yt_dlp/extractor/konserthusetplay.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     float_or_none,
   5     int_or_none,
   6     url_or_none,
   7 )
   8
   9
  10 class KonserthusetPlayIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?(?:konserthusetplay|rspoplay)\.se/\?.*\bm=(?P<id>[^&]+)'
  12     _TESTS = [{
  13         'url': 'http://www.konserthusetplay.se/?m=CKDDnlCY-dhWAAqiMERd-A',
  14         'md5': 'e3fd47bf44e864bd23c08e487abe1967',
  15         'info_dict': {
  16             'id': 'CKDDnlCY-dhWAAqiMERd-A',
  17             'ext': 'mp4',
  18             'title': 'Orkesterns instrument: Valthornen',
  19             'description': 'md5:f10e1f0030202020396a4d712d2fa827',
  20             'thumbnail': 're:^https?://.*$',
  21             'duration': 398.76,
  22         },
  23     }, {
  24         'url': 'http://rspoplay.se/?m=elWuEH34SMKvaO4wO_cHBw',
  25         'only_matching': True,
  26     }]
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         e = self._search_regex(
  34             r'https?://csp\.picsearch\.com/rest\?.*\be=(.+?)[&"\']', webpage, 'e')
  35
  36         rest = self._download_json(
  37             'http://csp.picsearch.com/rest?e=%s&containerId=mediaplayer&i=object' % e,
  38             video_id, transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1])
  39
  40         media = rest['media']
  41         player_config = media['playerconfig']
  42         playlist = player_config['playlist']
  43
  44         source = next(f for f in playlist if f.get('bitrates') or f.get('provider'))
  45
  46         FORMAT_ID_REGEX = r'_([^_]+)_h264m\.mp4'
  47
  48         formats = []
  49
  50         m3u8_url = source.get('url')
  51         if m3u8_url and determine_ext(m3u8_url) == 'm3u8':
  52             formats.extend(self._extract_m3u8_formats(
  53                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  54                 m3u8_id='hls', fatal=False))
  55
  56         fallback_url = source.get('fallbackUrl')
  57         fallback_format_id = None
  58         if fallback_url:
  59             fallback_format_id = self._search_regex(
  60                 FORMAT_ID_REGEX, fallback_url, 'format id', default=None)
  61
  62         connection_url = (player_config.get('rtmp', {}).get(
  63             'netConnectionUrl') or player_config.get(
  64             'plugins', {}).get('bwcheck', {}).get('netConnectionUrl'))
  65         if connection_url:
  66             for f in source['bitrates']:
  67                 video_url = f.get('url')
  68                 if not video_url:
  69                     continue
  70                 format_id = self._search_regex(
  71                     FORMAT_ID_REGEX, video_url, 'format id', default=None)
  72                 f_common = {
  73                     'vbr': int_or_none(f.get('bitrate')),
  74                     'width': int_or_none(f.get('width')),
  75                     'height': int_or_none(f.get('height')),
  76                 }
  77                 f = f_common.copy()
  78                 f.update({
  79                     'url': connection_url,
  80                     'play_path': video_url,
  81                     'format_id': 'rtmp-%s' % format_id if format_id else 'rtmp',
  82                     'ext': 'flv',
  83                 })
  84                 formats.append(f)
  85                 if format_id and format_id == fallback_format_id:
  86                     f = f_common.copy()
  87                     f.update({
  88                         'url': fallback_url,
  89                         'format_id': 'http-%s' % format_id if format_id else 'http',
  90                     })
  91                     formats.append(f)
  92
  93         if not formats and fallback_url:
  94             formats.append({
  95                 'url': fallback_url,
  96             })
  97
  98         title = player_config.get('title') or media['title']
  99         description = player_config.get('mediaInfo', {}).get('description')
 100         thumbnail = media.get('image')
 101         duration = float_or_none(media.get('duration'), 1000)
 102
 103         subtitles = {}
 104         captions = source.get('captionsAvailableLanguages')
 105         if isinstance(captions, dict):
 106             for lang, subtitle_url in captions.items():
 107                 subtitle_url = url_or_none(subtitle_url)
 108                 if lang != 'none' and subtitle_url:
 109                     subtitles.setdefault(lang, []).append({'url': subtitle_url})
 110
 111         return {
 112             'id': video_id,
 113             'title': title,
 114             'description': description,
 115             'thumbnail': thumbnail,
 116             'duration': duration,
 117             'formats': formats,
 118             'subtitles': subtitles,
 119         }