diff options
Diffstat (limited to 'youtube_dl/extractor/rtbf.py')
| -rw-r--r-- | youtube_dl/extractor/rtbf.py | 50 | 
1 files changed, 32 insertions, 18 deletions
| diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index dce64e151..e4215d546 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -1,10 +1,11 @@  # coding: utf-8  from __future__ import unicode_literals -import re -import json -  from .common import InfoExtractor +from ..utils import ( +    int_or_none, +    unescapeHTML, +)  class RTBFIE(InfoExtractor): @@ -16,34 +17,47 @@ class RTBFIE(InfoExtractor):              'id': '1921274',              'ext': 'mp4',              'title': 'Les Diables au coeur (épisode 2)', -            'description': 'Football - Diables Rouges',              'duration': 3099, -            'timestamp': 1398456336, -            'upload_date': '20140425',          }      } -    def _real_extract(self, url): -        mobj = re.match(self._VALID_URL, url) -        video_id = mobj.group('id') +    _QUALITIES = [ +        ('mobile', 'mobile'), +        ('web', 'SD'), +        ('url', 'MD'), +        ('high', 'HD'), +    ] -        page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id) +    def _real_extract(self, url): +        video_id = self._match_id(url) -        data = json.loads(self._html_search_regex( -            r'<div class="js-player-embed(?: player-embed)?" data-video="([^"]+)"', page, 'data video'))['data'] +        webpage = self._download_webpage( +            'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id) -        video_url = data.get('downloadUrl') or data.get('url') +        data = self._parse_json( +            unescapeHTML(self._search_regex( +                r'data-video="([^"]+)"', webpage, 'data video')), +            video_id) -        if data['provider'].lower() == 'youtube': +        if data.get('provider').lower() == 'youtube': +            video_url = data.get('downloadUrl') or data.get('url')              return self.url_result(video_url, 'Youtube') +        formats = [] +        for key, format_id in self._QUALITIES: +            format_url = data['sources'].get(key) +            if format_url: +                formats.append({ +                    'format_id': format_id, +                    'url': format_url, +                })          return {              'id': video_id, -            'url': video_url, +            'formats': formats,              'title': data['title'],              'description': data.get('description') or data.get('subtitle'), -            'thumbnail': data['thumbnail']['large'], +            'thumbnail': data.get('thumbnail'),              'duration': data.get('duration') or data.get('realDuration'), -            'timestamp': data['created'], -            'view_count': data['viewCount'], +            'timestamp': int_or_none(data.get('created')), +            'view_count': int_or_none(data.get('viewCount')),          } | 
