app.py

import requests
from bs4 import BeautifulSoup
import streamlit as st
from urllib.parse import quote

@st.cache_resource
def display_glossary_entity(k):
    search_urls = {
        "🚀🌌ArXiv": lambda k: f"https://arxiv.org/search/?query={quote(k)}&searchtype=all&source=header",
        "📖Wiki": lambda k: f"https://en.wikipedia.org/wiki/{quote(k)}",
        "🔍Google": lambda k: f"https://www.google.com/search?q={quote(k)}",
        "🔎Bing": lambda k: f"https://www.bing.com/search?q={quote(k)}",
        "🎥YouTube": lambda k: f"https://www.youtube.com/results?search_query={quote(k)}",
        "🐦Twitter": lambda k: f"https://twitter.com/search?q={quote(k)}",
    }
    links_md = ' '.join([f"[{emoji}]({url(k)})" for emoji, url in search_urls.items()])
    st.markdown(f"**{k}** <small>{links_md}</small>", unsafe_allow_html=True)

def perform_search(search_query, search_engine):
    if search_engine == "Google":
        url = f"https://www.google.com/search?q={search_query}"
        response = requests.get(url)
        soup = BeautifulSoup(response.text, "html.parser")
        
        html_content = soup.prettify()
        text_content = soup.get_text()
        links = [link["href"] for link in soup.find_all("a", href=True)]
        images = [img["src"] for img in soup.find_all("img", src=True)]
        
        results = {
            "html": html_content,
            "text": text_content,
            "links": links,
            "images": images
        }
    elif search_engine == "Bing":
        url = f"https://www.bing.com/search?q={search_query}"
        response = requests.get(url)
        soup = BeautifulSoup(response.text, "html.parser")
        
        html_content = soup.prettify()
        text_content = soup.get_text()
        links = [link["href"] for link in soup.find_all("a", href=True)]
        images = [img["src"] for img in soup.find_all("img", src=True)]
        
        results = {
            "html": html_content,
            "text": text_content,
            "links": links,
            "images": images
        }
    elif search_engine == "Wikipedia":
        url = f"https://en.wikipedia.org/w/index.php?search={search_query}"
        response = requests.get(url)
        soup = BeautifulSoup(response.text, "html.parser")
        
        html_content = soup.prettify()
        text_content = soup.get_text()
        links = [link["href"] for link in soup.find_all("a", href=True)]
        images = [img["src"] for img in soup.find_all("img", src=True)]
        
        results = {
            "html": html_content,
            "text": text_content,
            "links": links,
            "images": images
        }
    elif search_engine == "Twitter":
        url = f"https://twitter.com/search?q={search_query}"
        response = requests.get(url)
        soup = BeautifulSoup(response.text, "html.parser")
        
        html_content = soup.prettify()
        text_content = soup.get_text()
        links = [link["href"] for link in soup.find_all("a", href=True)]
        images = [img["src"] for img in soup.find_all("img", src=True)]
        
        results = {
            "html": html_content,
            "text": text_content,
            "links": links,
            "images": images
        }
    
    return results

def main():
    st.set_page_config(page_title="Web Search App", page_icon=":mag:", layout="wide")
    
    st.title("Web Search App")
    st.write("Search Google, Bing, Wikipedia, and Twitter simultaneously!")
    
    search_query = st.text_input("Enter your search query")
    display_glossary_entity(search_query)
    
    col1, col2, col3, col4 = st.columns(4)
    
    with col1:
        st.header("Google Search Results")
        if st.button("Search Google"):
            google_results = perform_search(search_query, "Google")
            st.write("HTML Content:")
            st.code(google_results["html"], language="html")
            st.write("Text Content:")
            st.write(google_results["text"])
            st.write("Links:")
            for link in google_results["links"]:
                st.write(link)
            st.write("Images:")
            for image in google_results["images"]:
                st.image(image)
    
    with col2:
        st.header("Bing Search Results")
        if st.button("Search Bing"):
            bing_results = perform_search(search_query, "Bing")
            st.write("HTML Content:")
            st.code(bing_results["html"], language="html")
            st.write("Text Content:")
            st.write(bing_results["text"])
            st.write("Links:")
            for link in bing_results["links"]:
                st.write(link)
            st.write("Images:")
            for image in bing_results["images"]:
                st.image(image)
    
    with col3:
        st.header("Wikipedia Search Results")
        if st.button("Search Wikipedia"):
            wikipedia_results = perform_search(search_query, "Wikipedia")
            st.write("HTML Content:")
            st.code(wikipedia_results["html"], language="html")
            st.write("Text Content:")
            st.write(wikipedia_results["text"])
            st.write("Links:")
            for link in wikipedia_results["links"]:
                st.write(link)
            st.write("Images:")
            for image in wikipedia_results["images"]:
                st.image(image)
    
    with col4:
        st.header("Twitter Search Results")
        if st.button("Search Twitter"):
            twitter_results = perform_search(search_query, "Twitter")
            st.write("HTML Content:")
            st.code(twitter_results["html"], language="html")
            st.write("Text Content:")
            st.write(twitter_results["text"])
            st.write("Links:")
            for link in twitter_results["links"]:
                st.write(link)
            st.write("Images:")
            for image in twitter_results["images"]:
                st.image(image)

if __name__ == "__main__":
    main()