Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/audimedia.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_iso8601,
   8 )
   9
  10
  11 class AudiMediaIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?:video/)?(?P<id>[^/?#]+)'
  13     _TESTS = [{
  14         'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467',
  15         'md5': '79a8b71c46d49042609795ab59779b66',
  16         'info_dict': {
  17             'id': '1565',
  18             'ext': 'mp4',
  19             'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
  20             'description': 'md5:60e5d30a78ced725f7b8d34370762941',
  21             'upload_date': '20151124',
  22             'timestamp': 1448354940,
  23             'duration': 74022,
  24             'view_count': int,
  25         }
  26     }, {
  27         'url': 'https://www.audi-mediacenter.com/en/audimediatv/video/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-2991',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         display_id = self._match_id(url)
  33         webpage = self._download_webpage(url, display_id)
  34
  35         raw_payload = self._search_regex([
  36             r'class="amtv-embed"[^>]+id="([0-9a-z-]+)"',
  37             r'id="([0-9a-z-]+)"[^>]+class="amtv-embed"',
  38             r'class=\\"amtv-embed\\"[^>]+id=\\"([0-9a-z-]+)\\"',
  39             r'id=\\"([0-9a-z-]+)\\"[^>]+class=\\"amtv-embed\\"',
  40             r'id=(?:\\)?"(amtve-[a-z]-\d+-[a-z]{2})',
  41         ], webpage, 'raw payload')
  42         _, stage_mode, video_id, _ = raw_payload.split('-')
  43
  44         # TODO: handle s and e stage_mode (live streams and ended live streams)
  45         if stage_mode not in ('s', 'e'):
  46             video_data = self._download_json(
  47                 'https://www.audimedia.tv/api/video/v1/videos/' + video_id,
  48                 video_id, query={
  49                     'embed[]': ['video_versions', 'thumbnail_image'],
  50                 })['results']
  51             formats = []
  52
  53             stream_url_hls = video_data.get('stream_url_hls')
  54             if stream_url_hls:
  55                 formats.extend(self._extract_m3u8_formats(
  56                     stream_url_hls, video_id, 'mp4',
  57                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  58
  59             stream_url_hds = video_data.get('stream_url_hds')
  60             if stream_url_hds:
  61                 formats.extend(self._extract_f4m_formats(
  62                     stream_url_hds + '?hdcore=3.4.0',
  63                     video_id, f4m_id='hds', fatal=False))
  64
  65             for video_version in video_data.get('video_versions', []):
  66                 video_version_url = video_version.get('download_url') or video_version.get('stream_url')
  67                 if not video_version_url:
  68                     continue
  69                 f = {
  70                     'url': video_version_url,
  71                     'width': int_or_none(video_version.get('width')),
  72                     'height': int_or_none(video_version.get('height')),
  73                     'abr': int_or_none(video_version.get('audio_bitrate')),
  74                     'vbr': int_or_none(video_version.get('video_bitrate')),
  75                 }
  76                 bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None)
  77                 if bitrate:
  78                     f.update({
  79                         'format_id': 'http-%s' % bitrate,
  80                     })
  81                 formats.append(f)
  82             self._sort_formats(formats)
  83
  84             return {
  85                 'id': video_id,
  86                 'title': video_data['title'],
  87                 'description': video_data.get('subtitle'),
  88                 'thumbnail': video_data.get('thumbnail_image', {}).get('file'),
  89                 'timestamp': parse_iso8601(video_data.get('publication_date')),
  90                 'duration': int_or_none(video_data.get('duration')),
  91                 'view_count': int_or_none(video_data.get('view_count')),
  92                 'formats': formats,
  93             }