Create app.py

app.py

@@ -0,0 +1,34 @@
+import streamlit as st
+import advertools as adv
+import pandas as pd
+
+def extract_headers(url):
+    try:
+        # Crawl the webpage
+        crawl_data = adv.crawl(url, follow_links=False)
+
+        # Extract HTML content
+        html_content = crawl_data['body'][0]
+
+        # Use pandas to parse the headers
+        headers = pd.read_html(html_content, header=0)[0]
+        headers = headers.loc[:, headers.columns.str.contains('h1|h2|h3|h4|h5|h6', case=False)]
+        
+        return headers
+    except Exception as e:
+        return str(e)
+
+def main():
+    st.title("Web Page Header Extractor")
+
+    url = st.text_input("Enter the URL of the web page:")
+    if st.button("Extract Headers"):
+        if url:
+            headers = extract_headers(url)
+            st.write("Extracted Headers:")
+            st.write(headers)
+        else:
+            st.error("Please enter a valid URL.")
+
+if __name__ == "__main__":
+    main()