# coding: utf-8
from __future__ import unicode_literals
-import re
-import json
-
from .common import InfoExtractor
-from ..utils import clean_html
+from ..utils import (
+ int_or_none,
+ unescapeHTML,
+)
+
-class RTBFVideoIE(InfoExtractor):
- _VALID_URL = r'https?://www.rtbf.be/video/(?P<title>[^?]+)\?.*id=(?P<id>[0-9]+)'
- _TEST = {
+class RTBFIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?rtbf\.be/(?:video/[^?]+\?.*\bid=|ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=)(?P<id>\d+)'
+ _TESTS = [{
'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
'md5': '799f334ddf2c0a582ba80c44655be570',
'info_dict': {
'title': 'Les Diables au coeur (épisode 2)',
'duration': 3099,
}
- }
+ }, {
+ # geo restricted
+ 'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858',
+ 'only_matching': True,
+ }]
+
+ _QUALITIES = [
+ ('mobile', 'mobile'),
+ ('web', 'SD'),
+ ('url', 'MD'),
+ ('high', 'HD'),
+ ]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
- # TODO more code goes here, for example ...
- webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(
- r'<meta property="og:description" content="([^"]*)"',
- webpage, 'title', mobj.group('title'))
+ webpage = self._download_webpage(
+ 'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
- iframe_url = self._html_search_regex(r'<iframe [^>]*src="([^"]+)"',
- webpage, 'iframe')
- iframe = self._download_webpage(iframe_url, video_id)
+ data = self._parse_json(
+ unescapeHTML(self._search_regex(
+ r'data-media="([^"]+)"', webpage, 'data video')),
+ video_id)
- data_video_idx = iframe.find('data-video')
- next_data_idx = iframe.find('data-', data_video_idx + 1)
- json_data_start = data_video_idx + len('data-video=') + 1
- json_data_end = next_data_idx - 2
- video_data = json.loads(clean_html(iframe[json_data_start:json_data_end]))
+ 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,
- 'title': title,
- 'url': video_data['data']['downloadUrl'],
- 'duration': video_data['data']['duration'],
+ 'formats': formats,
+ 'title': data['title'],
+ 'description': data.get('description') or data.get('subtitle'),
+ 'thumbnail': data.get('thumbnail'),
+ 'duration': data.get('duration') or data.get('realDuration'),
+ 'timestamp': int_or_none(data.get('created')),
+ 'view_count': int_or_none(data.get('viewCount')),
}