Function api_web_dork

IntelOSINT.py:19653–19769

()

@app.route('/api/web_dork', methods=['POST'])
def api_web_dork():
    from bs4 import BeautifulSoup
    from playwright.sync_api import sync_playwright
    import urllib.parse
    
    query = request.json.get('query', '').strip()
    if not query:
        return jsonify({"results": []})
        
    results = []
    
    try:
        with sync_playwright() as p:
            browser = p.chromium.launch(headless=True, args=["--disable-blink-features=AutomationControlled"])
            context = browser.new_context(
                user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
                viewport={"width": 1280, "height": 720}
            )
            
            # Iniezione cookie per bypassare il pop-up di consenso europeo di Google
            context.add_cookies([{"name": "CONSENT", "value": "YES+cb.20230501-14-p0.it+FX+874", "domain": ".google.com", "path": "/"}])
            page = context.new_page()
            
            # --- GOOGLE CSE ---
            try:
                page.goto(f"https://cse.google.com/cse?cx=d28c23ec014bd4cca&q={urllib.parse.quote(query)}", wait_until="domcontentloaded", timeout=15000)
                
                for _ in range(3):
                    try: page.wait_for_selector('.gsc-webResult', timeout=8000)
                    except: pass
                    
                    soup = BeautifulSoup(page.content(), 'html.parser')
                    for res in soup.find_all('div', class_='gsc-webResult'):
                        a = res.find('a', class_='gs-title')
                        if a and a.get('href'):
                            title = a.text.strip()
                            url_node = a.get('data-ctorig') or a.get('href')
                            if url_node and url_node.startswith('http'):
                                snippet_div = res.find('div', class_='gs-snippet')
                                snippet = snippet_div.text.strip() if snippet_div else ""
                                if title:
                                    results.append({
                                        "engine": "Google",
                                        "title": title,
                                        "snippet": snippet,
                                        "url": url_node
                                    })
                    try:
                        has_next = page.evaluate('''() => {
                            let curr = document.querySelector('.gsc-cursor-current-page');
                            if(curr && curr.nextSibling) {
                                curr.nextSibling.click();
                                return true;
                            }
                            return false;
                        }''')
                        if has_next:
                            page.wait_for_timeout(2000)