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     _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': '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': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
 132             'only_matching': True,
 133         },
 134         {
 135             'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil',
 136             'only_matching': True,
 137         },
 138         {
 139             # geoblocked
 140             'url': 'http://www.vgtv.no/#!/video/127205/inside-the-mind-of-favela-funk',
 141             'only_matching': True,
 142         },
 143         {
 144             'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
 145             'only_matching': True,
 146         },
 147         {
 148             'url': 'https://www.aftonbladet.se/tv/a/36015',
 149             'only_matching': True,
 150         },
 151         {
 152             'url': 'abtv:140026',
 153             'only_matching': True,
 154         },
 155         {
 156             'url': 'http://www.vgtv.no/video/84196/hevnen-er-soet-episode-10-abu',
 157             'only_matching': True,
 158         },
 159     ]
 160
 161     def _real_extract(self, url):
 162         mobj = re.match(self._VALID_URL, url)
 163         video_id = mobj.group('id')
 164         host = mobj.group('host')
 165         appname = self._HOST_TO_APPNAME[host] if host else mobj.group('appname')
 166         vendor = self._APP_NAME_TO_VENDOR[appname]
 167
 168         data = self._download_json(
 169             'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
 170             % (vendor, video_id, appname),
 171             video_id, 'Downloading media JSON')
 172
 173         if data.get('status') == 'inactive':
 174             raise ExtractorError(
 175                 'Video %s is no longer available' % video_id, expected=True)
 176
 177         info = {
 178             'formats': [],
 179         }
 180         if len(video_id) == 5:
 181             if appname == 'bttv':
 182                 info = self._extract_video_info('btno', video_id)
 183
 184         streams = data['streamUrls']
 185         stream_type = data.get('streamType')
 186         is_live = stream_type == 'live'
 187         formats = []
 188
 189         hls_url = streams.get('hls')
 190         if hls_url:
 191             formats.extend(self._extract_m3u8_formats(
 192                 hls_url, video_id, 'mp4',
 193                 entry_protocol='m3u8' if is_live else 'm3u8_native',
 194                 m3u8_id='hls', fatal=False))
 195
 196         hds_url = streams.get('hds')
 197         if hds_url:
 198             hdcore_sign = 'hdcore=3.7.0'
 199             f4m_formats = self._extract_f4m_formats(
 200                 hds_url + '?%s' % hdcore_sign, video_id, f4m_id='hds', fatal=False)
 201             if f4m_formats:
 202                 for entry in f4m_formats:
 203                     # URLs without the extra param induce an 404 error
 204                     entry.update({'extra_param_to_segment_url': hdcore_sign})
 205                     formats.append(entry)
 206
 207         mp4_urls = streams.get('pseudostreaming') or []
 208         mp4_url = streams.get('mp4')
 209         if mp4_url:
 210             mp4_urls.append(mp4_url)
 211         for mp4_url in mp4_urls:
 212             format_info = {
 213                 'url': mp4_url,
 214             }
 215             mobj = re.search(r'(\d+)_(\d+)_(\d+)', mp4_url)
 216             if mobj:
 217                 tbr = int(mobj.group(3))
 218                 format_info.update({
 219                     'width': int(mobj.group(1)),
 220                     'height': int(mobj.group(2)),
 221                     'tbr': tbr,
 222                     'format_id': 'mp4-%s' % tbr,
 223                 })
 224             formats.append(format_info)
 225
 226         info['formats'].extend(formats)
 227
 228         if not info['formats']:
 229             properties = try_get(
 230                 data, lambda x: x['streamConfiguration']['properties'], list)
 231             if properties and 'geoblocked' in properties:
 232                 raise self.raise_geo_restricted(
 233                     countries=[host.rpartition('.')[-1].partition('/')[0].upper()])
 234
 235         self._sort_formats(info['formats'])
 236
 237         info.update({
 238             'id': video_id,
 239             'title': self._live_title(data['title']) if is_live else data['title'],
 240             'description': data['description'],
 241             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
 242             'timestamp': data['published'],
 243             'duration': float_or_none(data['duration'], 1000),
 244             'view_count': data['displays'],
 245             'is_live': is_live,
 246         })
 247         return info
 248
 249
 250 class BTArticleIE(InfoExtractor):
 251     IE_NAME = 'bt:article'
 252     IE_DESC = 'Bergens Tidende Articles'
 253     _VALID_URL = r'https?://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
 254     _TEST = {
 255         'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
 256         'md5': '2acbe8ad129b3469d5ae51b1158878df',
 257         'info_dict': {
 258             'id': '23199',
 259             'ext': 'mp4',
 260             'title': 'Alrekstad internat',
 261             'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
 262             'thumbnail': r're:^https?://.*\.jpg',
 263             'duration': 191,
 264             'timestamp': 1289991323,
 265             'upload_date': '20101117',
 266             'view_count': int,
 267         },
 268     }
 269
 270     def _real_extract(self, url):
 271         webpage = self._download_webpage(url, self._match_id(url))
 272         video_id = self._search_regex(
 273             r'<video[^>]+data-id="(\d+)"', webpage, 'video id')
 274         return self.url_result('bttv:%s' % video_id, 'VGTV')
 275
 276
 277 class BTVestlendingenIE(InfoExtractor):
 278     IE_NAME = 'bt:vestlendingen'
 279     IE_DESC = 'Bergens Tidende - Vestlendingen'
 280     _VALID_URL = r'https?://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
 281     _TESTS = [{
 282         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
 283         'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
 284         'info_dict': {
 285             'id': '86588',
 286             'ext': 'mov',
 287             'title': 'Otto Wollertsen',
 288             'description': 'Vestlendingen Otto Fredrik Wollertsen',
 289             'timestamp': 1430473209,
 290             'upload_date': '20150501',
 291         },
 292         'skip': '404 Error',
 293     }, {
 294         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86255',
 295         'md5': 'a2893f8632e96389f4bdf36aa9463ceb',
 296         'info_dict': {
 297             'id': '86255',
 298             'ext': 'mov',
 299             'title': 'Du må tåle å fryse og være sulten',
 300             'description': 'md5:b8046f4d022d5830ddab04865791d063',
 301             'upload_date': '20150321',
 302             'timestamp': 1426942023,
 303         },
 304     }]
 305
 306     def _real_extract(self, url):
 307         return self.url_result('bttv:%s' % self._match_id(url), 'VGTV')