Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/performgroup.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 int_or_none
   8
   9
  10 class PerformGroupIE(InfoExtractor):
  11     _VALID_URL = r'https?://player\.performgroup\.com/eplayer(?:/eplayer\.html|\.js)#/?(?P<id>[0-9a-f]{26})\.(?P<auth_token>[0-9a-z]{26})'
  12     _TESTS = [{
  13         # http://www.faz.net/aktuell/sport/fussball/wm-2018-playoffs-schweiz-besiegt-nordirland-1-0-15286104.html
  14         'url': 'http://player.performgroup.com/eplayer/eplayer.html#d478c41c5d192f56b9aa859de8.1w4crrej5w14e1ed4s1ce4ykab',
  15         'md5': '259cb03d142e2e52471e8837ecacb29f',
  16         'info_dict': {
  17             'id': 'xgrwobuzumes1lwjxtcdpwgxd',
  18             'ext': 'mp4',
  19             'title': 'Liga MX: Keine Einsicht nach Horrorfoul',
  20             'description': 'md5:7cd3b459c82725b021e046ab10bf1c5b',
  21             'timestamp': 1511533477,
  22             'upload_date': '20171124',
  23         }
  24     }]
  25
  26     def _call_api(self, service, auth_token, content_id, referer_url):
  27         return self._download_json(
  28             'http://ep3.performfeeds.com/ep%s/%s/%s/' % (service, auth_token, content_id),
  29             content_id, headers={
  30                 'Referer': referer_url,
  31                 'Origin': 'http://player.performgroup.com',
  32             }, query={
  33                 '_fmt': 'json',
  34             })
  35
  36     def _real_extract(self, url):
  37         player_id, auth_token = re.search(self._VALID_URL, url).groups()
  38         bootstrap = self._call_api('bootstrap', auth_token, player_id, url)
  39         video = bootstrap['config']['dataSource']['sourceItems'][0]['videos'][0]
  40         video_id = video['uuid']
  41         vod = self._call_api('vod', auth_token, video_id, url)
  42         media = vod['videos']['video'][0]['media']
  43
  44         formats = []
  45         hls_url = media.get('hls', {}).get('url')
  46         if hls_url:
  47             formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
  48
  49         hds_url = media.get('hds', {}).get('url')
  50         if hds_url:
  51             formats.extend(self._extract_f4m_formats(hds_url + '?hdcore', video_id, f4m_id='hds', fatal=False))
  52
  53         for c in media.get('content', []):
  54             c_url = c.get('url')
  55             if not c_url:
  56                 continue
  57             tbr = int_or_none(c.get('bitrate'), 1000)
  58             format_id = 'http'
  59             if tbr:
  60                 format_id += '-%d' % tbr
  61             formats.append({
  62                 'format_id': format_id,
  63                 'url': c_url,
  64                 'tbr': tbr,
  65                 'width': int_or_none(c.get('width')),
  66                 'height': int_or_none(c.get('height')),
  67                 'filesize': int_or_none(c.get('fileSize')),
  68                 'vcodec': c.get('type'),
  69                 'fps': int_or_none(c.get('videoFrameRate')),
  70                 'vbr': int_or_none(c.get('videoRate'), 1000),
  71                 'abr': int_or_none(c.get('audioRate'), 1000),
  72             })
  73         self._sort_formats(formats)
  74
  75         return {
  76             'id': video_id,
  77             'title': video['title'],
  78             'description': video.get('description'),
  79             'thumbnail': video.get('poster'),
  80             'duration': int_or_none(video.get('duration')),
  81             'timestamp': int_or_none(video.get('publishedTime'), 1000),
  82             'formats': formats,
  83         }