优化代码

financial-penalty-monitor/backend/src/main/java/com/fintech/penalty/config/CrawlerConfig.java

@@ -35,9 +35,9 @@ public class CrawlerConfig {
     private int maxRetries = 3;
     
     /**
-     * 超时时间(毫秒)
+     * 超时时间(毫秒)，0表示不限制
      */
-    private int timeout = 30000;
+    private int timeout = 0;
     
     /**
      * 数据源列表
@@ -51,5 +51,7 @@ public class CrawlerConfig {
         private String baseUrl;
         private String listUrl;
         private boolean enabled = true;
+        private String detailUrl;
+        private String detailUrlPattern;
     }
 }

financial-penalty-monitor/backend/src/main/java/com/fintech/penalty/controller/CrawlController.java

@@ -48,6 +48,18 @@ public class CrawlController {
         return ResponseEntity.ok(ApiResponse.success(response));
     }
 
+    /**
+     * 停止爬取任务
+     */
+    @PostMapping("/stop")
+    public ResponseEntity<ApiResponse<Void>> stopCrawl() {
+        if (!crawlScheduler.isRunning()) {
+            return ResponseEntity.ok(ApiResponse.error(400, "没有正在执行的爬取任务"));
+        }
+        crawlScheduler.stopCrawl();
+        return ResponseEntity.ok(ApiResponse.success("爬取任务已停止", null));
+    }
+
     /**
      * 获取爬取状态
      */

financial-penalty-monitor/backend/src/main/java/com/fintech/penalty/crawler/PenaltyCrawler.java

@@ -16,6 +16,7 @@ import org.jsoup.Jsoup;
 import org.jsoup.nodes.Document;
 import org.jsoup.nodes.Element;
 import org.jsoup.select.Elements;
+import org.jsoup.safety.Safelist;
 import org.springframework.beans.factory.annotation.Value;
 import org.springframework.scheduling.annotation.Async;
 import org.springframework.stereotype.Component;
@@ -29,14 +30,13 @@ import java.time.LocalDate;
 import java.time.LocalDateTime;
 import java.time.format.DateTimeFormatter;
 import java.time.format.DateTimeParseException;
-import java.util.ArrayList;
-import java.util.List;
-import java.util.Optional;
-import java.util.UUID;
+import java.util.*;
 import java.util.concurrent.CompletableFuture;
-import java.util.concurrent.atomic.AtomicInteger;
+import java.util.concurrent.ConcurrentHashMap;
+import java.util.concurrent.atomic.AtomicLong;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
+import java.util.stream.Collectors;
 
 /**
  * 处罚信息爬虫 - 核心爬虫类（支持断点续传）
@@ -52,24 +52,35 @@ public class PenaltyCrawler {
     private final CrawlerConfig crawlerConfig;
 
     @Value("${crawler.resume.enabled:true}")
-    private boolean resumeEnabled;  // 是否启用断点续传，默认启用
+    private boolean resumeEnabled;
 
     @Value("${crawler.resume.force-restart:false}")
-    private boolean forceRestart;  // 是否强制重新开始，默认false
+    private boolean forceRestart;
+
+    @Value("${crawler.nfra.page-size:18}")
+    private int defaultPageSize;
+
+    @Value("${crawler.nfra.max-pages:10000}")
+    private int maxPages;
+
+    @Value("${crawler.nfra.request-interval-ms:1000}")
+    private long requestIntervalMs;
+
+    @Value("${crawler.nfra.batch-save-size:50}")
+    private int batchSaveSize;
 
     private static final String 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";
     private static final DateTimeFormatter DATE_FORMATTER = DateTimeFormatter.ofPattern("yyyy-MM-dd");
     private static final DateTimeFormatter DATE_FORMATTER_CN = DateTimeFormatter.ofPattern("yyyy[-/年]MM[-/月]dd[日]");
 
-    // 线程安全的罚单编号计数器（生产环境建议用数据库序列或Redis）
-    private final AtomicInteger penaltySeq = new AtomicInteger(0);
+    // 请求频率控制器
+    private final Map<String, AtomicLong> lastRequestTime = new ConcurrentHashMap<>();
 
     // 当前任务的唯一标识
     private String currentTaskId;
 
     @Async("crawlExecutor")
     public CompletableFuture<CrawlResult> crawl(CrawlerConfig.SourceConfig source) {
-        // 生成任务ID
         currentTaskId = UUID.randomUUID().toString();
 
         log.info("========== 开始爬取任务 ==========");
@@ -85,7 +96,6 @@ public class PenaltyCrawler {
         try {
             List<PenaltyRecord> records = crawlNFRA(source);
 
-            // 标记任务完成
             markTaskCompleted(source.getName());
 
             result.setSuccess(true);
@@ -99,7 +109,6 @@ public class PenaltyCrawler {
             log.error("爬取失败: {} - {}", source.getName(), e.getMessage(), e);
             result.setSuccess(false);
             result.setErrorMessage(e.getMessage());
-            // 标记任务失败
             markTaskFailed(source.getName());
         }
 
@@ -118,9 +127,8 @@ public class PenaltyCrawler {
         try {
             String baseUrl = normalizeBaseUrl(source.getBaseUrl());
 
-            // ========== 获取上次爬取进度 ==========
             int startPage = 1;
-            int pageSize = 18;
+            int pageSize = defaultPageSize;
             int totalPages = 4093;
             int totalNewRecords = 0;
 
@@ -128,7 +136,7 @@ public class PenaltyCrawler {
                 Optional<CrawlProgress> progressOpt = getLastProgress(source.getName());
                 if (progressOpt.isPresent() && !isTaskCompleted(source.getName())) {
                     CrawlProgress progress = progressOpt.get();
-                    startPage = progress.getLastPageIndex() + 1;  // 从下一页开始
+                    startPage = progress.getLastPageIndex() + 1;
                     totalPages = progress.getTotalPages() != null ? progress.getTotalPages() : totalPages;
                     totalNewRecords = progress.getTotalRecordsCrawled() != null ? progress.getTotalRecordsCrawled() : 0;
                     log.info("========== 检测到上次未完成的任务 ==========");
@@ -138,31 +146,29 @@ public class PenaltyCrawler {
                     log.info("本次将从第 {} 页继续爬取", startPage);
                 } else if (progressOpt.isPresent() && isTaskCompleted(source.getName())) {
                     log.info("上次任务已完成，本次从头开始爬取");
-                    // 清除旧的完成记录，开始新任务
                     clearProgress(source.getName());
                 } else {
                     log.info("未检测到未完成的任务，从头开始爬取");
                 }
             } else {
                 log.info("断点续传已禁用或强制重启，从头开始爬取");
-                // 清除旧的进度记录
                 clearProgress(source.getName());
             }
 
-            // 初始化进度记录
             initProgress(source.getName(), startPage - 1, totalPages, totalNewRecords);
 
-            // 记录失败的页码，用于后续重试
             List<Integer> failedPages = new ArrayList<>();
 
             int pageIndex = startPage;
-            int maxPages = 1000000;
 
             while (pageIndex <= totalPages && pageIndex <= maxPages) {
                 String listUrl = buildListApiUrl(source, pageIndex, pageSize);
                 log.info("正在抓取第{}页: {}", pageIndex, listUrl);
 
                 try {
+                    // 请求频率控制
+                    waitForRateLimit(source.getName());
+
                     String json = fetchJson(listUrl);
                     JsonNode rootNode = mapper.readTree(json);
 
@@ -172,7 +178,6 @@ public class PenaltyCrawler {
 
                         if (pageInfo.has("totalPages")) {
                             totalPages = pageInfo.get("totalPages").asInt();
-                            // 更新总页数到进度表
                             updateTotalPages(source.getName(), totalPages);
                         } else if (pageInfo.has("total")) {
                             int total = pageInfo.get("total").asInt();
@@ -180,72 +185,35 @@ public class PenaltyCrawler {
                             updateTotalPages(source.getName(), totalPages);
                         }
 
-                        int pageRecordCount = 0;
-                        int failedCount = 0;
-
-                        for (int i = 0; i < rows.size(); i++) {
-                            JsonNode row = rows.get(i);
-                            try {
-                                String docId = row.has("guid") ? row.get("guid").asText() :
-                                        (row.has("docId") ? row.get("docId").asText() : null);
-                                String title = row.has("docTitle") ? row.get("docTitle").asText() : "";
-
-                                if (docId == null || title.isEmpty()) {
-                                    log.debug("跳过无效记录: docId={}, title={}", docId, title);
-                                    failedCount++;
-                                    continue;
-                                }
-
-                                String detailUrl = baseUrl + "cn/static/data/DocInfo/SelectByDocId/data_docId=" + docId + ".json";
+                        // 解析当前页面的记录
+                        List<PenaltyRecord> pageRecords = parseRecordsFromJson(rows, source, baseUrl);
 
-                                PenaltyRecord record = fetchWithRetry(detailUrl, title, source, 3);
-                                if (record != null) {
-                                    // 检查是否已存在
-                                    boolean isNew = false;
-                                    if (record.getSourceUrl() != null && !record.getSourceUrl().isEmpty()) {
-                                        if (!penaltyRecordRepository.existsBySourceUrl(record.getSourceUrl())) {
-                                            isNew = true;
-                                        }
-                                    } else {
-                                        if (!penaltyRecordRepository.existsByIllegalFactsAndRegulator(
-                                                record.getIllegalFacts(), record.getRegulator())) {
-                                            isNew = true;
-                                        }
-                                    }
-
-                                    if (isNew) {
+                        int pageNewCount = 0;
+                        for (PenaltyRecord record : pageRecords) {
+                            if (!isRecordExists(record)) {
                                 batchBuffer.add(record);
                                 records.add(record);
-                                        pageRecordCount++;
+                                pageNewCount++;
                                 totalNewRecords++;
                             }
-                                } else {
-                                    failedCount++;
                         }
 
-                            } catch (Exception e) {
-                                failedCount++;
-                                log.error("解析第{}页第{}条记录失败: {}", pageIndex, i, e.getMessage());
-                            }
-                        }
-
-                        // ========== 每抓取10页保存一次到数据库 ==========
-                        if (pageIndex % 10 == 0 && !batchBuffer.isEmpty()) {
+                        // 批量保存
+                        if (batchBuffer.size() >= batchSaveSize) {
                             int savedCount = saveBatchToDatabase(batchBuffer);
                             log.info("===== 已抓取{}页，批量保存{}条新记录到数据库 =====", pageIndex, savedCount);
                             batchBuffer.clear();
                         }
 
-                        // ========== 每抓取5页更新一次进度（断点续传） ==========
+                        // 更新进度
                         if (pageIndex % 5 == 0) {
                             updateProgress(source.getName(), pageIndex, totalNewRecords);
                             log.info("===== 已更新爬取进度: 第{}页，累计{}条记录 =====", pageIndex, totalNewRecords);
                         }
 
-                        // 输出页面进度
                         double progress = (double) pageIndex / totalPages * 100;
-                        log.info("第{}页爬取完成，本页获取{}条新记录，失败{}条，累计{}条新记录，总进度：{:.2f}% ({}/{})",
-                                pageIndex, pageRecordCount, failedCount, totalNewRecords, progress, pageIndex, totalPages);
+                        log.info("第{}页爬取完成，本页获取{}条新记录，累计{}条新记录，总进度：{:.2f}% ({}/{})",
+                                pageIndex, pageNewCount, totalNewRecords, progress, pageIndex, totalPages);
 
                     } else if (rootNode.has("rptCode") && rootNode.get("rptCode").asText().equals("200")) {
                         log.warn("NFRA API返回结束标记(rptCode=200)，停止爬取");
@@ -263,27 +231,25 @@ public class PenaltyCrawler {
                     pageIndex++;
                 }
 
-                // 每爬完一页停留5秒
+                // 页面间隔
                 if (pageIndex <= totalPages && pageIndex <= maxPages) {
-                    log.info("等待5秒后继续爬取下一页...");
-                    Thread.sleep(1000);
+                    Thread.sleep(requestIntervalMs);
                 }
             }
 
-            // ========== 保存剩余不足10页的数据 ==========
+            // 保存剩余数据
             if (!batchBuffer.isEmpty()) {
                 int savedCount = saveBatchToDatabase(batchBuffer);
                 log.info("===== 爬取完成，保存最后{}条新记录到数据库 =====", savedCount);
                 batchBuffer.clear();
             }
 
-            // 最终更新进度
             updateProgress(source.getName(), pageIndex - 1, totalNewRecords);
 
             // 重试失败的页面
             if (!failedPages.isEmpty()) {
                 log.info("开始重试失败的页面: {}", failedPages);
-                retryFailedPagesWithBatchSave(source, failedPages, records, mapper, baseUrl, pageSize);
+                retryFailedPages(source, failedPages, records, mapper, baseUrl, pageSize);
             }
 
             if (records.isEmpty()) {
@@ -298,16 +264,14 @@ public class PenaltyCrawler {
 
         } catch (Exception e) {
             log.error("NFRA爬取失败: {}", e.getMessage(), e);
-            // 异常时也尝试保存已缓存的数据
             if (!batchBuffer.isEmpty()) {
                 saveBatchToDatabase(batchBuffer);
             }
-            // 更新失败状态
             updateProgressStatus(source.getName(), "FAILED");
             try {
-                records = crawlNFRADirect(source);
-                if (!records.isEmpty()) {
-                    saveBatchToDatabase(records);
+                List<PenaltyRecord> htmlRecords = crawlNFRADirect(source);
+                if (!htmlRecords.isEmpty()) {
+                    saveBatchToDatabase(htmlRecords);
                 }
             } catch (Exception ex) {
                 log.error("NFRA HTML解析也失败: {}", ex.getMessage());
@@ -316,33 +280,83 @@ public class PenaltyCrawler {
         return records;
     }
 
-    // ==================== 断点续传相关方法 ====================
+    /**
+     * 从JSON解析记录列表
+     */
+    private List<PenaltyRecord> parseRecordsFromJson(JsonNode rows, CrawlerConfig.SourceConfig source, String baseUrl) {
+        List<PenaltyRecord> records = new ArrayList<>();
+        for (JsonNode row : rows) {
+            try {
+                String docId = row.has("guid") ? row.get("guid").asText() :
+                        (row.has("docId") ? row.get("docId").asText() : null);
+                String title = row.has("docTitle") ? row.get("docTitle").asText() : "";
+
+                if (docId == null || title.isEmpty()) {
+                    log.debug("跳过无效记录: docId={}, title={}", docId, title);
+                    continue;
+                }
+
+                String detailUrl = baseUrl + "cn/static/data/DocInfo/SelectByDocId/data_docId=" + docId + ".json";
+                PenaltyRecord record = fetchWithRetry(detailUrl, title, source, 3);
+                if (record != null) {
+                    records.add(record);
+                }
+            } catch (Exception e) {
+                log.debug("解析记录失败: {}", e.getMessage());
+            }
+        }
+        return records;
+    }
 
     /**
-     * 获取上次的爬取进度
+     * 检查记录是否已存在
      */
-    private Optional<CrawlProgress> getLastProgress(String sourceName) {
-        return crawlProgressRepository.findBySourceNameAndStatus(sourceName, "RUNNING");
+    private boolean isRecordExists(PenaltyRecord record) {
+        try {
+            if (record.getSourceUrl() != null && !record.getSourceUrl().isEmpty()) {
+                return penaltyRecordRepository.existsBySourceUrl(record.getSourceUrl());
+            } else {
+                return penaltyRecordRepository.existsByIllegalFactsAndRegulator(
+                        record.getIllegalFacts(), record.getRegulator());
+            }
+        } catch (Exception e) {
+            log.error("检查记录是否存在失败: {}", e.getMessage());
+            return false;
+        }
     }
 
     /**
-     * 检查任务是否已完成
+     * 请求频率控制
      */
+    private void waitForRateLimit(String source) {
+        AtomicLong lastTime = lastRequestTime.computeIfAbsent(source, k -> new AtomicLong(0));
+        long now = System.currentTimeMillis();
+        long elapsed = now - lastTime.get();
+        if (elapsed < requestIntervalMs) {
+            try {
+                Thread.sleep(requestIntervalMs - elapsed);
+            } catch (InterruptedException e) {
+                Thread.currentThread().interrupt();
+            }
+        }
+        lastTime.set(System.currentTimeMillis());
+    }
+
+    // ==================== 断点续传相关方法 ====================
+
+    private Optional<CrawlProgress> getLastProgress(String sourceName) {
+        return crawlProgressRepository.findBySourceNameAndStatus(sourceName, "RUNNING");
+    }
+
     private boolean isTaskCompleted(String sourceName) {
         Optional<CrawlProgress> progressOpt = crawlProgressRepository.findBySourceNameAndStatus(sourceName, "COMPLETED");
         return progressOpt.isPresent();
     }
 
-    /**
-     * 初始化爬取进度
-     */
     private void initProgress(String sourceName, int lastPage, int totalPages, int totalRecords) {
         try {
-            // 先删除旧的RUNNING状态记录
             Optional<CrawlProgress> existing = crawlProgressRepository.findBySourceNameAndStatus(sourceName, "RUNNING");
-            if (existing.isPresent()) {
-                crawlProgressRepository.delete(existing.get());
-            }
+            existing.ifPresent(crawlProgressRepository::delete);
 
             CrawlProgress progress = CrawlProgress.builder()
                     .sourceName(sourceName)
@@ -361,9 +375,6 @@ public class PenaltyCrawler {
         }
     }
 
-    /**
-     * 更新爬取进度
-     */
     private void updateProgress(String sourceName, int pageIndex, int totalRecords) {
         try {
             crawlProgressRepository.updateProgress(sourceName, currentTaskId, pageIndex, LocalDateTime.now());
@@ -373,9 +384,6 @@ public class PenaltyCrawler {
         }
     }
 
-    /**
-     * 更新总页数
-     */
     private void updateTotalPages(String sourceName, int totalPages) {
         try {
             crawlProgressRepository.updateTotalPages(sourceName, currentTaskId, totalPages, LocalDateTime.now());
@@ -384,9 +392,6 @@ public class PenaltyCrawler {
         }
     }
 
-    /**
-     * 更新进度状态
-     */
     private void updateProgressStatus(String sourceName, String status) {
         try {
             crawlProgressRepository.updateStatus(sourceName, currentTaskId, status, LocalDateTime.now());
@@ -395,25 +400,16 @@ public class PenaltyCrawler {
         }
     }
 
-    /**
-     * 标记任务完成
-     */
     private void markTaskCompleted(String sourceName) {
         updateProgressStatus(sourceName, "COMPLETED");
         log.info("任务完成: source={}, taskId={}", sourceName, currentTaskId);
     }
 
-    /**
-     * 标记任务失败
-     */
     private void markTaskFailed(String sourceName) {
         updateProgressStatus(sourceName, "FAILED");
         log.info("任务失败: source={}, taskId={}", sourceName, currentTaskId);
     }
 
-    /**
-     * 清除进度记录
-     */
     private void clearProgress(String sourceName) {
         try {
             Optional<CrawlProgress> running = crawlProgressRepository.findBySourceNameAndStatus(sourceName, "RUNNING");
@@ -429,15 +425,25 @@ public class PenaltyCrawler {
     }
 
     /**
-     * 批量保存记录到数据库
+     * 批量保存记录到数据库（带去重）
      */
     private int saveBatchToDatabase(List<PenaltyRecord> records) {
         if (records == null || records.isEmpty()) {
             return 0;
         }
 
+        // 去重
+        List<PenaltyRecord> distinctRecords = records.stream()
+                .filter(record -> !isRecordExists(record))
+                .collect(Collectors.toList());
+
+        if (distinctRecords.isEmpty()) {
+            log.debug("批量保存: 所有记录都已存在，跳过");
+            return 0;
+        }
+
         int savedCount = 0;
-        for (PenaltyRecord record : records) {
+        for (PenaltyRecord record : distinctRecords) {
             try {
                 penaltyRecordRepository.save(record);
                 savedCount++;
@@ -446,14 +452,15 @@ public class PenaltyCrawler {
             }
         }
 
-        log.debug("批量保存完成: 成功保存{}条/共{}条", savedCount, records.size());
+        log.debug("批量保存完成: 成功保存{}条/共{}条（去重后{}条）",
+                savedCount, records.size(), distinctRecords.size());
         return savedCount;
     }
 
     /**
-     * 重试失败的页面（支持批量保存）
+     * 重试失败的页面
      */
-    private void retryFailedPagesWithBatchSave(CrawlerConfig.SourceConfig source, List<Integer> failedPages,
+    private void retryFailedPages(CrawlerConfig.SourceConfig source, List<Integer> failedPages,
                                   List<PenaltyRecord> records, ObjectMapper mapper,
                                   String baseUrl, int pageSize) {
         List<PenaltyRecord> retryBuffer = new ArrayList<>();
@@ -461,44 +468,27 @@ public class PenaltyCrawler {
         for (Integer pageIndex : failedPages) {
             try {
                 log.info("重试第{}页", pageIndex);
+                waitForRateLimit(source.getName());
+
                 String listUrl = buildListApiUrl(source, pageIndex, pageSize);
                 String json = fetchJson(listUrl);
                 JsonNode rootNode = mapper.readTree(json);
 
                 if (rootNode.has("data") && rootNode.get("data").has("rows")) {
                     JsonNode rows = rootNode.get("data").get("rows");
-                    for (JsonNode row : rows) {
-                        try {
-                            String docId = row.has("guid") ? row.get("guid").asText() :
-                                    (row.has("docId") ? row.get("docId").asText() : null);
-                            String title = row.has("docTitle") ? row.get("docTitle").asText() : "";
-
-                            if (docId != null && !title.isEmpty()) {
-                                String detailUrl = baseUrl + "cn/static/data/DocInfo/SelectByDocId/data_docId=" + docId + ".json";
-                                PenaltyRecord record = fetchWithRetry(detailUrl, title, source, 2);
-                                if (record != null && !records.contains(record)) {
-                                    boolean exists = false;
-                                    if (record.getSourceUrl() != null && !record.getSourceUrl().isEmpty()) {
-                                        exists = penaltyRecordRepository.existsBySourceUrl(record.getSourceUrl());
-                                    } else {
-                                        exists = penaltyRecordRepository.existsByIllegalFactsAndRegulator(
-                                                record.getIllegalFacts(), record.getRegulator());
-                                    }
+                    List<PenaltyRecord> pageRecords = parseRecordsFromJson(rows, source, baseUrl);
 
-                                    if (!exists) {
+                    for (PenaltyRecord record : pageRecords) {
+                        if (!isRecordExists(record) && !records.contains(record)) {
                             retryBuffer.add(record);
                             records.add(record);
                         }
                     }
                 }
-                        } catch (Exception e) {
-                            log.debug("重试时解析记录失败: {}", e.getMessage());
-                        }
-                    }
-                }
-                Thread.sleep(3000);
 
-                if (retryBuffer.size() >= 50) {
+                Thread.sleep(requestIntervalMs);
+
+                if (retryBuffer.size() >= batchSaveSize) {
                     saveBatchToDatabase(retryBuffer);
                     retryBuffer.clear();
                 }
@@ -512,11 +502,11 @@ public class PenaltyCrawler {
         }
     }
 
-    // 添加重试方法
     private PenaltyRecord fetchWithRetry(String detailUrl, String title,
                                          CrawlerConfig.SourceConfig source, int maxRetries) {
         for (int attempt = 1; attempt <= maxRetries; attempt++) {
             try {
+                waitForRateLimit(source.getName());
                 return fetchAndParseDetail(detailUrl, title, source);
             } catch (Exception e) {
                 if (attempt == maxRetries) {
@@ -524,7 +514,7 @@ public class PenaltyCrawler {
                     return null;
                 }
                 try {
-                    Thread.sleep(1000 * attempt);
+                    Thread.sleep(1000L * attempt);
                 } catch (InterruptedException ie) {
                     Thread.currentThread().interrupt();
                     return null;
@@ -540,7 +530,7 @@ public class PenaltyCrawler {
         if (pageIndex < 4) {
             return "https://www.nfra.gov.cn/cn/static/data/DocInfo/getDocInfoListByItemId/data_itemId=" + itemId + ",pageIndex=" + pageIndex + ",pageSize=" + pageSize + ".json";
         } else {
-            return "https://www.nfra.gov.cn/cbircweb/DocInfo/SelectDocByItemIdAndChild?itemId=" + itemId + "&pageSize=100&pageIndex="+pageIndex;
+            return "https://www.nfra.gov.cn/cbircweb/DocInfo/SelectDocByItemIdAndChild?itemId=" + itemId + "&pageSize=100&pageIndex=" + pageIndex;
         }
     }
 
@@ -553,6 +543,13 @@ public class PenaltyCrawler {
         return "1855";
     }
 
+    private String buildSourceUrl(String detailUrlPattern, String docId) {
+        if (detailUrlPattern == null || detailUrlPattern.isEmpty()) {
+            return "";
+        }
+        return detailUrlPattern.replace("*", docId);
+    }
+
     private String normalizeBaseUrl(String baseUrl) {
         if (baseUrl == null) return "https://www.nfra.gov.cn/";
         if (!baseUrl.endsWith("/")) {
@@ -563,12 +560,15 @@ public class PenaltyCrawler {
 
     private String fetchJson(String url) throws Exception {
         HttpURLConnection conn = null;
+        long timeout = crawlerConfig.getTimeout();
         try {
             conn = (HttpURLConnection) new URL(url).openConnection();
             conn.setRequestMethod("GET");
             conn.setRequestProperty("User-Agent", USER_AGENT);
-            conn.setConnectTimeout(30000);
-            conn.setReadTimeout(30000);
+            if (timeout > 0) {
+                conn.setConnectTimeout((int) timeout);
+                conn.setReadTimeout((int) timeout);
+            }
             conn.connect();
 
             try (BufferedReader reader = new BufferedReader(new InputStreamReader(conn.getInputStream(), "UTF-8"))) {
@@ -586,6 +586,283 @@ public class PenaltyCrawler {
         }
     }
 
+    // ==================== NFRA 表格解析专用方法 ====================
+
+    /**
+     * 专门解析 NFRA 处罚决定书的表格内容
+     * 这种表格格式是固定的：第一列是标签，第二列是对应的值
+     *
+     * 表格结构示例：
+     * | 行政处罚决定书文号 | 金罚决字〔2024〕28号 |
+     * | 被处罚当事人 | xxx |
+     * | 主要违法违规事实 | xxx |
+     * | 行政处罚依据 | xxx |
+     * | 行政处罚决定 | xxx |
+     * | 作出处罚决定的机关名称 | xxx |
+     * | 作出处罚决定的日期 | xxx |
+     */
+    private NFRAViolationInfo extractViolationInfoFromTable(String docClob) {
+        NFRAViolationInfo info = new NFRAViolationInfo();
+
+        if (docClob == null || docClob.isEmpty()) {
+            return info;
+        }
+
+        try {
+            // 解析HTML
+            Document document = Jsoup.parse(docClob);
+
+            // 查找所有表格
+            Elements tables = document.select("table");
+
+            for (Element table : tables) {
+                // 遍历表格行
+                Elements rows = table.select("tr");
+                for (Element row : rows) {
+                    Elements cells = row.select("td");
+                    if (cells.size() >= 2) {
+                        // 第一列是标签，第二列是值
+                        String label = cleanText(cells.get(0).text());
+                        String value = cleanText(cells.get(1).text());
+
+                        if (label.contains("行政处罚决定书文号")) {
+                            info.penaltyNumber = value;
+                        } else if (label.contains("被处罚当事人")) {
+                            info.institutionName = value;
+                            // 提取当事人姓名/名称
+                            info.personName = extractPersonNameFromParty(value);
+                        } else if (label.contains("主要违法违规事实")) {
+                            info.illegalFacts = value;
+                        } else if (label.contains("行政处罚依据")) {
+                            info.penaltyBasis = value;
+                        } else if (label.contains("行政处罚决定")) {
+                            info.penaltyDecision = value;
+                            // 从处罚决定中提取处罚类型和金额
+                            info.penaltyType = extractPenaltyTypeFromDecision(value);
+                            info.penaltyAmount = extractAmountFromDecision(value);
+                        } else if (label.contains("作出处罚决定的机关名称")) {
+                            info.regulator = value;
+                        } else if (label.contains("作出处罚决定的日期")) {
+                            info.penaltyDateStr = value;
+                        }
+                    }
+                }
+            }
+
+            // 如果表格解析没有获取到机构名称，尝试从文本中提取
+            if (info.institutionName.isEmpty()) {
+                info.institutionName = extractInstitutionFromText(document.text());
+            }
+
+            log.debug("表格解析结果: 文号={}, 机构={}, 违法事实={}, 处罚决定={}, 处罚金额={}",
+                    info.penaltyNumber, info.institutionName, info.illegalFacts,
+                    info.penaltyDecision, info.penaltyAmount);
+
+        } catch (Exception e) {
+            log.warn("解析处罚决定书表格失败: {}", e.getMessage());
+        }
+
+        return info;
+    }
+
+    /**
+     * 从当事人字符串中提取姓名/名称
+     * 格式如: "袁良明（时任中国信达资产管理股份有限公司风险管理部总经理）"
+     */
+    private String extractPersonNameFromParty(String partyStr) {
+        if (partyStr == null || partyStr.isEmpty()) {
+            return "";
+        }
+
+        // 提取括号前的姓名
+        Pattern pattern = Pattern.compile("^([^（(]+)");
+        Matcher matcher = pattern.matcher(partyStr);
+        if (matcher.find()) {
+            String name = matcher.group(1).trim();
+            if (name.length() > 0 && name.length() <= 50) {
+                return name;
+            }
+        }
+
+        return partyStr.length() > 50 ? partyStr.substring(0, 50) : partyStr;
+    }
+
+    /**
+     * 从处罚决定中提取处罚类型
+     */
+    private String extractPenaltyTypeFromDecision(String decision) {
+        if (decision == null || decision.isEmpty()) {
+            return "行政处罚";
+        }
+
+        if (decision.contains("警告")) {
+            return "警告";
+        } else if (decision.contains("罚款")) {
+            return "罚款";
+        } else if (decision.contains("没收")) {
+            return "没收违法所得";
+        } else if (decision.contains("吊销")) {
+            return "吊销许可证";
+        } else if (decision.contains("停业")) {
+            return "停业整顿";
+        } else if (decision.contains("市场禁入")) {
+            return "市场禁入";
+        }
+
+        return "行政处罚";
+    }
+
+    /**
+     * 从处罚决定中提取罚款金额
+     */
+    private BigDecimal extractAmountFromDecision(String decision) {
+        if (decision == null || decision.isEmpty()) {
+            return null;
+        }
+
+        // 匹配罚款金额
+        Pattern pattern = Pattern.compile("罚款\\s*(\\d+(?:,\\d{3})*(?:\\.\\d+)?)\\s*(?:万元?|元)");
+        Matcher matcher = pattern.matcher(decision);
+        if (matcher.find()) {
+            String amountStr = matcher.group(1).replace(",", "");
+            try {
+                BigDecimal amount = new BigDecimal(amountStr);
+                if (matcher.group().contains("万")) {
+                    return amount.multiply(new BigDecimal("10000"));
+                }
+                return amount;
+            } catch (NumberFormatException e) {
+                log.debug("金额解析失败: {}", amountStr);
+            }
+        }
+
+        return null;
+    }
+
+    /**
+     * 从文本中提取机构名称
+     */
+    private String extractInstitutionFromText(String text) {
+        if (text == null || text.isEmpty()) {
+            return "";
+        }
+
+        // 匹配 "被处罚当事人：xxx" 格式
+        Pattern pattern = Pattern.compile("被处罚当事人[：:]\\s*([^\\n\\r，,。]+)");
+        Matcher matcher = pattern.matcher(text);
+        if (matcher.find()) {
+            String name = matcher.group(1).trim();
+            if (name.length() > 0 && name.length() <= 100) {
+                return name;
+            }
+        }
+
+        return "";
+    }
+
+    /**
+     * 清理文本，去除多余空白和特殊字符
+     */
+    private String cleanText(String text) {
+        if (text == null) {
+            return "";
+        }
+        // 去除首尾空白，将多个空白替换为单个空格
+        return text.trim().replaceAll("\\s+", " ");
+    }
+
+    /**
+     * 从 docClob 中提取内容，只保留文本和表格
+     */
+    private String extractCleanContentWithTables(String docClob) {
+        if (docClob == null || docClob.isEmpty()) {
+            return "";
+        }
+
+        try {
+            Document document = Jsoup.parse(docClob);
+
+            StringBuilder result = new StringBuilder();
+
+            // 提取表格内容
+            Elements tables = document.select("table");
+            if (!tables.isEmpty()) {
+                result.append("\n【表格内容】\n");
+                for (Element table : tables) {
+                    String tableText = extractTableContent(table);
+                    result.append(tableText).append("\n");
+                }
+                result.append("【表格内容结束】\n");
+            }
+
+            // 移除所有脚本、样式、链接等
+            document.select("script, style, link, meta, head, nav, footer, aside").remove();
+
+            // 获取纯文本
+            String textContent = document.text();
+
+            if (result.length() > 0) {
+                return result.toString() + "\n【其他内容】\n" + textContent;
+            } else {
+                return textContent;
+            }
+
+        } catch (Exception e) {
+            log.debug("解析 docClob 失败: {}", e.getMessage());
+            return Jsoup.clean(docClob, Safelist.simpleText());
+        }
+    }
+
+    /**
+     * 提取表格内容为可读格式
+     */
+    private String extractTableContent(Element table) {
+        StringBuilder tableContent = new StringBuilder();
+
+        try {
+            Elements headers = table.select("th");
+            if (!headers.isEmpty()) {
+                tableContent.append("表头: ");
+                for (int i = 0; i < headers.size(); i++) {
+                    if (i > 0) tableContent.append(" | ");
+                    tableContent.append(headers.get(i).text().trim());
+                }
+                tableContent.append("\n");
+            }
+
+            Elements rows = table.select("tr");
+            int rowCount = 0;
+            for (Element row : rows) {
+                if (row.select("th").isEmpty()) {
+                    Elements cells = row.select("td");
+                    if (!cells.isEmpty()) {
+                        rowCount++;
+                        tableContent.append("第").append(rowCount).append("行: ");
+                        for (int i = 0; i < cells.size(); i++) {
+                            if (i > 0) tableContent.append(" | ");
+                            String cellText = cells.get(i).text().trim();
+                            if (cellText.length() > 200) {
+                                cellText = cellText.substring(0, 200) + "...";
+                            }
+                            tableContent.append(cellText);
+                        }
+                        tableContent.append("\n");
+                    }
+                }
+            }
+
+            if (rowCount == 0) {
+                tableContent.append("表格数据: ").append(table.text()).append("\n");
+            }
+
+        } catch (Exception e) {
+            log.debug("提取表格内容失败: {}", e.getMessage());
+            tableContent.append("表格数据: ").append(table.text()).append("\n");
+        }
+
+        return tableContent.toString();
+    }
+
     private PenaltyRecord fetchAndParseDetail(String detailUrl, String title, CrawlerConfig.SourceConfig source) {
         try {
             ObjectMapper mapper = new ObjectMapper();
@@ -599,24 +876,75 @@ public class PenaltyCrawler {
             String publishDate = data.has("publishDate") ? data.get("publishDate").asText() : "";
             String docClob = data.has("docClob") ? data.get("docClob").asText() : "";
 
-            String penaltyNumber = extractPenaltyNumber(docTitle);
-            String institutionName = extractInstitutionNameFromContent(docClob);
-            String penaltyAmountStr = extractPenaltyAmount(docClob);
-            String illegalFacts = extractIllegalFacts(docClob);
+            // 从API URL中提取docId，构造正确的展示链接
+            String docId = null;
+            Pattern docIdPattern = Pattern.compile("data_docId=([^\\.]+)");
+            Matcher docIdMatcher = docIdPattern.matcher(detailUrl);
+            if (docIdMatcher.find()) {
+                docId = docIdMatcher.group(1);
+            }
+
+            // 优先使用表格解析
+            NFRAViolationInfo tableInfo = extractViolationInfoFromTable(docClob);
+
+            String penaltyNumber;
+            String institutionName;
+            String illegalFacts;
+            String penaltyBasis;
+            BigDecimal penaltyAmount;
+            String penaltyType;
+            String regulator;
+            LocalDate penaltyDate;
+
+            // 如果表格解析有结果，使用表格数据；否则使用原有的正则解析
+            if (tableInfo != null && (tableInfo.penaltyNumber != null && !tableInfo.penaltyNumber.isEmpty()
+                    || tableInfo.institutionName != null && !tableInfo.institutionName.isEmpty())) {
+
+                // 使用表格解析的数据
+                penaltyNumber = !tableInfo.penaltyNumber.isEmpty() ? tableInfo.penaltyNumber : extractPenaltyNumber(docTitle);
+                institutionName = !tableInfo.institutionName.isEmpty() ? tableInfo.institutionName : extractInstitutionNameFromContent(docClob);
+                if (institutionName.isEmpty()) {
+                    institutionName = extractInstitutionName(docTitle);
+                }
+                illegalFacts = !tableInfo.illegalFacts.isEmpty() ? tableInfo.illegalFacts : extractIllegalFacts(docClob);
+                penaltyBasis = !tableInfo.penaltyBasis.isEmpty() ? tableInfo.penaltyBasis : extractPenaltyBasis(docClob);
+                penaltyAmount = tableInfo.penaltyAmount != null ? tableInfo.penaltyAmount : extractPenaltyAmountImproved(docClob);
+                penaltyType = !tableInfo.penaltyType.isEmpty() ? tableInfo.penaltyType : guessPenaltyType(docTitle);
+                regulator = !tableInfo.regulator.isEmpty() ? tableInfo.regulator : "国家金融监督管理总局";
+                penaltyDate = !tableInfo.penaltyDateStr.isEmpty() ? parseDateSafely(tableInfo.penaltyDateStr) : parseDateSafely(publishDate);
+
+                log.debug("使用表格解析结果: 文号={}, 机构={}, 违法事实={}, 处罚依据={}, 处罚类型={}",
+                        penaltyNumber, institutionName, illegalFacts, penaltyBasis, penaltyType);
+            } else {
+                // 回退到原有的正则解析
+                penaltyNumber = extractPenaltyNumber(docTitle);
+                institutionName = extractInstitutionNameFromContent(docClob);
+                if (institutionName.isEmpty()) {
+                    institutionName = extractInstitutionName(docTitle);
+                }
+                illegalFacts = extractIllegalFacts(docClob);
+                penaltyBasis = extractPenaltyBasis(docClob);
+                penaltyAmount = extractPenaltyAmountImproved(docClob);
+                penaltyType = guessPenaltyType(docTitle);
+                regulator = "国家金融监督管理总局";
+                penaltyDate = parseDateSafely(publishDate);
+            }
 
-            LocalDate penaltyDate = parseDateSafely(publishDate);
+            String sourceUrl = buildSourceUrl(source.getDetailUrlPattern(), docId);
+            String province = extractProvince(institutionName, docClob);
 
             return PenaltyRecord.builder()
                     .penaltyNumber(penaltyNumber)
-                    .institutionName(institutionName.isEmpty() ? extractInstitutionName(docTitle) : institutionName)
+                    .institutionName(institutionName)
                     .institutionType(guessInstitutionType(institutionName))
-                    .penaltyType("行政处罚")
-                    .penaltyAmount(penaltyAmountStr != null ? new BigDecimal(penaltyAmountStr) : null)
+                    .penaltyType(penaltyType)
+                    .penaltyAmount(penaltyAmount)
                     .penaltyDate(penaltyDate)
-                    .regulator("国家金融监督管理总局")
+                    .regulator(regulator)
+                    .province(province)
                     .illegalFacts(illegalFacts)
-                    .penaltyBasis(extractPenaltyBasis(docClob))
-                    .sourceUrl(detailUrl)
+                    .penaltyBasis(penaltyBasis)
+                    .sourceUrl(sourceUrl)
                     .createdAt(LocalDateTime.now())
                     .isNew(true)
                     .build();
@@ -627,6 +955,39 @@ public class PenaltyCrawler {
         }
     }
 
+    /**
+     * 改进的处罚金额解析（支持多种格式和单位转换）
+     */
+    private BigDecimal extractPenaltyAmountImproved(String content) {
+        if (content == null) return null;
+
+        String[] patterns = {
+                "罚款[：:]?\\s*(\\d+(?:,\\d{3})*(?:\\.\\d+)?)\\s*(?:万元?|元)",
+                "没收[^\\d]*(\\d+(?:,\\d{3})*(?:\\.\\d+)?)\\s*(?:万元?|元)",
+                "处以?\\s*(\\d+(?:,\\d{3})*(?:\\.\\d+)?)\\s*(?:万元?|元)",
+                "合计[^\\d]*(\\d+(?:,\\d{3})*(?:\\.\\d+)?)\\s*(?:万元?|元)",
+                "金额[：:]?\\s*(\\d+(?:,\\d{3})*(?:\\.\\d+)?)\\s*(?:万元?|元)"
+        };
+
+        for (String pattern : patterns) {
+            Matcher matcher = Pattern.compile(pattern, Pattern.CASE_INSENSITIVE).matcher(content);
+            if (matcher.find()) {
+                String amountStr = matcher.group(1).replace(",", "");
+                try {
+                    BigDecimal amount = new BigDecimal(amountStr);
+                    String matchedText = matcher.group();
+                    if (matchedText.contains("万")) {
+                        return amount.multiply(new BigDecimal("10000"));
+                    }
+                    return amount;
+                } catch (NumberFormatException e) {
+                    log.debug("金额数字解析失败: {}", amountStr);
+                }
+            }
+        }
+        return null;
+    }
+
     private LocalDate parseDateSafely(String dateStr) {
         if (dateStr == null || dateStr.isEmpty()) {
             return LocalDate.now();
@@ -694,8 +1055,8 @@ public class PenaltyCrawler {
             case "国家金融监督管理总局" -> "金监";
             default -> "文";
         };
-        int seq = penaltySeq.incrementAndGet() % 10000;
-        return prefix + "罚决字〔" + LocalDate.now().getYear() + "〕" + String.format("%04d", seq);
+        String seq = String.format("%04d", System.currentTimeMillis() % 10000);
+        return prefix + "罚决字〔" + LocalDate.now().getYear() + "〕" + seq;
     }
 
     private String extractInstitutionName(String title) {
@@ -750,7 +1111,7 @@ public class PenaltyCrawler {
         return baseUrl + "/" + relativeUrl;
     }
 
-    // ==================== NFRA 内容解析 ====================
+    // ==================== NFRA 内容解析（正则备用） ====================
 
     private String extractPenaltyNumber(String text) {
         if (text == null) return "";
@@ -776,35 +1137,27 @@ public class PenaltyCrawler {
         return "";
     }
 
-    private String extractPenaltyAmount(String content) {
-        if (content == null) return null;
-        Pattern pattern = Pattern.compile("罚款[：:]?\\s*(\\d+(?:\\.\\d+)?)\\s*(?:万元?|元)");
-        Matcher matcher = pattern.matcher(content);
-        if (matcher.find()) {
-            return matcher.group(1);
-        }
-        pattern = Pattern.compile("处以?\\s*(\\d+(?:\\.\\d+)?)\\s*(?:万元?|元)");
-        matcher = pattern.matcher(content);
-        if (matcher.find()) {
-            return matcher.group(1);
-        }
-        return null;
-    }
-
     private String extractIllegalFacts(String content) {
         if (content == null) return "";
         Pattern pattern = Pattern.compile("主要违法违规事实[：:]?\\s*(.+?)(?=处罚内容|作出处罚决定|$)", Pattern.DOTALL);
         Matcher matcher = pattern.matcher(content);
         if (matcher.find()) {
             String facts = matcher.group(1).trim();
+            facts = stripHtmlTags(facts);
             return facts.length() > 500 ? facts.substring(0, 500) : facts;
         }
+        content = stripHtmlTags(content);
         if (content.length() > 200) {
             return content.substring(0, 200);
         }
         return content;
     }
 
+    private String stripHtmlTags(String html) {
+        if (html == null || html.isEmpty()) return "";
+        return html.replaceAll("<[^>]+>", "");
+    }
+
     private String extractPenaltyBasis(String content) {
         if (content == null) return "";
         Pattern pattern = Pattern.compile("处罚依据[：:]?\\s*(.+?)(?=\\。\\s*\\《|\\、|作出处罚决定|$)", Pattern.DOTALL);
@@ -816,6 +1169,30 @@ public class PenaltyCrawler {
         return "";
     }
 
+    private String extractProvince(String institutionName, String content) {
+        if (institutionName == null) return "";
+        String[] provinces = {"北京", "天津", "河北", "山西", "内蒙古", "辽宁", "吉林", "黑龙江",
+                "上海", "江苏", "浙江", "安徽", "福建", "江西", "山东", "河南", "湖北", "湖南",
+                "广东", "广西", "海南", "重庆", "四川", "贵州", "云南", "西藏", "陕西", "甘肃",
+                "青海", "宁夏", "新疆", "深圳", "宁波", "青岛", "大连", "厦门"};
+        for (String province : provinces) {
+            if (institutionName.contains(province)) {
+                return province;
+            }
+        }
+        Pattern pattern = Pattern.compile("([\\u4e00-\\u9fa5]{2,6}(?:省|市|自治区|特别行政区))");
+        Matcher matcher = pattern.matcher(content);
+        while (matcher.find()) {
+            String match = matcher.group(1);
+            for (String province : provinces) {
+                if (match.contains(province)) {
+                    return province;
+                }
+            }
+        }
+        return "";
+    }
+
     // ==================== HTML 直接解析备用 ====================
 
     private List<PenaltyRecord> crawlNFRADirect(CrawlerConfig.SourceConfig source) throws Exception {
@@ -843,6 +1220,7 @@ public class PenaltyCrawler {
                             .penaltyType(guessPenaltyType(title))
                             .penaltyDate(penaltyDate)
                             .regulator("国家金融监督管理总局")
+                            .province(extractProvince(extractInstitutionName(title), ""))
                             .illegalFacts(title)
                             .sourceUrl(buildFullUrl(source.getBaseUrl(), href))
                             .createdAt(LocalDateTime.now())
@@ -900,6 +1278,7 @@ public class PenaltyCrawler {
                             .penaltyType(guessPenaltyType(title))
                             .penaltyDate(penaltyDate)
                             .regulator(regulator)
+                            .province(extractProvince(extractInstitutionName(title), ""))
                             .illegalFacts(title)
                             .sourceUrl(buildFullUrl(source.getBaseUrl(), href))
                             .createdAt(LocalDateTime.now())
@@ -933,4 +1312,22 @@ public class PenaltyCrawler {
                 .isNew(entity.getIsNew())
                 .build();
     }
+
+    // ==================== 内部类 ====================
+
+    /**
+     * 内部类，用于存储从表格中提取的处罚信息
+     */
+    private static class NFRAViolationInfo {
+        String penaltyNumber = "";
+        String institutionName = "";
+        String personName = "";
+        String illegalFacts = "";
+        String penaltyBasis = "";
+        String penaltyDecision = "";
+        String penaltyType = "";
+        String regulator = "";
+        String penaltyDateStr = "";
+        BigDecimal penaltyAmount = null;
+    }
 }
\ No newline at end of file

financial-penalty-monitor/backend/src/main/java/com/fintech/penalty/dto/PenaltyRecordDTO.java

@@ -26,6 +26,7 @@ public class PenaltyRecordDTO {
     private BigDecimal penaltyAmount;
     private LocalDate penaltyDate;
     private String regulator;
+    private String province;
     private String illegalFacts;
     private String penaltyBasis;
     private String sourceUrl;

financial-penalty-monitor/backend/src/main/java/com/fintech/penalty/entity/PenaltyRecord.java

@@ -20,6 +20,7 @@ import java.time.LocalDateTime;
     @Index(name = "idx_penalty_type", columnList = "penaltyType"),
     @Index(name = "idx_penalty_date", columnList = "penaltyDate"),
     @Index(name = "idx_regulator", columnList = "regulator"),
+    @Index(name = "idx_province", columnList = "province"),
     @Index(name = "idx_is_new", columnList = "isNew"),
     @Index(name = "idx_created_at", columnList = "createdAt")
 })
@@ -75,6 +76,12 @@ public class PenaltyRecord {
     @Column(name = "regulator", length = 100)
     private String regulator;
 
+    /**
+     * 省份
+     */
+    @Column(name = "province", length = 50)
+    private String province;
+    
     /**
      * 违法事实
      */

financial-penalty-monitor/backend/src/main/java/com/fintech/penalty/scheduler/CrawlScheduler.java

@@ -94,6 +94,7 @@ public class CrawlScheduler {
         config.setCode(source.getSourceType());
         config.setBaseUrl(source.getSourceUrl());
         config.setListUrl(source.getSourceUrl() + (source.getListUrlPattern() != null ? source.getListUrlPattern() : ""));
+        config.setDetailUrlPattern(source.getDetailUrlPattern());
         config.setEnabled(source.getIsEnabled());
         return config;
     }
@@ -156,4 +157,16 @@ public class CrawlScheduler {
     public boolean isRunning() {
         return isRunning;
     }
+
+    /**
+     * 停止爬取任务
+     */
+    public void stopCrawl() {
+        if (!isRunning) {
+            log.warn("没有正在执行的爬取任务");
+            return;
+        }
+        isRunning = false;
+        log.info("爬取任务已请求停止");
+    }
 }

financial-penalty-monitor/backend/src/main/java/com/fintech/penalty/service/CrawlTaskService.java

@@ -107,9 +107,6 @@ public class CrawlTaskService {
         return crawlSourceRepository.findAllByOrderBySortOrder();
     }
 
-    public List<CrawlSource> getAllSources() {
-        return crawlSourceRepository.findAll();
-    }
     
     /**
      * 获取最新任务状态

financial-penalty-monitor/backend/src/main/java/com/fintech/penalty/service/PenaltyRecordService.java

@@ -243,6 +243,7 @@ public class PenaltyRecordService {
                 .penaltyAmount(entity.getPenaltyAmount())
                 .penaltyDate(entity.getPenaltyDate())
                 .regulator(entity.getRegulator())
+                .province(entity.getProvince())
                 .illegalFacts(entity.getIllegalFacts())
                 .penaltyBasis(entity.getPenaltyBasis())
                 .sourceUrl(entity.getSourceUrl())

financial-penalty-monitor/backend/src/main/resources/application.yml

 server:
-  port: 8080
+  port: 8082
   servlet:
     context-path: /api
 
@@ -10,7 +10,7 @@ spring:
   datasource:
     url: jdbc:mysql://localhost:3306/penalty_monitor?useUnicode=true&characterEncoding=utf8&serverTimezone=Asia/Shanghai&useSSL=false
     username: root
-    password: 123456
+    password: ZhongRunChangHong/123
     driver-class-name: com.mysql.cj.jdbc.Driver
     hikari:
       minimum-idle: 5
@@ -38,6 +38,7 @@ spring:
       write-dates-as-timestamps: false
 
 # 爬虫配置（数据源从数据库 crawl_sources 表读取）
+
 crawler:
   enabled: true
   cron: "0 0 2 * * ?"
@@ -47,6 +48,10 @@ crawler:
   resume:
     enabled: true          # 是否启用断点续传
     force-restart: false   # 是否强制重新开始（设为true会忽略之前的进度）
+  nfra:
+    page-size: 18
+    max-pages: 10000
+    request-interval-ms: 1000
 
 deepseek:
   api:

financial-penalty-monitor/backend/target/classes/application.yml

@@ -38,6 +38,7 @@ spring:
       write-dates-as-timestamps: false
 
 # 爬虫配置（数据源从数据库 crawl_sources 表读取）
+
 crawler:
   enabled: true
   cron: "0 0 2 * * ?"
@@ -47,6 +48,10 @@ crawler:
   resume:
     enabled: true          # 是否启用断点续传
     force-restart: false   # 是否强制重新开始（设为true会忽略之前的进度）
+  nfra:
+    page-size: 18
+    max-pages: 10000
+    request-interval-ms: 1000
 
 deepseek:
   api:

financial-penalty-monitor/backend/target/maven-status/maven-compiler-plugin/compile/default-compile/inputFiles.lst

@@ -46,6 +46,7 @@ D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\service\ReportTemplateService.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\entity\AnalysisKeyword.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\dto\CreateUserRequest.java
+D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\entity\CrawlProgress.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\controller\ReportTemplateController.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\service\PermissionService.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\dto\CreatePermissionRequest.java
@@ -72,6 +73,7 @@ D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\dto\PenaltyRecordDTO.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\controller\RoleController.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\dto\StatisticsDTO.java
+D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\repository\CrawlProgressRepository.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\dto\UpdatePermissionRequest.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\scheduler\CrawlScheduler.java
 D:\new_workspace_06\aispace\financial-penalty-monitor\backend\src\main\java\com\fintech\penalty\dto\CreateMenuRequest.java

financial-penalty-monitor/frontend/dist/index.html

@@ -5,7 +5,7 @@
     <link rel="icon" href="/favicon.ico">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <title>金融监管处罚监控系统</title>
-    <script type="module" crossorigin src="/assets/index-BM812JBU.js"></script>
+    <script type="module" crossorigin src="/assets/index-D0VsMWb-.js"></script>
     <link rel="stylesheet" crossorigin href="/assets/index-D_lRsYFa.css">
   </head>
   <body>

financial-penalty-monitor/frontend/package.json

@@ -5,7 +5,7 @@
   "private": true,
   "scripts": {
     "dev": "vite",
-    "build": "vite build",
+    "build": "vite build --mode prod",
     "preview": "vite preview"
   },
   "dependencies": {

financial-penalty-monitor/frontend/src/api/index.js

@@ -159,6 +159,7 @@ export default {
   
   // 爬取任务
   triggerCrawl: () => request.post('/crawl/trigger'),
+  stopCrawl: () => request.post('/crawl/stop'),
   getCrawlStatus: () => request.get('/crawl/status'),
   getCrawlHistory: (params) => request.get('/crawl/history', { params }),
   clearCrawlHistory: () => request.delete('/crawl/history'),

financial-penalty-monitor/frontend/src/views/CrawlManage.vue

@@ -10,6 +10,9 @@
             <el-button type="primary" @click="handleTrigger" :loading="loading" :icon="Refresh">
               立即爬取
             </el-button>
+            <el-button type="danger" @click="handleStop" :loading="stopLoading" :disabled="!isRunning">
+              停止爬取
+            </el-button>
           </div>
         </div>
       </template>
@@ -222,6 +225,8 @@ import api from '../api'
 import dayjs from 'dayjs'
 
 const loading = ref(false)
+const stopLoading = ref(false)
+const isRunning = ref(false)
 const crawlingSource = ref(null)
 const sources = ref([])
 const historyData = ref([])
@@ -305,6 +310,7 @@ const fetchSources = async () => {
 const fetchStatus = async () => {
   try {
     const res = await api.getCrawlStatus()
+    isRunning.value = res.data.isRunning
     const tasks = res.data.tasks || []
     taskStatuses.value = {}
     tasks.forEach(task => {
@@ -358,6 +364,23 @@ const handleTrigger = async () => {
     }
   } finally {
     loading.value = false
+    fetchStatus()
+  }
+}
+
+const handleStop = async () => {
+  try {
+    await ElMessageBox.confirm('确定要停止当前爬取任务吗？', '警告', { type: 'warning' })
+    stopLoading.value = true
+    await api.stopCrawl()
+    ElMessage.success('已发送停止请求')
+    fetchStatus()
+  } catch (error) {
+    if (error !== 'cancel') {
+      ElMessage.error('停止失败')
+    }
+  } finally {
+    stopLoading.value = false
   }
 }
 
@@ -540,6 +563,9 @@ onMounted(() => {
   fetchSources()
   fetchStatus()
   fetchHistory()
+  setInterval(() => {
+    fetchStatus()
+  }, 3000)
 })
 </script>
 

financial-penalty-monitor/frontend/src/views/PenaltyList.vue

@@ -66,9 +66,9 @@
       <el-table 
         :data="tableData" 
         v-loading="loading" 
-        stripe 
+         
         @selection-change="handleSelectionChange"
-        border
+        border="true"
         resizable
       >
         <el-table-column type="selection" width="55" />
@@ -79,7 +79,7 @@
             </el-link>
           </template>
         </el-table-column>
-        <el-table-column prop="institutionName" label="机构名称" min-width="200" show-overflow-tooltip resizable />
+        <el-table-column prop="institutionName" label="机构名称" min-width="100" show-overflow-tooltip resizable />
         <el-table-column prop="institutionType" label="机构类型" width="100" resizable>
           <template #default="{ row }">
             <el-tag size="small" :type="getTypeColor(row.institutionType)">{{ row.institutionType }}</el-tag>
@@ -93,14 +93,15 @@
           </template>
         </el-table-column>
         <el-table-column prop="penaltyDate" label="处罚日期" width="120" resizable />
-        <el-table-column prop="regulator" label="监管机构" width="120" resizable />
+        <el-table-column prop="regulator" label="监管机构" width="250"  show-overflow-tooltip resizable />
+        <el-table-column prop="province" label="省份" width="130" resizable />
         <el-table-column prop="isNew" label="状态" width="80" resizable>
           <template #default="{ row }">
             <el-tag v-if="row.isNew" type="danger" size="small">新</el-tag>
             <span v-else style="color: #909399">已读</span>
           </template>
         </el-table-column>
-        <el-table-column label="分析状态" width="100" resizable>
+        <el-table-column label="分析状态" width="120">
           <template #default="{ row }">
             <el-tag v-if="row.analysisStatus == 'pending'" size="small">待分析</el-tag>
             <el-tag v-else-if="row.analysisStatus == 'analyzing'" type="warning" size="small">分析中</el-tag>
@@ -109,7 +110,7 @@
             <span v-else>-</span>
           </template>
         </el-table-column>
-        <el-table-column label="操作" width="250" fixed="right">
+        <el-table-column label="操作" width="230" fixed="right" align="center">
           <template #default="{ row }">
             <el-button type="primary" link @click="viewDetail(row)">详情</el-button>
             <el-button type="primary" link @click="openReportDrawer(row)">报告</el-button>
@@ -142,7 +143,7 @@
     </el-card>
 
     <!-- 详情弹窗 -->
-    <el-dialog v-model="detailVisible" title="处罚详情" width="825px" :fullscreen="detailFullscreen" show-fullscreen>
+    <el-dialog v-model="detailVisible" title="处罚详情" width="750px" :fullscreen="detailFullscreen" show-fullscreen>
       <template #header>
         <div class="detail-header">
           <span>处罚详情</span>
@@ -151,7 +152,7 @@
           </el-button>
         </div>
       </template>
-      <el-descriptions v-if="currentRecord" :column="2" border>
+      <el-descriptions v-if="currentRecord" :column="2" border label-width="100px">
         <el-descriptions-item label="处罚编号" :span="2">{{ currentRecord.penaltyNumber }}</el-descriptions-item>
         <el-descriptions-item label="被处罚机构" :span="2">{{ currentRecord.institutionName }}</el-descriptions-item>
         <el-descriptions-item label="机构类型">{{ currentRecord.institutionType }}</el-descriptions-item>