diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-02-08 23:15:39 +0700 | 
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-02-08 23:15:39 +0700 | 
| commit | b9c9cb5f7958f924949adbe37824df1fc1530519 (patch) | |
| tree | f826430c66840c3e8083002f92620987977cd089 | |
| parent | fdf9b959bc600c9377d6567d29081baa4f23f0da (diff) | |
[6play] Fix extraction (closes #12011)
| -rw-r--r-- | youtube_dl/extractor/sixplay.py | 69 | 
1 files changed, 44 insertions, 25 deletions
| diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index d3aba58a2..460e18e26 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -2,63 +2,82 @@  from __future__ import unicode_literals  from .common import InfoExtractor +from ..compat import compat_str  from ..utils import ( -    qualities, -    int_or_none, -    mimetype2ext,      determine_ext, +    int_or_none, +    try_get, +    qualities,  )  class SixPlayIE(InfoExtractor):      _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)'      _TEST = { -        'url': 'http://www.6play.fr/jamel-et-ses-amis-au-marrakech-du-rire-p_1316/jamel-et-ses-amis-au-marrakech-du-rire-2015-c_11495320', +        'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450',          'md5': '42310bffe4ba3982db112b9cd3467328',          'info_dict': { -            'id': '11495320', +            'id': '11638450',              'ext': 'mp4', -            'title': 'Jamel et ses amis au Marrakech du rire 2015', -            'description': 'md5:ba2149d5c321d5201b78070ee839d872', +            'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6', +            'description': 'md5:308853f6a5f9e2d55a30fc0654de415f', +            'duration': 39, +            'series': 'Le meilleur pâtissier', +        }, +        'params': { +            'skip_download': True,          },      }      def _real_extract(self, url):          video_id = self._match_id(url) -        clip_data = self._download_json( -            'https://player.m6web.fr/v2/video/config/6play-auth/FR/%s.json' % video_id, -            video_id) -        video_data = clip_data['videoInfo'] + +        data = self._download_json( +            'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id, +            video_id, query={ +                'csa': 5, +                'with': 'clips', +            }) + +        clip_data = data['clips'][0] +        title = clip_data['title']          quality_key = qualities(['lq', 'sd', 'hq', 'hd'])          formats = [] -        for source in clip_data['sources']: -            source_type, source_url = source.get('type'), source.get('src') -            if not source_url or source_type == 'hls/primetime': +        for asset in clip_data['assets']: +            asset_url = asset.get('full_physical_path') +            if not asset_url:                  continue -            ext = mimetype2ext(source_type) or determine_ext(source_url) -            if ext == 'm3u8': +            container = asset.get('video_container') +            ext = determine_ext(asset_url) +            if container == 'm3u8' or ext == 'm3u8':                  formats.extend(self._extract_m3u8_formats( -                    source_url, video_id, 'mp4', 'm3u8_native', +                    asset_url, video_id, 'mp4', 'm3u8_native',                      m3u8_id='hls', fatal=False))                  formats.extend(self._extract_f4m_formats( -                    source_url.replace('.m3u8', '.f4m'), +                    asset_url.replace('.m3u8', '.f4m'),                      video_id, f4m_id='hds', fatal=False)) -            elif ext == 'mp4': -                quality = source.get('quality') +            elif container == 'mp4' or ext == 'mp4': +                quality = asset.get('video_quality')                  formats.append({ -                    'url': source_url, +                    'url': asset_url,                      'format_id': quality,                      'quality': quality_key(quality),                      'ext': ext,                  })          self._sort_formats(formats) +        def get(getter): +            for src in (data, clip_data): +                v = try_get(src, getter, compat_str) +                if v: +                    return v +          return {              'id': video_id, -            'title': video_data['title'].strip(), -            'description': video_data.get('description'), -            'duration': int_or_none(video_data.get('duration')), -            'series': video_data.get('titlePgm'), +            'title': title, +            'description': get(lambda x: x['description']), +            'duration': int_or_none(clip_data.get('duration')), +            'series': get(lambda x: x['program']['title']),              'formats': formats,          } | 
