function for naming output file

app.py

@@ -2,6 +2,13 @@ import streamlit as st
 import os
 import time
 import json
+import re
+
+def clean_string_for_filename(s):
+    """Cleans a string to make it safe for use as a filename."""
+    s = re.sub(r"[^\w\s-]", "", s)  # Remove invalid characters
+    s = re.sub(r"\s+", "_", s)  # Replace spaces with underscores
+    return s.strip("_")
 
 def check_scraping_status(log_file="scraping_status.log"):
     try:
@@ -12,14 +19,19 @@ def check_scraping_status(log_file="scraping_status.log"):
     except FileNotFoundError:
         return "Scraping not run yet"  # Log file does not exist; assume scraping is ongoing
 
-def run_scraping(url):
+def run_scraping(url, depth_limit, pagecount_limit):
+    # Generate a safe filename based on the URL
+    identifier = clean_string_for_filename(url)
+    output_filename = f"output_{identifier}.json"
 
-    if os.path.exists("output.json"):
-        os.remove("output.json")
+    if os.path.exists(output_filename):
+        os.remove(output_filename)
 
-    os.popen(f"scrapy runspider homespider.py -a start_url={url} -a depth_limit={depth_limit} -a pagecount_limit={pagecount_limit} -o output.json")
+    # Run the scraping command
+    os.popen(f"scrapy runspider homespider.py -a start_url={url} -a depth_limit={depth_limit} -a pagecount_limit={pagecount_limit} -o {output_filename}")
 
-    st.success("Scraping started")
+    st.success(f"Scraping started. Output will be saved to {output_filename}.")
+    return output_filename
 
 # Streamlit interface
 st.title("Scraping")