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     }
  28
  29     _APP_NAME_TO_VENDOR = {
  30         'vgtv': 'vgtv',
  31         'bttv': 'bt',
  32         'satv': 'sa',
  33         'fvntv': 'fvn',
  34         'aptv': 'ap',
  35         'abtv': 'ab',
  36     }
  37
  38     _VALID_URL = r'''(?x)
  39                     (?:https?://(?:www\.)?
  40                     (?P<host>
  41                         %s
  42                     )
  43                     /?
  44                     (?:
  45                         \#!/(?:video|live)/|
  46                         embed?.*id=|
  47                         articles/
  48                     )|
  49                     (?P<appname>
  50                         %s
  51                     ):)
  52                     (?P<id>\d+)
  53                     ''' % ('|'.join(_HOST_TO_APPNAME.keys()), '|'.join(_APP_NAME_TO_VENDOR.keys()))
  54
  55     _TESTS = [
  56         {
  57             # streamType: vod
  58             'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
  59             'md5': 'b8be7a234cebb840c0d512c78013e02f',
  60             'info_dict': {
  61                 'id': '84196',
  62                 'ext': 'mp4',
  63                 'title': 'Hevnen er søt: Episode 10 - Abu',
  64                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
  65                 'thumbnail': r're:^https?://.*\.jpg',
  66                 'duration': 648.000,
  67                 'timestamp': 1404626400,
  68                 'upload_date': '20140706',
  69                 'view_count': int,
  70             },
  71         },
  72         {
  73             # streamType: wasLive
  74             'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
  75             'info_dict': {
  76                 'id': '100764',
  77                 'ext': 'flv',
  78                 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
  79                 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
  80                 'thumbnail': r're:^https?://.*\.jpg',
  81                 'duration': 9103.0,
  82                 'timestamp': 1410113864,
  83                 'upload_date': '20140907',
  84                 'view_count': int,
  85             },
  86             'params': {
  87                 # m3u8 download
  88                 'skip_download': True,
  89             },
  90             'skip': 'Video is no longer available',
  91         },
  92         {
  93             # streamType: wasLive
  94             'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',
  95             'info_dict': {
  96                 'id': '113063',
  97                 'ext': 'mp4',
  98                 'title': 'V75 fra Solvalla 30.05.15',
  99                 'description': 'md5:b3743425765355855f88e096acc93231',
 100                 'thumbnail': r're:^https?://.*\.jpg',
 101                 'duration': 25966,
 102                 'timestamp': 1432975582,
 103                 'upload_date': '20150530',
 104                 'view_count': int,
 105             },
 106             'params': {
 107                 # m3u8 download
 108                 'skip_download': True,
 109             },
 110         },
 111         {
 112             'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
 113             'md5': 'fd828cd29774a729bf4d4425fe192972',
 114             'info_dict': {
 115                 'id': '21039',
 116                 'ext': 'mp4',
 117                 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more',
 118                 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
 119                 'duration': 66,
 120                 'timestamp': 1417002452,
 121                 'upload_date': '20141126',
 122                 'view_count': int,
 123             },
 124             'params': {
 125                 # m3u8 download
 126                 'skip_download': True,
 127             },
 128         },
 129         {
 130             'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
 131             'only_matching': True,
 132         },
 133         {
 134             'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil',
 135             'only_matching': True,
 136         },
 137         {
 138             # geoblocked
 139             'url': 'http://www.vgtv.no/#!/video/127205/inside-the-mind-of-favela-funk',
 140             'only_matching': True,
 141         },
 142         {
 143             'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
 144             'only_matching': True,
 145         },
 146         {
 147             'url': 'abtv:140026',
 148             'only_matching': True,
 149         }
 150     ]
 151
 152     def _real_extract(self, url):
 153         mobj = re.match(self._VALID_URL, url)
 154         video_id = mobj.group('id')
 155         host = mobj.group('host')
 156         appname = self._HOST_TO_APPNAME[host] if host else mobj.group('appname')
 157         vendor = self._APP_NAME_TO_VENDOR[appname]
 158
 159         data = self._download_json(
 160             'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
 161             % (vendor, video_id, appname),
 162             video_id, 'Downloading media JSON')
 163
 164         if data.get('status') == 'inactive':
 165             raise ExtractorError(
 166                 'Video %s is no longer available' % video_id, expected=True)
 167
 168         info = {
 169             'formats': [],
 170         }
 171         if len(video_id) == 5:
 172             if appname == 'bttv':
 173                 info = self._extract_video_info('btno', video_id)
 174
 175         streams = data['streamUrls']
 176         stream_type = data.get('streamType')
 177
 178         formats = []
 179
 180         hls_url = streams.get('hls')
 181         if hls_url:
 182             formats.extend(self._extract_m3u8_formats(
 183                 hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
 184
 185         hds_url = streams.get('hds')
 186         if hds_url:
 187             hdcore_sign = 'hdcore=3.7.0'
 188             f4m_formats = self._extract_f4m_formats(
 189                 hds_url + '?%s' % hdcore_sign, video_id, f4m_id='hds', fatal=False)
 190             if f4m_formats:
 191                 for entry in f4m_formats:
 192                     # URLs without the extra param induce an 404 error
 193                     entry.update({'extra_param_to_segment_url': hdcore_sign})
 194                     formats.append(entry)
 195
 196         mp4_urls = streams.get('pseudostreaming') or []
 197         mp4_url = streams.get('mp4')
 198         if mp4_url:
 199             mp4_urls.append(mp4_url)
 200         for mp4_url in mp4_urls:
 201             format_info = {
 202                 'url': mp4_url,
 203             }
 204             mobj = re.search(r'(\d+)_(\d+)_(\d+)', mp4_url)
 205             if mobj:
 206                 tbr = int(mobj.group(3))
 207                 format_info.update({
 208                     'width': int(mobj.group(1)),
 209                     'height': int(mobj.group(2)),
 210                     'tbr': tbr,
 211                     'format_id': 'mp4-%s' % tbr,
 212                 })
 213             formats.append(format_info)
 214
 215         info['formats'].extend(formats)
 216
 217         if not info['formats']:
 218             properties = try_get(
 219                 data, lambda x: x['streamConfiguration']['properties'], list)
 220             if properties and 'geoblocked' in properties:
 221                 raise self.raise_geo_restricted(
 222                     countries=[host.rpartition('.')[-1].partition('/')[0].upper()])
 223
 224         self._sort_formats(info['formats'])
 225
 226         info.update({
 227             'id': video_id,
 228             'title': self._live_title(data['title']) if stream_type == 'live' else data['title'],
 229             'description': data['description'],
 230             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
 231             'timestamp': data['published'],
 232             'duration': float_or_none(data['duration'], 1000),
 233             'view_count': data['displays'],
 234             'is_live': True if stream_type == 'live' else False,
 235         })
 236         return info
 237
 238
 239 class BTArticleIE(InfoExtractor):
 240     IE_NAME = 'bt:article'
 241     IE_DESC = 'Bergens Tidende Articles'
 242     _VALID_URL = r'https?://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
 243     _TEST = {
 244         'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
 245         'md5': '2acbe8ad129b3469d5ae51b1158878df',
 246         'info_dict': {
 247             'id': '23199',
 248             'ext': 'mp4',
 249             'title': 'Alrekstad internat',
 250             'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
 251             'thumbnail': r're:^https?://.*\.jpg',
 252             'duration': 191,
 253             'timestamp': 1289991323,
 254             'upload_date': '20101117',
 255             'view_count': int,
 256         },
 257     }
 258
 259     def _real_extract(self, url):
 260         webpage = self._download_webpage(url, self._match_id(url))
 261         video_id = self._search_regex(
 262             r'<video[^>]+data-id="(\d+)"', webpage, 'video id')
 263         return self.url_result('bttv:%s' % video_id, 'VGTV')
 264
 265
 266 class BTVestlendingenIE(InfoExtractor):
 267     IE_NAME = 'bt:vestlendingen'
 268     IE_DESC = 'Bergens Tidende - Vestlendingen'
 269     _VALID_URL = r'https?://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
 270     _TESTS = [{
 271         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
 272         'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
 273         'info_dict': {
 274             'id': '86588',
 275             'ext': 'mov',
 276             'title': 'Otto Wollertsen',
 277             'description': 'Vestlendingen Otto Fredrik Wollertsen',
 278             'timestamp': 1430473209,
 279             'upload_date': '20150501',
 280         },
 281         'skip': '404 Error',
 282     }, {
 283         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86255',
 284         'md5': 'a2893f8632e96389f4bdf36aa9463ceb',
 285         'info_dict': {
 286             'id': '86255',
 287             'ext': 'mov',
 288             'title': 'Du må tåle å fryse og være sulten',
 289             'description': 'md5:b8046f4d022d5830ddab04865791d063',
 290             'upload_date': '20150321',
 291             'timestamp': 1426942023,
 292         },
 293     }]
 294
 295     def _real_extract(self, url):
 296         return self.url_result('bttv:%s' % self._match_id(url), 'VGTV')