Spaces:

Em4e
/

chunk-based-text-editor

Sleeping

Em4e commited on Jun 9, 2025

Commit

acdf80d

verified ·

1 Parent(s): 259dab0

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -15,10 +15,7 @@ class WebpageContentProcessor:
     This class is responsible for the entire content processing pipeline.
     """
     def __init__(self):
-        # --- MODIFIED: Removed the converter instantiation from init ---
-        # The MarkItDown library is instantiated per-conversion.
         pass
-        # -----------------------------------------------------------
     def fetch_and_convert_to_markdown(self, url: str) -> str:
         """
@@ -45,11 +42,11 @@ class WebpageContentProcessor:
             if not content_container:
                 return "Error: Could not find the <body> of the webpage."
-            # --- MODIFIED: Corrected MarkItDown usage ---
-            # Instantiate the converter directly with the HTML content.
-            # The result object's 'text' attribute holds the markdown.
-            markdown_converter_instance = MarkItDown(str(content_container))
-            markdown_output = markdown_converter_instance.text
             # -----------------------------------------------
             # Post-processing to clean up the resulting Markdown
@@ -326,4 +323,4 @@ with tab2:
             st.rerun()
     st.subheader("Final Compiled Document")
-    st.text_area("Final Markdown Output", manager.get_final_markdown(), height=500, key="final_markdown")

     This class is responsible for the entire content processing pipeline.
     """
     def __init__(self):
         pass
     def fetch_and_convert_to_markdown(self, url: str) -> str:
         """
             if not content_container:
                 return "Error: Could not find the <body> of the webpage."
+            # --- MODIFIED: Corrected MarkItDown usage for the installed library version ---
+            # 1. Instantiate the converter object.
+            markdown_converter_instance = MarkItDown()
+            # 2. Call the .convert() method with the HTML content.
+            markdown_output = markdown_converter_instance.convert(str(content_container))
             # -----------------------------------------------
             # Post-processing to clean up the resulting Markdown
             st.rerun()
     st.subheader("Final Compiled Document")
+    st.text_area("Final Markdown Output", manager.get_final_markdown(), height=500, key="final_markdown")