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