yt_dlp/extractor/sixplay.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_str,
   8 )
   9 from ..utils import (
  10     determine_ext,
  11     int_or_none,
  12     parse_qs,
  13     try_get,
  14     qualities,
  15 )
  16
  17
  18 class SixPlayIE(InfoExtractor):
  19     IE_NAME = '6play'
  20     _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr|rtlmost\.hu)/.+?-c_)(?P<id>[0-9]+)'
  21     _TESTS = [{
  22         'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
  23         'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
  24         'info_dict': {
  25             'id': '12041051',
  26             'ext': 'mp4',
  27             'title': 'Le but qui a marqué l\'histoire du football français !',
  28             'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851',
  29         },
  30     }, {
  31         'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869',
  32         'only_matching': True,
  33     }, {
  34         'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989',
  35         'only_matching': True,
  36     }, {
  37         'url': 'https://www.rtlmost.hu/megtorve-p_14167/megtorve-6-resz-c_12397787',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         domain, video_id = self._match_valid_url(url).groups()
  43         service, consumer_name = {
  44             '6play.fr': ('6play', 'm6web'),
  45             'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
  46             'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'),
  47             'rtlmost.hu': ('rtlhu_rtl_most', 'rtlhu'),
  48         }.get(domain, ('6play', 'm6web'))
  49
  50         data = self._download_json(
  51             'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/%s/videos/clip_%s' % (service, video_id),
  52             video_id, headers={
  53                 'x-customer-name': consumer_name
  54             }, query={
  55                 'csa': 5,
  56                 'with': 'clips',
  57             })
  58
  59         clip_data = data['clips'][0]
  60         title = clip_data['title']
  61
  62         urls = []
  63         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
  64         formats = []
  65         subtitles = {}
  66         assets = clip_data.get('assets') or []
  67         for asset in assets:
  68             asset_url = asset.get('full_physical_path')
  69             protocol = asset.get('protocol')
  70             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:
  71                 continue
  72             urls.append(asset_url)
  73             container = asset.get('video_container')
  74             ext = determine_ext(asset_url)
  75             if protocol == 'http_subtitle' or ext == 'vtt':
  76                 subtitles.setdefault('fr', []).append({'url': asset_url})
  77                 continue
  78             if container == 'm3u8' or ext == 'm3u8':
  79                 if protocol == 'usp':
  80                     if parse_qs(asset_url).get('token', [None])[0]:
  81                         urlh = self._request_webpage(
  82                             asset_url, video_id, fatal=False,
  83                             headers=self.geo_verification_headers())
  84                         if not urlh:
  85                             continue
  86                         asset_url = urlh.geturl()
  87                     asset_url = asset_url.replace('_drmnp.ism/', '_unpnp.ism/')
  88                     for i in range(3, 0, -1):
  89                         asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i)
  90                         m3u8_formats = self._extract_m3u8_formats(
  91                             asset_url, video_id, 'mp4', 'm3u8_native',
  92                             m3u8_id='hls', fatal=False)
  93                         formats.extend(m3u8_formats)
  94                         formats.extend(self._extract_mpd_formats(
  95                             asset_url.replace('.m3u8', '.mpd'),
  96                             video_id, mpd_id='dash', fatal=False))
  97                         if m3u8_formats:
  98                             break
  99                 else:
 100                     formats.extend(self._extract_m3u8_formats(
 101                         asset_url, video_id, 'mp4', 'm3u8_native',
 102                         m3u8_id='hls', fatal=False))
 103             elif container == 'mp4' or ext == 'mp4':
 104                 quality = asset.get('video_quality')
 105                 formats.append({
 106                     'url': asset_url,
 107                     'format_id': quality,
 108                     'quality': quality_key(quality),
 109                     'ext': ext,
 110                 })
 111         self._sort_formats(formats)
 112
 113         def get(getter):
 114             for src in (data, clip_data):
 115                 v = try_get(src, getter, compat_str)
 116                 if v:
 117                     return v
 118
 119         return {
 120             'id': video_id,
 121             'title': title,
 122             'description': get(lambda x: x['description']),
 123             'duration': int_or_none(clip_data.get('duration')),
 124             'series': get(lambda x: x['program']['title']),
 125             'formats': formats,
 126             'subtitles': subtitles,
 127         }