Update app.py

app.py

@@ -2,6 +2,7 @@
 import gradio as gr
 import pandas as pd
 import numpy as np
+import io
 import json
 import time
 import random
@@ -24,49 +25,47 @@ class WebScrapingSimulator:
             "https://python.org": "OTHER"
         }
 
-    def simulate_scraping(self, urls_text, progress=gr.Progress()):
-        """Simulate the web scraping and classification process"""
-        if not urls_text.strip():
-            return "Please enter at least one URL", "", ""
-
-        urls = [url.strip() for url in urls_text.split('\n') if url.strip()]
-        if not urls:
-            return "Please enter valid URLs", "", ""
-
-        results = {}
-        progress_bar = progress.tqdm(urls, desc="Processing URLs")
-
-        for url in progress_bar:
-            time.sleep(1)  # Simulate processing time
-            # Use demo results or random classification
-            if url in self.demo_results:
-                classification = self.demo_results[url]
-            else:
-                classification = random.choice(["OTHER", "NEWS/BLOG", "E-COMMERCE"])
-
-            results[url] = {
-                "url": url,
-                "classification": classification,
-                "confidence": round(random.uniform(0.75, 0.99), 2),
-                "processed_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-            }
-
-            # progress_bar.set_description(f"Processed {url}")
-
-        # Format results for display
-        results_text = "Classification Results:\n\n"
-        for url, data in results.items():
-            results_text += f"URL: {url}\n"
-            results_text += f"Classification: {data['classification']}\n"
-            results_text += f"Confidence: {data['confidence']}\n"
-            results_text += f"Processed: {data['processed_at']}\n"
-            results_text += "-" * 50 + "\n"
-
-        # Create downloadable JSON
-        json_results = json.dumps(results, indent=2)
-
-        return results_text, json_results, f"Processed {len(results)} URLs successfully!"
 
+def simulate_scraping(self, urls_text, progress=gr.Progress()):
+    if not urls_text.strip():
+        return "Please enter at least one URL", None, ""
+
+    urls = [url.strip() for url in urls_text.split('\n') if url.strip()]
+    if not urls:
+        return "Please enter valid URLs", None, ""
+
+    results = {}
+    progress_bar = progress.tqdm(urls, desc="Processing URLs")
+
+    for url in progress_bar:
+        time.sleep(1)
+        if url in self.demo_results:
+            classification = self.demo_results[url]
+        else:
+            classification = random.choice(["OTHER", "NEWS/BLOG", "E-COMMERCE"])
+
+        results[url] = {
+            "url": url,
+            "classification": classification,
+            "confidence": round(random.uniform(0.75, 0.99), 2),
+            "processed_at": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        }
+
+    # Format results for display
+    results_text = "Classification Results:\n\n"
+    for url, data in results.items():
+        results_text += f"URL: {url}\n"
+        results_text += f"Classification: {data['classification']}\n"
+        results_text += f"Confidence: {data['confidence']}\n"
+        results_text += f"Processed: {data['processed_at']}\n"
+        results_text += "-" * 50 + "\n"
+
+    # ✅ Create in-memory JSON file for download
+    json_bytes = json.dumps(results, indent=2).encode('utf-8')
+    file_obj = io.BytesIO(json_bytes)
+    file_obj.name = "scraping_results.json"  # optional but helpful
+
+    return results_text, file_obj, f"Processed {len(results)} URLs successfully!"
 # Computer Vision simulator
 @spaces.GPU
 def simulate_cv_processing(image, model_type):