app.py

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")