Parser openbare proxy van Google Zoeken (gratis). Python

pip install beautifulsoup4 google

from googlesearch import search
from bs4 import BeautifulSoup
import requests

def fetch_proxies():
    proxies = []
    # Perform a Google search for public proxy lists
    query = "public proxy list"
    for url in search(query, num=5, stop=5, pause=2):
        # Fetch the HTML content of the search result
        try:
            response = requests.get(url, timeout=10)
            if response.status_code == 200:
                html_content = response.text
                # Parse the HTML using BeautifulSoup
                soup = BeautifulSoup(html_content, 'html.parser')
                # Find proxy IP addresses and ports
                for row in soup.find_all('tr'):
                    cols = row.find_all('td')
                    if len(cols) >= 2:
                        proxy = cols[0].text.strip() + ':' + cols[1].text.strip()
                        proxies.append(proxy)
        except Exception as e:
            print(f"Error fetching proxies from {url}: {e}")
    return proxies

if __name__ == "__main__":
    proxies = fetch_proxies()
    for proxy in proxies:
        print(proxy)