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         },
  73         # age limit + video-password
  74         {
  75             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
  76             'md5': '91e909c9f0521adf5ee86fbe073aad70',
  77             'info_dict': {
  78                 'id': 'v15408898bcf',
  79                 'ext': 'flv',
  80                 'title': 'этот ролик не покажут по ТВ',
  81                 'uploader': 'zzxxx',
  82                 'uploader_id': 'ueggb',
  83                 'upload_date': '20101001',
  84                 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
  85                 'age_limit': 18,
  86             },
  87             'params': {
  88                 'videopassword': '333'
  89             }
  90         },
  91         # swf player
  92         {
  93             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
  94             'md5': '4d47034979d9390d14acdf59c4935bc2',
  95             'info_dict': {
  96                 'id': 'v9188090500',
  97                 'ext': 'mp4',
  98                 'title': 'Shakira - Don\'t Bother',
  99                 'uploader': 'HannahL',
 100                 'uploader_id': 'lisaha95',
 101                 'upload_date': '20090331',
 102                 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
 103             },
 104         },
 105     ]
 106
 107     @classmethod
 108     def _extract_url(cls, webpage):
 109         mobj = re.search(
 110             r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
 111             webpage)
 112         if mobj is not None:
 113             return mobj.group('url')
 114
 115         mobj = re.search(
 116             r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
 117                     <div\s+class="video_image">[^<]+</div>\s*
 118                     <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
 119         if mobj is not None:
 120             return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
 121
 122     def _search_meta(self, name, html, display_name=None):
 123         if display_name is None:
 124             display_name = name
 125         return self._html_search_regex(
 126             r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
 127             html, display_name, fatal=False)
 128         return self._html_search_meta(name, html, display_name)
 129
 130     def _real_extract(self, url):
 131         video_id = self._match_id(url)
 132
 133         video_form = {
 134             'ticket': video_id,
 135             'video_url': '1',
 136             'frame_url': '1',
 137             'devid': 'LoadupFlashPlayer',
 138             'getvideoinfo': '1',
 139         }
 140
 141         request = compat_urllib_request.Request(
 142             'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
 143         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 144
 145         video = self._download_json(request, video_id, 'Downloading video JSON')
 146
 147         if video.get('_moderate_no') or not video.get('moderated'):
 148             raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True)
 149
 150         if video.get('error'):
 151             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 152
 153         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 154         title = video['title']
 155         thumbnail = video['_imgURL']
 156         upload_date = unified_strdate(video['added'])
 157         uploader = video['userNick']
 158         uploader_id = video['userLogin']
 159         duration = int_or_none(video['duration'])
 160
 161         # Video JSON does not provide enough meta data
 162         # We will extract some from the video web page instead
 163         webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
 164         webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
 165
 166         # Warning if video is unavailable
 167         warning = self._html_search_regex(
 168             r'<div class="videoUnModer">(.*?)</div>', webpage,
 169             'warning message', default=None)
 170         if warning is not None:
 171             self._downloader.report_warning(
 172                 'Video %s may not be available; smotri said: %s ' %
 173                 (video_id, warning))
 174
 175         # Adult content
 176         if re.search('EroConfirmText">', webpage) is not None:
 177             self.report_age_confirmation()
 178             confirm_string = self._html_search_regex(
 179                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
 180                 webpage, 'confirm string')
 181             confirm_url = webpage_url + '&confirm=%s' % confirm_string
 182             webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
 183             adult_content = True
 184         else:
 185             adult_content = False
 186
 187         view_count = self._html_search_regex(
 188             'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
 189             webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
 190
 191         return {
 192             'id': video_id,
 193             'url': video_url,
 194             'title': title,
 195             'thumbnail': thumbnail,
 196             'uploader': uploader,
 197             'upload_date': upload_date,
 198             'uploader_id': uploader_id,
 199             'duration': duration,
 200             'view_count': int_or_none(view_count),
 201             'age_limit': 18 if adult_content else 0,
 202         }
 203
 204
 205 class SmotriCommunityIE(InfoExtractor):
 206     IE_DESC = 'Smotri.com community videos'
 207     IE_NAME = 'smotri:community'
 208     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
 209     _TEST = {
 210         'url': 'http://smotri.com/community/video/kommuna',
 211         'info_dict': {
 212             'id': 'kommuna',
 213             'title': 'КПРФ',
 214         },
 215         'playlist_mincount': 4,
 216     }
 217
 218     def _real_extract(self, url):
 219         mobj = re.match(self._VALID_URL, url)
 220         community_id = mobj.group('communityid')
 221
 222         url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
 223         rss = self._download_xml(url, community_id, 'Downloading community RSS')
 224
 225         entries = [self.url_result(video_url.text, 'Smotri')
 226                    for video_url in rss.findall('./channel/item/link')]
 227
 228         description_text = rss.find('./channel/description').text
 229         community_title = self._html_search_regex(
 230             '^Видео сообщества "([^"]+)"$', description_text, 'community title')
 231
 232         return self.playlist_result(entries, community_id, community_title)
 233
 234
 235 class SmotriUserIE(InfoExtractor):
 236     IE_DESC = 'Smotri.com user videos'
 237     IE_NAME = 'smotri:user'
 238     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
 239     _TESTS = [{
 240         'url': 'http://smotri.com/user/inspector',
 241         'info_dict': {
 242             'id': 'inspector',
 243             'title': 'Inspector',
 244         },
 245         'playlist_mincount': 9,
 246     }]
 247
 248     def _real_extract(self, url):
 249         mobj = re.match(self._VALID_URL, url)
 250         user_id = mobj.group('userid')
 251
 252         url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
 253         rss = self._download_xml(url, user_id, 'Downloading user RSS')
 254
 255         entries = [self.url_result(video_url.text, 'Smotri')
 256                    for video_url in rss.findall('./channel/item/link')]
 257
 258         description_text = rss.find('./channel/description').text
 259         user_nickname = self._html_search_regex(
 260             '^Видео режиссера (.*)$', description_text,
 261             'user nickname')
 262
 263         return self.playlist_result(entries, user_id, user_nickname)
 264
 265
 266 class SmotriBroadcastIE(InfoExtractor):
 267     IE_DESC = 'Smotri.com broadcasts'
 268     IE_NAME = 'smotri:broadcast'
 269     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
 270
 271     def _real_extract(self, url):
 272         mobj = re.match(self._VALID_URL, url)
 273         broadcast_id = mobj.group('broadcastid')
 274
 275         broadcast_url = 'http://' + mobj.group('url')
 276         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 277
 278         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 279             raise ExtractorError(
 280                 'Broadcast %s does not exist' % broadcast_id, expected=True)
 281
 282         # Adult content
 283         if re.search('EroConfirmText">', broadcast_page) is not None:
 284
 285             (username, password) = self._get_login_info()
 286             if username is None:
 287                 raise ExtractorError(
 288                     'Erotic broadcasts allowed only for registered users, '
 289                     'use --username and --password options to provide account credentials.',
 290                     expected=True)
 291
 292             login_form = {
 293                 'login-hint53': '1',
 294                 'confirm_erotic': '1',
 295                 'login': username,
 296                 'password': password,
 297             }
 298
 299             request = compat_urllib_request.Request(
 300                 broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
 301             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 302             broadcast_page = self._download_webpage(
 303                 request, broadcast_id, 'Logging in and confirming age')
 304
 305             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
 306                 raise ExtractorError('Unable to log in: bad username or password', expected=True)
 307
 308             adult_content = True
 309         else:
 310             adult_content = False
 311
 312         ticket = self._html_search_regex(
 313             r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",
 314             broadcast_page, 'broadcast ticket')
 315
 316         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 317
 318         broadcast_password = self._downloader.params.get('videopassword', None)
 319         if broadcast_password:
 320             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 321
 322         broadcast_json_page = self._download_webpage(
 323             url, broadcast_id, 'Downloading broadcast JSON')
 324
 325         try:
 326             broadcast_json = json.loads(broadcast_json_page)
 327
 328             protected_broadcast = broadcast_json['_pass_protected'] == 1
 329             if protected_broadcast and not broadcast_password:
 330                 raise ExtractorError(
 331                     'This broadcast is protected by a password, use the --video-password option',
 332                     expected=True)
 333
 334             broadcast_offline = broadcast_json['is_play'] == 0
 335             if broadcast_offline:
 336                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 337
 338             rtmp_url = broadcast_json['_server']
 339             mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
 340             if not mobj:
 341                 raise ExtractorError('Unexpected broadcast rtmp URL')
 342
 343             broadcast_playpath = broadcast_json['_streamName']
 344             broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
 345             broadcast_thumbnail = broadcast_json['_imgURL']
 346             broadcast_title = self._live_title(broadcast_json['title'])
 347             broadcast_description = broadcast_json['description']
 348             broadcaster_nick = broadcast_json['nick']
 349             broadcaster_login = broadcast_json['login']
 350             rtmp_conn = 'S:%s' % uuid.uuid4().hex
 351         except KeyError:
 352             if protected_broadcast:
 353                 raise ExtractorError('Bad broadcast password', expected=True)
 354             raise ExtractorError('Unexpected broadcast JSON')
 355
 356         return {
 357             'id': broadcast_id,
 358             'url': rtmp_url,
 359             'title': broadcast_title,
 360             'thumbnail': broadcast_thumbnail,
 361             'description': broadcast_description,
 362             'uploader': broadcaster_nick,
 363             'uploader_id': broadcaster_login,
 364             'age_limit': 18 if adult_content else 0,
 365             'ext': 'flv',
 366             'play_path': broadcast_playpath,
 367             'player_url': 'http://pics.smotri.com/broadcast_play.swf',
 368             'app': broadcast_app,
 369             'rtmp_live': True,
 370             'rtmp_conn': rtmp_conn,
 371             'is_live': True,
 372         }