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