_ Git - youtube-dl/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 ..utils import (
  11     compat_urllib_parse,
  12     compat_urllib_request,
  13     ExtractorError,
  14     int_or_none,
  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
  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         },
  71         # age limit + video-password
  72         {
  73             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
  74             'md5': '91e909c9f0521adf5ee86fbe073aad70',
  75             'info_dict': {
  76                 'id': 'v15408898bcf',
  77                 'ext': 'flv',
  78                 'title': 'этот ролик не покажут по ТВ',
  79                 'uploader': 'zzxxx',
  80                 'uploader_id': 'ueggb',
  81                 'upload_date': '20101001',
  82                 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
  83                 'age_limit': 18,
  84             },
  85             'params': {
  86                 'videopassword': '333'
  87             }
  88         },
  89         # swf player
  90         {
  91             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
  92             'md5': '4d47034979d9390d14acdf59c4935bc2',
  93             'info_dict': {
  94                 'id': 'v9188090500',
  95                 'ext': 'mp4',
  96                 'title': 'Shakira - Don\'t Bother',
  97                 'uploader': 'HannahL',
  98                 'uploader_id': 'lisaha95',
  99                 'upload_date': '20090331',
 100                 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
 101             },
 102         },
 103     ]
 104
 105     @classmethod
 106     def _extract_url(cls, webpage):
 107         mobj = re.search(
 108             r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
 109             webpage)
 110         if mobj is not None:
 111             return mobj.group('url')
 112
 113         mobj = re.search(
 114             r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
 115                     <div\s+class="video_image">[^<]+</div>\s*
 116                     <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
 117         if mobj is not None:
 118             return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
 119
 120     def _search_meta(self, name, html, display_name=None):
 121         if display_name is None:
 122             display_name = name
 123         return self._html_search_regex(
 124             r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
 125             html, display_name, fatal=False)
 126         return self._html_search_meta(name, html, display_name)
 127
 128     def _real_extract(self, url):
 129         video_id = self._match_id(url)
 130
 131         video_form = {
 132             'ticket': video_id,
 133             'video_url': '1',
 134             'frame_url': '1',
 135             'devid': 'LoadupFlashPlayer',
 136             'getvideoinfo': '1',
 137         }
 138
 139         request = compat_urllib_request.Request(
 140             'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
 141         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 142
 143         video = self._download_json(request, video_id, 'Downloading video JSON')
 144
 145         if video.get('_moderate_no') or not video.get('moderated'):
 146             raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True)
 147
 148         if video.get('error'):
 149             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 150
 151         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 152         title = video['title']
 153         thumbnail = video['_imgURL']
 154         upload_date = unified_strdate(video['added'])
 155         uploader = video['userNick']
 156         uploader_id = video['userLogin']
 157         duration = int_or_none(video['duration'])
 158
 159         # Video JSON does not provide enough meta data
 160         # We will extract some from the video web page instead
 161         webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
 162         webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
 163
 164         # Warning if video is unavailable
 165         warning = self._html_search_regex(
 166             r'<div class="videoUnModer">(.*?)</div>', webpage,
 167             'warning message', default=None)
 168         if warning is not None:
 169             self._downloader.report_warning(
 170                 'Video %s may not be available; smotri said: %s ' %
 171                 (video_id, warning))
 172
 173         # Adult content
 174         if re.search('EroConfirmText">', webpage) is not None:
 175             self.report_age_confirmation()
 176             confirm_string = self._html_search_regex(
 177                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
 178                 webpage, 'confirm string')
 179             confirm_url = webpage_url + '&confirm=%s' % confirm_string
 180             webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
 181             adult_content = True
 182         else:
 183             adult_content = False
 184
 185         view_count = self._html_search_regex(
 186             'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
 187             webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
 188
 189         return {
 190             'id': video_id,
 191             'url': video_url,
 192             'title': title,
 193             'thumbnail': thumbnail,
 194             'uploader': uploader,
 195             'upload_date': upload_date,
 196             'uploader_id': uploader_id,
 197             'duration': duration,
 198             'view_count': int_or_none(view_count),
 199             'age_limit': 18 if adult_content else 0,
 200         }
 201
 202
 203 class SmotriCommunityIE(InfoExtractor):
 204     IE_DESC = 'Smotri.com community videos'
 205     IE_NAME = 'smotri:community'
 206     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
 207     _TEST = {
 208         'url': 'http://smotri.com/community/video/kommuna',
 209         'info_dict': {
 210             'id': 'kommuna',
 211             'title': 'КПРФ',
 212         },
 213         'playlist_mincount': 4,
 214     }
 215
 216     def _real_extract(self, url):
 217         mobj = re.match(self._VALID_URL, url)
 218         community_id = mobj.group('communityid')
 219
 220         url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
 221         rss = self._download_xml(url, community_id, 'Downloading community RSS')
 222
 223         entries = [self.url_result(video_url.text, 'Smotri')
 224                    for video_url in rss.findall('./channel/item/link')]
 225
 226         description_text = rss.find('./channel/description').text
 227         community_title = self._html_search_regex(
 228             '^Видео сообщества "([^"]+)"$', description_text, 'community title')
 229
 230         return self.playlist_result(entries, community_id, community_title)
 231
 232
 233 class SmotriUserIE(InfoExtractor):
 234     IE_DESC = 'Smotri.com user videos'
 235     IE_NAME = 'smotri:user'
 236     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
 237     _TESTS = [{
 238         'url': 'http://smotri.com/user/inspector',
 239         'info_dict': {
 240             'id': 'inspector',
 241             'title': 'Inspector',
 242         },
 243         'playlist_mincount': 9,
 244     }]
 245
 246     def _real_extract(self, url):
 247         mobj = re.match(self._VALID_URL, url)
 248         user_id = mobj.group('userid')
 249
 250         url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
 251         rss = self._download_xml(url, user_id, 'Downloading user RSS')
 252
 253         entries = [self.url_result(video_url.text, 'Smotri')
 254                    for video_url in rss.findall('./channel/item/link')]
 255
 256         description_text = rss.find('./channel/description').text
 257         user_nickname = self._html_search_regex(
 258             '^Видео режиссера (.*)$', description_text,
 259             'user nickname')
 260
 261         return self.playlist_result(entries, user_id, user_nickname)
 262
 263
 264 class SmotriBroadcastIE(InfoExtractor):
 265     IE_DESC = 'Smotri.com broadcasts'
 266     IE_NAME = 'smotri:broadcast'
 267     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
 268
 269     def _real_extract(self, url):
 270         mobj = re.match(self._VALID_URL, url)
 271         broadcast_id = mobj.group('broadcastid')
 272
 273         broadcast_url = 'http://' + mobj.group('url')
 274         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 275
 276         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 277             raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True)
 278
 279         # Adult content
 280         if re.search('EroConfirmText">', broadcast_page) is not None:
 281
 282             (username, password) = self._get_login_info()
 283             if username is None:
 284                 raise ExtractorError('Erotic broadcasts allowed only for registered users, '
 285                                      'use --username and --password options to provide account credentials.', expected=True)
 286
 287             login_form = {
 288                 'login-hint53': '1',
 289                 'confirm_erotic': '1',
 290                 'login': username,
 291                 'password': password,
 292             }
 293
 294             request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
 295             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 296             broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age')
 297
 298             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
 299                 raise ExtractorError('Unable to log in: bad username or password', expected=True)
 300
 301             adult_content = True
 302         else:
 303             adult_content = False
 304
 305         ticket = self._html_search_regex(
 306             'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
 307             broadcast_page, 'broadcast ticket')
 308
 309         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 310
 311         broadcast_password = self._downloader.params.get('videopassword', None)
 312         if broadcast_password:
 313             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 314
 315         broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON')
 316
 317         try:
 318             broadcast_json = json.loads(broadcast_json_page)
 319
 320             protected_broadcast = broadcast_json['_pass_protected'] == 1
 321             if protected_broadcast and not broadcast_password:
 322                 raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True)
 323
 324             broadcast_offline = broadcast_json['is_play'] == 0
 325             if broadcast_offline:
 326                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 327
 328             rtmp_url = broadcast_json['_server']
 329             if not rtmp_url.startswith('rtmp://'):
 330                 raise ExtractorError('Unexpected broadcast rtmp URL')
 331
 332             broadcast_playpath = broadcast_json['_streamName']
 333             broadcast_thumbnail = broadcast_json['_imgURL']
 334             broadcast_title = broadcast_json['title']
 335             broadcast_description = broadcast_json['description']
 336             broadcaster_nick = broadcast_json['nick']
 337             broadcaster_login = broadcast_json['login']
 338             rtmp_conn = 'S:%s' % uuid.uuid4().hex
 339         except KeyError:
 340             if protected_broadcast:
 341                 raise ExtractorError('Bad broadcast password', expected=True)
 342             raise ExtractorError('Unexpected broadcast JSON')
 343
 344         return {
 345             'id': broadcast_id,
 346             'url': rtmp_url,
 347             'title': broadcast_title,
 348             'thumbnail': broadcast_thumbnail,
 349             'description': broadcast_description,
 350             'uploader': broadcaster_nick,
 351             'uploader_id': broadcaster_login,
 352             'age_limit': 18 if adult_content else 0,
 353             'ext': 'flv',
 354             'play_path': broadcast_playpath,
 355             'rtmp_live': True,
 356             'rtmp_conn': rtmp_conn
 357         }