1

dl_admin/ruoyi-admin/src/main/java/com/ruoyi/busi/service/impl/BusiKeywordItemServiceImpl.java

@@ -7,10 +7,14 @@ import cn.hutool.core.date.DateUtil;
 import com.alibaba.fastjson2.JSONObject;
 import com.baomidou.mybatisplus.core.metadata.IPage;
 import com.baomidou.mybatisplus.extension.plugins.pagination.Page;
+import com.ruoyi.base.domain.BaseSite;
+import com.ruoyi.base.service.IBaseSiteInfoService;
+import com.ruoyi.base.service.IBaseSiteService;
 import com.ruoyi.busi.domain.BusiKeyword;
 import com.ruoyi.busi.service.IBusiKeywordService;
 import com.ruoyi.busi.vo.BusiKeywordItemQueryVO;
 import com.ruoyi.busi.vo.BusiKeywordRankStatVO;
+import com.ruoyi.common.utils.GoogleUtil;
 import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.stereotype.Service;
 import com.baomidou.mybatisplus.extension.service.impl.ServiceImpl;
@@ -31,6 +35,8 @@ public class BusiKeywordItemServiceImpl extends ServiceImpl<BusiKeywordItemMappe
     private BusiKeywordItemMapper busiKeywordItemMapper;
     @Autowired
     private IBusiKeywordService busiKeywordService;
+    @Autowired
+    private IBaseSiteService baseSiteService;
 
     @Override
     public IPage<BusiKeywordItem> queryListPage(BusiKeywordItem pageReqVO, Page<BusiKeywordItem> page) {
@@ -46,6 +52,9 @@ public class BusiKeywordItemServiceImpl extends ServiceImpl<BusiKeywordItemMappe
     @Override
     public void getKeywordRanking() {
         Date nowDate = new Date();
+        //所有网站
+        List<BaseSite> siteList = baseSiteService.list();
+        Map<String,String> siteMap = siteList.stream().collect(Collectors.toMap(BaseSite::getId, BaseSite::getSiteUrl));
         List<BusiKeyword> keywordList = busiKeywordService.list();
         //删除今日所有的排名数据
         busiKeywordItemMapper.deleteBySelectDateInt(DateUtil.formatDate(nowDate));
@@ -54,8 +63,12 @@ public class BusiKeywordItemServiceImpl extends ServiceImpl<BusiKeywordItemMappe
             BusiKeywordItem busiKeywordItem = new BusiKeywordItem();
             busiKeywordItem.setTitle(keyword.getId());
             busiKeywordItem.setSelectDate(nowDate);
-            //TODO 调朱哥的接口获取排名
+            int ranking = GoogleUtil.getGoogleRank(keyword.getId(), siteMap.get(keyword.getTenantId()));
-            busiKeywordItem.setRanking(1);
+            if(ranking>0 && ranking<=20){
+                busiKeywordItem.setRanking(ranking);
+            }else{
+                busiKeywordItem.setRanking(0);
+            }
             busiKeywordItem.setTenantId(keyword.getTenantId());
             insertList.add(busiKeywordItem);
         }

dl_admin/ruoyi-admin/src/main/resources/application-druid.yml

@@ -4,16 +4,16 @@ spring:
         type: com.alibaba.druid.pool.DruidDataSource
         driverClassName: com.mysql.cj.jdbc.Driver
         druid:
-            # 主库数据源-点亮开发库
+#            # 主库数据源-点亮开发库
-            master:
-                url: jdbc:mysql://82.156.161.160:3306/dl_site_system?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
-                username: site
-                password: 123456
-             #主库数据源-客户测试服务器
 #            master:
-#                url: jdbc:mysql://127.0.0.1:3306/dl_site_system?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
+#                url: jdbc:mysql://82.156.161.160:3306/dl_site_system?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
 #                username: site
 #                password: 123456
+#             主库数据源-客户测试服务器
+            master:
+                url: jdbc:mysql://1.92.99.15:3306/dl_site_system?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
+                username: site
+                password: 123456
             # 从库数据源
             slave:
                 # 从数据源开关/默认关闭

dl_admin/ruoyi-common/src/main/java/com/ruoyi/common/utils/GoogleUtil.java

@@ -13,29 +13,33 @@ import org.openqa.selenium.chrome.ChromeDriver;
 import org.openqa.selenium.chrome.ChromeOptions;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
+import io.github.bonigarcia.wdm.WebDriverManager;
+import org.openqa.selenium.By;
+import org.openqa.selenium.support.ui.WebDriverWait;
+import org.openqa.selenium.support.ui.ExpectedConditions;
+import org.springframework.stereotype.Component;
+
 
 import java.net.URLEncoder;
+import java.net.URLDecoder;
+import java.net.URL;
 import java.nio.charset.StandardCharsets;
 import java.util.Arrays;
 import java.util.List;
 import java.util.concurrent.TimeUnit;
+import java.util.HashMap;
+import java.util.Map;
+import java.nio.file.Files;
+import java.nio.file.Paths;
 
 public class GoogleUtil {
     private static final Logger log = LoggerFactory.getLogger(GoogleUtil.class);
-    // 可配置参数（Ruoyi项目建议用@Value从application.yml读取）
+    // 行为开关：是否保留浏览器窗口（默认为 false，可在运行时通过 setter 修改）
+    private static volatile boolean KEEP_BROWSER_OPEN = false;
+    // 可配置参数
     private static final String GOOGLE_SEARCH_URL = "https://www.google.com/search?q=";
-    private static final String PROXY_HOST = "127.0.0.1";
-    private static final int PROXY_PORT = 7897;
     private static final int CONNECT_TIMEOUT = 10000;
     private static final int READ_TIMEOUT = 15000;
-    // 重试机制
-    private static final Retryer<Boolean> RETRYER = RetryerBuilder.<Boolean>newBuilder()
-            .retryIfExceptionOfType(Exception.class)
-            .retryIfResult(result -> result != null && !result)
-            .withStopStrategy(StopStrategies.stopAfterAttempt(3))
-            .withWaitStrategy(WaitStrategies.fixedWait(1, TimeUnit.SECONDS))
-            .build();
-
     // 扩展User-Agent池（增加移动端标识，反爬更友好）
     private static final List<String> USER_AGENTS = Arrays.asList(
             "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36",
@@ -45,6 +49,21 @@ public class GoogleUtil {
             "Mozilla/5.0 (Android 14; Mobile; rv:120.0) Gecko/120.0 Firefox/120.0"
     );
 
+    public static void setKeepBrowserOpen(boolean keep) {
+        KEEP_BROWSER_OPEN = keep;
+    }
+
+    public static boolean isKeepBrowserOpen() {
+        return KEEP_BROWSER_OPEN;
+    }
+
+    // 是否要求页面 UI 显示“网页/全部”筛选（默认开启）。若未检测到则跳过本次采集。
+    private static volatile boolean REQUIRE_WEB_TAB = true;
+
+    public static void setRequireWebTab(boolean require) {
+        REQUIRE_WEB_TAB = require;
+    }
+
     /**
      * 核心方法：获取Google搜索排名（使用Selenium实现）
      */
@@ -88,6 +107,11 @@ public class GoogleUtil {
             return 0;
         }
         String finalUrl = GOOGLE_SEARCH_URL + encodedSearchText;
+        // 允许指定 gl（地域）
+        String gl = System.getenv("GOOGLE_GL");
+        if (gl != null && !gl.trim().isEmpty()) {
+            finalUrl = finalUrl + "&gl=" + gl.trim();
+        }
         log.info("发起Google搜索请求：url={}, 目标网站={}", finalUrl, webSite);
 
         WebDriver driver = null;
@@ -96,16 +120,57 @@ public class GoogleUtil {
             driver = createWebDriver();
 
             int rank = -1;
-            // 搜索前三页
+            // 仅搜索前2页（前20名）
-            for (int page = 1; page <= 3; page++) {
+            for (int page = 1; page <= 2; page++) {
                 String pageUrl = page == 1 ? finalUrl : finalUrl + "&start=" + ((page - 1) * 10);
+                // 统一参数：关闭个性化、语言，仅网页结果（udm=14）
+                pageUrl += "&hl=zh-CN&pws=0&num=10&udm=14";
                 log.info("搜索第{}页: {}", page, pageUrl);
 
+                // 先访问 NCR 以避免地区重定向
+                try {
+                    driver.get("https://www.google.com/ncr");
+                } catch (Exception ignore) {
+                }
+                // 访问后立刻检查是否跳转到人机验证/异常流量页面
+                try {
+                    String cur = driver.getCurrentUrl().toLowerCase();
+                    if (cur.contains("/sorry/") || cur.contains("sorry/index") || cur.contains("security-check") || cur.contains("captcha")) {
+                        log.warn("发现跳转至验证页面: {}", cur);
+                        return -2;
+                    }
+                } catch (Exception e) {
+                    log.warn("获取当前URL失败，可能窗口被关闭或被拦截: {}", e.getMessage());
+                    return -2;
+                }
+
+
                 // 访问Google搜索页面
                 driver.get(pageUrl);
 
-                // 随机延时，模拟人类行为（增加延时以减少被识别为机器人的可能性）
+                // 显式等待搜索结果区域、标题出现，避免未加载完全
-                Thread.sleep((long) (3000 + Math.random() * 5000));
+                try {
+                    WebDriverWait wait = new WebDriverWait(driver, 10);
+                    wait.until(ExpectedConditions.presenceOfElementLocated(By.cssSelector("div#search")));
+                    // 等待有机结果容器
+                    wait.until(ExpectedConditions.presenceOfElementLocated(By.cssSelector("div#search div.MjjYud div.tF2Cxc, div#search a h3")));
+                } catch (Exception e) {
+                    log.warn("等待搜索结果元素出现超时: {}", e.getMessage());
+                }
+
+                // 人类化随机等待
+                Thread.sleep((long) (1500 + Math.random() * 3000));
+
+                // 轻微滚动，模拟浏览
+                try {
+                    org.openqa.selenium.JavascriptExecutor js = (org.openqa.selenium.JavascriptExecutor) driver;
+                    long steps = 2 + (int) (Math.random() * 3);
+                    for (int i = 0; i < steps; i++) {
+                        js.executeScript("window.scrollBy(0, arguments[0]);", 200 + (int) (Math.random() * 400));
+                        Thread.sleep((long) (400 + Math.random() * 600));
+                    }
+                } catch (Exception ignore) {
+                }
 
                 // 检查是否出现了验证码页面
                 if (isCaptchaPage(driver)) {
@@ -117,19 +182,40 @@ public class GoogleUtil {
                 String html = driver.getPageSource();
                 log.debug("第{}页请求成功：响应长度={}字节", page, html.length());
 
+                // 如需页面必须显示“网页/全部”筛选标签，则检查 UI，否则跳过采集
+                if (REQUIRE_WEB_TAB) {
+                    try {
+                        String curUrl = null;
+                        try { curUrl = driver.getCurrentUrl(); } catch (Exception ignore) {}
+                        boolean hasWebTab = (curUrl != null && curUrl.contains("udm=14"))
+                                || html.contains(">网页<") || html.contains(">全部<")
+                                || html.contains(">Web<") || html.contains(">All<");
+                        if (!hasWebTab) {
+                            log.warn("未检测到‘网页/全部’筛选标签，跳过本次采集（REQUIRE_WEB_TAB=true）");
+                            return 0;
+                        }
+                    } catch (Exception ignore) {
+                    }
+                }
+
                 // 解析当前页的排名
-                int pageRank = parseRankFromHtml(html, webSite, (page - 1) * 10);
+                int baseRankForPage = (page - 1) * 10;
+                int pageRank = parseRankFromHtml(html, webSite, baseRankForPage);
+                // 写入本页有机结果清单（仅用于排查）
+                try {
+                    dumpOrganicList(Jsoup.parse(html), baseRankForPage);
+                } catch (Exception ignore) {
+                }
                 if (pageRank > 0) {
                     rank = pageRank;
                     break;
                 }
 
                 // 页面间增加随机延时
-                if (page < 3) {
+                if (page < 2) {
                     Thread.sleep((long) (2000 + Math.random() * 3000));
                 }
             }
-
             return rank;
         } catch (Exception e) {
             log.error("获取排名异常：url={}, 原因={}", finalUrl, e.getMessage(), e);
@@ -137,10 +223,14 @@ public class GoogleUtil {
         } finally {
             // 关闭浏览器
             if (driver != null) {
-                try {
+                if (!KEEP_BROWSER_OPEN) {
-                    driver.quit();
+                    try {
-                } catch (Exception e) {
+                        driver.quit();
-                    log.error("关闭浏览器失败", e);
+                    } catch (Exception e) {
+                        log.error("关闭浏览器失败", e);
+                    }
+                } else {
+                    log.info("根据配置保留浏览器窗口开启（KEEP_BROWSER_OPEN=true）");
                 }
             }
         }
@@ -148,48 +238,78 @@ public class GoogleUtil {
 
     /**
      * 创建WebDriver实例
+     *
      * @return WebDriver
      */
     private static WebDriver createWebDriver() {
-        // 设置ChromeDriver路径（根据实际路径调整）
+        // 优先使用 WebDriverManager 自动管理驱动
-        System.setProperty("webdriver.chrome.driver", "D:/chromedriver-win64/chromedriver.exe");
+        try {
+            WebDriverManager.chromedriver().setup();
+            log.info("WebDriverManager 已自动配置 chromedriver");
+        } catch (Throwable t) {
+            // 允许失败后使用手动路径
+            log.warn("WebDriverManager 配置失败，尝试使用手动路径: {}", t.getMessage());
+            String sysProp = System.getProperty("webdriver.chrome.driver");
+            String envProp = System.getenv("CHROMEDRIVER_PATH");
+            if (sysProp == null || sysProp.isEmpty()) {
+                String path = (envProp != null && !envProp.isEmpty()) ? envProp : "D:/chromedriver.exe";
+                System.setProperty("webdriver.chrome.driver", path);
+                log.info("使用ChromeDriver路径: {}", path);
+            } else {
+                log.info("检测到系统属性webdriver.chrome.driver: {}", sysProp);
+            }
+        }
 
         ChromeOptions options = new ChromeOptions();
-        // 设置无头模式 (Selenium 3.x语法)
+        // 按环境变量决定是否 headless（默认有头，更像真实用户）
-        options.addArguments("--headless");
+        boolean headless = Boolean.parseBoolean(System.getenv().getOrDefault("GOOGLE_HEADLESS", "false"));
-        // 设置User-Agent
+        if (headless) options.addArguments("--headless=new");
+
+        // 语言与用户体验设置
+        options.addArguments("--lang=zh-CN");
+        Map<String, Object> prefs = new HashMap<>();
+        prefs.put("intl.accept_languages", "zh-CN,zh;q=0.9");
+        options.setExperimentalOption("prefs", prefs);
+
+        // User-Agent 随机化
         String randomUserAgent = USER_AGENTS.get((int) (Math.random() * USER_AGENTS.size()));
         options.addArguments("--user-agent=" + randomUserAgent);
-        // 禁用图片加载提高速度
+
-        options.addArguments("--blink-settings=imagesEnabled=false");
+        // 真实窗口大小（避免固定指纹）
-        // 设置窗口大小
+        int width = 1024 + (int) (Math.random() * 600);
-        options.addArguments("--window-size=1920,1080");
+        int height = 700 + (int) (Math.random() * 500);
-        // 禁用自动化控制特征
+        options.addArguments("--window-size=" + width + "," + height);
+
+        // 尽量减少自动化特征
         options.addArguments("--disable-blink-features=AutomationControlled");
         options.setExperimentalOption("excludeSwitches", Arrays.asList("enable-automation"));
-        // 禁用自动化标志
         options.addArguments("--disable-extensions");
         options.addArguments("--no-sandbox");
         options.addArguments("--disable-dev-shm-usage");
-        // 禁用SSL错误
         options.addArguments("--ignore-ssl-errors");
         options.addArguments("--ignore-certificate-errors");
-        // 禁用日志
-        options.addArguments("--log-level=3");
-        options.addArguments("--silent");
 
-        // 如果需要使用代理（轮换代理IP可以有效避免验证码）
+        // 复用用户数据目录（可降低验证码概率）
-        /*
+        String userDataDir = System.getenv("GOOGLE_CHROME_USER_DATA_DIR");
-        if (PROXY_HOST != null && !PROXY_HOST.isEmpty()) {
+        if (userDataDir != null && !userDataDir.trim().isEmpty()) {
-            // 可以在这里集成代理IP服务，每次使用不同的IP
+            options.addArguments("--user-data-dir=" + userDataDir.trim());
-            options.addArguments("--proxy-server=http://" + PROXY_HOST + ":" + PROXY_PORT);
         }
-        */
+
+        // 根据需求保留浏览器窗口（以静态变量为准）
+        boolean detach = KEEP_BROWSER_OPEN; // 当需要保留窗口时，开启 detach
+        options.setExperimentalOption("detach", detach);
+        if (detach) {
+            log.info("ChromeOptions 已启用 detach={}, 浏览器可能在会话结束后保持打开", detach);
+        }
+
 
         WebDriver driver = new ChromeDriver(options);
-        // 执行JavaScript隐藏webdriver属性
+        // 隐藏 webdriver 标志
-        ((org.openqa.selenium.JavascriptExecutor) driver).executeScript(
+        try {
-                "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})");
+            ((org.openqa.selenium.JavascriptExecutor) driver).executeScript(
+                    "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})");
+        } catch (Exception ignore) {
+        }
 
         return driver;
     }
@@ -206,137 +326,202 @@ public class GoogleUtil {
         }
     }
 
+    /**
+     * 将当前页面识别到的有机结果（已过滤 PAA）按序写入临时文件，便于对照
+     */
+    private static void dumpOrganicList(Document doc, int baseRank) {
+        try {
+            List<String> lines = new java.util.ArrayList<>();
+            java.util.Set<String> printed = new java.util.HashSet<>();
+            int idx = 0;
+            // 优先使用 tF2Cxc 容器
+            Elements tfItems = doc.select("div.tF2Cxc");
+            for (Element item : tfItems) {
+                // 仅基于 tF2Cxc 容器（udm=14 已筛选网页，通常无 PAA 干扰）
+                Element a = item.selectFirst(".yuRUbf a[href]");
+                if (a == null) continue;
+                String href = a.attr("href");
+                // 展开 /url?q=
+                if (href != null && href.startsWith("/url?")) {
+                    String query = href.substring(href.indexOf('?') + 1);
+                    for (String pair : query.split("&")) {
+                        int idxEq = pair.indexOf('=');
+                        if (idxEq > 0) {
+                            String key = pair.substring(0, idxEq);
+                            String val = pair.substring(idxEq + 1);
+                            if ("q".equals(key)) {
+                                try {
+                                    href = URLDecoder.decode(val, StandardCharsets.UTF_8.name());
+                                } catch (Exception ignore) {
+                                }
+                                break;
+                            }
+                        }
+                    }
+                }
+                String hrefHost = extractHost(href);
+                String citeHost = extractDisplayHostFromItem(item);
+                String effHost = (hrefHost != null && !hrefHost.isEmpty()) ? hrefHost : citeHost;
+                if (effHost == null || effHost.isEmpty()) continue;
+                if (effHost.endsWith("google.com") || effHost.endsWith("google.cn") || effHost.contains("google."))
+                    continue;
+                String key = (effHost == null ? "" : effHost) + "|" + (href == null ? "" : href);
+                if (!printed.add(key)) continue;
+                idx++;
+                int rank = baseRank + idx;
+                String line = String.format("#%d citeHost=%s hrefHost=%s href=%s", rank, citeHost, hrefHost, href);
+                lines.add(line);
+                log.info("本页有机{}: {}", idx, line);
+                if (idx >= 10) break;
+            }
+            // 兜底：如不足10条，回退到 a h3 结构补足
+            if (idx < 10) {
+                // 保持首页清单完整性的同时，尽量避免 fallback 误入非有机卡片；若你不需要 fallback 可以将本块去掉
+            }
+            log.info("本页有机共{}条", idx);
+        } catch (Exception e) {
+            log.warn("写入有机结果清单失败: {}", e.getMessage());
+        }
+    }
+
     /**
      * 解析排名
      */
     private static int parseRankFromHtml(String html, String targetWebSite, int baseRank) {
         Document doc = Jsoup.parse(html);
 
-        // 获取所有可能的搜索结果容器
+        // 优先按有机结果容器顺序计数：广义抓取 #search 下的 tF2Cxc，再在循环内过滤 PAA（Wt5Tfe/related-question-pair）
-        Elements resultContainers = doc.select("div.g");
+        Elements items = doc.select("div.tF2Cxc");
-
+        String cleanTarget = normalizeHost(targetWebSite);
-        if (resultContainers.isEmpty()) {
-            log.warn("未找到任何搜索结果容器");
-            return -1;
-        }
-
-        log.debug("找到 {} 个搜索结果容器", resultContainers.size());
-
-        String cleanTarget = targetWebSite
-                .replace("https://", "")
-                .replace("http://", "")
-                .replace("www.", "");
-
-        // 如果目标网站包含路径，则只取域名部分进行比较
-        if (cleanTarget.contains("/")) {
-            cleanTarget = cleanTarget.substring(0, cleanTarget.indexOf("/"));
-        }
 
         int validResultCount = 0;
+        java.util.Set<String> counted = new java.util.HashSet<>();
+        if (!items.isEmpty()) {
+            for (Element item : items) {
+                // 仅基于 tF2Cxc 容器（udm=14 已筛选网页，通常无 PAA 干扰）
 
-        for (Element container : resultContainers) {
+                Element a = item.selectFirst(".yuRUbf a[href]");
-            // 跳过图片和视频区块
+                if (a == null) continue;
-            if (container.select("div.XaIwc, div.islrc, div.JTuIPc, div.PiKbc, div[jscontroller]").size() > 0) {
+                String href = a.attr("href");
-                continue;
+                if (href == null || href.isEmpty()) continue;
-            }
 
-            // 查找容器中的链接
+                // 展开 /url?q= 形式
-            Elements links = container.select("a[href]");
+                if (href.startsWith("/url?")) {
-            if (links.isEmpty()) {
+                    String query = href.substring(href.indexOf('?') + 1);
-                continue;
+                    for (String pair : query.split("&")) {
-            }
+                        int idx = pair.indexOf('=');
+                        if (idx > 0) {
+                            String key = pair.substring(0, idx);
+                            String val = pair.substring(idx + 1);
+                            if ("q".equals(key)) {
+                                try {
+                                    href = URLDecoder.decode(val, StandardCharsets.UTF_8.name());
+                                } catch (Exception ignore) {
+                                }
+                                break;
+                            }
+                        }
+                    }
+                }
 
-            boolean isSearchResult = false;
+                String host = extractHost(href);
-            String resultUrl = "";
+                String citeHost = extractDisplayHostFromItem(item);
-
+                if (citeHost == null || citeHost.isEmpty()) citeHost = host;
-            // 查找有效的搜索结果链接
+                if (host == null || host.isEmpty()) host = citeHost;
-            for (Element link : links) {
+                if (host == null || host.isEmpty()) continue;
-                String href = link.attr("href");
+                if (host.endsWith("google.com") || host.endsWith("google.cn") || host.contains("google.")) {
-
-                // 跳过Google内部链接
-                if (href.contains("google.com") || href.startsWith("/url?") || href.startsWith("#")) {
                     continue;
                 }
-
+                String key = (host == null ? "" : host) + "|" + (href == null ? "" : href);
-                // 检查是否是标题链接（通常在h3标签内）
+                if (!counted.add(key)) continue; // 去重，确保与dump一致
-                if (link.parent() != null && link.parent().tagName().equals("h3")) {
+                validResultCount++;
-                    isSearchResult = true;
+                if (host.equalsIgnoreCase(cleanTarget) || citeHost.equalsIgnoreCase(cleanTarget) ||
-                    resultUrl = href;
+                        host.endsWith("." + cleanTarget) || citeHost.endsWith("." + cleanTarget) ||
-                    break;
+                        cleanTarget.endsWith("." + host) || cleanTarget.endsWith("." + citeHost)) {
+                    int actualRank = baseRank + validResultCount;
+                    log.info("找到目标网站：排名={}, URL={}, host={}, citeHost={}, target={}", actualRank, href, host, citeHost, cleanTarget);
+                    return actualRank;
                 }
-
-                // 或者检查是否在常见的搜索结果区块中
-                Element parent = link.parent();
-                while (parent != null) {
-                    if (parent.hasClass("yuRUbf") || parent.hasClass("tF2Cxc")) {
-                        isSearchResult = true;
-                        resultUrl = href;
-                        break;
-                    }
-                    parent = parent.parent();
-                }
-
-                if (isSearchResult) {
-                    break;
-                }
-            }
-
-            if (!isSearchResult) {
-                continue;
-            }
-
-            validResultCount++;
-
-            String cleanResult = resultUrl
-                    .replace("https://", "")
-                    .replace("http://", "")
-                    .replace("www.", "");
-
-            // 如果结果URL包含路径，则只取域名部分进行比较
-            if (cleanResult.contains("/")) {
-                int firstSlash = cleanResult.indexOf("/");
-                if (firstSlash > 0) {
-                    cleanResult = cleanResult.substring(0, firstSlash);
-                }
-            }
-
-            // 匹配目标网站
-            if (cleanResult.contains(cleanTarget) || cleanTarget.contains(cleanResult)) {
-                int actualRank = baseRank + validResultCount;
-                log.info("找到目标网站：排名={}, 结果URL={}, 目标网站={}", actualRank, resultUrl, targetWebSite);
-                return actualRank;
             }
         }
-
+        // 不使用 h3 兜底机制，避免引入非有机卡片造成误差；仅以 tF2Cxc 且非 PAA 的结果计数
         log.info("在当前页面未找到目标网站：targetWebSite={}", targetWebSite);
         return -1;
     }
 
+
+    /**
+     * 从有机结果容器中提取展示域名（来自 .byrV5b > cite 的可见链接）
+     */
+    private static String extractDisplayHostFromItem(Element item) {
+        try {
+            // 选择第一个“非 PAA 折叠容器(jsname=YrZdPb)内”的 cite 作为展示域名
+            Elements cites = item.select(".byrV5b cite");
+            Element cite = null;
+            for (Element c : cites) {
+                if (c.parents().select("[jsname=YrZdPb]").isEmpty()) {
+                    cite = c;
+                    break;
+                }
+            }
+            if (cite == null) return "";
+            String txt = cite.text(); // 例如：https://zh.wikipedia.org › zh-cn › 大型貨車
+            if (txt == null || txt.isEmpty()) return "";
+            // 仅取 URL 主体部分，丢弃“ › ”后面的路径
+            int idxArrow = txt.indexOf("›");
+            if (idxArrow > 0) {
+                txt = txt.substring(0, idxArrow).trim();
+            }
+            // 去掉多余空格
+            txt = txt.replace(" ", "");
+            // 提取 host
+            if (txt.startsWith("http")) {
+                try {
+                    URL u = new URL(txt);
+                    return normalizeHost(u.getHost());
+                } catch (Exception ignore) {
+                }
+            }
+            // 如果不是完整URL，比如直接显示 zh.wikipedia.org
+            return normalizeHost(txt);
+        } catch (Exception e) {
+            return "";
+        }
+    }
+
     /**
      * 检查是否为验证码页面
+     *
      * @param driver WebDriver实例
      * @return 是否为验证码页面
      */
     private static boolean isCaptchaPage(WebDriver driver) {
         try {
-            String pageSource = driver.getPageSource().toLowerCase();
+            String currentUrl = "";
-            String currentUrl = driver.getCurrentUrl().toLowerCase();
+            String pageSource = "";
+            try {
+                currentUrl = driver.getCurrentUrl().toLowerCase();
+            } catch (Exception ignore) {
+            }
+            try {
+                pageSource = driver.getPageSource().toLowerCase();
+            } catch (Exception ignore) {
+            }
 
-            // 检查页面是否包含验证码相关关键词
+            // URL 层面的强信号
+            boolean isCaptchaUrl = currentUrl.contains("sorry/index") ||
+                    currentUrl.contains("security-check") ||
+                    currentUrl.contains("captcha");
+
+            // 页面文本层面的信号
             boolean hasCaptchaKeywords = pageSource.contains("captcha") ||
                     pageSource.contains("recaptcha") ||
                     pageSource.contains("人机验证") ||
                     pageSource.contains("异常流量") ||
                     pageSource.contains("security check") ||
-                    pageSource.contains("sorry/index") ||
                     pageSource.contains("before we can serve your request");
 
-            // 检查URL是否为验证码页面
+            return isCaptchaUrl || hasCaptchaKeywords;
-            boolean isCaptchaUrl = currentUrl.contains("sorry/index") ||
-                    currentUrl.contains("security-check") ||
-                    currentUrl.contains("captcha");
-
-            return hasCaptchaKeywords || isCaptchaUrl;
         } catch (Exception e) {
             log.error("检查验证码页面时出错", e);
             return false;
@@ -346,10 +531,41 @@ public class GoogleUtil {
     // 测试方法
     public static void main(String[] args) {
         // 测试用例：搜索关键词，查找特定网站的排名
-        int rank1 = getGoogleRank("大卡车", "zh.wikipedia.org");
+        int rank1 =   getGoogleRank("大卡车", "zh.wikipedia.org");
         System.out.println("维基百科排名：" + formatRank(rank1));
     }
 
+    /**
+     * 提取并规范化 host
+     */
+    private static String extractHost(String urlStr) {
+        try {
+            // 绝对URL
+            if (urlStr.startsWith("http")) {
+                URL u = new URL(urlStr);
+                return normalizeHost(u.getHost());
+            }
+            // 可能是相对或协议相对
+            if (urlStr.startsWith("//")) {
+                URL u = new URL("https:" + urlStr);
+                return normalizeHost(u.getHost());
+            }
+            return null;
+        } catch (Exception e) {
+            return null;
+        }
+    }
+
+    private static String normalizeHost(String hostOrUrl) {
+        if (hostOrUrl == null || hostOrUrl.isEmpty()) return "";
+        String s = hostOrUrl.trim();
+        s = s.replace("https://", "").replace("http://", "");
+        if (s.contains("/")) s = s.substring(0, s.indexOf('/'));
+        if (s.startsWith("www.")) s = s.substring(4);
+        return s.toLowerCase();
+    }
+
+
     // 辅助方法：格式化排名输出
     private static String formatRank(int rank) {
         if (rank > 0) return rank + "名";

dl_vue/src/views/base/site/index.vue

@@ -114,7 +114,7 @@
     <!-- 添加或修改站点管理对话框 -->
     <el-dialog :title="title" :visible.sync="open" width="500px" append-to-body>
       <el-form ref="form" :model="form" :rules="rules" label-width="80px">
-        <el-form-item label="站点编码" prop="siteName">
+        <el-form-item label="站点编码" prop="id">
           <el-input v-model="form.id" placeholder="请输入站点编码" />
         </el-form-item>
         <el-form-item label="站点名称" prop="siteName">
@@ -179,7 +179,15 @@ export default {
       form: {},
       // 表单校验
       rules: {
-
+        id: [
+          { required: true, message: '请输入站点编码', trigger: 'blur' }
+        ],
+        siteName: [
+          { required: true, message: '请输入站点名称', trigger: 'blur' }
+        ],
+        siteUrl: [
+          { required: true, message: '请输入站点网址', trigger: 'blur' }
+        ],
       },
       //当前处理的数据id
       dealId:null,

dl_vue/src/views/busi/category/index.vue

@@ -87,7 +87,12 @@
       border
       :tree-props="{children: 'children', hasChildren: 'hasChildren'}"
       v-loading="loading" :data="categoryList" >
-      <el-table-column label="栏目名称" align="left" prop="catgName" />
+      <el-table-column label="栏目名称" align="left" prop="catgName" >
+        <template slot-scope="scope" >
+          {{scope.row.catgName}}
+          <template v-if="checkIfAppCatg(scope.row.id)"><el-tag>APP</el-tag></template>
+        </template>
+      </el-table-column>
       <el-table-column label="栏目级别" align="center" prop="catgLevel">
         <template slot-scope="scope">
           {{scope.row.catgLevel}}级栏目
@@ -161,7 +166,7 @@ import { listCategory,delCategory} from "@/api/busi/category";
 export default {
   name: "Category",
   components:{},
-  dicts: ['category_type'],
+  dicts: ['category_type','app_menu'],
   data() {
     return {
       // 遮罩层
@@ -233,7 +238,18 @@ export default {
       const url = `https://www.cdtruck.com/OutOpen/AddEmailRecord?callback=result&fromEmail=alicesales@scdtrailer.com&pathPage=https://www.cdtruck.com/&typeid=F9&_=1751524873382`
       window.open(url, "_blank");
     },
-
+    /**
+     * 判断是否APP栏目
+     */
+    checkIfAppCatg(catgId){
+      let arra = this.dict.type.app_menu
+      for(let i=0;i<arra.length;i++){
+        if(arra[i].label == catgId){
+          return true
+        }
+      }
+      return false
+    },
     /** 查询网站栏目列表 */
     getList() {
       this.loading = true;