File size: 4,020 Bytes
3cb2323 |
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 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
import requests
from bs4 import BeautifulSoup
import streamlit as st
# Custom CSS to mimic Google's interface
def load_css():
st.markdown("""
<style>
body {
font-family: Arial, sans-serif;
background-color: #f8f9fa;
}
.search-bar {
width: 50%;
margin: 20px auto;
display: flex;
align-items: center;
border: 1px solid #dfe1e5;
border-radius: 24px;
padding: 10px;
background-color: #fff;
box-shadow: 0px 2px 5px rgba(0, 0, 0, 0.1);
}
.search-bar input {
flex: 1;
border: none;
outline: none;
font-size: 16px;
padding: 5px;
}
.search-bar button {
background: none;
border: none;
color: #4285f4;
font-size: 18px;
cursor: pointer;
}
.search-result {
margin: 20px auto;
width: 80%;
padding: 15px;
border: 1px solid #dfe1e5;
border-radius: 8px;
background-color: #fff;
box-shadow: 0px 2px 5px rgba(0, 0, 0, 0.1);
}
.search-result h3 {
margin: 0;
color: #1a0dab;
font-size: 18px;
}
.search-result p {
margin: 5px 0;
color: #545454;
font-size: 14px;
}
.captcha-warning {
text-align: center;
margin-top: 50px;
}
.captcha-warning h3 {
color: #d93025;
}
</style>
""", unsafe_allow_html=True)
# Function to perform a Google search
def search_google(query, proxy=None):
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'
}
url = f'https://www.google.com/search?q={query.replace(" ", "+")}&hl=en'
proxies = {"http": proxy, "https": proxy} if proxy else None
response = requests.get(url, headers=headers, proxies=proxies, timeout=10)
if "detected unusual traffic" in response.text.lower(): # Detect CAPTCHA
return None, True
return response.text, False
# Function to parse Google search results
def parse_search_results(html_content):
soup = BeautifulSoup(html_content, 'html.parser')
results = []
for g in soup.find_all('div', class_='tF2Cxc'):
title = g.find('h3').text if g.find('h3') else "No title"
link = g.find('a')['href'] if g.find('a') else "No link"
snippet = g.find('span', class_='aCOpRe').text if g.find('span', class_='aCOpRe') else "No snippet"
results.append({'title': title, 'link': link, 'snippet': snippet})
return results
# Streamlit App
def main():
st.set_page_config(page_title="Google Search Clone", layout="centered")
load_css()
st.markdown('<div class="search-bar">', unsafe_allow_html=True)
query = st.text_input("Enter your search query:", label_visibility="collapsed")
search_button = st.button("Search")
st.markdown('</div>', unsafe_allow_html=True)
if search_button and query.strip():
with st.spinner("Searching..."):
html_content, captcha_detected = search_google(query)
if captcha_detected:
st.markdown("""
<div class="captcha-warning">
<h3>CAPTCHA Detected</h3>
<p>Google has detected unusual traffic from this application. Please solve the CAPTCHA manually or try again later.</p>
</div>
""", unsafe_allow_html=True)
return
if html_content:
search_results = parse_search_results(html_content)
for result in search_results:
st.markdown(f"""
<div class="search-result">
<h3><a href="{result['link']}" target="_blank">{result['title']}</a></h3>
<p>{result['snippet']}</p>
</div>
""", unsafe_allow_html=True)
if __name__ == "__main__":
main() |