]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/smotri.py
Update changelog.
[youtubedl] / youtube_dl / extractor / smotri.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5 import json
6 import hashlib
7 import uuid
8
9 from .common import InfoExtractor
10 from ..compat import (
11 compat_urllib_parse,
12 compat_urllib_request,
13 )
14 from ..utils import (
15 ExtractorError,
16 int_or_none,
17 unified_strdate,
18 )
19
20
21 class SmotriIE(InfoExtractor):
22 IE_DESC = 'Smotri.com'
23 IE_NAME = 'smotri'
24 _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
25 _NETRC_MACHINE = 'smotri'
26
27 _TESTS = [
28 # real video id 2610366
29 {
30 'url': 'http://smotri.com/video/view/?id=v261036632ab',
31 'md5': '2a7b08249e6f5636557579c368040eb9',
32 'info_dict': {
33 'id': 'v261036632ab',
34 'ext': 'mp4',
35 'title': 'катастрофа с камер видеонаблюдения',
36 'uploader': 'rbc2008',
37 'uploader_id': 'rbc08',
38 'upload_date': '20131118',
39 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
40 },
41 },
42 # real video id 57591
43 {
44 'url': 'http://smotri.com/video/view/?id=v57591cb20',
45 'md5': '830266dfc21f077eac5afd1883091bcd',
46 'info_dict': {
47 'id': 'v57591cb20',
48 'ext': 'flv',
49 'title': 'test',
50 'uploader': 'Support Photofile@photofile',
51 'uploader_id': 'support-photofile',
52 'upload_date': '20070704',
53 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
54 },
55 },
56 # video-password
57 {
58 'url': 'http://smotri.com/video/view/?id=v1390466a13c',
59 'md5': 'f6331cef33cad65a0815ee482a54440b',
60 'info_dict': {
61 'id': 'v1390466a13c',
62 'ext': 'mp4',
63 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
64 'uploader': 'timoxa40',
65 'uploader_id': 'timoxa40',
66 'upload_date': '20100404',
67 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
68 },
69 'params': {
70 'videopassword': 'qwerty',
71 },
72 'skip': 'Video is not approved by moderator',
73 },
74 # age limit + video-password
75 {
76 'url': 'http://smotri.com/video/view/?id=v15408898bcf',
77 'md5': '91e909c9f0521adf5ee86fbe073aad70',
78 'info_dict': {
79 'id': 'v15408898bcf',
80 'ext': 'flv',
81 'title': 'этот ролик не покажут по ТВ',
82 'uploader': 'zzxxx',
83 'uploader_id': 'ueggb',
84 'upload_date': '20101001',
85 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
86 'age_limit': 18,
87 },
88 'params': {
89 'videopassword': '333'
90 },
91 'skip': 'Video is not approved by moderator',
92 },
93 # not approved by moderator, but available
94 {
95 'url': 'http://smotri.com/video/view/?id=v28888533b73',
96 'md5': 'f44bc7adac90af518ef1ecf04893bb34',
97 'info_dict': {
98 'id': 'v28888533b73',
99 'ext': 'mp4',
100 'title': 'Russian Spies Killed By ISIL Child Soldier',
101 'uploader': 'Mopeder',
102 'uploader_id': 'mopeder',
103 'duration': 71,
104 'thumbnail': 'http://frame9.loadup.ru/d7/32/2888853.2.3.jpg',
105 'upload_date': '20150114',
106 },
107 },
108 # swf player
109 {
110 'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
111 'md5': '31099eeb4bc906712c5f40092045108d',
112 'info_dict': {
113 'id': 'v9188090500',
114 'ext': 'mp4',
115 'title': 'Shakira - Don\'t Bother',
116 'uploader': 'HannahL',
117 'uploader_id': 'lisaha95',
118 'upload_date': '20090331',
119 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
120 },
121 },
122 ]
123
124 @classmethod
125 def _extract_url(cls, webpage):
126 mobj = re.search(
127 r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
128 webpage)
129 if mobj is not None:
130 return mobj.group('url')
131
132 mobj = re.search(
133 r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
134 <div\s+class="video_image">[^<]+</div>\s*
135 <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
136 if mobj is not None:
137 return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
138
139 def _search_meta(self, name, html, display_name=None):
140 if display_name is None:
141 display_name = name
142 return self._html_search_meta(name, html, display_name)
143
144 def _real_extract(self, url):
145 video_id = self._match_id(url)
146
147 video_form = {
148 'ticket': video_id,
149 'video_url': '1',
150 'frame_url': '1',
151 'devid': 'LoadupFlashPlayer',
152 'getvideoinfo': '1',
153 }
154
155 request = compat_urllib_request.Request(
156 'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
157 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
158
159 video = self._download_json(request, video_id, 'Downloading video JSON')
160
161 video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
162
163 if not video_url:
164 if video.get('_moderate_no') or not video.get('moderated'):
165 raise ExtractorError(
166 'Video %s has not been approved by moderator' % video_id, expected=True)
167
168 if video.get('error'):
169 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
170
171 title = video['title']
172 thumbnail = video['_imgURL']
173 upload_date = unified_strdate(video['added'])
174 uploader = video['userNick']
175 uploader_id = video['userLogin']
176 duration = int_or_none(video['duration'])
177
178 # Video JSON does not provide enough meta data
179 # We will extract some from the video web page instead
180 webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
181 webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
182
183 # Warning if video is unavailable
184 warning = self._html_search_regex(
185 r'<div class="videoUnModer">(.*?)</div>', webpage,
186 'warning message', default=None)
187 if warning is not None:
188 self._downloader.report_warning(
189 'Video %s may not be available; smotri said: %s ' %
190 (video_id, warning))
191
192 # Adult content
193 if re.search('EroConfirmText">', webpage) is not None:
194 self.report_age_confirmation()
195 confirm_string = self._html_search_regex(
196 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
197 webpage, 'confirm string')
198 confirm_url = webpage_url + '&confirm=%s' % confirm_string
199 webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
200 adult_content = True
201 else:
202 adult_content = False
203
204 view_count = self._html_search_regex(
205 'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
206 webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
207
208 return {
209 'id': video_id,
210 'url': video_url,
211 'title': title,
212 'thumbnail': thumbnail,
213 'uploader': uploader,
214 'upload_date': upload_date,
215 'uploader_id': uploader_id,
216 'duration': duration,
217 'view_count': int_or_none(view_count),
218 'age_limit': 18 if adult_content else 0,
219 }
220
221
222 class SmotriCommunityIE(InfoExtractor):
223 IE_DESC = 'Smotri.com community videos'
224 IE_NAME = 'smotri:community'
225 _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
226 _TEST = {
227 'url': 'http://smotri.com/community/video/kommuna',
228 'info_dict': {
229 'id': 'kommuna',
230 'title': 'КПРФ',
231 },
232 'playlist_mincount': 4,
233 }
234
235 def _real_extract(self, url):
236 mobj = re.match(self._VALID_URL, url)
237 community_id = mobj.group('communityid')
238
239 url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
240 rss = self._download_xml(url, community_id, 'Downloading community RSS')
241
242 entries = [self.url_result(video_url.text, 'Smotri')
243 for video_url in rss.findall('./channel/item/link')]
244
245 description_text = rss.find('./channel/description').text
246 community_title = self._html_search_regex(
247 '^Видео сообщества "([^"]+)"$', description_text, 'community title')
248
249 return self.playlist_result(entries, community_id, community_title)
250
251
252 class SmotriUserIE(InfoExtractor):
253 IE_DESC = 'Smotri.com user videos'
254 IE_NAME = 'smotri:user'
255 _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
256 _TESTS = [{
257 'url': 'http://smotri.com/user/inspector',
258 'info_dict': {
259 'id': 'inspector',
260 'title': 'Inspector',
261 },
262 'playlist_mincount': 9,
263 }]
264
265 def _real_extract(self, url):
266 mobj = re.match(self._VALID_URL, url)
267 user_id = mobj.group('userid')
268
269 url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
270 rss = self._download_xml(url, user_id, 'Downloading user RSS')
271
272 entries = [self.url_result(video_url.text, 'Smotri')
273 for video_url in rss.findall('./channel/item/link')]
274
275 description_text = rss.find('./channel/description').text
276 user_nickname = self._html_search_regex(
277 '^Видео режиссера (.*)$', description_text,
278 'user nickname')
279
280 return self.playlist_result(entries, user_id, user_nickname)
281
282
283 class SmotriBroadcastIE(InfoExtractor):
284 IE_DESC = 'Smotri.com broadcasts'
285 IE_NAME = 'smotri:broadcast'
286 _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
287
288 def _real_extract(self, url):
289 mobj = re.match(self._VALID_URL, url)
290 broadcast_id = mobj.group('broadcastid')
291
292 broadcast_url = 'http://' + mobj.group('url')
293 broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
294
295 if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
296 raise ExtractorError(
297 'Broadcast %s does not exist' % broadcast_id, expected=True)
298
299 # Adult content
300 if re.search('EroConfirmText">', broadcast_page) is not None:
301
302 (username, password) = self._get_login_info()
303 if username is None:
304 raise ExtractorError(
305 'Erotic broadcasts allowed only for registered users, '
306 'use --username and --password options to provide account credentials.',
307 expected=True)
308
309 login_form = {
310 'login-hint53': '1',
311 'confirm_erotic': '1',
312 'login': username,
313 'password': password,
314 }
315
316 request = compat_urllib_request.Request(
317 broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
318 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
319 broadcast_page = self._download_webpage(
320 request, broadcast_id, 'Logging in and confirming age')
321
322 if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
323 raise ExtractorError('Unable to log in: bad username or password', expected=True)
324
325 adult_content = True
326 else:
327 adult_content = False
328
329 ticket = self._html_search_regex(
330 r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",
331 broadcast_page, 'broadcast ticket')
332
333 url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
334
335 broadcast_password = self._downloader.params.get('videopassword', None)
336 if broadcast_password:
337 url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
338
339 broadcast_json_page = self._download_webpage(
340 url, broadcast_id, 'Downloading broadcast JSON')
341
342 try:
343 broadcast_json = json.loads(broadcast_json_page)
344
345 protected_broadcast = broadcast_json['_pass_protected'] == 1
346 if protected_broadcast and not broadcast_password:
347 raise ExtractorError(
348 'This broadcast is protected by a password, use the --video-password option',
349 expected=True)
350
351 broadcast_offline = broadcast_json['is_play'] == 0
352 if broadcast_offline:
353 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
354
355 rtmp_url = broadcast_json['_server']
356 mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
357 if not mobj:
358 raise ExtractorError('Unexpected broadcast rtmp URL')
359
360 broadcast_playpath = broadcast_json['_streamName']
361 broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
362 broadcast_thumbnail = broadcast_json['_imgURL']
363 broadcast_title = self._live_title(broadcast_json['title'])
364 broadcast_description = broadcast_json['description']
365 broadcaster_nick = broadcast_json['nick']
366 broadcaster_login = broadcast_json['login']
367 rtmp_conn = 'S:%s' % uuid.uuid4().hex
368 except KeyError:
369 if protected_broadcast:
370 raise ExtractorError('Bad broadcast password', expected=True)
371 raise ExtractorError('Unexpected broadcast JSON')
372
373 return {
374 'id': broadcast_id,
375 'url': rtmp_url,
376 'title': broadcast_title,
377 'thumbnail': broadcast_thumbnail,
378 'description': broadcast_description,
379 'uploader': broadcaster_nick,
380 'uploader_id': broadcaster_login,
381 'age_limit': 18 if adult_content else 0,
382 'ext': 'flv',
383 'play_path': broadcast_playpath,
384 'player_url': 'http://pics.smotri.com/broadcast_play.swf',
385 'app': broadcast_app,
386 'rtmp_live': True,
387 'rtmp_conn': rtmp_conn,
388 'is_live': True,
389 }