v5.1.3发布

README.md

@@ -1,5 +1,4 @@
 <p align="center">
-    <a href="https://www.swiftproxy.net/?code=T2WV1VT50"><img src="https://xxyopen.com/images/ad1.png" alt="AD" ></a>
     <a href="https://cloud.tencent.com/act/cps/redirect?redirect=2446&cps_key=736e609d66e0ac4e57813316cec6fd0b&from=console"><img src="https://youdoc.github.io/img/tencent.jpg" alt="AD" ></a>
 </p>
 <p align="center">

novel-admin/pom.xml

@@ -5,7 +5,7 @@
 
     <groupId>com.java2nb</groupId>
     <artifactId>novel-admin</artifactId>
-    <version>5.1.1</version>
+    <version>5.1.3</version>
     <packaging>jar</packaging>
 
     <name>novel-admin</name>

novel-common/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <artifactId>novel</artifactId>
         <groupId>com.java2nb</groupId>
-        <version>5.1.1</version>
+        <version>5.1.3</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 

novel-common/src/main/java/com/java2nb/novel/core/cache/CacheKey.java

@@ -41,11 +41,6 @@ public interface CacheKey {
      * */
     String TEMPLATE_DIR_KEY =  "templateDirKey";;
 
-    /**
-     * 正在运行的爬虫线程存储KEY前缀
-     * */
-    String RUNNING_CRAWL_THREAD_KEY_PREFIX = "runningCrawlTreadDataKeyPrefix";
-
     /**
      * 上一次搜索引擎更新的时间
      * */

novel-crawl/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <artifactId>novel</artifactId>
         <groupId>com.java2nb</groupId>
-        <version>5.1.1</version>
+        <version>5.1.3</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 

novel-crawl/src/main/java/com/java2nb/novel/core/crawl/CrawlBookHandler.java

@@ -7,6 +7,6 @@ import com.java2nb.novel.entity.Book;
  * */
 public interface CrawlBookHandler {
 
-    void handle(Book book);
+    void handle(Book book) throws InterruptedException;
 
 }

novel-crawl/src/main/java/com/java2nb/novel/core/crawl/CrawlParser.java

@@ -10,9 +10,11 @@ import com.java2nb.novel.utils.CrawlHttpClient;
 import io.github.xxyopen.util.IdWorker;
 import lombok.RequiredArgsConstructor;
 import lombok.SneakyThrows;
+import lombok.extern.slf4j.Slf4j;
 import org.apache.commons.lang3.StringUtils;
 import org.springframework.stereotype.Component;
 
+import java.text.ParseException;
 import java.text.SimpleDateFormat;
 import java.util.ArrayList;
 import java.util.Date;
@@ -26,6 +28,7 @@ import java.util.regex.Pattern;
  *
  * @author Administrator
  */
+@Slf4j
 @Component
 @RequiredArgsConstructor
 public class CrawlParser {
@@ -34,8 +37,8 @@ public class CrawlParser {
 
     private final CrawlHttpClient crawlHttpClient;
 
-    @SneakyThrows
+    public void parseBook(RuleBean ruleBean, String bookId, CrawlBookHandler handler)
-    public void parseBook(RuleBean ruleBean, String bookId, CrawlBookHandler handler) {
+        throws InterruptedException {
         Book book = new Book();
         String bookDetailUrl = ruleBean.getBookDetailUrl().replace("{bookId}", bookId);
         String bookDetailHtml = crawlHttpClient.get(bookDetailUrl, ruleBean.getCharset());
@@ -120,8 +123,12 @@ public class CrawlParser {
                         if (isFindUpdateTime) {
                             String updateTime = updateTimeMatch.group(1);
                             //设置更新时间
+                            try {
                                 book.setLastIndexUpdateTime(
                                     new SimpleDateFormat(ruleBean.getUpadateTimeFormatPatten()).parse(updateTime));
+                            } catch (ParseException e) {
+                                log.error("解析最新章节更新时间出错", e);
+                            }
 
                         }
                     }
@@ -144,7 +151,7 @@ public class CrawlParser {
     }
 
     public boolean parseBookIndexAndContent(String sourceBookId, Book book, RuleBean ruleBean,
-        Map<Integer, BookIndex> existBookIndexMap, CrawlBookChapterHandler handler) {
+        Map<Integer, BookIndex> existBookIndexMap, CrawlBookChapterHandler handler) throws InterruptedException{
 
         Date currentDate = new Date();
 

novel-crawl/src/main/java/com/java2nb/novel/core/listener/StarterListener.java

@@ -74,10 +74,8 @@ public class StarterListener implements ServletContextInitializer {
                                         needUpdateBook.getId());
                                     //解析章节目录
                                     crawlParser.parseBookIndexAndContent(needUpdateBook.getCrawlBookId(), book,
-                                        ruleBean, existBookIndexMap, chapter -> {
+                                        ruleBean, existBookIndexMap, chapter -> bookService.updateBookAndIndexAndContent(book, chapter.getBookIndexList(),
-                                            bookService.updateBookAndIndexAndContent(book, chapter.getBookIndexList(),
+                                            chapter.getBookContentList(), existBookIndexMap));
-                                                chapter.getBookContentList(), existBookIndexMap);
-                                        });
                                 });
                             } catch (Exception e) {
                                 log.error(e.getMessage(), e);

novel-crawl/src/main/java/com/java2nb/novel/core/schedule/CrawlThreadMonitor.java

@@ -1,61 +0,0 @@
-package com.java2nb.novel.core.schedule;
-
-
-import com.java2nb.novel.core.cache.CacheKey;
-import com.java2nb.novel.core.cache.CacheService;
-import com.java2nb.novel.entity.CrawlSource;
-import com.java2nb.novel.service.CrawlService;
-import io.github.xxyopen.util.ThreadUtil;
-import lombok.RequiredArgsConstructor;
-import lombok.extern.slf4j.Slf4j;
-import org.springframework.scheduling.annotation.Scheduled;
-import org.springframework.stereotype.Service;
-
-import java.util.List;
-import java.util.Set;
-
-/**
- * 爬虫线程监控器,监控执行完成的爬虫源，并修改状态
- *
- * @author Administrator
- */
-@Service
-@RequiredArgsConstructor
-@Slf4j
-public class CrawlThreadMonitor {
-
-    private final CacheService cacheService;
-
-    private final CrawlService crawlService;
-
-    @Scheduled(fixedRate = 1000 * 60 * 5)
-    public void monitor() {
-
-        //查询需要监控的正在运行的爬虫源
-        List<CrawlSource> sources = crawlService.queryCrawlSourceByStatus((byte) 1);
-
-        for (CrawlSource source : sources) {
-            Set<Long> runningCrawlThreadIds = (Set<Long>) cacheService.getObject(CacheKey.RUNNING_CRAWL_THREAD_KEY_PREFIX + source.getId());
-            boolean sourceStop = true;
-            if (runningCrawlThreadIds != null) {
-                for (Long threadId : runningCrawlThreadIds) {
-                    Thread thread = ThreadUtil.findThread(threadId);
-
-                    if (thread != null && thread.isAlive()) {
-                        //有活跃线程，说明该爬虫源正在运行，数据库中状态正确，不需要修改
-                        sourceStop = false;
-
-                    }
-
-                }
-            }
-
-            if (sourceStop) {
-                crawlService.updateCrawlSourceStatus(source.getId(), (byte) 0);
-            }
-
-
-        }
-
-    }
-}

novel-crawl/src/main/java/com/java2nb/novel/service/CrawlService.java

@@ -53,7 +53,7 @@ public interface CrawlService {
      * @param ruleBean 采集规则\
      * @return true:成功，false:失败
      * */
-    boolean parseBookAndSave(int catId, RuleBean ruleBean, Integer sourceId, String bookId);
+    boolean parseBookAndSave(int catId, RuleBean ruleBean, Integer sourceId, String bookId) throws InterruptedException;
 
     /**
      * 根据爬虫状态查询爬虫源集合

novel-crawl/src/main/java/com/java2nb/novel/service/impl/CrawlServiceImpl.java

@@ -34,6 +34,7 @@ import org.mybatis.dynamic.sql.render.RenderingStrategies;
 import org.mybatis.dynamic.sql.select.render.SelectStatementProvider;
 import org.springframework.stereotype.Service;
 
+import java.time.Duration;
 import java.util.*;
 import java.util.concurrent.atomic.AtomicBoolean;
 import java.util.regex.Matcher;
@@ -65,6 +66,10 @@ public class CrawlServiceImpl implements CrawlService {
 
     private final CrawlHttpClient crawlHttpClient;
 
+    private final Map<Integer, Byte> crawlSourceStatusMap = new HashMap<>();
+
+    private final Map<Integer, Set<Long>> runningCrawlThread = new HashMap<>();
+
 
     @Override
     public void addCrawlSource(CrawlSource source) {
@@ -103,6 +108,8 @@ public class CrawlServiceImpl implements CrawlService {
             .build()
             .render(RenderingStrategies.MYBATIS3);
         List<CrawlSource> crawlSources = crawlSourceMapper.selectMany(render);
+        crawlSources.forEach(crawlSource -> crawlSource.setSourceStatus(
+            Optional.ofNullable(crawlSourceStatusMap.get(crawlSource.getId())).orElse((byte) 0)));
         PageBean<CrawlSource> pageBean = PageBuilder.build(crawlSources);
         pageBean.setList(BeanUtil.copyList(crawlSources, CrawlSourceVO.class));
         return pageBean;
@@ -112,14 +119,13 @@ public class CrawlServiceImpl implements CrawlService {
     @Override
     public void openOrCloseCrawl(Integer sourceId, Byte sourceStatus) {
 
-        //判断是开启还是关闭，如果是关闭，则修改数据库状态后获取该爬虫正在运行的线程集合并全部停止
+        // 判断是开启还是关闭，如果是关闭，则获取该爬虫源正在运行的线程集合并全部中断
-        //如果是开启，先查询数据库中状态，判断该爬虫源是否还在运行，如果在运行，则忽略，
+        // 如果是开启，先判断该爬虫源是否还在运行，如果在运行，则忽略，如果没有运行则启动线程爬取小说数据并加入到runningCrawlThread中
-        // 如果没有则修改数据库状态，并启动线程爬取小说数据加入到runningCrawlThread中
+        // 最后，保存爬虫源状态
         if (sourceStatus == (byte) 0) {
-            //关闭,直接修改数据库状态，并直接修改数据库状态后获取该爬虫正在运行的线程集合全部停止
+            // 关闭
-            SpringUtil.getBean(CrawlService.class).updateCrawlSourceStatus(sourceId, sourceStatus);
+            // 将该爬虫源正在运行的线程集合全部停止
-            Set<Long> runningCrawlThreadId = (Set<Long>) cacheService.getObject(
+            Set<Long> runningCrawlThreadId = runningCrawlThread.get(sourceId);
-                CacheKey.RUNNING_CRAWL_THREAD_KEY_PREFIX + sourceId);
             if (runningCrawlThreadId != null) {
                 for (Long ThreadId : runningCrawlThreadId) {
                     Thread thread = ThreadUtil.findThread(ThreadId);
@@ -131,16 +137,13 @@ public class CrawlServiceImpl implements CrawlService {
 
 
         } else {
-            //开启
+            // 开启
-            //查询爬虫源状态和规则
+            Byte realSourceStatus = Optional.ofNullable(crawlSourceStatusMap.get(sourceId)).orElse((byte) 0);
-            CrawlSource source = queryCrawlSource(sourceId);
-            Byte realSourceStatus = source.getSourceStatus();
-
             if (realSourceStatus == (byte) 0) {
-                //该爬虫源已经停止运行了,修改数据库状态，并启动线程爬取小说数据加入到runningCrawlThread中
+                // 查询爬虫源规则
-                SpringUtil.getBean(CrawlService.class).updateCrawlSourceStatus(sourceId, sourceStatus);
+                CrawlSource source = queryCrawlSource(sourceId);
+                //该爬虫源已经停止运行了,启动线程爬取小说数据并将线程加入到runningCrawlThread中
                 RuleBean ruleBean = new ObjectMapper().readValue(source.getCrawlRule(), RuleBean.class);
-
                 Set<Long> threadIds = new HashSet<>();
                 //按分类开始爬虫解析任务
                 for (int i = 1; i < 8; i++) {
@@ -149,15 +152,14 @@ public class CrawlServiceImpl implements CrawlService {
                     thread.start();
                     //thread加入到监控缓存中
                     threadIds.add(thread.getId());
-
                 }
-                cacheService.setObject(CacheKey.RUNNING_CRAWL_THREAD_KEY_PREFIX + sourceId, threadIds);
+                runningCrawlThread.put(sourceId, threadIds);
-
+            }
 
         }
 
-
+        // 保存爬虫源状态
-        }
+        crawlSourceStatusMap.put(sourceId, sourceStatus);
 
     }
 
@@ -248,6 +250,11 @@ public class CrawlServiceImpl implements CrawlService {
     @Override
     public void parseBookList(int catId, RuleBean ruleBean, Integer sourceId) {
 
+        String catIdRule = ruleBean.getCatIdRule().get("catId" + catId);
+        if (StringUtils.isBlank(catIdRule)) {
+            return;
+        }
+
         //当前页码1
         int page = 1;
         int totalPage = page;
@@ -255,9 +262,7 @@ public class CrawlServiceImpl implements CrawlService {
         while (page <= totalPage) {
 
             try {
-                String catIdRule = ruleBean.getCatIdRule().get("catId" + catId);
+                String catBookListUrl;
-                if (StringUtils.isNotBlank(catIdRule)) {
-                    String catBookListUrl = "";
                 if (StringUtils.isNotBlank(ruleBean.getBookListUrl())) {
                     // 兼容老规则
                     // 拼接分类URL
@@ -287,6 +292,12 @@ public class CrawlServiceImpl implements CrawlService {
 
                             String bookId = bookIdMatcher.group(1);
                             parseBookAndSave(catId, ruleBean, sourceId, bookId);
+                        } catch (InterruptedException e) {
+                            log.error(e.getMessage(), e);
+                            //1.阻塞过程（使用了 sleep,同步锁的 wait,socket 中的 receiver,accept 等方法时）
+                            //捕获中断异常InterruptedException来退出线程。
+                            //2.非阻塞过程中通过判断中断标志来退出线程。
+                            return;
                         } catch (Exception e) {
                             log.error(e.getMessage(), e);
                         }
@@ -302,26 +313,40 @@ public class CrawlServiceImpl implements CrawlService {
                         totalPage = Integer.parseInt(totalPageMatcher.group(1));
 
                     }
-
-
-                    }
                 }
+            } catch (InterruptedException e) {
+                log.error(e.getMessage(), e);
+                //1.阻塞过程（使用了 sleep,同步锁的 wait,socket 中的 receiver,accept 等方法时）
+                //捕获中断异常InterruptedException来退出线程。
+                //2.非阻塞过程中通过判断中断标志来退出线程。
+                return;
             } catch (Exception e) {
                 log.error(e.getMessage(), e);
             }
-            if (page == totalPage) {
+            if (page >= totalPage) {
                 // 第一遍采集完成，翻到第一页，继续第二次采集，适用于分页数比较少的最近更新列表
-                page = 0;
+                page = 1;
+                try {
+                    // 第一遍采集完成，休眠1分钟
+                    Thread.sleep(Duration.ofMinutes(1));
+                } catch (InterruptedException e) {
+                    log.error(e.getMessage(), e);
+                    //1.阻塞过程（使用了 sleep,同步锁的 wait,socket 中的 receiver,accept 等方法时）
+                    //捕获中断异常InterruptedException来退出线程。
+                    //2.非阻塞过程中通过判断中断标志来退出线程。
+                    return;
                 }
-
+            } else {
                 page += 1;
             }
+        }
 
 
     }
 
     @Override
-    public boolean parseBookAndSave(int catId, RuleBean ruleBean, Integer sourceId, String bookId) {
+    public boolean parseBookAndSave(int catId, RuleBean ruleBean, Integer sourceId, String bookId)
+        throws InterruptedException {
 
         final AtomicBoolean parseResult = new AtomicBoolean(false);
 
@@ -385,4 +410,5 @@ public class CrawlServiceImpl implements CrawlService {
             .render(RenderingStrategies.MYBATIS3);
         return crawlSourceMapper.selectMany(render);
     }
+
 }

novel-crawl/src/main/java/com/java2nb/novel/utils/CrawlHttpClient.java

@@ -25,13 +25,9 @@ public class CrawlHttpClient {
 
     private static final ThreadLocal<Integer> RETRY_COUNT = new ThreadLocal<>();
 
-    public String get(String url, String charset) {
+    public String get(String url, String charset) throws InterruptedException {
         if (Objects.nonNull(intervalMin) && Objects.nonNull(intervalMax) && intervalMax > intervalMin) {
-            try {
             Thread.sleep(random.nextInt(intervalMax - intervalMin + 1) + intervalMin);
-            } catch (InterruptedException e) {
-                log.error(e.getMessage(), e);
-            }
         }
         String body = HttpUtil.getByHttpClientWithChrome(url, charset);
         if (Objects.isNull(body) || body.length() < Constants.INVALID_HTML_LENGTH) {
@@ -41,7 +37,7 @@ public class CrawlHttpClient {
         return body;
     }
 
-    private String processErrorHttpResult(String url, String charset) {
+    private String processErrorHttpResult(String url, String charset) throws InterruptedException{
         Integer count = RETRY_COUNT.get();
         if (count == null) {
             count = 0;

novel-front/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <artifactId>novel</artifactId>
         <groupId>com.java2nb</groupId>
-        <version>5.1.1</version>
+        <version>5.1.3</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 

pom.xml

@@ -5,7 +5,7 @@
 
     <groupId>com.java2nb</groupId>
     <artifactId>novel</artifactId>
-    <version>5.1.1</version>
+    <version>5.1.3</version>
     <modules>
         <module>novel-common</module>
         <module>novel-front</module>