一款好用的js敏感信息收集脚本分享

0x00 作用：

用于输入网址后获取该页面所有的js脚本，根据自定义的关键字匹配对应的value，实现js信息收集的便利性与灵活性。

 

0x01 环境：

python3

 

0x02 脚本：

import requests
import re
import time
import random
from urllib.parse import urljoin, urlparse
from bs4 import BeautifulSoup
from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill


class JSAnalyzerPro:
    def __init__(self):
        self.session = requests.Session()
        self.headers = {
            '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',
            'Accept-Encoding': 'gzip, deflate'
        }
        self.visited = set()
        self.domain = ""
        self.keywords = []
        self.max_depth = 2
        self.results = []

    def configure(self, target_url, keywords):
        """配置参数并验证有效性"""
        try:
            # 自动补全URL协议
            if not target_url.startswith(('http://', 'https://')):
                target_url = f'https://{target_url}'

            parsed = urlparse(target_url)
            self.domain = parsed.netloc

            # 关键字处理（自动纠错+去重）
            self.keywords = list({k.strip().lower().replace('secert', 'secret')
                                  for k in keywords.split(',')})

            # 验证目标可达性
            test_res = self.session.head(target_url, timeout=10)
            test_res.raise_for_status()

            print(f"[系统检测] 成功连接到目标网站: {target_url}")

        except Exception as e:
            raise ConnectionError(f"配置失败: {str(e)}")

    def safe_extract(self, content):
        """增强型键值提取（带调试输出）"""
        try:
            pattern = r'''
            (["']?)\b({})\b(["']?)   # 键
            \s*[:=]\s*               # 分隔符
            (["']?)(.*?)(["']?)      # 值
            (?=\s*[,;}}\n])          # 终止符
            '''.format('|'.join(map(re.escape, self.keywords)))

            matches = re.findall(
                pattern,
                content,
                flags=re.IGNORECASE | re.VERBOSE | re.DOTALL
            )

            processed = []
            for q1, key, q2, q3, value, q4 in matches:
                clean_key = key.strip('\'"')
                clean_value = value.strip('\'"')
                if clean_key.lower() in self.keywords:
                    print(f"[数据提取] 发现匹配: {clean_key} = {clean_value[:30]}...")  # 调试输出
                    processed.append((clean_key, clean_value))
            return processed

        except Exception as e:
            print(f"[警告] 正则解析异常: {str(e)}")
            return []

    def crawl_js(self, url, depth=0):
        """带调试日志的递归爬取"""
        if depth > self.max_depth or url in self.visited:
            return

        print(f"\n[深度 {depth}] 分析: {url}")
        self.visited.add(url)

        try:
            # 请求参数优化
            time.sleep(random.uniform(1.5, 3.0))  # 更长的随机延迟
            verify_ssl = False  # 临时关闭SSL验证

            if url.startswith('http'):
                response = self.session.get(
                    url,
                    timeout=20,
                    verify=verify_ssl,
                    allow_redirects=True
                )
                response.encoding = 'utf-8'  # 强制UTF-8编码
                content = response.text
                print(f"[网络请求] 成功获取内容，长度: {len(content)}字节")
            else:
                content = url

            # 执行提取
            matches = self.safe_extract(content)
            for key, value in matches:
                self.results.append({
                    'source': url,
                    'keyword': key,
                    'value': value,
                    'depth': depth
                })

            # 深度控制
            if depth < self.max_depth:
                print(f"[深度控制] 进入第{depth + 1}层分析...")
                soup = BeautifulSoup(content, 'html.parser') if depth == 0 else None
                for js_url in self.find_js_links(content, soup, url):
                    self.crawl_js(js_url, depth + 1)

        except Exception as e:
            print(f"[严重错误] 处理 {url} 失败: {str(e)}")

    def find_js_links(self, content, soup, base_url):
        """改进的链接发现方法"""
        links = set()

        # 从HTML标签解析
        if soup:
            for tag in soup.find_all(['script', 'link']):
                src = None
                if tag.name == 'script' and tag.has_attr('src'):
                    src = tag['src']
                elif tag.name == 'link' and 'script' in tag.get('as', ''):
                    src = tag.get('href', '')

                if src:
                    absolute_url = urljoin(base_url, src.split('?')[0])
                    if self.is_valid_url(absolute_url):
                        links.add(absolute_url)

        # 从JS代码解析
        patterns = [
            r'\.src\s*=\s*["\'](.*?)["\']',
            r'load\(["\'](.*?)["\']\)',
            r'fetch\(["\'](.*?)["\']\)'
        ]
        for pattern in patterns:
            for match in re.finditer(pattern, content, re.IGNORECASE):
                absolute_url = urljoin(base_url, match.group(1))
                if self.is_valid_url(absolute_url):
                    links.add(absolute_url)

        print(f"[链接发现] 找到{len(links)}个新链接")
        return [link for link in links if link not in self.visited]

    def is_valid_url(self, url):
        """增强型URL验证"""
        parsed = urlparse(url)
        # 允许相对路径和同域名资源
        return not parsed.netloc or parsed.netloc == self.domain

    def generate_report(self):
        """带验证的报告生成"""
        if not self.results:
            print("[警告] 未发现任何匹配数据，不生成空报告")
            return

        try:
            wb = Workbook()
            ws = wb.active
            ws.title = "安全扫描报告"

            # 标题行
            headers = ["来源URL", "关键词", "提取值", "数据深度", "风险等级"]
            ws.append(headers)

            # 设置标题样式
            header_fill = PatternFill(start_color="2F5496", fill_type="solid")
            for col in ws.iter_cols(min_row=1, max_row=1):
                for cell in col:
                    cell.font = Font(bold=True, color="FFFFFF")
                    cell.fill = header_fill

            # 填充数据
            risk_keywords = {'password', 'secret', 'key', 'token'}
            for item in self.results:
                risk = "高危" if item['keyword'].lower() in risk_keywords else "中危"
                ws.append([
                    item['source'],
                    item['keyword'],
                    item['value'],
                    item['depth'],
                    risk
                ])

            # 自动调整列宽
            for col in ws.columns:
                max_len = max(len(str(cell.value)) for cell in col)
                adjusted_width = (max_len + 2) * 1.2
                ws.column_dimensions[col[0].column_letter].width = adjusted_width

            # 生成文件名
            domain_clean = self.domain.replace('.', '_').replace(':', '')
            filename = f"security_report_{domain_clean}_{int(time.time())}.xlsx"

            # 保存前验证
            if len(ws['A']) > 1:  # 确保有数据行
                wb.save(filename)
                print(f"[报告生成] 成功保存到: {filename}")
            else:
                print("[警告] 检测到空数据表，取消保存操作")

        except Exception as e:
            print(f"[严重错误] 生成报告失败: {str(e)}")
            raise


if __name__ == "__main__":
    analyzer = JSAnalyzerPro()

    try:
        target = input("请输入目标URL: ").strip()
        keys = input("请输入要提取的关键字(多个用逗号分隔): ").strip()

        analyzer.configure(target, keys)
        analyzer.crawl_js(target)
        analyzer.generate_report()

        print(f"[系统通知] 扫描完成，共发现 {len(analyzer.results)} 条敏感信息")

    except Exception as e:
        print(f"[致命错误] 程序运行失败: {str(e)}")
        print("故障排查建议：")
        print("1. 检查网络连接和代理设置")
        print("2. 尝试降低最大爬取深度（修改 max_depth）")
        print("3. 安装最新依赖：pip install --upgrade requests beautifulsoup4 openpyxl")

 

0x03 效果：