Fix: descriptionHtml2Text function to work if string not starting with "<div>"

archivist/sites/furaffinity/templatetags/custom_filters.py

@@ -7,6 +7,23 @@ from bs4 import BeautifulSoup
 
 register = template.Library()
 
+
+def is_html(string):
+    '''
+    Check if string is HTML
+    '''
+    soup = BeautifulSoup(string, "html.parser")
+    # Remove leading and trailing white space
+    stripped_string = string.strip()
+    stripped_soup = str(soup).strip()
+    # If the string remained the same after parsing with BeautifulSoup, it's probably not HTML
+    if stripped_string == stripped_soup:
+        return False
+    # If the string changed when parsed by BeautifulSoup, it's probably HTML
+    else:
+        return True
+
+
 @register.filter
 def is_image(file_url):
     image_extensions = ['.png', '.jpg', '.jpeg', '.gif', '.webp']
@@ -26,14 +43,13 @@ def is_pdf(file_url):
 
 @register.filter
 def descriptionHtml2Text(description):
-    if description.startswith("<div"):
+    if is_html(description):
         cleanHtml = nh3.clean(description)
         soup = BeautifulSoup(cleanHtml, "html.parser")
-        descriptionText = soup.get_text()
+        text = soup.get_text()
+        return text
     else:
-        descriptionText = description
-    
-    return descriptionText
+        return description
 
 
 @register.filter