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 ..utils import (
   8     ExtractorError,
   9     float_or_none,
  10 )
  11
  12
  13 class VGTVIE(InfoExtractor):
  14     IE_DESC = 'VGTV and BTTV'
  15     _VALID_URL = r'''(?x)
  16                     (?:
  17                         vgtv:|
  18                         http://(?:www\.)?
  19                     )
  20                     (?P<host>vgtv|bt)
  21                     (?:
  22                         :|
  23                         \.no/(?:tv/)?\#!/(?:video|live)/
  24                     )
  25                     (?P<id>[0-9]+)
  26                     '''
  27     _TESTS = [
  28         {
  29             # streamType: vod
  30             'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
  31             'md5': 'b8be7a234cebb840c0d512c78013e02f',
  32             'info_dict': {
  33                 'id': '84196',
  34                 'ext': 'mp4',
  35                 'title': 'Hevnen er søt: Episode 10 - Abu',
  36                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
  37                 'thumbnail': 're:^https?://.*\.jpg',
  38                 'duration': 648.000,
  39                 'timestamp': 1404626400,
  40                 'upload_date': '20140706',
  41                 'view_count': int,
  42             },
  43         },
  44         {
  45             # streamType: wasLive
  46             'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
  47             'info_dict': {
  48                 'id': '100764',
  49                 'ext': 'flv',
  50                 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
  51                 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
  52                 'thumbnail': 're:^https?://.*\.jpg',
  53                 'duration': 9103.0,
  54                 'timestamp': 1410113864,
  55                 'upload_date': '20140907',
  56                 'view_count': int,
  57             },
  58             'params': {
  59                 # m3u8 download
  60                 'skip_download': True,
  61             },
  62         },
  63         {
  64             # streamType: live
  65             'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',
  66             'info_dict': {
  67                 'id': '113063',
  68                 'ext': 'flv',
  69                 'title': 're:^DIREKTE: V75 fra Solvalla [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  70                 'description': 'md5:b3743425765355855f88e096acc93231',
  71                 'thumbnail': 're:^https?://.*\.jpg',
  72                 'duration': 0,
  73                 'timestamp': 1432975582,
  74                 'upload_date': '20150530',
  75                 'view_count': int,
  76             },
  77             'params': {
  78                 # m3u8 download
  79                 'skip_download': True,
  80             },
  81         },
  82         {
  83             'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
  84             'only_matching': True,
  85         },
  86     ]
  87
  88     def _real_extract(self, url):
  89         mobj = re.match(self._VALID_URL, url)
  90         video_id = mobj.group('id')
  91         host = mobj.group('host')
  92
  93         HOST_WEBSITES = {
  94             'vgtv': 'vgtv',
  95             'bt': 'bttv',
  96         }
  97
  98         data = self._download_json(
  99             'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
 100             % (host, video_id, HOST_WEBSITES[host]),
 101             video_id, 'Downloading media JSON')
 102
 103         if data.get('status') == 'inactive':
 104             raise ExtractorError(
 105                 'Video %s is no longer available' % video_id, expected=True)
 106
 107         streams = data['streamUrls']
 108         stream_type = data.get('streamType')
 109
 110         formats = []
 111
 112         hls_url = streams.get('hls')
 113         if hls_url:
 114             formats.extend(self._extract_m3u8_formats(
 115                 hls_url, video_id, 'mp4', m3u8_id='hls'))
 116
 117         hds_url = streams.get('hds')
 118         # wasLive hds are always 404
 119         if hds_url and stream_type != 'wasLive':
 120             formats.extend(self._extract_f4m_formats(
 121                 hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
 122                 video_id, f4m_id='hds'))
 123
 124         mp4_url = streams.get('mp4')
 125         if mp4_url:
 126             _url = hls_url or hds_url
 127             MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1])
 128             for mp4_format in _url.split(','):
 129                 m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format)
 130                 if not m:
 131                     continue
 132                 width = int(m.group('width'))
 133                 height = int(m.group('height'))
 134                 vbr = int(m.group('vbr'))
 135                 formats.append({
 136                     'url': MP4_URL_TEMPLATE % mp4_format,
 137                     'format_id': 'mp4-%s' % vbr,
 138                     'width': width,
 139                     'height': height,
 140                     'vbr': vbr,
 141                     'preference': 1,
 142                 })
 143         self._sort_formats(formats)
 144
 145         return {
 146             'id': video_id,
 147             'title': self._live_title(data['title']),
 148             'description': data['description'],
 149             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
 150             'timestamp': data['published'],
 151             'duration': float_or_none(data['duration'], 1000),
 152             'view_count': data['displays'],
 153             'formats': formats,
 154             'is_live': True if stream_type == 'live' else False,
 155         }
 156
 157
 158 class BTArticleIE(InfoExtractor):
 159     IE_NAME = 'bt:article'
 160     IE_DESC = 'Bergens Tidende Articles'
 161     _VALID_URL = 'http://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
 162     _TEST = {
 163         'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
 164         'md5': 'd055e8ee918ef2844745fcfd1a4175fb',
 165         'info_dict': {
 166             'id': '23199',
 167             'ext': 'mp4',
 168             'title': 'Alrekstad internat',
 169             'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
 170             'thumbnail': 're:^https?://.*\.jpg',
 171             'duration': 191,
 172             'timestamp': 1289991323,
 173             'upload_date': '20101117',
 174             'view_count': int,
 175         },
 176     }
 177
 178     def _real_extract(self, url):
 179         webpage = self._download_webpage(url, self._match_id(url))
 180         video_id = self._search_regex(
 181             r'SVP\.Player\.load\(\s*(\d+)', webpage, 'video id')
 182         return self.url_result('vgtv:bt:%s' % video_id, 'VGTV')
 183
 184
 185 class BTVestlendingenIE(InfoExtractor):
 186     IE_NAME = 'bt:vestlendingen'
 187     IE_DESC = 'Bergens Tidende - Vestlendingen'
 188     _VALID_URL = 'http://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
 189     _TEST = {
 190         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
 191         'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
 192         'info_dict': {
 193             'id': '86588',
 194             'ext': 'mov',
 195             'title': 'Otto Wollertsen',
 196             'description': 'Vestlendingen Otto Fredrik Wollertsen',
 197             'timestamp': 1430473209,
 198             'upload_date': '20150501',
 199         },
 200     }
 201
 202     def _real_extract(self, url):
 203         return self.url_result('xstream:btno:%s' % self._match_id(url), 'Xstream')