unquote url

tagger.py

@@ -2,6 +2,7 @@ import json
 import re
 from dataclasses import dataclass
 from html.parser import HTMLParser
+from urllib.parse import unquote_plus
 from pathlib import Path
 
 from exclude import EXCLUDED_WORDS
@@ -33,6 +34,7 @@ class FileScanner(HTMLParser):
         words_with_usage = {}
         words = []
         for text in self.texte:
+            text = unquote_plus(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('-'))