Add output path

main.py

@@ -3,14 +3,17 @@ from bs4 import BeautifulSoup
 from urllib.parse import urlparse, urlunparse
 import pandas as pd
 
-headers = {'User-Agent': 'myprogram/1.0'}
+def scrape_headings(url, output_path):
-def scrape_headings(url):
     try:
         # Check if the URL has a scheme (http/https), and add one if missing
         parsed_url = urlparse(url)
         if not parsed_url.scheme:
             url = urlunparse(('http',) + parsed_url[1:])
 
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
+        }
+
         # Send an HTTP GET request to the specified URL
         response = requests.get(url, headers=headers)
 
@@ -22,10 +25,13 @@ def scrape_headings(url):
             # Find all the heading elements (h1, h2, h3, etc.)
             headings = soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6'])
 
-            # Extract and put to csv the result of headings
+            # Extract the result of headings with their types
-            heading_list = [heading.text for heading in headings]
+            heading_data = [{"Heading Type": heading.name, "Text": heading.text.strip()} for heading in headings]
-            df = pd.DataFrame(heading_list)
+
-            df.to_csv('output.csv')
+            # Convert to DataFrame and save to CSV
+            df = pd.DataFrame(heading_data)
+            df.to_csv(output_path, index=False)
+            return heading_data
 
         else:
             print(f"Failed to retrieve content from {url}. Status code: {response.status_code}")
@@ -34,21 +40,19 @@ def scrape_headings(url):
         print(f"An error occurred: {str(e)}")
 
 
-# To check if to do another search for URL
-def main_start():
 
-    if __name__ == "__main__":
+def main():
     url = input("Enter the URL: ")
-        scrape_headings(url)
+    output_path = 'output.csv'
+    scrape_headings(url, output_path)
     # df = pd.DataFrame(scrape_headings(url))
     search_again = input("Do you want to search again? y/n:").lower()
     if search_again == 'y':
         # df.to_csv('output.csv')
-            main_start()
+        main()
     else:
         # df.to_csv('output.csv')
         exit()
 
-
+if __name__ == "__main__":
-main_start()
+    main()
-