bruh

web2json/pipeline.py

@@ -27,16 +27,16 @@ class Pipeline:
         """
         # Step 1: Preprocess the content
         preprocessed_content = self.preprocessor.preprocess(content, is_url)
-        # print(f"Preprocessed content: {preprocessed_content[:100]}...")
-        # print('+'*80)
+        print(f"Preprocessed content: {preprocessed_content[:100]}...")
+        print('+'*80)
         # Step 2: Extract structured information using AI
         extracted_data = self.ai_extractor.extract(preprocessed_content, schema)
-        # print(f"Extracted data: {extracted_data[:100]}...")
-        # print('+'*80)
+        print(f"Extracted data: {extracted_data[:100]}...")
+        print('+'*80)
         # Step 3: Post-process the extracted data
         final_output = self.postprocessor.process(extracted_data)
-        # print(f"Final output: {final_output}")
-        # print('+'*80)
+        print(f"Final output: {final_output}")
+        print('+'*80)
         
         return final_output