split url letters

This commit is contained in:
OneNewDev 2022-05-28 15:33:16 +02:00
parent c9f435f0f5
commit 233d1c94bf

View file

@ -33,7 +33,7 @@ class FileScanner(HTMLParser):
words_with_usage = {}
words = []
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')
title_words = set(self.file.parent.name.split('-'))
for word in words: