[teachertube] Improve extraction
This commit is contained in:
parent
d410fee91d
commit
c7df67edbd
|
@ -66,6 +66,7 @@ class TeacherTubeIE(InfoExtractor):
|
||||||
|
|
||||||
media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
|
media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
|
||||||
media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
|
media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
|
||||||
|
media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage))
|
||||||
|
|
||||||
formats = [
|
formats = [
|
||||||
{
|
{
|
||||||
|
@ -79,7 +80,7 @@ class TeacherTubeIE(InfoExtractor):
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
'thumbnail': self._html_search_regex(r'var\s+thumbUrl\s*=\s*"([^"]+)"', webpage, 'thumbnail'),
|
'thumbnail': self._html_search_regex(r'\'image\'\s*:\s*["\']([^"\']+)["\']', webpage, 'thumbnail'),
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'description': description,
|
'description': description,
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue