Raphaël G. Git Repositories - youtubedl/blob - 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 compat_urllib_parse
  11 from ..utils import (
  12     ExtractorError,
  13     int_or_none,
  14     sanitized_Request,
  15     unified_strdate,
  16 )
  17
  18
  19 class SmotriIE(InfoExtractor):
  20     IE_DESC = 'Smotri.com'
  21     IE_NAME = 'smotri'
  22     _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})'
  23     _NETRC_MACHINE = 'smotri'
  24
  25     _TESTS = [
  26         # real video id 2610366
  27         {
  28             'url': 'http://smotri.com/video/view/?id=v261036632ab',
  29             'md5': '2a7b08249e6f5636557579c368040eb9',
  30             'info_dict': {
  31                 'id': 'v261036632ab',
  32                 'ext': 'mp4',
  33                 'title': 'катастрофа с камер видеонаблюдения',
  34                 'uploader': 'rbc2008',
  35                 'uploader_id': 'rbc08',
  36                 'upload_date': '20131118',
  37                 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
  38             },
  39         },
  40         # real video id 57591
  41         {
  42             'url': 'http://smotri.com/video/view/?id=v57591cb20',
  43             'md5': '830266dfc21f077eac5afd1883091bcd',
  44             'info_dict': {
  45                 'id': 'v57591cb20',
  46                 'ext': 'flv',
  47                 'title': 'test',
  48                 'uploader': 'Support Photofile@photofile',
  49                 'uploader_id': 'support-photofile',
  50                 'upload_date': '20070704',
  51                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
  52             },
  53         },
  54         # video-password, not approved by moderator
  55         {
  56             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
  57             'md5': 'f6331cef33cad65a0815ee482a54440b',
  58             'info_dict': {
  59                 'id': 'v1390466a13c',
  60                 'ext': 'mp4',
  61                 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
  62                 'uploader': 'timoxa40',
  63                 'uploader_id': 'timoxa40',
  64                 'upload_date': '20100404',
  65                 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
  66             },
  67             'params': {
  68                 'videopassword': 'qwerty',
  69             },
  70             'skip': 'Video is not approved by moderator',
  71         },
  72         # video-password
  73         {
  74             'url': 'http://smotri.com/video/view/?id=v6984858774#',
  75             'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
  76             'info_dict': {
  77                 'id': 'v6984858774',
  78                 'ext': 'mp4',
  79                 'title': 'Дача Солженицина ПАРОЛЬ 223322',
  80                 'uploader': 'psavari1',
  81                 'uploader_id': 'psavari1',
  82                 'upload_date': '20081103',
  83                 'thumbnail': 're:^https?://.*\.jpg$',
  84             },
  85             'params': {
  86                 'videopassword': '223322',
  87             },
  88         },
  89         # age limit + video-password, not approved by moderator
  90         {
  91             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
  92             'md5': '91e909c9f0521adf5ee86fbe073aad70',
  93             'info_dict': {
  94                 'id': 'v15408898bcf',
  95                 'ext': 'flv',
  96                 'title': 'этот ролик не покажут по ТВ',
  97                 'uploader': 'zzxxx',
  98                 'uploader_id': 'ueggb',
  99                 'upload_date': '20101001',
 100                 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
 101                 'age_limit': 18,
 102             },
 103             'params': {
 104                 'videopassword': '333'
 105             },
 106             'skip': 'Video is not approved by moderator',
 107         },
 108         # age limit + video-password
 109         {
 110             'url': 'http://smotri.com/video/view/?id=v7780025814',
 111             'md5': 'b4599b068422559374a59300c5337d72',
 112             'info_dict': {
 113                 'id': 'v7780025814',
 114                 'ext': 'mp4',
 115                 'title': 'Sexy Beach (пароль 123)',
 116                 'uploader': 'вАся',
 117                 'uploader_id': 'asya_prosto',
 118                 'upload_date': '20081218',
 119                 'thumbnail': 're:^https?://.*\.jpg$',
 120                 'age_limit': 18,
 121             },
 122             'params': {
 123                 'videopassword': '123'
 124             },
 125         },
 126         # swf player
 127         {
 128             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
 129             'md5': '31099eeb4bc906712c5f40092045108d',
 130             'info_dict': {
 131                 'id': 'v9188090500',
 132                 'ext': 'mp4',
 133                 'title': 'Shakira - Don\'t Bother',
 134                 'uploader': 'HannahL',
 135                 'uploader_id': 'lisaha95',
 136                 'upload_date': '20090331',
 137                 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
 138             },
 139         },
 140     ]
 141
 142     @classmethod
 143     def _extract_url(cls, webpage):
 144         mobj = re.search(
 145             r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
 146             webpage)
 147         if mobj is not None:
 148             return mobj.group('url')
 149
 150         mobj = re.search(
 151             r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
 152                     <div\s+class="video_image">[^<]+</div>\s*
 153                     <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
 154         if mobj is not None:
 155             return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
 156
 157     def _search_meta(self, name, html, display_name=None):
 158         if display_name is None:
 159             display_name = name
 160         return self._html_search_meta(name, html, display_name)
 161
 162     def _real_extract(self, url):
 163         video_id = self._match_id(url)
 164
 165         video_form = {
 166             'ticket': video_id,
 167             'video_url': '1',
 168             'frame_url': '1',
 169             'devid': 'LoadupFlashPlayer',
 170             'getvideoinfo': '1',
 171         }
 172
 173         video_password = self._downloader.params.get('videopassword', None)
 174         if video_password:
 175             video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
 176
 177         request = sanitized_Request(
 178             'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
 179         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 180
 181         video = self._download_json(request, video_id, 'Downloading video JSON')
 182
 183         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 184
 185         if not video_url:
 186             if video.get('_moderate_no'):
 187                 raise ExtractorError(
 188                     'Video %s has not been approved by moderator' % video_id, expected=True)
 189
 190             if video.get('error'):
 191                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 192
 193             if video.get('_pass_protected') == 1:
 194                 msg = ('Invalid video password' if video_password
 195                        else 'This video is protected by a password, use the --video-password option')
 196                 raise ExtractorError(msg, expected=True)
 197
 198         title = video['title']
 199         thumbnail = video['_imgURL']
 200         upload_date = unified_strdate(video['added'])
 201         uploader = video['userNick']
 202         uploader_id = video['userLogin']
 203         duration = int_or_none(video['duration'])
 204
 205         # Video JSON does not provide enough meta data
 206         # We will extract some from the video web page instead
 207         webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
 208         webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
 209
 210         # Warning if video is unavailable
 211         warning = self._html_search_regex(
 212             r'<div class="videoUnModer">(.*?)</div>', webpage,
 213             'warning message', default=None)
 214         if warning is not None:
 215             self._downloader.report_warning(
 216                 'Video %s may not be available; smotri said: %s ' %
 217                 (video_id, warning))
 218
 219         # Adult content
 220         if re.search('EroConfirmText">', webpage) is not None:
 221             self.report_age_confirmation()
 222             confirm_string = self._html_search_regex(
 223                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
 224                 webpage, 'confirm string')
 225             confirm_url = webpage_url + '&confirm=%s' % confirm_string
 226             webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
 227             adult_content = True
 228         else:
 229             adult_content = False
 230
 231         view_count = self._html_search_regex(
 232             'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
 233             webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
 234
 235         return {
 236             'id': video_id,
 237             'url': video_url,
 238             'title': title,
 239             'thumbnail': thumbnail,
 240             'uploader': uploader,
 241             'upload_date': upload_date,
 242             'uploader_id': uploader_id,
 243             'duration': duration,
 244             'view_count': int_or_none(view_count),
 245             'age_limit': 18 if adult_content else 0,
 246         }
 247
 248
 249 class SmotriCommunityIE(InfoExtractor):
 250     IE_DESC = 'Smotri.com community videos'
 251     IE_NAME = 'smotri:community'
 252     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
 253     _TEST = {
 254         'url': 'http://smotri.com/community/video/kommuna',
 255         'info_dict': {
 256             'id': 'kommuna',
 257             'title': 'КПРФ',
 258         },
 259         'playlist_mincount': 4,
 260     }
 261
 262     def _real_extract(self, url):
 263         mobj = re.match(self._VALID_URL, url)
 264         community_id = mobj.group('communityid')
 265
 266         url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
 267         rss = self._download_xml(url, community_id, 'Downloading community RSS')
 268
 269         entries = [self.url_result(video_url.text, 'Smotri')
 270                    for video_url in rss.findall('./channel/item/link')]
 271
 272         description_text = rss.find('./channel/description').text
 273         community_title = self._html_search_regex(
 274             '^Видео сообщества "([^"]+)"$', description_text, 'community title')
 275
 276         return self.playlist_result(entries, community_id, community_title)
 277
 278
 279 class SmotriUserIE(InfoExtractor):
 280     IE_DESC = 'Smotri.com user videos'
 281     IE_NAME = 'smotri:user'
 282     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
 283     _TESTS = [{
 284         'url': 'http://smotri.com/user/inspector',
 285         'info_dict': {
 286             'id': 'inspector',
 287             'title': 'Inspector',
 288         },
 289         'playlist_mincount': 9,
 290     }]
 291
 292     def _real_extract(self, url):
 293         mobj = re.match(self._VALID_URL, url)
 294         user_id = mobj.group('userid')
 295
 296         url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
 297         rss = self._download_xml(url, user_id, 'Downloading user RSS')
 298
 299         entries = [self.url_result(video_url.text, 'Smotri')
 300                    for video_url in rss.findall('./channel/item/link')]
 301
 302         description_text = rss.find('./channel/description').text
 303         user_nickname = self._html_search_regex(
 304             '^Видео режиссера (.*)$', description_text,
 305             'user nickname')
 306
 307         return self.playlist_result(entries, user_id, user_nickname)
 308
 309
 310 class SmotriBroadcastIE(InfoExtractor):
 311     IE_DESC = 'Smotri.com broadcasts'
 312     IE_NAME = 'smotri:broadcast'
 313     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
 314
 315     def _real_extract(self, url):
 316         mobj = re.match(self._VALID_URL, url)
 317         broadcast_id = mobj.group('broadcastid')
 318
 319         broadcast_url = 'http://' + mobj.group('url')
 320         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 321
 322         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 323             raise ExtractorError(
 324                 'Broadcast %s does not exist' % broadcast_id, expected=True)
 325
 326         # Adult content
 327         if re.search('EroConfirmText">', broadcast_page) is not None:
 328
 329             (username, password) = self._get_login_info()
 330             if username is None:
 331                 self.raise_login_required('Erotic broadcasts allowed only for registered users')
 332
 333             login_form = {
 334                 'login-hint53': '1',
 335                 'confirm_erotic': '1',
 336                 'login': username,
 337                 'password': password,
 338             }
 339
 340             request = sanitized_Request(
 341                 broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
 342             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 343             broadcast_page = self._download_webpage(
 344                 request, broadcast_id, 'Logging in and confirming age')
 345
 346             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
 347                 raise ExtractorError('Unable to log in: bad username or password', expected=True)
 348
 349             adult_content = True
 350         else:
 351             adult_content = False
 352
 353         ticket = self._html_search_regex(
 354             r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",
 355             broadcast_page, 'broadcast ticket')
 356
 357         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 358
 359         broadcast_password = self._downloader.params.get('videopassword', None)
 360         if broadcast_password:
 361             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 362
 363         broadcast_json_page = self._download_webpage(
 364             url, broadcast_id, 'Downloading broadcast JSON')
 365
 366         try:
 367             broadcast_json = json.loads(broadcast_json_page)
 368
 369             protected_broadcast = broadcast_json['_pass_protected'] == 1
 370             if protected_broadcast and not broadcast_password:
 371                 raise ExtractorError(
 372                     'This broadcast is protected by a password, use the --video-password option',
 373                     expected=True)
 374
 375             broadcast_offline = broadcast_json['is_play'] == 0
 376             if broadcast_offline:
 377                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 378
 379             rtmp_url = broadcast_json['_server']
 380             mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
 381             if not mobj:
 382                 raise ExtractorError('Unexpected broadcast rtmp URL')
 383
 384             broadcast_playpath = broadcast_json['_streamName']
 385             broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
 386             broadcast_thumbnail = broadcast_json['_imgURL']
 387             broadcast_title = self._live_title(broadcast_json['title'])
 388             broadcast_description = broadcast_json['description']
 389             broadcaster_nick = broadcast_json['nick']
 390             broadcaster_login = broadcast_json['login']
 391             rtmp_conn = 'S:%s' % uuid.uuid4().hex
 392         except KeyError:
 393             if protected_broadcast:
 394                 raise ExtractorError('Bad broadcast password', expected=True)
 395             raise ExtractorError('Unexpected broadcast JSON')
 396
 397         return {
 398             'id': broadcast_id,
 399             'url': rtmp_url,
 400             'title': broadcast_title,
 401             'thumbnail': broadcast_thumbnail,
 402             'description': broadcast_description,
 403             'uploader': broadcaster_nick,
 404             'uploader_id': broadcaster_login,
 405             'age_limit': 18 if adult_content else 0,
 406             'ext': 'flv',
 407             'play_path': broadcast_playpath,
 408             'player_url': 'http://pics.smotri.com/broadcast_play.swf',
 409             'app': broadcast_app,
 410             'rtmp_live': True,
 411             'rtmp_conn': rtmp_conn,
 412             'is_live': True,
 413         }