Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vgtv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .xstream import XstreamIE
   8 from ..utils import (
   9     ExtractorError,
  10     float_or_none,
  11     try_get,
  12 )
  13
  14
  15 class VGTVIE(XstreamIE):
  16     IE_DESC = 'VGTV, BTTV, FTV, Aftenposten and Aftonbladet'
  17
  18     _HOST_TO_APPNAME = {
  19         'vgtv.no': 'vgtv',
  20         'bt.no/tv': 'bttv',
  21         'aftenbladet.no/tv': 'satv',
  22         'fvn.no/fvntv': 'fvntv',
  23         'aftenposten.no/webtv': 'aptv',
  24         'ap.vgtv.no/webtv': 'aptv',
  25         'tv.aftonbladet.se/abtv': 'abtv',
  26     }
  27
  28     _APP_NAME_TO_VENDOR = {
  29         'vgtv': 'vgtv',
  30         'bttv': 'bt',
  31         'satv': 'sa',
  32         'fvntv': 'fvn',
  33         'aptv': 'ap',
  34         'abtv': 'ab',
  35     }
  36
  37     _VALID_URL = r'''(?x)
  38                     (?:https?://(?:www\.)?
  39                     (?P<host>
  40                         %s
  41                     )
  42                     /?
  43                     (?:
  44                         \#!/(?:video|live)/|
  45                         embed?.*id=|
  46                         articles/
  47                     )|
  48                     (?P<appname>
  49                         %s
  50                     ):)
  51                     (?P<id>\d+)
  52                     ''' % ('|'.join(_HOST_TO_APPNAME.keys()), '|'.join(_APP_NAME_TO_VENDOR.keys()))
  53
  54     _TESTS = [
  55         {
  56             # streamType: vod
  57             'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
  58             'md5': 'b8be7a234cebb840c0d512c78013e02f',
  59             'info_dict': {
  60                 'id': '84196',
  61                 'ext': 'mp4',
  62                 'title': 'Hevnen er søt: Episode 10 - Abu',
  63                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
  64                 'thumbnail': 're:^https?://.*\.jpg',
  65                 'duration': 648.000,
  66                 'timestamp': 1404626400,
  67                 'upload_date': '20140706',
  68                 'view_count': int,
  69             },
  70         },
  71         {
  72             # streamType: wasLive
  73             'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
  74             'info_dict': {
  75                 'id': '100764',
  76                 'ext': 'flv',
  77                 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
  78                 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
  79                 'thumbnail': 're:^https?://.*\.jpg',
  80                 'duration': 9103.0,
  81                 'timestamp': 1410113864,
  82                 'upload_date': '20140907',
  83                 'view_count': int,
  84             },
  85             'params': {
  86                 # m3u8 download
  87                 'skip_download': True,
  88             },
  89             'skip': 'Video is no longer available',
  90         },
  91         {
  92             # streamType: wasLive
  93             'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',
  94             'info_dict': {
  95                 'id': '113063',
  96                 'ext': 'mp4',
  97                 'title': 'V75 fra Solvalla 30.05.15',
  98                 'description': 'md5:b3743425765355855f88e096acc93231',
  99                 'thumbnail': 're:^https?://.*\.jpg',
 100                 'duration': 25966,
 101                 'timestamp': 1432975582,
 102                 'upload_date': '20150530',
 103                 'view_count': int,
 104             },
 105             'params': {
 106                 # m3u8 download
 107                 'skip_download': True,
 108             },
 109         },
 110         {
 111             'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
 112             'md5': 'fd828cd29774a729bf4d4425fe192972',
 113             'info_dict': {
 114                 'id': '21039',
 115                 'ext': 'mp4',
 116                 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more',
 117                 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
 118                 'duration': 66,
 119                 'timestamp': 1417002452,
 120                 'upload_date': '20141126',
 121                 'view_count': int,
 122             },
 123             'params': {
 124                 # m3u8 download
 125                 'skip_download': True,
 126             },
 127         },
 128         {
 129             'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
 130             'only_matching': True,
 131         },
 132         {
 133             'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil',
 134             'only_matching': True,
 135         },
 136         {
 137             # geoblocked
 138             'url': 'http://www.vgtv.no/#!/video/127205/inside-the-mind-of-favela-funk',
 139             'only_matching': True,
 140         },
 141         {
 142             'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
 143             'only_matching': True,
 144         },
 145         {
 146             'url': 'abtv:140026',
 147             'only_matching': True,
 148         }
 149     ]
 150
 151     def _real_extract(self, url):
 152         mobj = re.match(self._VALID_URL, url)
 153         video_id = mobj.group('id')
 154         host = mobj.group('host')
 155         appname = self._HOST_TO_APPNAME[host] if host else mobj.group('appname')
 156         vendor = self._APP_NAME_TO_VENDOR[appname]
 157
 158         data = self._download_json(
 159             'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
 160             % (vendor, video_id, appname),
 161             video_id, 'Downloading media JSON')
 162
 163         if data.get('status') == 'inactive':
 164             raise ExtractorError(
 165                 'Video %s is no longer available' % video_id, expected=True)
 166
 167         info = {
 168             'formats': [],
 169         }
 170         if len(video_id) == 5:
 171             if appname == 'bttv':
 172                 info = self._extract_video_info('btno', video_id)
 173
 174         streams = data['streamUrls']
 175         stream_type = data.get('streamType')
 176
 177         formats = []
 178
 179         hls_url = streams.get('hls')
 180         if hls_url:
 181             formats.extend(self._extract_m3u8_formats(
 182                 hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
 183
 184         hds_url = streams.get('hds')
 185         if hds_url:
 186             hdcore_sign = 'hdcore=3.7.0'
 187             f4m_formats = self._extract_f4m_formats(
 188                 hds_url + '?%s' % hdcore_sign, video_id, f4m_id='hds', fatal=False)
 189             if f4m_formats:
 190                 for entry in f4m_formats:
 191                     # URLs without the extra param induce an 404 error
 192                     entry.update({'extra_param_to_segment_url': hdcore_sign})
 193                     formats.append(entry)
 194
 195         mp4_urls = streams.get('pseudostreaming') or []
 196         mp4_url = streams.get('mp4')
 197         if mp4_url:
 198             mp4_urls.append(mp4_url)
 199         for mp4_url in mp4_urls:
 200             format_info = {
 201                 'url': mp4_url,
 202             }
 203             mobj = re.search('(\d+)_(\d+)_(\d+)', mp4_url)
 204             if mobj:
 205                 tbr = int(mobj.group(3))
 206                 format_info.update({
 207                     'width': int(mobj.group(1)),
 208                     'height': int(mobj.group(2)),
 209                     'tbr': tbr,
 210                     'format_id': 'mp4-%s' % tbr,
 211                 })
 212             formats.append(format_info)
 213
 214         info['formats'].extend(formats)
 215
 216         if not info['formats']:
 217             properties = try_get(
 218                 data, lambda x: x['streamConfiguration']['properties'], list)
 219             if properties and 'geoblocked' in properties:
 220                 raise self.raise_geo_restricted()
 221
 222         self._sort_formats(info['formats'])
 223
 224         info.update({
 225             'id': video_id,
 226             'title': self._live_title(data['title']) if stream_type == 'live' else data['title'],
 227             'description': data['description'],
 228             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
 229             'timestamp': data['published'],
 230             'duration': float_or_none(data['duration'], 1000),
 231             'view_count': data['displays'],
 232             'is_live': True if stream_type == 'live' else False,
 233         })
 234         return info
 235
 236
 237 class BTArticleIE(InfoExtractor):
 238     IE_NAME = 'bt:article'
 239     IE_DESC = 'Bergens Tidende Articles'
 240     _VALID_URL = r'https?://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
 241     _TEST = {
 242         'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
 243         'md5': '2acbe8ad129b3469d5ae51b1158878df',
 244         'info_dict': {
 245             'id': '23199',
 246             'ext': 'mp4',
 247             'title': 'Alrekstad internat',
 248             'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
 249             'thumbnail': 're:^https?://.*\.jpg',
 250             'duration': 191,
 251             'timestamp': 1289991323,
 252             'upload_date': '20101117',
 253             'view_count': int,
 254         },
 255     }
 256
 257     def _real_extract(self, url):
 258         webpage = self._download_webpage(url, self._match_id(url))
 259         video_id = self._search_regex(
 260             r'<video[^>]+data-id="(\d+)"', webpage, 'video id')
 261         return self.url_result('bttv:%s' % video_id, 'VGTV')
 262
 263
 264 class BTVestlendingenIE(InfoExtractor):
 265     IE_NAME = 'bt:vestlendingen'
 266     IE_DESC = 'Bergens Tidende - Vestlendingen'
 267     _VALID_URL = r'https?://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
 268     _TESTS = [{
 269         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
 270         'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
 271         'info_dict': {
 272             'id': '86588',
 273             'ext': 'mov',
 274             'title': 'Otto Wollertsen',
 275             'description': 'Vestlendingen Otto Fredrik Wollertsen',
 276             'timestamp': 1430473209,
 277             'upload_date': '20150501',
 278         },
 279         'skip': '404 Error',
 280     }, {
 281         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86255',
 282         'md5': 'a2893f8632e96389f4bdf36aa9463ceb',
 283         'info_dict': {
 284             'id': '86255',
 285             'ext': 'mov',
 286             'title': 'Du må tåle å fryse og være sulten',
 287             'description': 'md5:b8046f4d022d5830ddab04865791d063',
 288             'upload_date': '20150321',
 289             'timestamp': 1426942023,
 290         },
 291     }]
 292
 293     def _real_extract(self, url):
 294         return self.url_result('bttv:%s' % self._match_id(url), 'VGTV')