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