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 compat_str
   8 from ..utils import (
   9     determine_ext,
  10     int_or_none,
  11     try_get,
  12     qualities,
  13 )
  14
  15
  16 class SixPlayIE(InfoExtractor):
  17     IE_NAME = '6play'
  18     _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)'
  19     _TEST = {
  20         'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450',
  21         'md5': '42310bffe4ba3982db112b9cd3467328',
  22         'info_dict': {
  23             'id': '11638450',
  24             'ext': 'mp4',
  25             'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6',
  26             'description': 'md5:308853f6a5f9e2d55a30fc0654de415f',
  27             'duration': 39,
  28             'series': 'Le meilleur pâtissier',
  29         },
  30         'params': {
  31             'skip_download': True,
  32         },
  33     }
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37
  38         data = self._download_json(
  39             'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id,
  40             video_id, query={
  41                 'csa': 5,
  42                 'with': 'clips',
  43             })
  44
  45         clip_data = data['clips'][0]
  46         title = clip_data['title']
  47
  48         urls = []
  49         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
  50         formats = []
  51         for asset in clip_data['assets']:
  52             asset_url = asset.get('full_physical_path')
  53             protocol = asset.get('protocol')
  54             if not asset_url or protocol == 'primetime' or asset_url in urls:
  55                 continue
  56             urls.append(asset_url)
  57             container = asset.get('video_container')
  58             ext = determine_ext(asset_url)
  59             if container == 'm3u8' or ext == 'm3u8':
  60                 if protocol == 'usp':
  61                     asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url)
  62                     formats.extend(self._extract_m3u8_formats(
  63                         asset_url, video_id, 'mp4', 'm3u8_native',
  64                         m3u8_id='hls', fatal=False))
  65                     formats.extend(self._extract_f4m_formats(
  66                         asset_url.replace('.m3u8', '.f4m'),
  67                         video_id, f4m_id='hds', fatal=False))
  68                     formats.extend(self._extract_mpd_formats(
  69                         asset_url.replace('.m3u8', '.mpd'),
  70                         video_id, mpd_id='dash', fatal=False))
  71                     formats.extend(self._extract_ism_formats(
  72                         re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url),
  73                         video_id, ism_id='mss', fatal=False))
  74                 else:
  75                     formats.extend(self._extract_m3u8_formats(
  76                         asset_url, video_id, 'mp4', 'm3u8_native',
  77                         m3u8_id='hls', fatal=False))
  78             elif container == 'mp4' or ext == 'mp4':
  79                 quality = asset.get('video_quality')
  80                 formats.append({
  81                     'url': asset_url,
  82                     'format_id': quality,
  83                     'quality': quality_key(quality),
  84                     'ext': ext,
  85                 })
  86         self._sort_formats(formats)
  87
  88         def get(getter):
  89             for src in (data, clip_data):
  90                 v = try_get(src, getter, compat_str)
  91                 if v:
  92                     return v
  93
  94         return {
  95             'id': video_id,
  96             'title': title,
  97             'description': get(lambda x: x['description']),
  98             'duration': int_or_none(clip_data.get('duration')),
  99             'series': get(lambda x: x['program']['title']),
 100             'formats': formats,
 101         }