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