Update app.py

app to save chunked data

app.py

@@ -2,19 +2,14 @@ import streamlit as st
 from googlesearch import search
 import requests
 from bs4 import BeautifulSoup
-import chunk  # Import the chunking functionality from app2.py
+import chunk  # Import the chunking function from chunk.py
+import json
 
-# Function to perform Google search and return the first two links
+# Function to perform Google search and return the first link
 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
+        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}")
@@ -30,19 +25,15 @@ def fetch_webpage_content(url):
         st.error(f"Failed to fetch the webpage content: {e}")
         return None
 
-# Function to scrape text from webpage content using BeautifulSoup
+# Function to scrape text from webpage content using Beautiful Soup
 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:
@@ -50,7 +41,7 @@ def scrape_text(webpage_content):
         return None
 
 # Streamlit app UI
-st.title("Search Link Finder")
+st.title("Search and Chunk Webpage Content")
 
 # Input field for search query
 query = st.text_input("Enter search query", "")
@@ -60,8 +51,8 @@ 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})")
+            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)
@@ -69,16 +60,21 @@ if st.button("Search"):
                     # 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
+                        # Chunk the scraped text using chunk.py
+                        chunked_text = chunk.chunk_text(scraped_text)
+
+                        # Save chunked data to a file for later use
+                        with open("chunked_data.json", "w") as f:
+                            json.dump(chunked_text, f)
+
+                        st.write(f"Chunked Data for Link {i}:")
+                        for chunk_part in chunked_text:
+                            st.write(chunk_part)
+
                         st.download_button(
-                            label=f"Download Full Webpage Content from Link {i+1}",
-                            data=scraped_text,
-                            file_name=f"webpage_content_{i+1}.txt",
+                            label="Download Chunked Webpage Content",
+                            data="\n".join(chunked_text),
+                            file_name="chunked_webpage_content.txt",
                             mime="text/plain"
                         )
         else: