v0.2.7.3

README.md

@@ -6,6 +6,17 @@
 
 **雪瞳** 是一款用于检测和提取网页中敏感信息的 Chrome 浏览器扩展。帮助用户快速获取网页中的敏感信息，并进行分析和处理。
 
+---
+## 一些使用技巧（方便好用）
+对于单个结果，鼠标悬浮即可看到来源，单击左键复制来源，ctrl+左键跳转来源链接，单击右键复制结果
+
+---
+## v0.2.7.3更新
+1. 大幅优化搜索时的网页卡顿问题，体验更流畅
+2. 适配webpack网页js搜集，绝不放过每一处可能存在的js
+
+和其他同类插件不同，雪瞳致力于更全面的js信息搜集，因此搜索时请多给雪瞳一些等待的时间，如果您发现了一些bug或是有更好的想法，欢迎提issue。
+
 ---
 ## v0.2.7.2更新
 
@@ -17,17 +28,17 @@
 6. 深度扫描新增js文件路径猜解拼接，提高访问命中率
 7. 其他细节优化......
 
-下个版本预计更新内容：当前版本问题优化，指纹添加，路径拼接优化，特殊网页处理，AI?，Maybe
-
 注意: 
 1. 深度扫描在一些情况下会出现很多js误匹配，此功能后续还需要多完善，正常情况下为了维持良好体验不建议使用
 2. 关于备案信息的查询建议注册登录接口盒子使用自己的Id和key，因为公开的接口查询有限制
+---
+下个版本预计更新内容：当前版本问题优化，指纹添加，路径拼接优化，特殊网页处理，AI?，Maybe
 
 如果您有更好的第三方接口欢迎提issue，当然您愿意分享的话。
-
 firfox版本后续更新，可能延迟一周左右。欢迎提issue，感谢支持！
 
 ---
+
 ## 功能特点
 
 1. 实现多种敏感信息，指纹等检测分类
@@ -37,7 +48,7 @@ firfox版本后续更新，可能延迟一周左右。欢迎提issue，感谢支
 ## 使用详情
 
 1. 将源码下载为压缩包文件后解压或直接clone
-2. 在浏览器扩展中打开开发者工具
+2. 在浏览器扩展中打开开发者模式
 3. 点击加载解压的扩展，选中解压的文件夹，即可在插件列表中使用插件
 
 ---

background/background.js

@@ -118,16 +118,12 @@ async function handleFetchRequest(request, sender, sendResponse) {
     }
   }
 }
-
-// 存储服务器指纹信息
 let serverFingerprints = new Map();
-
 const analyticsDetected = {
-  baidu: new Map(),    
-  yahoo: new Map(),    
-  google: new Map(),   
+  baidu: new Map(),
+  yahoo: new Map(),
+  google: new Map(),
 };
-// 统计服务检测处理函数
 function handleAnalyticsDetection(details, type) {
   if (analyticsDetected[type].get(details.tabId)) {
     return;
@@ -141,8 +137,6 @@ function handleAnalyticsDetection(details, type) {
     description: FINGERPRINT_CONFIG.ANALYTICS[type].description,
     version: FINGERPRINT_CONFIG.ANALYTICS[type].version
   });
-
-  // 更新存储
   serverFingerprints.set(details.tabId, fingerprints);
 }
 
@@ -195,7 +189,6 @@ function processHeaders(headers, tabId) {
   const headerMap = new Map(
     headers.map(h => [h.name.toLowerCase(), h.value])
   );
-  // 遍历所有指纹配置进行匹配
   for (const config of FINGERPRINT_CONFIG.HEADERS) {
     const headerValue = headerMap.get(config.header);
     if (headerValue) {
@@ -253,19 +246,14 @@ function getFingerprints(tabId){
   serverFingerprints.set(tabId, fingerprints);
   return fingerprints;
 }
-// 修改监听器的处理方式
 chrome.webRequest.onHeadersReceived.addListener(
   async (details) => {
-    // 只处理主文档请求，并且立即返回响应头
     if (details.type !== 'main_frame') return { responseHeaders: details.responseHeaders };
     if (!details.responseHeaders) return { responseHeaders: details.responseHeaders };
     
-    // 使用setTimeout将指纹处理放到下一个事件循环
     setTimeout(() => {
       const fingerprints = processHeaders(details.responseHeaders, details.tabId);
       serverFingerprints.set(details.tabId, fingerprints);
-    
-      // 延迟处理cookies
       chrome.cookies.getAll({ url: details.url }, (cookies) => {
         if (cookies.length > 0) {
           const cookieNames = cookies.map(cookie => cookie.name).join(';');
@@ -283,6 +271,47 @@ chrome.webRequest.onHeadersReceived.addListener(
   { urls: ['<all_urls>'] },
   ['responseHeaders']
 );
+function performRegexMatching(chunk, patterns, patternType) {
+  const matches = [];
+  let maxIterations = 10000;
+  
+  try {
+    for (const patternInfo of patterns) {
+      const { pattern: patternString} = patternInfo;
+      let regex;
+      try {
+        const match = patternString.match(/^\/(.+)\/([gimuy]*)$/);
+        if (match) {
+          regex = new RegExp(match[1], match[2]);
+        }
+      } catch (e) {
+        console.error(`无效的正则表达式: ${patternString}`, e);
+        continue;
+      }
+      let patternLastIndex = 0;
+      let match;
+      while ((match = regex.exec(chunk)) !== null) {
+        if (regex.lastIndex <= patternLastIndex) {
+          console.warn(`检测到可能的无限循环: ${patternType} Pattern - ${patternName}`);
+          break;
+        }
+        patternLastIndex = regex.lastIndex;
+        if (--maxIterations <= 0) {
+          console.warn(`达到最大迭代次数: ${patternType}`);
+          break;
+        }
+        matches.push({
+          match: match[0],
+        });
+      }
+      regex.lastIndex = 0;
+    }
+  } catch (e) {
+    console.error(`${patternType} 匹配出错:`, e);
+  }
+  
+  return matches;
+}
 
 chrome.runtime.onMessage.addListener((request, sender, sendResponse) => {
   if (request.to !== 'background') return false;
@@ -317,7 +346,7 @@ chrome.runtime.onMessage.addListener((request, sender, sendResponse) => {
       }
       case 'REGISTER_CONTENT': {
         const tabJs = Array.from(tabJsMap[sender.tab.id] || []);
-        sendResponse({ tabJs: tabJs });
+        sendResponse({ tabJs: tabJs, tabId: sender.tab.id });
         return true;
       }
       case 'UPDATE_BADGE': {
@@ -328,6 +357,12 @@ chrome.runtime.onMessage.addListener((request, sender, sendResponse) => {
         sendResponse({ tabId: sender.tab?.id });
         return true;
       }
+      case 'REGEX_MATCH': {
+        const { chunk, patterns, patternType } = request;
+        const matches = performRegexMatching(chunk, patterns, patternType);
+        sendResponse({ matches });
+        return true;
+      }
       case 'GET_SITE_ANALYSIS': {
         const domain = getRootDomain(request.domain);
         const tabId = request.tabId;

content/content.js

@@ -7,7 +7,7 @@ let maxDepth = 3;
 let tabJs = new Set();
 let isWhitelisted = false;
 let hostname = null;
-
+let isUseWebpack = false;
 const tree = {};
 const jsQueue = [];
 const queueSet = new Set();
@@ -27,6 +27,8 @@ async function initSettings() {
       chrome.runtime.sendMessage({ type: 'REGISTER_CONTENT', from: 'content', to: 'background' }, (response) => {
         if(isWhitelisted) return;
         tabJs = response.tabJs;
+        currentTabId = response.tabId;
+        getTabResults(currentTabId);
         tabJs.forEach(url => {
           enqueueJsUrl(url, 'background');
         });
@@ -47,7 +49,6 @@ const waitForDependencies = () => {
     })();
   });
 };
-// 获取tabId
 const getTabId = () => {
   return new Promise(resolve => {
     chrome.runtime.sendMessage({ type: 'GET_TAB_ID', from: 'content', to: 'background'}, response => {
@@ -109,10 +110,10 @@ function enqueueJsUrl(url, source='page', basePath = '') {
     jsFileMap.set(fileName, filePath);
     queueSet.add(url);
     jsQueue.push(url);
+    tabResults.get(currentTabId).jsFiles.set(url, "暂无法展示来源");
     processJsQueue();
   }
 }
-//分块处理
 function* splitIntoChunks(text) {
   if (text.length <= MAX_CHUNK_SIZE) {
     yield text;
@@ -131,8 +132,6 @@ function* splitIntoChunks(text) {
         currentLines = [];
         currentSize = 0;
       }
-
-      // 对超长单行进行切割
       if (line.length > MAX_CHUNK_SIZE) {
         for (let i = 0; i < line.length; i += MAX_CHUNK_SIZE) {
           yield line.slice(i, i + MAX_CHUNK_SIZE);
@@ -152,7 +151,7 @@ function* splitIntoChunks(text) {
   }
 }
 //匹配函数
-const matchPatterns = (chunk, isHtmlContent = false, url) => {
+const matchPatterns = async (chunk, isHtmlContent = false, url) => {
   const patterns = Object.entries(SCANNER_CONFIG.PATTERNS);
   const resultsSet = tabResults.get(currentTabId);
   let update = false;
@@ -166,7 +165,6 @@ const matchPatterns = (chunk, isHtmlContent = false, url) => {
     
     try {
       if (key === 'FINGER') {
-        // 对每个模式进行匹配
         for (const {pattern: fingerPattern, name: fingerName, class: fingerClass, type: fingerType, description: fingerDescription, extType: fingerExtType, extName: fingerExtName} of pattern.patterns) {
           if (resultsSet.fingers.has(fingerClass)) continue;
           const matches = chunk.match(fingerPattern);
@@ -188,7 +186,6 @@ const matchPatterns = (chunk, isHtmlContent = false, url) => {
         }
         continue;
       }
-      // 域名使用不同的匹配模式
       if (key === 'DOMAIN') {
         const domainPattern = isHtmlContent ? pattern : SCANNER_CONFIG.PATTERNS.DOMAIN_RESOURCE;
         while ((match = domainPattern.exec(chunk)) !== null) {
@@ -209,7 +206,6 @@ const matchPatterns = (chunk, isHtmlContent = false, url) => {
         }
         continue;
       }
-      // API模式特殊处理
       if (key === 'API') {
         const apiPattern = SCANNER_CONFIG.API.PATTERN;
         apiPattern.lastIndex = 0;
@@ -230,58 +226,39 @@ const matchPatterns = (chunk, isHtmlContent = false, url) => {
         }
         continue;
       }
-      if (key === 'CREDENTIALS') {
-        // 对每个模式进行匹配
-        for (const {pattern: credentialsPattern} of pattern.patterns) {
-          let patternLastIndex = 0;  // 每个模式独立的 lastIndex
-          while ((match = credentialsPattern.exec(chunk)) !== null) {
-            if (credentialsPattern.lastIndex <= patternLastIndex) {
-              window.logger.warn(`检测到可能的无限循环: CREDENTIALS Pattern`);
-              break;
-            }
-            patternLastIndex = credentialsPattern.lastIndex;
-            
-            if (--maxIterations <= 0) {
-              window.logger.warn(`达到最大迭代次数: CREDENTIALS`);
-              break;
-            }
-            
-            if (filter(match[0], url, resultsSet)) {
-              update = true;
-            }
+      if (key === 'CREDENTIALS' || key === 'ID_KEY' || key === 'EMAIL') {
+        let patterns = [];
+        if (key === 'EMAIL') {
+          patterns = [{"pattern": SCANNER_CONFIG.PATTERNS.EMAIL.toString()}];
+        }else{
+          patterns = pattern.patterns.map(p => ({
+            pattern: p.pattern.toString(),
+          }));
+        }
+        try {
+          const response = await new Promise((resolve) => {
+            chrome.runtime.sendMessage({
+              type: 'REGEX_MATCH',
+              from: 'content',
+              to: 'background',
+              chunk: chunk,
+              patterns: patterns,
+              patternType: key
+            }, resolve);
+          });
+          
+          if (response && response.matches) {
+            response.matches.forEach(({match}) => {
+              if (filter(match, url, resultsSet)) {
+                update = true;
+              }
+            });
           }
-          // 重置正则表达式的 lastIndex
-          credentialsPattern.lastIndex = 0;
+        } catch (e) {
+          window.logger.error('CREDENTIALS匹配出错:', e);
         }
         continue;
       }
-      // ID_KEY模式特殊处理
-      if (key === 'ID_KEY') {
-        // 对每个模式进行匹配
-        for (const {pattern: idKeyPattern} of pattern.patterns) {
-          let patternLastIndex = 0;  // 每个模式独立的 lastIndex
-          while ((match = idKeyPattern.exec(chunk)) !== null) {
-            if (idKeyPattern.lastIndex <= patternLastIndex) {
-              window.logger.warn(`检测到可能的无限循环: ID_KEY Pattern`);
-              break;
-            }
-            patternLastIndex = idKeyPattern.lastIndex;
-            
-            if (--maxIterations <= 0) {
-              window.logger.warn(`达到最大迭代次数: ID_KEY`);
-              break;
-            }
-            
-            if (filter(match[0], url, resultsSet)) {
-              update = true;
-            }
-          }
-          // 重置正则表达式的 lastIndex
-          idKeyPattern.lastIndex = 0;
-        }
-        continue;
-      }
-      // 其他模式使用exec
       while ((match = pattern.exec(chunk)) !== null) {
         if (pattern.lastIndex <= lastIndex) {
           window.logger.warn(`检测到可能的无限循环: ${pattern}`);
@@ -305,12 +282,34 @@ const matchPatterns = (chunk, isHtmlContent = false, url) => {
   }
   return update;
 };
-// 收集页面的js
 const collectJsUrls = (content) => {
   const jsUrls = new Set();
   const baseUrl = window.location.origin;
   const jsPattern = /['"](?:[^'"]+\.(?:js)(?:\?[^\s'"]*)?)['"]/g;
-  const matches = Array.from(content.matchAll(jsPattern))
+  const chunkCodePattern = /("[a-z/]*")[+|()\[\]\{\}a-z]*\+"."\+{(?:"?[0-9a-z-]*"?:"?[0-9a-z-]{1,}"?,?){1,}}\[[a-z]\]\+".js"/i;
+  const chunkJsPattern = /"?[0-9a-z-]*"?\s*:\s*"?[0-9a-z-]*"?/g;
+  const chunkMatch = content.match(chunkCodePattern);
+  if (chunkMatch) {
+    isUseWebpack = true;
+    let chunkBasePath = chunkMatch[1].slice(1, -1);
+    if (!chunkBasePath.startsWith('/')) {
+      chunkBasePath = '/' + chunkBasePath;
+    }
+    Array.from(chunkMatch[0].matchAll(chunkJsPattern)).forEach(chunkJsMatch => {
+      let chunkId = chunkJsMatch[0].split(":")[0];
+      if(chunkId.includes("\"")||chunkId.includes("\'")){
+        chunkId = chunkId.slice(1, -1);
+      }
+      let chunkHash = chunkJsMatch[0].split(":")[1];
+      if(chunkHash.includes("\"")||chunkHash.includes("\'")){
+        chunkHash = chunkHash.slice(1, -1);
+      }
+      const chunkUrl = baseUrl + chunkBasePath + chunkId + '.' + chunkHash + '.js';
+      jsUrls.add(chunkUrl);
+    });
+  }
+  if (!isUseWebpack && deepScanEnabled) {
+    const matches = Array.from(content.matchAll(jsPattern))
     .map(match => {
       const path = match[0].slice(1, -1);
       let url = null
@@ -334,8 +333,8 @@ const collectJsUrls = (content) => {
       }
     })
     .filter(url => url !== null);
-
-  matches.forEach(url => jsUrls.add(url));
+    matches.forEach(url => jsUrls.add(url));
+  }
   return jsUrls;
 };
 //扫描函数
@@ -344,7 +343,7 @@ async function scanSources(sources, isHtmlContent = false, url) {
     for (const source of sources) {
       if (!source) continue;
       for (const chunk of splitIntoChunks(source)) {
-        let update = matchPatterns(chunk, isHtmlContent, url);
+        let update = await matchPatterns(chunk, isHtmlContent, url);
         if (update) sendUpdate();
         await new Promise(r => setTimeout(r, 0));
       }
@@ -365,9 +364,8 @@ const debounceScan = () => {
     if (htmlContent) {
       scanSources([htmlContent], true, document.location.href);
     }
-  }, 1000); // 2秒内的变化会被合并为一次扫描
+  }, 1000); 
 };
-//监听 DOM 变化
 const observer = new MutationObserver((mutations) => {
   if (!dynamicScanEnabled) return;
 
@@ -383,38 +381,38 @@ const observer = new MutationObserver((mutations) => {
     debounceScan();
   }
 });
-// 初始化扫描
+function getTabResults(currentTabId){
+  if (!tabResults.has(currentTabId)) {
+    tabResults.set(currentTabId, {
+      domains: new Map(),
+      absoluteApis: new Map(),
+      apis: new Map(),
+      moduleFiles: new Map(),
+      docFiles: new Map(),
+      ips: new Map(),
+      phones: new Map(),
+      emails: new Map(),
+      idcards: new Map(),
+      jwts: new Map(),
+      imageFiles: new Map(),
+      jsFiles: new Map(),
+      vueFiles: new Map(),
+      urls: new Map(),
+      githubUrls: new Map(),
+      companies: new Map(),
+      credentials: new Map(),
+      cookies: new Map(),
+      idKeys: new Map(),
+      fingers: new Map(),
+      progress: new Map()
+    });
+  }
+}
 async function initScan() {
   try {
     await waitForDependencies();
     if (!currentTabId) await getTabId();
-
-    if (!tabResults.has(currentTabId)) {
-      tabResults.set(currentTabId, {
-        domains: new Map(),     
-        absoluteApis: new Map(),
-        apis: new Map(),        
-        moduleFiles: new Map(), 
-        docFiles: new Map(),    
-        ips: new Map(),         
-        phones: new Map(),      
-        emails: new Map(),      
-        idcards: new Map(),     
-        jwts: new Map(),        
-        imageFiles: new Map(),  
-        jsFiles: new Map(),     
-        vueFiles: new Map(),    
-        urls: new Map(),        
-        githubUrls: new Map(),  
-        companies: new Map(),   
-        credentials: new Map(),  
-        cookies: new Map(),      
-        idKeys: new Map(),       
-        fingers: new Map(), 
-        progress: new Map()
-      });
-    }
-
+    getTabResults(currentTabId);
     window.logger.info('开始扫描...');
     Object.keys(tabResults.get(currentTabId)).forEach(key => {
       tabResults.get(currentTabId)[key].clear();
@@ -463,7 +461,6 @@ const sendUpdate = () => {
       results: results,
       tabId: currentTabId,
     }).catch(() => {
-      // 忽略消息发送失败的错误
     });
     
     chrome.runtime.sendMessage({
@@ -473,7 +470,6 @@ const sendUpdate = () => {
       results: results,
       tabId: currentTabId,
     }).catch(() => {
-      // 忽略消息发送失败的错误
     });
   } catch (e) {
     if (e.message !== 'Extension context invalidated.') {
@@ -504,17 +500,11 @@ async function handleJsTask(url) {
     const response = await new Promise(resolve => {
       chrome.runtime.sendMessage({ type: 'FETCH_JS', url: url, from: 'content', to: 'background'}, resolve);
     });
-
     if (response?.content) {
-      //扫描js
       await scanSources([response.content], false, url);
-      if(deepScanEnabled){
-        // 收集新的js
-        const newJsUrls = collectJsUrls(response.content);
-        const basePath = getBasePath(url);
-        if(newJsUrls){
-          newJsUrls.forEach(jsUrl => enqueueJsUrl(jsUrl, 'page', basePath));
-        }
+      const newJsUrls = collectJsUrls(response.content);
+      if(newJsUrls){
+        newJsUrls.forEach(jsUrl => enqueueJsUrl(jsUrl, 'page', getBasePath(url)));
       }
     }
   } catch (e) {

manifest.json

@@ -2,7 +2,7 @@
   "manifest_version": 3,
 
   "name": "雪瞳",
-  "version": "0.2.7.2",
+  "version": "0.2.7.3",
   "description": "洞悉无形，守护无界",
 
   "icons": {