yt_dlp/extractor/sixplay.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_str,
   4 )
   5 from ..utils import (
   6     determine_ext,
   7     int_or_none,
   8     parse_qs,
   9     qualities,
  10     try_get,
  11 )
  12
  13
  14 class SixPlayIE(InfoExtractor):
  15     IE_NAME = '6play'
  16     _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr|rtlmost\.hu)/.+?-c_)(?P<id>[0-9]+)'
  17     _TESTS = [{
  18         'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
  19         'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
  20         'info_dict': {
  21             'id': '12041051',
  22             'ext': 'mp4',
  23             'title': 'Le but qui a marqué l\'histoire du football français !',
  24             'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851',
  25         },
  26     }, {
  27         'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869',
  28         'only_matching': True,
  29     }, {
  30         'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989',
  31         'only_matching': True,
  32     }, {
  33         'url': 'https://www.rtlmost.hu/megtorve-p_14167/megtorve-6-resz-c_12397787',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         domain, video_id = self._match_valid_url(url).groups()
  39         service, consumer_name = {
  40             '6play.fr': ('6play', 'm6web'),
  41             'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
  42             'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'),
  43             'rtlmost.hu': ('rtlhu_rtl_most', 'rtlhu'),
  44         }.get(domain, ('6play', 'm6web'))
  45
  46         data = self._download_json(
  47             'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/%s/videos/clip_%s' % (service, video_id),
  48             video_id, headers={
  49                 'x-customer-name': consumer_name
  50             }, query={
  51                 'csa': 5,
  52                 'with': 'clips',
  53             })
  54
  55         clip_data = data['clips'][0]
  56         title = clip_data['title']
  57
  58         urls = []
  59         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
  60         formats = []
  61         subtitles = {}
  62         assets = clip_data.get('assets') or []
  63         for asset in assets:
  64             asset_url = asset.get('full_physical_path')
  65             protocol = asset.get('protocol')
  66             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:
  67                 continue
  68             urls.append(asset_url)
  69             container = asset.get('video_container')
  70             ext = determine_ext(asset_url)
  71             if protocol == 'http_subtitle' or ext == 'vtt':
  72                 subtitles.setdefault('fr', []).append({'url': asset_url})
  73                 continue
  74             if container == 'm3u8' or ext == 'm3u8':
  75                 if protocol == 'usp':
  76                     if parse_qs(asset_url).get('token', [None])[0]:
  77                         urlh = self._request_webpage(
  78                             asset_url, video_id, fatal=False,
  79                             headers=self.geo_verification_headers())
  80                         if not urlh:
  81                             continue
  82                         asset_url = urlh.url
  83                     asset_url = asset_url.replace('_drmnp.ism/', '_unpnp.ism/')
  84                     for i in range(3, 0, -1):
  85                         asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i)
  86                         m3u8_formats = self._extract_m3u8_formats(
  87                             asset_url, video_id, 'mp4', 'm3u8_native',
  88                             m3u8_id='hls', fatal=False)
  89                         formats.extend(m3u8_formats)
  90                         formats.extend(self._extract_mpd_formats(
  91                             asset_url.replace('.m3u8', '.mpd'),
  92                             video_id, mpd_id='dash', fatal=False))
  93                         if m3u8_formats:
  94                             break
  95                 else:
  96                     formats.extend(self._extract_m3u8_formats(
  97                         asset_url, video_id, 'mp4', 'm3u8_native',
  98                         m3u8_id='hls', fatal=False))
  99             elif container == 'mp4' or ext == 'mp4':
 100                 quality = asset.get('video_quality')
 101                 formats.append({
 102                     'url': asset_url,
 103                     'format_id': quality,
 104                     'quality': quality_key(quality),
 105                     'ext': ext,
 106                 })
 107
 108         def get(getter):
 109             for src in (data, clip_data):
 110                 v = try_get(src, getter, compat_str)
 111                 if v:
 112                     return v
 113
 114         return {
 115             'id': video_id,
 116             'title': title,
 117             'description': get(lambda x: x['description']),
 118             'duration': int_or_none(clip_data.get('duration')),
 119             'series': get(lambda x: x['program']['title']),
 120             'formats': formats,
 121             'subtitles': subtitles,
 122         }