有时候客户突然扔过来一个扫描报告，里面都是一些要处理外链，但是报告又没有明确指出出现在哪个页面或者JS，让人抓急。

在一个有python环境的Llinux（Windows也可以，这里以Linux举例）

1.准备环境

pip3 install requests bs4 beautifulsoup4 --break-system-packages

2.执行脚本

Linux复制代码，生成site_scanner.py

python3 site_scanner.py

MAX_THREADS 是最大线程

MAX_DEPTH是最大深度

BASE_URL是要扫描的网址

扫完之后会在当前目录下生成scan_result.txt

cat << 'EOF' > site_scanner.py
# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse, urljoin
from concurrent.futures import ThreadPoolExecutor
import re
import urllib3
# Disable SSL warnings
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
# --- Configuration ---
BASE_URL = "这里输入网址" 
MAX_THREADS = 50                 # Optimized for N100
MAX_DEPTH = 3                    
# ---------------------
TARGET_DOMAIN = urlparse(BASE_URL).netloc
visited_urls = set()      
external_found = set()    
scanned_assets = set()    
URL_PATTERN = re.compile(r'https?://[^\s\'"<>]+')
def analyze_js(js_url):
    if js_url in scanned_assets:
        return
    scanned_assets.add(js_url)
    try:
        print(f"  [+] Analyzing JS: {js_url}")
        res = requests.get(js_url, timeout=3, verify=False)
        found = URL_PATTERN.findall(res.text)
        for link in found:
            link_domain = urlparse(link).netloc
            if link_domain and TARGET_DOMAIN not in link_domain:
                if not any(x in link for x in ['w3.org', 'schema.org']):
                    external_found.add(link)
    except:
        pass
def scan_page(url, depth=1):
    if depth > MAX_DEPTH or url in visited_urls:
        return
    # Check if it's internal domain
    parsed_url = urlparse(url)
    if TARGET_DOMAIN not in parsed_url.netloc and parsed_url.netloc != "":
        external_found.add(url)
        return
    visited_urls.add(url)
    try:
        print(f"[*] Scanning ({depth}/{MAX_DEPTH}): {url}")
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
        res = requests.get(url, timeout=5, headers=headers, verify=False)
        soup = BeautifulSoup(res.text, 'html.parser')
        # 1. Collect Links & JS
        local_links = []
        for a in soup.find_all('a', href=True):
            full_url = urljoin(url, a['href'])
            local_links.append(full_url)
        for script in soup.find_all('script', src=True):
            js_url = urljoin(url, script['src'])
            analyze_js(js_url)
        # 2. Multi-threaded crawling
        if depth < MAX_DEPTH:
            with ThreadPoolExecutor(max_workers=MAX_THREADS) as executor:
                for link in local_links:
                    executor.submit(scan_page, link, depth + 1)
    except Exception as e:
        pass
if __name__ == "__main__":
    print(f"Starting Fast Scanner on N100 (Threads: {MAX_THREADS})")
    print(f"Target: {BASE_URL}\n")
    scan_page(BASE_URL)
    print("\n" + "="*50)
    print(f"Scan Finished!")
    print(f"Pages visited: {len(visited_urls)}")
    print(f"JS analyzed: {len(scanned_assets)}")
    print(f"External links found: {len(external_found)}")
    print("="*50)
    with open("scan_result.txt", "w") as f:
        for link in sorted(external_found):
            print(link)
            f.write(link + "\n")
    print(f"\nResults saved to scan_result.txt")
EOF