yt_dlp/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     _GEO_BYPASS = False
  18
  19     _HOST_TO_APPNAME = {
  20         'vgtv.no': 'vgtv',
  21         'bt.no/tv': 'bttv',
  22         'aftenbladet.no/tv': 'satv',
  23         'fvn.no/fvntv': 'fvntv',
  24         'aftenposten.no/webtv': 'aptv',
  25         'ap.vgtv.no/webtv': 'aptv',
  26         'tv.aftonbladet.se': 'abtv',
  27         # obsolete URL schemas, kept in order to save one HTTP redirect
  28         'tv.aftonbladet.se/abtv': 'abtv',
  29         'www.aftonbladet.se/tv': 'abtv',
  30     }
  31
  32     _APP_NAME_TO_VENDOR = {
  33         'vgtv': 'vgtv',
  34         'bttv': 'bt',
  35         'satv': 'sa',
  36         'fvntv': 'fvn',
  37         'aptv': 'ap',
  38         'abtv': 'ab',
  39     }
  40
  41     _VALID_URL = r'''(?x)
  42                     (?:https?://(?:www\.)?
  43                     (?P<host>
  44                         %s
  45                     )
  46                     /?
  47                     (?:
  48                         (?:\#!/)?(?:video|live)/|
  49                         embed?.*id=|
  50                         a(?:rticles)?/
  51                     )|
  52                     (?P<appname>
  53                         %s
  54                     ):)
  55                     (?P<id>\d+)
  56                     ''' % ('|'.join(_HOST_TO_APPNAME.keys()), '|'.join(_APP_NAME_TO_VENDOR.keys()))
  57
  58     _TESTS = [
  59         {
  60             # streamType: vod
  61             'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
  62             'md5': 'b8be7a234cebb840c0d512c78013e02f',
  63             'info_dict': {
  64                 'id': '84196',
  65                 'ext': 'mp4',
  66                 'title': 'Hevnen er søt: Episode 10 - Abu',
  67                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
  68                 'thumbnail': r're:^https?://.*\.jpg',
  69                 'duration': 648.000,
  70                 'timestamp': 1404626400,
  71                 'upload_date': '20140706',
  72                 'view_count': int,
  73             },
  74         },
  75         {
  76             # streamType: wasLive
  77             'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
  78             'info_dict': {
  79                 'id': '100764',
  80                 'ext': 'flv',
  81                 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
  82                 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
  83                 'thumbnail': r're:^https?://.*\.jpg',
  84                 'duration': 9103.0,
  85                 'timestamp': 1410113864,
  86                 'upload_date': '20140907',
  87                 'view_count': int,
  88             },
  89             'params': {
  90                 # m3u8 download
  91                 'skip_download': True,
  92             },
  93             'skip': 'Video is no longer available',
  94         },
  95         {
  96             # streamType: wasLive
  97             'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',
  98             'info_dict': {
  99                 'id': '113063',
 100                 'ext': 'mp4',
 101                 'title': 'V75 fra Solvalla 30.05.15',
 102                 'description': 'md5:b3743425765355855f88e096acc93231',
 103                 'thumbnail': r're:^https?://.*\.jpg',
 104                 'duration': 25966,
 105                 'timestamp': 1432975582,
 106                 'upload_date': '20150530',
 107                 'view_count': int,
 108             },
 109             'params': {
 110                 # m3u8 download
 111                 'skip_download': True,
 112             },
 113         },
 114         {
 115             'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
 116             'md5': 'fd828cd29774a729bf4d4425fe192972',
 117             'info_dict': {
 118                 'id': '21039',
 119                 'ext': 'mp4',
 120                 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more',
 121                 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
 122                 'duration': 66,
 123                 'timestamp': 1417002452,
 124                 'upload_date': '20141126',
 125                 'view_count': int,
 126             },
 127             'params': {
 128                 # m3u8 download
 129                 'skip_download': True,
 130             },
 131         },
 132         {
 133             'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
 134             'only_matching': True,
 135         },
 136         {
 137             'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil',
 138             'only_matching': True,
 139         },
 140         {
 141             # geoblocked
 142             'url': 'http://www.vgtv.no/#!/video/127205/inside-the-mind-of-favela-funk',
 143             'only_matching': True,
 144         },
 145         {
 146             'url': 'https://tv.aftonbladet.se/video/36015/vulkanutbrott-i-rymden-nu-slapper-nasa-bilderna',
 147             'only_matching': True,
 148         },
 149         {
 150             'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
 151             'only_matching': True,
 152         },
 153         {
 154             'url': 'https://www.aftonbladet.se/tv/a/36015',
 155             'only_matching': True,
 156         },
 157         {
 158             'url': 'abtv:140026',
 159             'only_matching': True,
 160         },
 161         {
 162             'url': 'http://www.vgtv.no/video/84196/hevnen-er-soet-episode-10-abu',
 163             'only_matching': True,
 164         },
 165     ]
 166
 167     def _real_extract(self, url):
 168         mobj = self._match_valid_url(url)
 169         video_id = mobj.group('id')
 170         host = mobj.group('host')
 171         appname = self._HOST_TO_APPNAME[host] if host else mobj.group('appname')
 172         vendor = self._APP_NAME_TO_VENDOR[appname]
 173
 174         data = self._download_json(
 175             'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
 176             % (vendor, video_id, appname),
 177             video_id, 'Downloading media JSON')
 178
 179         if data.get('status') == 'inactive':
 180             raise ExtractorError(
 181                 'Video %s is no longer available' % video_id, expected=True)
 182
 183         info = {
 184             'formats': [],
 185         }
 186         if len(video_id) == 5:
 187             if appname == 'bttv':
 188                 info = self._extract_video_info('btno', video_id)
 189
 190         streams = data['streamUrls']
 191         stream_type = data.get('streamType')
 192         is_live = stream_type == 'live'
 193         formats = []
 194
 195         hls_url = streams.get('hls')
 196         if hls_url:
 197             formats.extend(self._extract_m3u8_formats(
 198                 hls_url, video_id, 'mp4',
 199                 entry_protocol='m3u8' if is_live else 'm3u8_native',
 200                 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         self._sort_formats(info['formats'])
 242
 243         info.update({
 244             'id': video_id,
 245             'title': data['title'],
 246             'description': data['description'],
 247             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
 248             'timestamp': data['published'],
 249             'duration': float_or_none(data['duration'], 1000),
 250             'view_count': data['displays'],
 251             'is_live': is_live,
 252         })
 253         return info
 254
 255
 256 class BTArticleIE(InfoExtractor):
 257     IE_NAME = 'bt:article'
 258     IE_DESC = 'Bergens Tidende Articles'
 259     _VALID_URL = r'https?://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
 260     _TEST = {
 261         'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
 262         'md5': '2acbe8ad129b3469d5ae51b1158878df',
 263         'info_dict': {
 264             'id': '23199',
 265             'ext': 'mp4',
 266             'title': 'Alrekstad internat',
 267             'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
 268             'thumbnail': r're:^https?://.*\.jpg',
 269             'duration': 191,
 270             'timestamp': 1289991323,
 271             'upload_date': '20101117',
 272             'view_count': int,
 273         },
 274     }
 275
 276     def _real_extract(self, url):
 277         webpage = self._download_webpage(url, self._match_id(url))
 278         video_id = self._search_regex(
 279             r'<video[^>]+data-id="(\d+)"', webpage, 'video id')
 280         return self.url_result('bttv:%s' % video_id, 'VGTV')
 281
 282
 283 class BTVestlendingenIE(InfoExtractor):
 284     IE_NAME = 'bt:vestlendingen'
 285     IE_DESC = 'Bergens Tidende - Vestlendingen'
 286     _VALID_URL = r'https?://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
 287     _TESTS = [{
 288         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
 289         'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
 290         'info_dict': {
 291             'id': '86588',
 292             'ext': 'mov',
 293             'title': 'Otto Wollertsen',
 294             'description': 'Vestlendingen Otto Fredrik Wollertsen',
 295             'timestamp': 1430473209,
 296             'upload_date': '20150501',
 297         },
 298         'skip': '404 Error',
 299     }, {
 300         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86255',
 301         'md5': 'a2893f8632e96389f4bdf36aa9463ceb',
 302         'info_dict': {
 303             'id': '86255',
 304             'ext': 'mov',
 305             'title': 'Du må tåle å fryse og være sulten',
 306             'description': 'md5:b8046f4d022d5830ddab04865791d063',
 307             'upload_date': '20150321',
 308             'timestamp': 1426942023,
 309         },
 310     }]
 311
 312     def _real_extract(self, url):
 313         return self.url_result('bttv:%s' % self._match_id(url), 'VGTV')