Update app.py

app.py

@@ -12,11 +12,6 @@ import time
 import shutil
 from pathlib import Path
 import json
-import logging
-
-# Set up logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
 
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
@@ -53,7 +48,6 @@ def run_GOT(pdf_file):
     
     images = pdf_to_images(pdf_path)
     results = []
-    html_content = ""
     
     try:
         for i, image in enumerate(images):
@@ -62,40 +56,29 @@ def run_GOT(pdf_file):
             
             result_path = os.path.join(RESULTS_FOLDER, f"{unique_id}_page_{i+1}.html")
             
-            logger.info(f"Processing page {i+1}...")
             res = model.chat_crop(tokenizer, image_path, ocr_type='format', render=True, save_render_file=result_path)
             
             # Read the rendered HTML content
-            if os.path.exists(result_path):
-                with open(result_path, 'r', encoding='utf-8') as f:
-                    page_html_content = f.read()
-                logger.info(f"HTML content for page {i+1} read successfully.")
-            else:
-                logger.error(f"HTML file for page {i+1} not found at {result_path}.")
-                page_html_content = ""
+            with open(result_path, 'r') as f:
+                html_content = f.read()
             
             results.append({
                 "page_number": i + 1,
                 "text": res,
-                "html": page_html_content
+                "html": html_content
             })
             
-            html_content += f"<h2>Page {i + 1}</h2>"
-            html_content += page_html_content + "<br><hr><br>"  # Add a separator between pages
-            
             if os.path.exists(image_path):
                 os.remove(image_path)
             if os.path.exists(result_path):
                 os.remove(result_path)
     except Exception as e:
-        logger.error(f"Error occurred: {str(e)}")
         return f"Error: {str(e)}", None
     finally:
         if os.path.exists(pdf_path):
             os.remove(pdf_path)
     
-    print(html_content)  # Debug: Check the content of html_content
-    return json.dumps(results, indent=4), html_content
+    return json.dumps(results, indent=4)
 
 def cleanup_old_files():
     current_time = time.time()
@@ -111,13 +94,12 @@ with gr.Blocks() as demo:
             submit_button = gr.Button("Submit")
         
         with gr.Column():
-            ocr_result = gr.JSON(label="GOT output (JSON)")
-            html_result = gr.HTML(label="GOT output (HTML)", sanitize=False)
-    
+            ocr_result = gr.JSON(label="GOT output")
+
     submit_button.click(
         run_GOT,
         inputs=[pdf_input],
-        outputs=[ocr_result, html_result]
+        outputs=[ocr_result]
     )
 
 if __name__ == "__main__":