File size: 3,252 Bytes
e67d52b
 
 
 
04e30ca
0d9ed80
04e30ca
73a33e7
0d9ed80
04e30ca
 
e67d52b
0d9ed80
73a33e7
e67d52b
0d9ed80
73a33e7
 
0d9ed80
 
73a33e7
 
0d9ed80
73a33e7
e67d52b
0d9b82c
04e30ca
0d9b82c
 
 
 
 
 
 
 
c2d6566
0d9b82c
 
 
e67d52b
0d9ed80
73a33e7
04e30ca
0d9ed80
73a33e7
e67d52b
0d9ed80
73a33e7
 
0d9ed80
e67d52b
 
04e30ca
 
e6312eb
e67d52b
 
 
 
 
 
04e30ca
 
 
ca30905
 
 
04e30ca
 
 
 
 
ca30905
e67d52b
04e30ca
ca30905
04e30ca
e67d52b
 
73a33e7
e67d52b
0d9ed80
e67d52b
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
import streamlit as st
from googlesearch import search
import requests
from bs4 import BeautifulSoup
import chunk  # Import the chunking function from chunk.py

# Function to perform Google search and return the first link
def google_search(query):
    try:
        search_results = search(query, num_results=2)  # Get first two results
        first_two_links = [next(search_results, None), next(search_results, None)]
        return first_two_links
    except Exception as e:
        st.error(f"An error occurred: {e}")
        return None

# Function to fetch webpage content
def fetch_webpage_content(url):
    try:
        response = requests.get(url)
        response.raise_for_status()  # Check if the request was successful
        return response.text
    except Exception as e:
        st.error(f"Failed to fetch the webpage content: {e}")
        return None

# Function to scrape text from webpage content using Beautiful Soup
def scrape_text(webpage_content):
    try:
        soup = BeautifulSoup(webpage_content, 'html.parser')
        for script in soup(["script", "style"]):
            script.decompose()
        text = soup.get_text()
        lines = (line.strip() for line in text.splitlines())
        chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
        text = '\n'.join(chunk for chunk in chunks if chunk)
        return text
    except Exception as e:
        st.error(f"Failed to scrape text from webpage content: {e}")
        return None

# Streamlit app UI
st.title("Search and Chunk Webpage Content")

# Input field for search query
query = st.text_input("Enter search query", "")

# Button to trigger search
if st.button("Search"):
    if query:
        first_two_links = google_search(query)
        if first_two_links:
            for i, link in enumerate(first_two_links, 1):
                st.success(f"Link {i}: [Click here]({link})")

                # Fetch webpage content
                webpage_content = fetch_webpage_content(link)
                if webpage_content:
                    # Scrape text from webpage content
                    scraped_text = scrape_text(webpage_content)
                    if scraped_text:
                        # Chunk the scraped text using chunk.py
                        chunked_text = chunk.chunk_text(scraped_text)

                        # Save chunked data to a .txt file for later use
                        with open("chunked_data.txt", "w") as f:
                            f.write("\n---\n".join(chunked_text))  # Separate chunks by a line break and delimiter

                        st.write(f"Chunked Data for Link {i}:")
                        for chunk_part in chunked_text:
                            st.write(chunk_part)

                        # Provide download button for the chunked text
                        st.download_button(
                            label="Download Chunked Webpage Content",
                            data="\n---\n".join(chunked_text),
                            file_name="chunked_webpage_content.txt",
                            mime="text/plain"
                        )
        else:
            st.warning("No results found")
    else:
        st.error("Please enter a query")