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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_parse_qs,
   9     compat_str,
  10     compat_urllib_parse_urlparse,
  11 )
  12 from ..utils import (
  13     determine_ext,
  14     int_or_none,
  15     try_get,
  16     qualities,
  17 )
  18
  19
  20 class SixPlayIE(InfoExtractor):
  21     IE_NAME = '6play'
  22     _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)'
  23     _TEST = {
  24         'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450',
  25         'md5': '42310bffe4ba3982db112b9cd3467328',
  26         'info_dict': {
  27             'id': '11638450',
  28             'ext': 'mp4',
  29             'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6',
  30             'description': 'md5:308853f6a5f9e2d55a30fc0654de415f',
  31             'duration': 39,
  32             'series': 'Le meilleur pâtissier',
  33         },
  34         'params': {
  35             'skip_download': True,
  36         },
  37     }
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         data = self._download_json(
  43             'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id,
  44             video_id, query={
  45                 'csa': 5,
  46                 'with': 'clips',
  47             })
  48
  49         clip_data = data['clips'][0]
  50         title = clip_data['title']
  51
  52         urls = []
  53         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
  54         formats = []
  55         subtitles = {}
  56         for asset in clip_data['assets']:
  57             asset_url = asset.get('full_physical_path')
  58             protocol = asset.get('protocol')
  59             if not asset_url or protocol == 'primetime' or asset_url in urls:
  60                 continue
  61             urls.append(asset_url)
  62             container = asset.get('video_container')
  63             ext = determine_ext(asset_url)
  64             if protocol == 'http_subtitle' or ext == 'vtt':
  65                 subtitles.setdefault('fr', []).append({'url': asset_url})
  66                 continue
  67             if container == 'm3u8' or ext == 'm3u8':
  68                 if protocol == 'usp' and not compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]:
  69                     asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url)
  70                     formats.extend(self._extract_m3u8_formats(
  71                         asset_url, video_id, 'mp4', 'm3u8_native',
  72                         m3u8_id='hls', fatal=False))
  73                     formats.extend(self._extract_f4m_formats(
  74                         asset_url.replace('.m3u8', '.f4m'),
  75                         video_id, f4m_id='hds', fatal=False))
  76                     formats.extend(self._extract_mpd_formats(
  77                         asset_url.replace('.m3u8', '.mpd'),
  78                         video_id, mpd_id='dash', fatal=False))
  79                     formats.extend(self._extract_ism_formats(
  80                         re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url),
  81                         video_id, ism_id='mss', fatal=False))
  82                 else:
  83                     formats.extend(self._extract_m3u8_formats(
  84                         asset_url, video_id, 'mp4', 'm3u8_native',
  85                         m3u8_id='hls', fatal=False))
  86             elif container == 'mp4' or ext == 'mp4':
  87                 quality = asset.get('video_quality')
  88                 formats.append({
  89                     'url': asset_url,
  90                     'format_id': quality,
  91                     'quality': quality_key(quality),
  92                     'ext': ext,
  93                 })
  94         self._sort_formats(formats)
  95
  96         def get(getter):
  97             for src in (data, clip_data):
  98                 v = try_get(src, getter, compat_str)
  99                 if v:
 100                     return v
 101
 102         return {
 103             'id': video_id,
 104             'title': title,
 105             'description': get(lambda x: x['description']),
 106             'duration': int_or_none(clip_data.get('duration')),
 107             'series': get(lambda x: x['program']['title']),
 108             'formats': formats,
 109             'subtitles': subtitles,
 110         }