yt_dlp/extractor/sixplay.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     int_or_none,
   5     parse_qs,
   6     qualities,
   7     try_get,
   8 )
   9
  10
  11 class SixPlayIE(InfoExtractor):
  12     IE_NAME = '6play'
  13     _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr|rtlmost\.hu)/.+?-c_)(?P<id>[0-9]+)'
  14     _TESTS = [{
  15         'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
  16         'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
  17         'info_dict': {
  18             'id': '12041051',
  19             'ext': 'mp4',
  20             'title': 'Le but qui a marqué l\'histoire du football français !',
  21             'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851',
  22         },
  23     }, {
  24         'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869',
  25         'only_matching': True,
  26     }, {
  27         'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989',
  28         'only_matching': True,
  29     }, {
  30         'url': 'https://www.rtlmost.hu/megtorve-p_14167/megtorve-6-resz-c_12397787',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         domain, video_id = self._match_valid_url(url).groups()
  36         service, consumer_name = {
  37             '6play.fr': ('6play', 'm6web'),
  38             'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
  39             'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'),
  40             'rtlmost.hu': ('rtlhu_rtl_most', 'rtlhu'),
  41         }.get(domain, ('6play', 'm6web'))
  42
  43         data = self._download_json(
  44             f'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/{service}/videos/clip_{video_id}',
  45             video_id, headers={
  46                 'x-customer-name': consumer_name,
  47             }, query={
  48                 'csa': 5,
  49                 'with': 'clips',
  50             })
  51
  52         clip_data = data['clips'][0]
  53         title = clip_data['title']
  54
  55         urls = []
  56         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
  57         formats = []
  58         subtitles = {}
  59         assets = clip_data.get('assets') or []
  60         for asset in assets:
  61             asset_url = asset.get('full_physical_path')
  62             protocol = asset.get('protocol')
  63             if not asset_url or ((protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264') and not ('_drmnp.ism/' in asset_url or '_unpnp.ism/' in asset_url)) or asset_url in urls:
  64                 continue
  65             urls.append(asset_url)
  66             container = asset.get('video_container')
  67             ext = determine_ext(asset_url)
  68             if protocol == 'http_subtitle' or ext == 'vtt':
  69                 subtitles.setdefault('fr', []).append({'url': asset_url})
  70                 continue
  71             if container == 'm3u8' or ext == 'm3u8':
  72                 if protocol == 'usp':
  73                     if parse_qs(asset_url).get('token', [None])[0]:
  74                         urlh = self._request_webpage(
  75                             asset_url, video_id, fatal=False,
  76                             headers=self.geo_verification_headers())
  77                         if not urlh:
  78                             continue
  79                         asset_url = urlh.url
  80                     asset_url = asset_url.replace('_drmnp.ism/', '_unpnp.ism/')
  81                     for i in range(3, 0, -1):
  82                         asset_url = asset_url.replace('_sd1/', f'_sd{i}/')
  83                         m3u8_formats = self._extract_m3u8_formats(
  84                             asset_url, video_id, 'mp4', 'm3u8_native',
  85                             m3u8_id='hls', fatal=False)
  86                         formats.extend(m3u8_formats)
  87                         formats.extend(self._extract_mpd_formats(
  88                             asset_url.replace('.m3u8', '.mpd'),
  89                             video_id, mpd_id='dash', fatal=False))
  90                         if m3u8_formats:
  91                             break
  92                 else:
  93                     formats.extend(self._extract_m3u8_formats(
  94                         asset_url, video_id, 'mp4', 'm3u8_native',
  95                         m3u8_id='hls', fatal=False))
  96             elif container == 'mp4' or ext == 'mp4':
  97                 quality = asset.get('video_quality')
  98                 formats.append({
  99                     'url': asset_url,
 100                     'format_id': quality,
 101                     'quality': quality_key(quality),
 102                     'ext': ext,
 103                 })
 104
 105         def get(getter):
 106             for src in (data, clip_data):
 107                 v = try_get(src, getter, str)
 108                 if v:
 109                     return v
 110
 111         return {
 112             'id': video_id,
 113             'title': title,
 114             'description': get(lambda x: x['description']),
 115             'duration': int_or_none(clip_data.get('duration')),
 116             'series': get(lambda x: x['program']['title']),
 117             'formats': formats,
 118             'subtitles': subtitles,
 119         }