yt_dlp/extractor/vgtv.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from .xstream import XstreamIE
   5 from ..utils import (
   6     ExtractorError,
   7     float_or_none,
   8     try_get,
   9 )
  10
  11
  12 class VGTVIE(XstreamIE):  # XXX: Do not subclass from concrete IE
  13     IE_DESC = 'VGTV, BTTV, FTV, Aftenposten and Aftonbladet'
  14     _GEO_BYPASS = False
  15
  16     _HOST_TO_APPNAME = {
  17         'tv.vg.no': 'vgtv',
  18         'vgtv.no': 'vgtv',
  19         'bt.no/tv': 'bttv',
  20         'aftenbladet.no/tv': 'satv',
  21         'fvn.no/fvntv': 'fvntv',
  22         'aftenposten.no/webtv': 'aptv',
  23         'ap.vgtv.no/webtv': 'aptv',
  24         'tv.aftonbladet.se': 'abtv',
  25         # obsolete URL schemas, kept in order to save one HTTP redirect
  26         'tv.aftonbladet.se/abtv': 'abtv',
  27         'www.aftonbladet.se/tv': 'abtv',
  28     }
  29
  30     _APP_NAME_TO_VENDOR = {
  31         'vgtv': 'vgtv',
  32         'bttv': 'bt',
  33         'satv': 'sa',
  34         'fvntv': 'fvn',
  35         'aptv': 'ap',
  36         'abtv': 'ab',
  37     }
  38
  39     _VALID_URL = r'''(?x)
  40                     (?:https?://(?:www\.)?
  41                     (?P<host>
  42                         %s
  43                     )
  44                     /?
  45                     (?:
  46                         (?:\#!/)?(?:video|live)/|
  47                         embed?.*id=|
  48                         a(?:rticles)?/
  49                     )|
  50                     (?P<appname>
  51                         %s
  52                     ):)
  53                     (?P<id>\d+)
  54                     ''' % ('|'.join(_HOST_TO_APPNAME.keys()), '|'.join(_APP_NAME_TO_VENDOR.keys()))
  55
  56     _TESTS = [
  57         {
  58             # streamType: vod
  59             'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
  60             'md5': 'b8be7a234cebb840c0d512c78013e02f',
  61             'info_dict': {
  62                 'id': '84196',
  63                 'ext': 'mp4',
  64                 'title': 'Hevnen er søt: Episode 10 - Abu',
  65                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
  66                 'thumbnail': r're:^https?://.*\.jpg',
  67                 'duration': 648.000,
  68                 'timestamp': 1404626400,
  69                 'upload_date': '20140706',
  70                 'view_count': int,
  71             },
  72         },
  73         {
  74             # streamType: wasLive
  75             'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
  76             'info_dict': {
  77                 'id': '100764',
  78                 'ext': 'flv',
  79                 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
  80                 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
  81                 'thumbnail': r're:^https?://.*\.jpg',
  82                 'duration': 9103.0,
  83                 'timestamp': 1410113864,
  84                 'upload_date': '20140907',
  85                 'view_count': int,
  86             },
  87             'params': {
  88                 # m3u8 download
  89                 'skip_download': True,
  90             },
  91             'skip': 'Video is no longer available',
  92         },
  93         {
  94             # streamType: wasLive
  95             'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',
  96             'info_dict': {
  97                 'id': '113063',
  98                 'ext': 'mp4',
  99                 'title': 'V75 fra Solvalla 30.05.15',
 100                 'description': 'md5:b3743425765355855f88e096acc93231',
 101                 'thumbnail': r're:^https?://.*\.jpg',
 102                 'duration': 25966,
 103                 'timestamp': 1432975582,
 104                 'upload_date': '20150530',
 105                 'view_count': int,
 106             },
 107             'params': {
 108                 # m3u8 download
 109                 'skip_download': True,
 110             },
 111         },
 112         {
 113             'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
 114             'md5': 'fd828cd29774a729bf4d4425fe192972',
 115             'info_dict': {
 116                 'id': '21039',
 117                 'ext': 'mp4',
 118                 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more',
 119                 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
 120                 'duration': 66,
 121                 'timestamp': 1417002452,
 122                 'upload_date': '20141126',
 123                 'view_count': int,
 124             },
 125             'params': {
 126                 # m3u8 download
 127                 'skip_download': True,
 128             },
 129         },
 130         {
 131             'url': 'https://tv.vg.no/video/241779/politiets-ekstremkjoering',
 132             'only_matching': True,
 133         },
 134         {
 135             'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
 136             'only_matching': True,
 137         },
 138         {
 139             'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil',
 140             'only_matching': True,
 141         },
 142         {
 143             # geoblocked
 144             'url': 'http://www.vgtv.no/#!/video/127205/inside-the-mind-of-favela-funk',
 145             'only_matching': True,
 146         },
 147         {
 148             'url': 'https://tv.aftonbladet.se/video/36015/vulkanutbrott-i-rymden-nu-slapper-nasa-bilderna',
 149             'only_matching': True,
 150         },
 151         {
 152             'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
 153             'only_matching': True,
 154         },
 155         {
 156             'url': 'https://www.aftonbladet.se/tv/a/36015',
 157             'only_matching': True,
 158         },
 159         {
 160             'url': 'abtv:140026',
 161             'only_matching': True,
 162         },
 163         {
 164             'url': 'http://www.vgtv.no/video/84196/hevnen-er-soet-episode-10-abu',
 165             'only_matching': True,
 166         },
 167     ]
 168
 169     def _real_extract(self, url):
 170         mobj = self._match_valid_url(url)
 171         video_id = mobj.group('id')
 172         host = mobj.group('host')
 173         appname = self._HOST_TO_APPNAME[host] if host else mobj.group('appname')
 174         vendor = self._APP_NAME_TO_VENDOR[appname]
 175
 176         data = self._download_json(
 177             'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
 178             % (vendor, video_id, appname),
 179             video_id, 'Downloading media JSON')
 180
 181         if data.get('status') == 'inactive':
 182             raise ExtractorError(
 183                 'Video %s is no longer available' % video_id, expected=True)
 184
 185         info = {
 186             'formats': [],
 187         }
 188         if len(video_id) == 5:
 189             if appname == 'bttv':
 190                 info = self._extract_video_info('btno', video_id)
 191
 192         streams = data['streamUrls']
 193         stream_type = data.get('streamType')
 194         is_live = stream_type == 'live'
 195         formats = []
 196
 197         hls_url = streams.get('hls')
 198         if hls_url:
 199             formats.extend(self._extract_m3u8_formats(
 200                 hls_url, video_id, 'mp4', live=is_live, m3u8_id='hls', fatal=False))
 201
 202         hds_url = streams.get('hds')
 203         if hds_url:
 204             hdcore_sign = 'hdcore=3.7.0'
 205             f4m_formats = self._extract_f4m_formats(
 206                 hds_url + '?%s' % hdcore_sign, video_id, f4m_id='hds', fatal=False)
 207             if f4m_formats:
 208                 for entry in f4m_formats:
 209                     # URLs without the extra param induce an 404 error
 210                     entry.update({'extra_param_to_segment_url': hdcore_sign})
 211                     formats.append(entry)
 212
 213         mp4_urls = streams.get('pseudostreaming') or []
 214         mp4_url = streams.get('mp4')
 215         if mp4_url:
 216             mp4_urls.append(mp4_url)
 217         for mp4_url in mp4_urls:
 218             format_info = {
 219                 'url': mp4_url,
 220             }
 221             mobj = re.search(r'(\d+)_(\d+)_(\d+)', mp4_url)
 222             if mobj:
 223                 tbr = int(mobj.group(3))
 224                 format_info.update({
 225                     'width': int(mobj.group(1)),
 226                     'height': int(mobj.group(2)),
 227                     'tbr': tbr,
 228                     'format_id': 'mp4-%s' % tbr,
 229                 })
 230             formats.append(format_info)
 231
 232         info['formats'].extend(formats)
 233
 234         if not info['formats']:
 235             properties = try_get(
 236                 data, lambda x: x['streamConfiguration']['properties'], list)
 237             if properties and 'geoblocked' in properties:
 238                 raise self.raise_geo_restricted(
 239                     countries=[host.rpartition('.')[-1].partition('/')[0].upper()])
 240
 241         info.update({
 242             'id': video_id,
 243             'title': data['title'],
 244             'description': data['description'],
 245             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
 246             'timestamp': data['published'],
 247             'duration': float_or_none(data['duration'], 1000),
 248             'view_count': data['displays'],
 249             'is_live': is_live,
 250         })
 251         return info
 252
 253
 254 class BTArticleIE(InfoExtractor):
 255     IE_NAME = 'bt:article'
 256     IE_DESC = 'Bergens Tidende Articles'
 257     _VALID_URL = r'https?://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
 258     _TEST = {
 259         'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
 260         'md5': '2acbe8ad129b3469d5ae51b1158878df',
 261         'info_dict': {
 262             'id': '23199',
 263             'ext': 'mp4',
 264             'title': 'Alrekstad internat',
 265             'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
 266             'thumbnail': r're:^https?://.*\.jpg',
 267             'duration': 191,
 268             'timestamp': 1289991323,
 269             'upload_date': '20101117',
 270             'view_count': int,
 271         },
 272     }
 273
 274     def _real_extract(self, url):
 275         webpage = self._download_webpage(url, self._match_id(url))
 276         video_id = self._search_regex(
 277             r'<video[^>]+data-id="(\d+)"', webpage, 'video id')
 278         return self.url_result('bttv:%s' % video_id, 'VGTV')
 279
 280
 281 class BTVestlendingenIE(InfoExtractor):
 282     IE_NAME = 'bt:vestlendingen'
 283     IE_DESC = 'Bergens Tidende - Vestlendingen'
 284     _VALID_URL = r'https?://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
 285     _TESTS = [{
 286         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
 287         'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
 288         'info_dict': {
 289             'id': '86588',
 290             'ext': 'mov',
 291             'title': 'Otto Wollertsen',
 292             'description': 'Vestlendingen Otto Fredrik Wollertsen',
 293             'timestamp': 1430473209,
 294             'upload_date': '20150501',
 295         },
 296         'skip': '404 Error',
 297     }, {
 298         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86255',
 299         'md5': 'a2893f8632e96389f4bdf36aa9463ceb',
 300         'info_dict': {
 301             'id': '86255',
 302             'ext': 'mov',
 303             'title': 'Du må tåle å fryse og være sulten',
 304             'description': 'md5:b8046f4d022d5830ddab04865791d063',
 305             'upload_date': '20150321',
 306             'timestamp': 1426942023,
 307         },
 308     }]
 309
 310     def _real_extract(self, url):
 311         return self.url_result('bttv:%s' % self._match_id(url), 'VGTV')