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 (
  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             },
 106         },
 107         # swf player
 108         {
 109             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
 110             'md5': '4d47034979d9390d14acdf59c4935bc2',
 111             'info_dict': {
 112                 'id': 'v9188090500',
 113                 'ext': 'mp4',
 114                 'title': 'Shakira - Don\'t Bother',
 115                 'uploader': 'HannahL',
 116                 'uploader_id': 'lisaha95',
 117                 'upload_date': '20090331',
 118                 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
 119             },
 120         },
 121     ]
 122
 123     @classmethod
 124     def _extract_url(cls, webpage):
 125         mobj = re.search(
 126             r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
 127             webpage)
 128         if mobj is not None:
 129             return mobj.group('url')
 130
 131         mobj = re.search(
 132             r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
 133                     <div\s+class="video_image">[^<]+</div>\s*
 134                     <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
 135         if mobj is not None:
 136             return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
 137
 138     def _search_meta(self, name, html, display_name=None):
 139         if display_name is None:
 140             display_name = name
 141         return self._html_search_regex(
 142             r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
 143             html, display_name, fatal=False)
 144         return self._html_search_meta(name, html, display_name)
 145
 146     def _real_extract(self, url):
 147         video_id = self._match_id(url)
 148
 149         video_form = {
 150             'ticket': video_id,
 151             'video_url': '1',
 152             'frame_url': '1',
 153             'devid': 'LoadupFlashPlayer',
 154             'getvideoinfo': '1',
 155         }
 156
 157         request = compat_urllib_request.Request(
 158             'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
 159         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 160
 161         video = self._download_json(request, video_id, 'Downloading video JSON')
 162
 163         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 164
 165         if not video_url:
 166             if video.get('_moderate_no') or not video.get('moderated'):
 167                 raise ExtractorError(
 168                     'Video %s has not been approved by moderator' % video_id, expected=True)
 169
 170             if video.get('error'):
 171                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 172
 173         title = video['title']
 174         thumbnail = video['_imgURL']
 175         upload_date = unified_strdate(video['added'])
 176         uploader = video['userNick']
 177         uploader_id = video['userLogin']
 178         duration = int_or_none(video['duration'])
 179
 180         # Video JSON does not provide enough meta data
 181         # We will extract some from the video web page instead
 182         webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
 183         webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
 184
 185         # Warning if video is unavailable
 186         warning = self._html_search_regex(
 187             r'<div class="videoUnModer">(.*?)</div>', webpage,
 188             'warning message', default=None)
 189         if warning is not None:
 190             self._downloader.report_warning(
 191                 'Video %s may not be available; smotri said: %s ' %
 192                 (video_id, warning))
 193
 194         # Adult content
 195         if re.search('EroConfirmText">', webpage) is not None:
 196             self.report_age_confirmation()
 197             confirm_string = self._html_search_regex(
 198                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
 199                 webpage, 'confirm string')
 200             confirm_url = webpage_url + '&confirm=%s' % confirm_string
 201             webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
 202             adult_content = True
 203         else:
 204             adult_content = False
 205
 206         view_count = self._html_search_regex(
 207             'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
 208             webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
 209
 210         return {
 211             'id': video_id,
 212             'url': video_url,
 213             'title': title,
 214             'thumbnail': thumbnail,
 215             'uploader': uploader,
 216             'upload_date': upload_date,
 217             'uploader_id': uploader_id,
 218             'duration': duration,
 219             'view_count': int_or_none(view_count),
 220             'age_limit': 18 if adult_content else 0,
 221         }
 222
 223
 224 class SmotriCommunityIE(InfoExtractor):
 225     IE_DESC = 'Smotri.com community videos'
 226     IE_NAME = 'smotri:community'
 227     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
 228     _TEST = {
 229         'url': 'http://smotri.com/community/video/kommuna',
 230         'info_dict': {
 231             'id': 'kommuna',
 232             'title': 'КПРФ',
 233         },
 234         'playlist_mincount': 4,
 235     }
 236
 237     def _real_extract(self, url):
 238         mobj = re.match(self._VALID_URL, url)
 239         community_id = mobj.group('communityid')
 240
 241         url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
 242         rss = self._download_xml(url, community_id, 'Downloading community RSS')
 243
 244         entries = [self.url_result(video_url.text, 'Smotri')
 245                    for video_url in rss.findall('./channel/item/link')]
 246
 247         description_text = rss.find('./channel/description').text
 248         community_title = self._html_search_regex(
 249             '^Видео сообщества "([^"]+)"$', description_text, 'community title')
 250
 251         return self.playlist_result(entries, community_id, community_title)
 252
 253
 254 class SmotriUserIE(InfoExtractor):
 255     IE_DESC = 'Smotri.com user videos'
 256     IE_NAME = 'smotri:user'
 257     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
 258     _TESTS = [{
 259         'url': 'http://smotri.com/user/inspector',
 260         'info_dict': {
 261             'id': 'inspector',
 262             'title': 'Inspector',
 263         },
 264         'playlist_mincount': 9,
 265     }]
 266
 267     def _real_extract(self, url):
 268         mobj = re.match(self._VALID_URL, url)
 269         user_id = mobj.group('userid')
 270
 271         url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
 272         rss = self._download_xml(url, user_id, 'Downloading user RSS')
 273
 274         entries = [self.url_result(video_url.text, 'Smotri')
 275                    for video_url in rss.findall('./channel/item/link')]
 276
 277         description_text = rss.find('./channel/description').text
 278         user_nickname = self._html_search_regex(
 279             '^Видео режиссера (.*)$', description_text,
 280             'user nickname')
 281
 282         return self.playlist_result(entries, user_id, user_nickname)
 283
 284
 285 class SmotriBroadcastIE(InfoExtractor):
 286     IE_DESC = 'Smotri.com broadcasts'
 287     IE_NAME = 'smotri:broadcast'
 288     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
 289
 290     def _real_extract(self, url):
 291         mobj = re.match(self._VALID_URL, url)
 292         broadcast_id = mobj.group('broadcastid')
 293
 294         broadcast_url = 'http://' + mobj.group('url')
 295         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 296
 297         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 298             raise ExtractorError(
 299                 'Broadcast %s does not exist' % broadcast_id, expected=True)
 300
 301         # Adult content
 302         if re.search('EroConfirmText">', broadcast_page) is not None:
 303
 304             (username, password) = self._get_login_info()
 305             if username is None:
 306                 raise ExtractorError(
 307                     'Erotic broadcasts allowed only for registered users, '
 308                     'use --username and --password options to provide account credentials.',
 309                     expected=True)
 310
 311             login_form = {
 312                 'login-hint53': '1',
 313                 'confirm_erotic': '1',
 314                 'login': username,
 315                 'password': password,
 316             }
 317
 318             request = compat_urllib_request.Request(
 319                 broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
 320             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 321             broadcast_page = self._download_webpage(
 322                 request, broadcast_id, 'Logging in and confirming age')
 323
 324             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
 325                 raise ExtractorError('Unable to log in: bad username or password', expected=True)
 326
 327             adult_content = True
 328         else:
 329             adult_content = False
 330
 331         ticket = self._html_search_regex(
 332             r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",
 333             broadcast_page, 'broadcast ticket')
 334
 335         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 336
 337         broadcast_password = self._downloader.params.get('videopassword', None)
 338         if broadcast_password:
 339             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 340
 341         broadcast_json_page = self._download_webpage(
 342             url, broadcast_id, 'Downloading broadcast JSON')
 343
 344         try:
 345             broadcast_json = json.loads(broadcast_json_page)
 346
 347             protected_broadcast = broadcast_json['_pass_protected'] == 1
 348             if protected_broadcast and not broadcast_password:
 349                 raise ExtractorError(
 350                     'This broadcast is protected by a password, use the --video-password option',
 351                     expected=True)
 352
 353             broadcast_offline = broadcast_json['is_play'] == 0
 354             if broadcast_offline:
 355                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 356
 357             rtmp_url = broadcast_json['_server']
 358             mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
 359             if not mobj:
 360                 raise ExtractorError('Unexpected broadcast rtmp URL')
 361
 362             broadcast_playpath = broadcast_json['_streamName']
 363             broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
 364             broadcast_thumbnail = broadcast_json['_imgURL']
 365             broadcast_title = self._live_title(broadcast_json['title'])
 366             broadcast_description = broadcast_json['description']
 367             broadcaster_nick = broadcast_json['nick']
 368             broadcaster_login = broadcast_json['login']
 369             rtmp_conn = 'S:%s' % uuid.uuid4().hex
 370         except KeyError:
 371             if protected_broadcast:
 372                 raise ExtractorError('Bad broadcast password', expected=True)
 373             raise ExtractorError('Unexpected broadcast JSON')
 374
 375         return {
 376             'id': broadcast_id,
 377             'url': rtmp_url,
 378             'title': broadcast_title,
 379             'thumbnail': broadcast_thumbnail,
 380             'description': broadcast_description,
 381             'uploader': broadcaster_nick,
 382             'uploader_id': broadcaster_login,
 383             'age_limit': 18 if adult_content else 0,
 384             'ext': 'flv',
 385             'play_path': broadcast_playpath,
 386             'player_url': 'http://pics.smotri.com/broadcast_play.swf',
 387             'app': broadcast_app,
 388             'rtmp_live': True,
 389             'rtmp_conn': rtmp_conn,
 390             'is_live': True,
 391         }