File size: 3,290 Bytes
e67d52b
 
 
 
e6312eb
0d9ed80
e67d52b
73a33e7
0d9ed80
084f54d
73a33e7
e67d52b
 
 
 
 
 
 
0d9ed80
73a33e7
e67d52b
0d9ed80
73a33e7
 
0d9ed80
 
73a33e7
 
0d9ed80
73a33e7
e67d52b
0d9b82c
e6312eb
0d9b82c
 
 
 
 
 
 
e6312eb
0d9b82c
 
 
 
c2d6566
0d9b82c
 
 
e67d52b
0d9ed80
73a33e7
e67d52b
0d9ed80
73a33e7
e67d52b
0d9ed80
73a33e7
 
0d9ed80
e67d52b
 
 
 
e6312eb
e67d52b
 
 
 
 
 
e6312eb
 
 
 
 
 
e67d52b
e6312eb
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
85
86
87
88
import streamlit as st
from googlesearch import search
import requests
from bs4 import BeautifulSoup
import chunk  # Import the chunking functionality from app2.py

# Function to perform Google search and return the first two links
def google_search(query):
    try:
        query = query + "/t site:https://medium.com/"
        search_results = search(query, num_results=10)  # Get up to 10 results
        first_two_links = []
        for i, link in enumerate(search_results):
            if i < 2:
                first_two_links.append(link)
            else:
                break
        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 BeautifulSoup
def scrape_text(webpage_content):
    try:
        soup = BeautifulSoup(webpage_content, 'html.parser')
        # Remove all script and style elements
        for script in soup(["script", "style"]):
            script.decompose()
        text = soup.get_text()
        # Break the text into lines and remove leading/trailing spaces
        lines = (line.strip() for line in text.splitlines())
        # Break multi-headlines into a line each
        chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
        # Drop blank lines
        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 Link Finder")

# 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):
                st.success(f"Link {i+1}: [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:
                        st.write(f"Scraped Content from Link {i+1} (Chunked):")
                        
                        # Call the chunking function from app2.py
                        chunk.display_chunks(scraped_text)
                        
                        # Option to download the entire scraped content
                        st.download_button(
                            label=f"Download Full Webpage Content from Link {i+1}",
                            data=scraped_text,
                            file_name=f"webpage_content_{i+1}.txt",
                            mime="text/plain"
                        )
        else:
            st.warning("No results found")
    else:
        st.error("Please enter a query")