add some strip characters
This commit is contained in:
parent
b55a2543e6
commit
96c8c49030
|
@ -52,7 +52,7 @@ class FileScanner(HTMLParser):
|
||||||
title_words = set(title.split('-'))
|
title_words = set(title.split('-'))
|
||||||
for word in words:
|
for word in words:
|
||||||
# Verschiedene Zeichen vom Anfang und Ende der Wörter entfernen.
|
# Verschiedene Zeichen vom Anfang und Ende der Wörter entfernen.
|
||||||
tag_name = word.strip(".,:;!?\"'()«»")
|
tag_name = word.strip(".,:;!?\"'()-„“«» ")
|
||||||
# Leere Wörter ignorieren
|
# Leere Wörter ignorieren
|
||||||
if not tag_name:
|
if not tag_name:
|
||||||
continue
|
continue
|
||||||
|
|
Loading…
Reference in a new issue