feat(arte_extractor): add alt_title for regular shows ❯❯❯

Most repeating Arte.tv shows have an essential subtitle (not to confuse with the one already in the extractor!).
Without that title those shows get the same title for all
potentially hundreds of shows.

Here is an example of the German version of the ARTE Reportage show:

https://www.arte.tv/de/videos/030273-820-A/arte-reportage/

Now: title is `ARTE Reportage` and no alt_title is available
With this: title is `ARTE Reportage` and
           alt_title is `Sudan: Die Tigray fliehen aus Äthiopien`
This commit is contained in:
Kaspar Vollenweider 2021-07-17 17:45:17 +02:00
parent a803582717
commit f861761a90
No known key found for this signature in database
GPG Key ID: 9039A456BC9C0F78

View File

@ -33,6 +33,16 @@ class ArteTVIE(ArteTVBaseIE):
/(?P<id>\d{6}-\d{3}-[AF])
''' % {'langs': ArteTVBaseIE._ARTE_LANGUAGES}
_TESTS = [{
'url': 'https://www.arte.tv/de/videos/092724-001-A/lasst-mich-schlafen/',
'info_dict': {
'id': '092724-001-A',
'ext': 'mp4',
'title': 'Lasst mich schlafen!',
'alt_title': 'Wie schlafen wir?',
'description': 'Gegen Abend signalisiert die biologische Uhr dem Körper durch das Ausschütten von Melatonin, dass es Zeit ist, herunterzufahren. Doch was geschieht dabei im Gehirn? Der Schlafforscher Raphael Heinzer vom Schlafforschungszentrum Lausanne will dies herausfinden und beobachtet die Hirnströme in den verschiedenen Schlafphasen.',
'upload_date': '20200224'
},
}, {
'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
'info_dict': {
'id': '088501-000-A',
@ -170,7 +180,7 @@ class ArteTVIE(ArteTVBaseIE):
self._sort_formats(formats)
return {
extracted_metadata = {
'id': player_info.get('VID') or video_id,
'title': title,
'description': player_info.get('VDE'),
@ -178,6 +188,9 @@ class ArteTVIE(ArteTVBaseIE):
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
'formats': formats,
}
if player_info.get('subtitle', '').strip():
extracted_metadata['alt_title'] = player_info.get('subtitle', '').strip()
return extracted_metadata
class ArteTVEmbedIE(InfoExtractor):