Колдонуучу:KETC Parser for WikiMediaExport

Category Appending

def tokenize_pages(tree, output_image_dir, page_tag="page", title_tag="title", text_wrapper_tag="text"):

   body = tree.find("body")
   if body is None:
       return tree
       
   children = list(body)
   new_body_elements = []
   
   current_page = None
   current_revision = None
   current_text = None
   current_title_str = ""
   
   # Prompt the user ONCE for the whole document before looping through pages
   global_category = prompt_for_global_wiki_category()
   
   current_timestamp_str = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
   
   def finalize_current_page():
       nonlocal current_page, current_revision, current_text, current_title_str
       if current_page is not None:
           if current_text is not None and len(current_text) > 0:
               assign_captions_to_images(current_text)
               replace_images_with_medi

==

Бөлүмдүн аталышы

==

awiki_syntax(current_text, current_title_str, output_image_dir)

               inner_html_string = "".join(
                   html.tostring(child, encoding="unicode", method="html") 
                   for child in current_text
               )
               
               cleaned_html_string = process_hyphenations(inner_html_string)
               
               # Append the global category if the user entered one
               if global_category:
                   cleaned_html_string += global_category
               
               current_text.clear()
               fragment = html.fragment_fromstring(cleaned_html_string, create_parent="div")
               for child in list(fragment):
                   current_text.append(child)
               
               current_revision.append(current_text)
               
           new_body_elements.append(current_page)

   # ... rest of your loop structure remains identical