Upload data_prep.py

data_prep.py

@@ -9,7 +9,7 @@ def extract_div_contents_from_url(url):
         return pd.DataFrame(columns=['title', 'text_url', 'deletion_discussion', 'label', 'confirmation', 'discussion', 'verdict'])
 
     soup = BeautifulSoup(response.content, 'html.parser')
-    div_classes = ['boilerplate afd vfd xfd-closed', 'boilerplate afd vfd xfd-closed archived mw-archivedtalk']
+    div_classes = ["mw-heading mw-heading3",'boilerplate afd vfd xfd-closed', 'boilerplate afd vfd xfd-closed archived mw-archivedtalk']
     divs = []
     for div_class in div_classes:
         divs.extend(soup.find_all('div', class_=div_class))