split url letters
This commit is contained in:
parent
c9f435f0f5
commit
233d1c94bf
|
@ -33,7 +33,7 @@ class FileScanner(HTMLParser):
|
||||||
words_with_usage = {}
|
words_with_usage = {}
|
||||||
words = []
|
words = []
|
||||||
for text in self.texte:
|
for text in self.texte:
|
||||||
words += re.split(r'[ /\-_#\n]', text)
|
words += re.split(r'[ /\-_#\n.?=]', text)
|
||||||
print(f'\nFile {self.file.parent.name} contains {len(words)} words')
|
print(f'\nFile {self.file.parent.name} contains {len(words)} words')
|
||||||
title_words = set(self.file.parent.name.split('-'))
|
title_words = set(self.file.parent.name.split('-'))
|
||||||
for word in words:
|
for word in words:
|
||||||
|
|
Loading…
Reference in a new issue