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 float_or_none
   8
   9
  10 class VGTVIE(InfoExtractor):
  11     IE_DESC = 'VGTV and BTTV'
  12     _VALID_URL = r'''(?x)
  13                     (?:
  14                         vgtv:|
  15                         http://(?:www\.)?
  16                     )
  17                     (?P<host>vgtv|bt)
  18                     (?:
  19                         :|
  20                         \.no/(?:tv/)?\#!/(?:video|live)/
  21                     )
  22                     (?P<id>[0-9]+)
  23                     '''
  24     _TESTS = [
  25         {
  26             # streamType: vod
  27             'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
  28             'md5': 'b8be7a234cebb840c0d512c78013e02f',
  29             'info_dict': {
  30                 'id': '84196',
  31                 'ext': 'mp4',
  32                 'title': 'Hevnen er søt: Episode 10 - Abu',
  33                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
  34                 'thumbnail': 're:^https?://.*\.jpg',
  35                 'duration': 648.000,
  36                 'timestamp': 1404626400,
  37                 'upload_date': '20140706',
  38                 'view_count': int,
  39             },
  40         },
  41         {
  42             # streamType: wasLive
  43             'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
  44             'info_dict': {
  45                 'id': '100764',
  46                 'ext': 'flv',
  47                 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
  48                 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
  49                 'thumbnail': 're:^https?://.*\.jpg',
  50                 'duration': 9103.0,
  51                 'timestamp': 1410113864,
  52                 'upload_date': '20140907',
  53                 'view_count': int,
  54             },
  55             'params': {
  56                 # m3u8 download
  57                 'skip_download': True,
  58             },
  59         },
  60         {
  61             # streamType: live
  62             'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen',
  63             'info_dict': {
  64                 'id': '100015',
  65                 'ext': 'flv',
  66                 'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!',
  67                 'description': 'md5:9a60cc23fa349f761628924e56eeec2d',
  68                 'thumbnail': 're:^https?://.*\.jpg',
  69                 'duration': 0,
  70                 'timestamp': 1407423348,
  71                 'upload_date': '20140807',
  72                 'view_count': int,
  73             },
  74             'params': {
  75                 # m3u8 download
  76                 'skip_download': True,
  77             },
  78         },
  79         {
  80             'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
  81             'only_matching': True,
  82         },
  83     ]
  84
  85     def _real_extract(self, url):
  86         mobj = re.match(self._VALID_URL, url)
  87         video_id = mobj.group('id')
  88         host = mobj.group('host')
  89
  90         HOST_WEBSITES = {
  91             'vgtv': 'vgtv',
  92             'bt': 'bttv',
  93         }
  94
  95         data = self._download_json(
  96             'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
  97             % (host, video_id, HOST_WEBSITES[host]),
  98             video_id, 'Downloading media JSON')
  99
 100         streams = data['streamUrls']
 101
 102         formats = []
 103
 104         hls_url = streams.get('hls')
 105         if hls_url:
 106             formats.extend(self._extract_m3u8_formats(
 107                 hls_url, video_id, 'mp4', m3u8_id='hls'))
 108
 109         hds_url = streams.get('hds')
 110         if hds_url:
 111             formats.extend(self._extract_f4m_formats(
 112                 hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
 113                 video_id, f4m_id='hds'))
 114
 115         mp4_url = streams.get('mp4')
 116         if mp4_url:
 117             _url = hls_url or hds_url
 118             MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1])
 119             for mp4_format in _url.split(','):
 120                 m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format)
 121                 if not m:
 122                     continue
 123                 width = int(m.group('width'))
 124                 height = int(m.group('height'))
 125                 vbr = int(m.group('vbr'))
 126                 formats.append({
 127                     'url': MP4_URL_TEMPLATE % mp4_format,
 128                     'format_id': 'mp4-%s' % vbr,
 129                     'width': width,
 130                     'height': height,
 131                     'vbr': vbr,
 132                     'preference': 1,
 133                 })
 134         self._sort_formats(formats)
 135
 136         return {
 137             'id': video_id,
 138             'title': data['title'],
 139             'description': data['description'],
 140             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
 141             'timestamp': data['published'],
 142             'duration': float_or_none(data['duration'], 1000),
 143             'view_count': data['displays'],
 144             'formats': formats,
 145         }
 146
 147
 148 class BTArticleIE(InfoExtractor):
 149     IE_NAME = 'bt:article'
 150     IE_DESC = 'Bergens Tidende Articles'
 151     _VALID_URL = 'http://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
 152     _TEST = {
 153         'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
 154         'md5': 'd055e8ee918ef2844745fcfd1a4175fb',
 155         'info_dict': {
 156             'id': '23199',
 157             'ext': 'mp4',
 158             'title': 'Alrekstad internat',
 159             'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
 160             'thumbnail': 're:^https?://.*\.jpg',
 161             'duration': 191,
 162             'timestamp': 1289991323,
 163             'upload_date': '20101117',
 164             'view_count': int,
 165         },
 166     }
 167
 168     def _real_extract(self, url):
 169         webpage = self._download_webpage(url, self._match_id(url))
 170         video_id = self._search_regex(
 171             r'SVP\.Player\.load\(\s*(\d+)', webpage, 'video id')
 172         return self.url_result('vgtv:bt:%s' % video_id, 'VGTV')
 173
 174
 175 class BTVestlendingenIE(InfoExtractor):
 176     IE_NAME = 'bt:vestlendingen'
 177     IE_DESC = 'Bergens Tidende - Vestlendingen'
 178     _VALID_URL = 'http://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
 179     _TEST = {
 180         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
 181         'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
 182         'info_dict': {
 183             'id': '86588',
 184             'ext': 'mov',
 185             'title': 'Otto Wollertsen',
 186             'description': 'Vestlendingen Otto Fredrik Wollertsen',
 187             'timestamp': 1430473209,
 188             'upload_date': '20150501',
 189         },
 190     }
 191
 192     def _real_extract(self, url):
 193         return self.url_result('xstream:btno:%s' % self._match_id(url), 'Xstream')