Upload app.py with huggingface_hub

app.py

@@ -1,71 +1,59 @@
 
-# app.py
-# app.py
 # app.py
 import streamlit as st
+from googlesearch import search
 import requests
-from bs4 import BeautifulSoup
-import re
 
-def get_first_link(query):
+# Function to perform Google search and return the first link
+def google_search(query):
     try:
-        # Use a basic Google search URL (may not work indefinitely)
-        url = f"https://www.google.com/search?q={query.replace(' ', '+')}"
-        headers = {
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
-        }
-        response = requests.get(url, headers=headers)
-        response.raise_for_status()
-
-        # Parse the search results page
-        soup = BeautifulSoup(response.text, 'html.parser')
-        
-        # Find the first link in the search results
-        link_elements = soup.find_all('a', href=re.compile(r"\/url\?q="))
-        if link_elements:
-            first_link = re.search(r'/url\?q=(.*?)&', link_elements[0]['href']).group(1)
-            return first_link
-        else:
-            st.error("No links found in the search results.")
-            return None
+        # Perform the search and get an iterator of results
+        search_results = search(query, num_results=10)  # Get up to 10 results
+        first_link = next(search_results, None)  # Get the first result
+        return first_link
     except Exception as e:
-        st.error(f"Error fetching search results: {e}")
+        st.error(f"An error occurred: {e}")
         return None
 
-def download_webpage_content(url):
+# Function to fetch webpage content
+def fetch_webpage_content(url):
     try:
         response = requests.get(url)
-        response.raise_for_status()
-        soup = BeautifulSoup(response.text, 'html.parser')
-        return soup.prettify()
+        response.raise_for_status()  # Check if the request was successful
+        return response.text
     except Exception as e:
-        st.error(f"Error fetching webpage content: {e}")
+        st.error(f"Failed to fetch the webpage content: {e}")
         return None
 
-st.title("Webpage Content Downloader")
+# Streamlit app UI
+st.title("Search Link Finder")
 
-query = st.text_input("Enter your search query:")
+# Input field for search query
+query = st.text_input("Enter search query", "")
 
-if st.button("Fetch First Link and Download Content"):
+# Button to trigger search
+if st.button("Search"):
     if query:
-        with st.spinner("Fetching the first link..."):
-            first_link = get_first_link(query)
-            if first_link:
-                st.success(f"First Link Found: {first_link}")
-                with st.spinner("Downloading webpage content..."):
-                    webpage_content = download_webpage_content(first_link)
-                    if webpage_content:
-                        st.success("Content Downloaded!")
-                        st.download_button(
-                            label="Download Webpage Content",
-                            data=webpage_content,
-                            file_name="webpage_content.html",
-                            mime="text/html"
-                        )
-            else:
-                st.error("No links found for the query.")
+        first_link = google_search(query)
+        if first_link:
+            st.success(f"First link: [Click here]({first_link})")
+
+            # Fetch webpage content
+            webpage_content = fetch_webpage_content(first_link)
+
+            if webpage_content:
+                # Download button for the webpage content
+                st.download_button(
+                    label="Download Webpage Content",
+                    data=webpage_content,
+                    file_name="webpage_content.html",
+                    mime="text/html"
+                )
+        else:
+            st.warning("No results found")
     else:
-        st.error("Please enter a query.")
+        st.error("Please enter a query")
+