info_dict': {
224 'id': '205387401',
225 },
226 'playlist_mincount': 4,
227 }
228
229 def _real_extract(self, url):
230 page_id = self._match_id(url)
231 page = self._download_webpage(url, page_id)
232 video_ids = orderedSet(
233 m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page))
234 url_entries = [
235 self.url_result(
236 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
237 for video_id in video_ids]
238 return self.playlist_result(url_entries, page_id)