--- ValBot/Python/check_interwiki_links.py	2023/08/15 02:03:16	1185
+++ ValBot/Python/check_interwiki_links.py	2024/09/16 23:08:26	1192
@@ -62,15 +62,33 @@ def find_section(page_text, page_name, p
    # Read linked page to see if it really has this anchor link
    soup = BeautifulSoup(page_text, 'html.parser')
    found_section = False
-   for span_tag in soup.findAll('span'): # search for span with ID matching the section name
-      span_name = span_tag.get('id', None)
-      if span_name == anchor_name:
+   for the_tag in soup.findAll('span'): # search for span with ID matching the section name
+      tag_name = the_tag.get('id', None)
+      if tag_name == anchor_name:
          found_section = True
          break
    if found_section == False:
-      for span_tag in soup.findAll('div'): # search for div with ID matching the section name
-         span_name = span_tag.get('id', None)
-         if span_name == anchor_name:
+      for the_tag in soup.findAll('div'): # search for div with ID matching the section name
+         tag_name = the_tag.get('id', None)
+         if tag_name == anchor_name:
+            found_section = True
+            break
+   if found_section == False:
+      for the_tag in soup.findAll('h2'): # search for h2 with ID matching the section name
+         tag_name = the_tag.get('id', None)
+         if tag_name == anchor_name:
+            found_section = True
+            break
+   if found_section == False:
+      for the_tag in soup.findAll('h3'): # search for h3 with ID matching the section name
+         tag_name = the_tag.get('id', None)
+         if tag_name == anchor_name:
+            found_section = True
+            break
+   if found_section == False:
+      for the_tag in soup.findAll('h4'): # search for h4 with ID matching the section name
+         tag_name = the_tag.get('id', None)
+         if tag_name == anchor_name:
             found_section = True
             break
    if found_section == False:
@@ -161,7 +179,7 @@ def scan_for_interwiki_links(page_text,
 
    for prefix in interwiki_prefixes:
       # Isolate strings that start with "[[prefix:" and end with "|" or "]"
-      iw_link = "\[\[" + prefix + ":[^|\]]*(\||\])"
+      iw_link = r"\[\[" + prefix + r":[^|\]]*(\||\])"
       for match in re.finditer(iw_link, page_text):
          # Extract just the page title from this regex match
          s = match.start() + 2 + len(prefix) + 1