diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-05-24 21:09:08 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-05-24 21:09:08 +0600 |
commit | 63f3cab4aee5da45dc9b91a9661d5d52b5a72ec6 (patch) | |
tree | ccfa6c7fb141eea4525ff1109c96b8312bcc5cb4 /youtube_dl | |
parent | 8cdf03a7a2140d0ca82f03e3c41887ea7491828e (diff) |
[rtbf] Fix extraction (Closes #5803)
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/rtbf.py | 30 |
1 files changed, 15 insertions, 15 deletions
diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index dce64e151..5a381d9ce 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): @@ -16,25 +17,24 @@ 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') + video_id = self._match_id(url) - page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id) + webpage = self._download_webpage( + 'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id) - data = json.loads(self._html_search_regex( - r'<div class="js-player-embed(?: player-embed)?" data-video="([^"]+)"', page, 'data video'))['data'] + data = self._parse_json( + unescapeHTML(self._search_regex( + r'data-video="([^"]+)"', webpage, 'data video')), + video_id) video_url = data.get('downloadUrl') or data.get('url') - if data['provider'].lower() == 'youtube': + if data.get('provider').lower() == 'youtube': return self.url_result(video_url, 'Youtube') return { @@ -42,8 +42,8 @@ class RTBFIE(InfoExtractor): 'url': video_url, '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')), } |