title = self._html_search_regex(
r'<h2 class="white">(.*?)</h2>', webpage, 'title')
video_info_dicts = re.findall(
- r"({\s*src\s*:\s*'https://film\.bpb\.de/[^}]+})", webpage)
+ r"({\s*src\s*:\s*'https?://film\.bpb\.de/[^}]+})", webpage)
formats = []
for video_info in video_info_dicts:
- video_info = self._parse_json(video_info, video_id, transform_source=js_to_json)
- video_url = video_info['src']
- quality = 'high' if re.search(r'_high\.', video_url) else 'low'
+ video_info = self._parse_json(
+ video_info, video_id, transform_source=js_to_json, fatal=False)
+ if not video_info:
+ continue
+ video_url = video_info.get('src')
+ if not video_url:
+ continue
+ quality = 'high' if '_high' in video_url else 'low'
formats.append({
'url': video_url,
'preference': 10 if quality == 'high' else 0,