File size: 1,236 Bytes
7f5f166
 
 
 
 
 
6a96128
c2d57f1
 
 
 
 
 
 
 
 
 
 
 
 
6a96128
7f5f166
 
 
 
 
 
 
 
 
c2d57f1
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
import streamlit as st
import advertools as adv
import pandas as pd

def extract_headers(url):
    try:
        # Define the output file path
        output_file = "crawl_output.jl"

        # Perform the crawl
        adv.crawl(url, output_file=output_file, follow_links=True)

        # Load the crawl data
        crawl_df = pd.read_json(output_file, lines=True)

        # Extract headers from h1 to h6
        headers_columns = [col for col in crawl_df.columns if col.startswith('h')]
        headers = crawl_df[headers_columns].apply(lambda x: x.str.split('@@').explode()).dropna().reset_index(drop=True)

        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)
            if isinstance(headers, pd.DataFrame) and not headers.empty:
                st.write("Extracted Headers:")
                st.write(headers)
            else:
                st.error("No headers found or an error occurred.")
        else:
            st.error("Please enter a valid URL.")

if __name__ == "__main__":
    main()