R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[ProSiebenSat1] Improve title extraction (#13915)

Browse Source 
With this commit, og:title titles are preferred over the old extraction.
Some tests had to be adjusted, but I have verified the now extracted
titles are equally well or better.
This commit is contained in:
Kay B 2017-09-05 20:17:16 +02:00
parent bc35f07537
commit 36b93e52e2
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
youtube_dl/extractor/prosiebensat1.py
View File

@ -148,7 +148,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'info_dict': { 'info_dict': {
'id': '2104602', 'id': '2104602',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Episode 18 - Staffel 2', 'title': 'CIRCUS HALLIGALLI - Episode 18 - Staffel 2',
'description': 'md5:8733c81b702ea472e069bc48bb658fc1', 'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
'upload_date': '20131231', 'upload_date': '20131231',
'duration': 5845.04, 'duration': 5845.04,
@ -255,7 +255,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'info_dict': { 'info_dict': {
'id': '2572814', 'id': '2572814',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Andreas Kümmert: Rocket Man', 'title': 'The Voice of Germany - Andreas Kümmert: Rocket Man',
'description': 'md5:6ddb02b0781c6adf778afea606652e38', 'description': 'md5:6ddb02b0781c6adf778afea606652e38',
'upload_date': '20131017', 'upload_date': '20131017',
'duration': 469.88, 'duration': 469.88,
@ -292,7 +292,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'info_dict': { 'info_dict': {
'id': '4187506', 'id': '4187506',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Best of Circus HalliGalli', 'title': 'Best of Circus HalliGalli - Circus Halligalli - 7TV',
'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9', 'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9',
'upload_date': '20151229', 'upload_date': '20151229',
}, },
@ -385,9 +385,11 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
def _extract_clip(self, url, webpage): def _extract_clip(self, url, webpage):
clip_id = self._html_search_regex( clip_id = self._html_search_regex(
self._CLIPID_REGEXES, webpage, 'clip id') self._CLIPID_REGEXES, webpage, 'clip id')
title = self._html_search_regex( title = self._og_search_title(webpage)
self._TITLE_REGEXES, webpage, 'title', if title is None:
default=None) or self._og_search_title(webpage) self._html_search_regex(
self._TITLE_REGEXES, webpage, 'title',
default=None)
info = self._extract_video_info(url, clip_id) info = self._extract_video_info(url, clip_id)
description = self._html_search_regex( description = self._html_search_regex(
self._DESCRIPTION_REGEXES, webpage, 'description', default=None) self._DESCRIPTION_REGEXES, webpage, 'description', default=None)