Merge pull request #71 from a100488/task_updateCrawlSource

feat(新增编辑规则测试规则): 新增编辑规则测试规则

novel-admin/pom.xml

@@ -224,17 +224,17 @@
         <!--<scope>provided</scope>-->
         <!--</dependency>-->
     </dependencies>
-    <build>
+  <!--  <build>
         <plugins>
-            <!--<plugin>
+            &lt;!&ndash;<plugin>
                 <groupId>org.springframework.boot</groupId>
                 <artifactId>spring-boot-maven-plugin</artifactId>
                 <configuration>
                     <executable>true</executable>
                 </configuration>
-            </plugin>-->
+            </plugin>&ndash;&gt;
-            <!--SpringBoot项目默认使用spring-boot-maven-plugin，要打成被其他项目引用的jar包，需要更换此插件-->
+            &lt;!&ndash;SpringBoot项目默认使用spring-boot-maven-plugin，要打成被其他项目引用的jar包，需要更换此插件&ndash;&gt;
-            <!-- <plugin>
+            &lt;!&ndash; <plugin>
                  <groupId>org.apache.maven.plugins</groupId>
                  <artifactId>maven-compiler-plugin</artifactId>
                  <configuration>
@@ -242,12 +242,91 @@
                      <target>1.8</target>
                      <encoding>UTF-8</encoding>
                  </configuration>
-             </plugin>-->
+             </plugin>&ndash;&gt;
             <plugin>
                 <groupId>org.springframework.boot</groupId>
                 <artifactId>spring-boot-maven-plugin</artifactId>
             </plugin>
         </plugins>
+    </build>-->
+    <build>
+        <plugins>
+            <plugin>
+                <!--打包时去除第三方依赖-->
+                <groupId>org.springframework.boot</groupId>
+                <artifactId>spring-boot-maven-plugin</artifactId>
+                <configuration>
+                    <layout>ZIP</layout>
+                    <includes>
+                        <include>
+                            <groupId>non-exists</groupId>
+                            <artifactId>non-exists</artifactId>
+                        </include>
+                    </includes>
+                </configuration>
+            </plugin>
+            <!--拷贝第三方依赖文件到指定目录-->
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-dependency-plugin</artifactId>
+                <executions>
+                    <execution>
+                        <id>copy-dependencies</id>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>copy-dependencies</goal>
+                        </goals>
+                        <configuration>
+                            <!--target/lib是依赖jar包的输出目录，根据自己喜好配置-->
+                            <outputDirectory>target/lib</outputDirectory>
+                            <excludeTransitive>false</excludeTransitive>
+                            <stripVersion>false</stripVersion>
+                            <includeScope>runtime</includeScope>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+            <plugin>
+                <artifactId>maven-antrun-plugin</artifactId>
+                <version>1.8</version>
+                <executions>
+                    <execution>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>run</goal>
+                        </goals>
+                        <configuration>
+                            <tasks>
+                                <!-- 文件夹 -->
+                                <copy todir="${project.build.directory}/build/conf" overwrite="true">
+                                    <fileset dir="${basedir}/src/main/resources">
+                                        <include name="**/*.*"/>
+                                        <exclude name="mybatis/*/*.*"/>
+                                    </fileset>
+                                </copy>
+                                <move todir="${project.build.directory}/build/lib">
+                                    <fileset dir="target/lib"/>
+                                </move>
+                                <copy file="${project.build.directory}/${project.artifactId}-${project.version}.jar"
+                                      tofile="${project.build.directory}/build/${project.artifactId}.jar" />
+
+                                <fixcrlf srcdir="${basedir}/src/main/build/scripts" eol="unix"/>
+                                <copy todir="${project.build.directory}/build/bin">
+                                    <fileset dir="${basedir}/src/main/build/scripts">
+                                        <include name="*.sh" />
+                                        <include name="*.txt" />
+                                        <include name="*.bat" />
+                                    </fileset>
+                                </copy>
+                                <zip destfile='${project.build.directory}/build/${project.artifactId}.zip'>
+                                    <zipfileset filemode="755" dir= '${project.build.directory}/build/' />
+                                </zip>
+                            </tasks>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+        </plugins>
     </build>
     <!--<distributionManagement>
         <repository>

novel-admin/src/main/build/scripts/readme.txt

@@ -0,0 +1,8 @@
+1：linux启动环境
+sh start.sh
+
+3：windows启动环境
+windows-start.bat
+
+3：linux停止应用
+sh stop.sh

novel-admin/src/main/build/scripts/start.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+ENGINE=novel-admin.jar
+cd ../
+
+#部署目路
+DEPLOY_DIR=`pwd`
+#获取到当前目录的名称
+SERVER_NAME=`basename $DEPLOY_DIR`
+
+#应用进程
+PIDS=`ps -ef | grep java | grep "$ENGINE" |awk '{print $2}'`
+#设置日志文件的输出目录
+LOGS_DIR=$DEPLOY_DIR/logs
+if [ ! -d $LOGS_DIR ]; then
+    mkdir $LOGS_DIR
+fi
+#日志
+STDOUT_FILE=$LOGS_DIR/stdout.log
+#JAVA 环境配置
+JAVA_OPTS=" -Djava.net.preferIPv4Stack=true -Dlog.home=$LOGS_DIR"
+
+JAVA_MEM_OPTS=" -server -Xms1024m -Xmx1024m -XX:MetaspaceSize=64m -XX:MaxMetaspaceSize=256m  -XX:+UseG1GC -XX:MaxGCPauseMillis=100 -XX:InitiatingHeapOccupancyPercent=50 -XX:+PrintGCApplicationStoppedTime -XX:+PrintGCApplicationConcurrentTime -XX:+PrintGCDateStamps -verbose:gc -XX:+PrintGCDetails -XX:+PrintHeapAtGC -Xloggc:$LOGS_DIR/gc.log -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=10 -XX:GCLogFileSize=100M -XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=dump.hprof "
+#退出标志
+RETVAL="0"
+
+if [ -n "$PIDS" ]; then
+		echo "ERROR: The $SERVER_NAME already started!"
+		echo "PID: $PIDS"
+		exit $RETVAL
+fi
+
+nohup java -jar  $JAVA_OPTS $JAVA_MEM_OPTS  -Dloader.path=conf,lib $ENGINE > $STDOUT_FILE 2>&1 &
+COUNT=0
+	while [ $COUNT -lt 1 ]; do
+		echo -e ".\c"
+		sleep 1
+		COUNT=`ps -f | grep java | grep "$DEPLOY_DIR" | awk '{print $2}' | wc -l`
+		if [ $COUNT -gt 0 ]; then
+			break
+		fi
+	done
+
+	echo "OK!"
+	PIDS=`ps -f | grep java | grep "$DEPLOY_DIR" | awk '{print $2}'`
+	echo "PID: $PIDS"
+	echo "STDOUT: $STDOUT_FILE"

novel-admin/src/main/build/scripts/stop.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+SERVER_NAME=novel-admin.jar
+
+#应用进程
+PIDS=`ps -ef | grep java | grep "$SERVER_NAME" |awk '{print $2}'`
+if [ -z "$PIDS" ]; then
+    		echo "ERROR: The $SERVER_NAME does not started!"
+    	exit 1
+	fi
+
+	echo -e "Stopping the $SERVER_NAME ...\c"
+	for PID in $PIDS ; do
+    		kill $PID > /dev/null 2>&1
+	done
+
+	COUNT=0
+	while [ $COUNT -lt 1 ]; do
+    		echo -e ".\c"
+    		sleep 1
+    		COUNT=1
+    		for PID in $PIDS ; do
+        	PID_EXIST=`ps -f -p $PID | grep java`
+        	if [ -n "$PID_EXIST" ]; then
+            		COUNT=0
+            		break
+        	fi
+    		done
+	done
+
+	echo "OK!"
+	echo "PID: $PIDS"
+	PIDS=""
+

novel-admin/src/main/build/scripts/windows-start.bat

@@ -0,0 +1,10 @@
+@echo off
+setlocal enabledelayedexpansion
+set JAVA=java
+
+set OPTS=-XX:MetaspaceSize=128m -XX:MaxMetaspaceSize=128m -Xms1024m -Xmx1024m -Xmn256m -Xss256k -XX:SurvivorRatio=8 -XX:+UseConcMarkSweepGC
+set ENGINE=novel-admin.jar
+cd ../
+java -jar %OPTS%   -Dloader.path=conf,lib %ENGINE%
+pause
+

novel-admin/src/main/resources/logback-spring.xml

@@ -56,7 +56,7 @@
     <!-- 指定项目中某个包，当有日志操作行为时的日志记录级别 -->
     <!-- com.maijinjie.springboot 为根包，也就是只要是发生在这个根包下面的所有日志操作行为的权限都是DEBUG -->
     <!-- 级别依次为【从高到低】：FATAL > ERROR > WARN > INFO > DEBUG > TRACE -->
-    <logger name="com.java2nb" level="DEBUG">
+    <logger name="com.java2nb" level="DEBUG" additivity="false">
         <appender-ref ref="debug" />
     </logger>
 </configuration>

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

@@ -65,4 +65,8 @@ public interface CacheKey {
      * 累积的小说点击量
      * */
     String BOOK_ADD_VISIT_COUNT = "bookAddVisitCount";
-}
+    /**
+     * 测试爬虫规则缓存
+     */
+    String BOOK_TEST_PARSE = "testParse";
+}

novel-common/src/main/java/com/java2nb/novel/entity/News.java

@@ -1,9 +1,11 @@
 package com.java2nb.novel.entity;
 
+import java.io.Serializable;
 import java.util.Date;
 import javax.annotation.Generated;
 
-public class News {
+public class News implements Serializable {
+
     @Generated("org.mybatis.generator.api.MyBatisGenerator")
     private Long id;
 
@@ -146,4 +148,4 @@ public class News {
     public void setContent(String content) {
         this.content = content == null ? null : content.trim();
     }
-}
+}

novel-crawl/pom.xml

@@ -32,11 +32,82 @@
     <build>
         <plugins>
             <plugin>
+                <!--打包时去除第三方依赖-->
                 <groupId>org.springframework.boot</groupId>
                 <artifactId>spring-boot-maven-plugin</artifactId>
+                <configuration>
+                    <layout>ZIP</layout>
+                    <includes>
+                        <include>
+                            <groupId>non-exists</groupId>
+                            <artifactId>non-exists</artifactId>
+                        </include>
+                    </includes>
+                </configuration>
+            </plugin>
+            <!--拷贝第三方依赖文件到指定目录-->
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-dependency-plugin</artifactId>
+                <executions>
+                    <execution>
+                        <id>copy-dependencies</id>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>copy-dependencies</goal>
+                        </goals>
+                        <configuration>
+                            <!--target/lib是依赖jar包的输出目录，根据自己喜好配置-->
+                            <outputDirectory>target/lib</outputDirectory>
+                            <excludeTransitive>false</excludeTransitive>
+                            <stripVersion>false</stripVersion>
+                            <includeScope>runtime</includeScope>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+            <plugin>
+                <artifactId>maven-antrun-plugin</artifactId>
+                <version>1.8</version>
+                <executions>
+                    <execution>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>run</goal>
+                        </goals>
+                        <configuration>
+                            <tasks>
+                                <!-- 文件夹 -->
+                                <copy todir="${project.build.directory}/build/conf" overwrite="true">
+                                    <fileset dir="${basedir}/src/main/resources">
+                                        <include name="**/*.*"/>
+                                        <exclude name="mybatis/*/*.*"/>
+                                    </fileset>
+                                </copy>
+                                <move todir="${project.build.directory}/build/lib">
+                                <fileset dir="target/lib"/>
+                                </move>
+                                <copy file="${project.build.directory}/${project.artifactId}-${project.version}.jar"
+                                      tofile="${project.build.directory}/build/${project.artifactId}.jar" />
+
+                                <fixcrlf srcdir="${basedir}/src/main/build/scripts" eol="unix"/>
+                                <copy todir="${project.build.directory}/build/bin">
+                                    <fileset dir="${basedir}/src/main/build/scripts">
+                                        <include name="*.sh" />
+                                        <include name="*.txt" />
+                                        <include name="*.bat" />
+                                    </fileset>
+                                </copy>
+                                <zip destfile='${project.build.directory}/build/${project.artifactId}.zip'>
+                                    <zipfileset filemode="755" dir= '${project.build.directory}/build/' />
+                                </zip>
+                            </tasks>
+                        </configuration>
+                    </execution>
+                </executions>
             </plugin>
         </plugins>
     </build>
 
 
-</project>
+</project>

novel-crawl/src/main/build/scripts/readme.txt

@@ -0,0 +1,8 @@
+1：linux启动环境
+sh start.sh
+
+3：windows启动环境
+windows-start.bat
+
+3：linux停止应用
+sh stop.sh

novel-crawl/src/main/build/scripts/start.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+ENGINE=novel-crawl.jar
+cd ../
+
+#部署目路
+DEPLOY_DIR=`pwd`
+#获取到当前目录的名称
+SERVER_NAME=`basename $DEPLOY_DIR`
+
+#应用进程
+PIDS=`ps -ef | grep java | grep "$ENGINE" |awk '{print $2}'`
+#设置日志文件的输出目录
+LOGS_DIR=$DEPLOY_DIR/logs
+if [ ! -d $LOGS_DIR ]; then
+    mkdir $LOGS_DIR
+fi
+#日志
+STDOUT_FILE=$LOGS_DIR/stdout.log
+#JAVA 环境配置
+JAVA_OPTS=" -Djava.net.preferIPv4Stack=true -Dlog.home=$LOGS_DIR"
+
+JAVA_MEM_OPTS=" -server -Xms1024m -Xmx1024m -XX:MetaspaceSize=64m -XX:MaxMetaspaceSize=256m  -XX:+UseG1GC -XX:MaxGCPauseMillis=100 -XX:InitiatingHeapOccupancyPercent=50 -XX:+PrintGCApplicationStoppedTime -XX:+PrintGCApplicationConcurrentTime -XX:+PrintGCDateStamps -verbose:gc -XX:+PrintGCDetails -XX:+PrintHeapAtGC -Xloggc:$LOGS_DIR/gc.log -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=10 -XX:GCLogFileSize=100M -XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=dump.hprof "
+#退出标志
+RETVAL="0"
+
+if [ -n "$PIDS" ]; then
+		echo "ERROR: The $SERVER_NAME already started!"
+		echo "PID: $PIDS"
+		exit $RETVAL
+fi
+
+nohup java -jar  $JAVA_OPTS $JAVA_MEM_OPTS  -Dloader.path=conf,lib $ENGINE > $STDOUT_FILE 2>&1 &
+COUNT=0
+	while [ $COUNT -lt 1 ]; do
+		echo -e ".\c"
+		sleep 1
+		COUNT=`ps -f | grep java | grep "$DEPLOY_DIR" | awk '{print $2}' | wc -l`
+		if [ $COUNT -gt 0 ]; then
+			break
+		fi
+	done
+
+	echo "OK!"
+	PIDS=`ps -f | grep java | grep "$DEPLOY_DIR" | awk '{print $2}'`
+	echo "PID: $PIDS"
+	echo "STDOUT: $STDOUT_FILE"

novel-crawl/src/main/build/scripts/stop.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+SERVER_NAME=novel-crawl.jar
+
+#应用进程
+PIDS=`ps -ef | grep java | grep "$SERVER_NAME" |awk '{print $2}'`
+if [ -z "$PIDS" ]; then
+    		echo "ERROR: The $SERVER_NAME does not started!"
+    	exit 1
+	fi
+
+	echo -e "Stopping the $SERVER_NAME ...\c"
+	for PID in $PIDS ; do
+    		kill $PID > /dev/null 2>&1
+	done
+
+	COUNT=0
+	while [ $COUNT -lt 1 ]; do
+    		echo -e ".\c"
+    		sleep 1
+    		COUNT=1
+    		for PID in $PIDS ; do
+        	PID_EXIST=`ps -f -p $PID | grep java`
+        	if [ -n "$PID_EXIST" ]; then
+            		COUNT=0
+            		break
+        	fi
+    		done
+	done
+
+	echo "OK!"
+	echo "PID: $PIDS"
+	PIDS=""
+

novel-crawl/src/main/build/scripts/windows-start.bat

@@ -0,0 +1,10 @@
+@echo off
+setlocal enabledelayedexpansion
+set JAVA=java
+
+set OPTS=-XX:MetaspaceSize=128m -XX:MaxMetaspaceSize=128m -Xms1024m -Xmx1024m -Xmn256m -Xss256k -XX:SurvivorRatio=8 -XX:+UseConcMarkSweepGC
+set ENGINE=novel-crawl.jar
+cd ../
+java -jar %OPTS%   -Dloader.path=conf,lib %ENGINE%
+pause
+

novel-crawl/src/main/java/com/java2nb/novel/controller/CrawlController.java

@@ -1,13 +1,26 @@
 package com.java2nb.novel.controller;
 
+import com.fasterxml.jackson.databind.ObjectMapper;
 import com.java2nb.novel.core.bean.PageBean;
 import com.java2nb.novel.core.bean.ResultBean;
+import com.java2nb.novel.core.cache.CacheKey;
+import com.java2nb.novel.core.cache.CacheService;
+import com.java2nb.novel.core.crawl.CrawlParser;
+import com.java2nb.novel.core.crawl.RuleBean;
+import com.java2nb.novel.core.utils.HttpUtil;
+import com.java2nb.novel.entity.BookIndex;
 import com.java2nb.novel.entity.CrawlSingleTask;
 import com.java2nb.novel.entity.CrawlSource;
 import com.java2nb.novel.service.CrawlService;
+import com.java2nb.novel.utils.Constants;
 import lombok.RequiredArgsConstructor;
 import org.springframework.web.bind.annotation.*;
 
+import java.util.HashMap;
+import java.util.Map;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
 /**
  * @author Administrator
  */
@@ -18,7 +31,7 @@ public class CrawlController {
 
     private final CrawlService crawlService;
 
-
+    private final CacheService cacheService;
     /**
      * 新增爬虫源
      * */
@@ -38,7 +51,70 @@ public class CrawlController {
 
         return ResultBean.ok(crawlService.listCrawlByPage(page,pageSize));
     }
+    /**
+     * 获取爬虫源
+     * */
+    @GetMapping("getCrawlSource/{id}")
+    public ResultBean<CrawlSource> getCrawlSource(@PathVariable("id") Integer id){
+        CrawlSource crawlSource=  crawlService.getCrawlSource(id);
+        return ResultBean.ok(crawlSource);
 
+    }
+
+    /**
+     * 测试规则
+     * @param rule
+     * @param url
+     * @param isRefresh
+     * @return
+     */
+    @PostMapping("testParse")
+    public ResultBean<Object> testParse(String rule,String url,String isRefresh){
+
+        Map<String,Object> resultMap=new HashMap<>();
+        String html =null;
+        if(url.startsWith("https://")||url.startsWith("http://")){
+            String refreshCache="1";
+            if(!refreshCache.equals(isRefresh)) {
+                Object cache = cacheService.getObject(CacheKey.BOOK_TEST_PARSE + url);
+                if (cache == null) {
+                    isRefresh="1";
+                }else {
+                    html = (String) cache;
+                }
+            }
+            if(refreshCache.equals(isRefresh)){
+                html = HttpUtil.getByHttpClientWithChrome(url);
+                if (html != null) {
+                    cacheService.setObject(CacheKey.BOOK_TEST_PARSE + url, html, 60 * 10);
+                }else{
+                    resultMap.put("msg","html is null");
+                    return ResultBean.ok(resultMap);
+                }
+            }
+        }else{
+            resultMap.put("html","url is null");
+            return ResultBean.ok(resultMap);
+        }
+        Pattern pattern = Pattern.compile(rule);
+        Matcher matcher = pattern.matcher(html);
+        boolean isFind = matcher.find();
+        resultMap.put("是否匹配",isFind);
+        if(isFind){
+            resultMap.put("匹配结果",matcher.group(1));
+        }
+       // resultMap.put("url",url);
+        return ResultBean.ok(resultMap);
+    }
+    /**
+     * 修改爬虫源
+     * */
+    @PostMapping("updateCrawlSource")
+    public ResultBean<Void> updateCrawlSource(CrawlSource source){
+        crawlService.updateCrawlSource(source);
+        return ResultBean.ok();
+
+    }
     /**
      * 开启或停止爬虫
      * */

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

@@ -1,6 +1,7 @@
 package com.java2nb.novel.service;
 
 import com.java2nb.novel.core.bean.PageBean;
+import com.java2nb.novel.core.bean.ResultBean;
 import com.java2nb.novel.core.crawl.RuleBean;
 import com.java2nb.novel.entity.CrawlSingleTask;
 import com.java2nb.novel.entity.CrawlSource;
@@ -18,7 +19,11 @@ public interface CrawlService {
      * */
     void addCrawlSource(CrawlSource source);
 
-
+    /**
+     * 修改爬虫源
+     * @param source
+     */
+    void updateCrawlSource(CrawlSource source);
     /**
      * 爬虫源分页列表
      * @param page 当前页码
@@ -106,4 +111,11 @@ public interface CrawlService {
      * @param status 采集状态
      * */
     void updateCrawlSingleTask(CrawlSingleTask task, Byte status);
+
+    /**
+     * 获取采集规则详细
+     * @param id
+     * @return
+     */
+    CrawlSource getCrawlSource(Integer id);
 }

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

@@ -39,6 +39,7 @@ import java.util.regex.Pattern;
 
 import static com.java2nb.novel.core.utils.HttpUtil.getByHttpClientWithChrome;
 import static com.java2nb.novel.mapper.CrawlSourceDynamicSqlSupport.*;
+import static com.java2nb.novel.mapper.CrawlSourceDynamicSqlSupport.id;
 import static org.mybatis.dynamic.sql.SqlBuilder.isEqualTo;
 import static org.mybatis.dynamic.sql.select.SelectDSL.select;
 
@@ -69,7 +70,24 @@ public class CrawlServiceImpl implements CrawlService {
         crawlSourceMapper.insertSelective(source);
 
     }
-
+    @Override
+    public void updateCrawlSource(CrawlSource source) {
+        if(source.getId()!=null){
+            Optional<CrawlSource> opt=crawlSourceMapper.selectByPrimaryKey(source.getId());
+            if(opt.isPresent()) {
+                CrawlSource crawlSource =opt.get();
+                if (crawlSource.getSourceStatus() == (byte) 1) {
+                    //关闭
+                    openOrCloseCrawl(crawlSource.getId(),(byte)0);
+                }
+                Date currentDate = new Date();
+                crawlSource.setUpdateTime(currentDate);
+                crawlSource.setCrawlRule(source.getCrawlRule());
+                crawlSource.setSourceName(source.getSourceName());
+                crawlSourceMapper.updateByPrimaryKey(crawlSource);
+            }
+        }
+    }
     @Override
     public PageBean<CrawlSource> listCrawlByPage(int page, int pageSize) {
         PageHelper.startPage(page, pageSize);
@@ -138,12 +156,17 @@ public class CrawlServiceImpl implements CrawlService {
 
     @Override
     public CrawlSource queryCrawlSource(Integer sourceId) {
-        SelectStatementProvider render = select(CrawlSourceDynamicSqlSupport.sourceStatus, CrawlSourceDynamicSqlSupport.crawlRule)
+
+        SelectStatementProvider render = select(id, sourceName, sourceStatus, createTime, updateTime,crawlRule)
                 .from(crawlSource)
                 .where(id, isEqualTo(sourceId))
                 .build()
                 .render(RenderingStrategies.MYBATIS3);
-        return crawlSourceMapper.selectMany(render).get(0);
+        List<CrawlSource>  list= crawlSourceMapper.selectMany(render);
+        if(list!=null&&list.size()>0){
+            return list.get(0);
+        }
+        return null;
     }
 
     @Override
@@ -205,6 +228,16 @@ public class CrawlServiceImpl implements CrawlService {
 
     }
 
+    @Override
+    public CrawlSource getCrawlSource(Integer id) {
+            Optional<CrawlSource> opt=crawlSourceMapper.selectByPrimaryKey(id);
+            if(opt.isPresent()) {
+                CrawlSource crawlSource =opt.get();
+                return crawlSource;
+            }
+            return null;
+    }
+
     /**
      * 解析分类列表
      */

novel-crawl/src/main/resources/logback-boot.xml

@@ -57,8 +57,8 @@
     <!-- 指定项目中某个包，当有日志操作行为时的日志记录级别 -->
     <!-- com.maijinjie.springboot 为根包，也就是只要是发生在这个根包下面的所有日志操作行为的权限都是DEBUG -->
     <!-- 级别依次为【从高到低】：FATAL > ERROR > WARN > INFO > DEBUG > TRACE -->
-    <logger name="com.java2nb" level="DEBUG">
+    <logger name="com.java2nb" level="DEBUG" additivity="false">
         <appender-ref ref="STDOUT" />
         <appender-ref ref="FILE" />
     </logger>
-</configuration>
+</configuration>

novel-crawl/src/main/resources/templates/crawl/crawlSingleTask_add.html

@@ -30,6 +30,7 @@
             <ul class="log_list">
                 <li><a class="link_1" href="/">爬虫源管理</a></li>
                 <li><a class="link_1 on" href="/crawl/crawlSingleTask_list.html">单本采集管理</a></li>
+                <li><a class="link_1" href="/crawl/crawlSource_test.html" target="_blank" >规则测试</a></li>
                 <!--<li><a class="link_1 " href="/user/userinfo.html">批量小说爬取</a></li>
                 <li><a class="link_4 " href="/user/favorites.html">单本小说爬取</a></li>-->
             </ul>

novel-crawl/src/main/resources/templates/crawl/crawlSingleTask_list.html

@@ -30,6 +30,7 @@
             <ul class="log_list">
                 <li><a class="link_1" href="/">爬虫源管理</a></li>
                 <li><a class="link_1 on" href="/crawl/crawlSingleTask_list.html">单本采集管理</a></li>
+                <li><a class="link_1" href="/crawl/crawlSource_test.html" target="_blank" >规则测试</a></li>
                 <!-- <li><a class="link_1 " href="/user/userinfo.html">批量小说爬取</a></li>
                  <li><a class="link_4 " href="/user/favorites.html">单本小说爬取</a></li>-->
             </ul>

novel-crawl/src/main/resources/templates/crawl/crawlSource_add.html

@@ -30,6 +30,7 @@
             <ul class="log_list">
                 <li><a class="link_1 on" href="/">爬虫源管理</a></li>
                 <li><a class="link_1" href="/crawl/crawlSingleTask_list.html">单本采集管理</a></li>
+                <li><a class="link_1" href="/crawl/crawlSource_test.html" target="_blank" >规则测试</a></li>
                 <!--<li><a class="link_1 " href="/user/userinfo.html">批量小说爬取</a></li>
                 <li><a class="link_4 " href="/user/favorites.html">单本小说爬取</a></li>-->
             </ul>

novel-crawl/src/main/resources/templates/crawl/crawlSource_list.html

@@ -29,6 +29,7 @@
             <ul class="log_list">
                 <li><a class="link_1 on" href="/">爬虫源管理</a></li>
                 <li><a class="link_1" href="/crawl/crawlSingleTask_list.html">单本采集管理</a></li>
+                <li><a class="link_1" href="/crawl/crawlSource_test.html" target="_blank" >规则测试</a></li>
                <!-- <li><a class="link_1 " href="/user/userinfo.html">批量小说爬取</a></li>
                 <li><a class="link_4 " href="/user/favorites.html">单本小说爬取</a></li>-->
             </ul>
@@ -38,7 +39,7 @@
             <div class="my_bookshelf">
                 <div class="title cf">
                     <h2 class="fl">爬虫源列表</h2>
-                    <div class="fr"><a href="/crawl/crawlSource_add.html" class="btn_red">增加爬虫源</a></div>
+                    <div class="fr"><a href="/crawl/crawlSource_add.html" class="btn_red">增加爬虫源</a>
                 </div>
 
                 <div id="divData" class="updateTable">
@@ -119,8 +120,8 @@
 <script language="javascript" type="text/javascript">
     search(1, 10);
 
+    var pageCrawlSourceList=null;
     function search(curr, limit) {
-
         $.ajax({
             type: "get",
             url: "/crawl/listCrawlByPage",
@@ -129,6 +130,7 @@
             success: function (data) {
                 if (data.code == 200) {
                     var crawlSourceList = data.data.list;
+                    pageCrawlSourceList=data.data.list;
                     if (crawlSourceList.length > 0) {
                         var crawlSourceListHtml = "";
                         for(var i=0;i<crawlSourceList.length;i++){
@@ -147,7 +149,9 @@
                                 "                            <td class=\"goread\" id='sourceStatus"+crawlSource.id+"'>"+(crawlSource.sourceStatus==0?'停止运行':'正在运行')+
                                 "                            </td>\n" +
 
-                                " <td class=\"goread\" id='opt"+crawlSource.id+"'><a href='javascript:openOrStopCrawl("+crawlSource.id+","+crawlSource.sourceStatus+")'>"+(crawlSource.sourceStatus==0?'开启':'关闭')+"  </a></td>                     </tr>");
+                                " <td class=\"goread\" id='opt"+crawlSource.id+"'><a href='javascript:openOrStopCrawl("+crawlSource.id+","+crawlSource.sourceStatus+")'>"+(crawlSource.sourceStatus==0?'开启':'关闭')+"  </a>" +
+                                "<a href='javascript:updateCrawlSource("+crawlSource.id+")'>修改  </a>" +
+                                "</td>                     </tr>");
                         }
                         $("#crawlSourceList").html(crawlSourceListHtml);
 
@@ -196,7 +200,12 @@
         })
 
     }
+    function updateCrawlSource(crawlSourceId){
 
+        localStorage.setItem("crawlSourceId",crawlSourceId);
+        window.location.href="/crawl/crawlSource_update.html";
+
+    }
 
     function openOrStopCrawl(sourceId,status) {
 

novel-crawl/src/main/resources/templates/crawl/crawlSource_test.html

@@ -0,0 +1,171 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+        "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+    <head>
+        <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
+        <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"/>
+        <title>爬虫管理系统-小说精品屋</title>
+        <link rel="stylesheet" href="/css/base.css?v=1"/>
+        <link rel="stylesheet" href="/css/user.css"/>
+    </head>
+</head>
+<body class="">
+
+<div class="header">
+    <div class="mainNav" id="mainNav">
+        <div class="box_center cf"
+             style="text-align: center;height: 44px;line-height: 48px;color: #fff;font-size: 16px;">
+
+            小说精品屋爬虫管理
+
+        </div>
+    </div>
+</div>
+
+<div class="main box_center cf">
+    <div class="userBox cf">
+        <div class="my_l">
+
+            <ul class="log_list">
+                <li><a class="link_1 on" href="/">爬虫源管理</a></li>
+                <li><a class="link_1" href="/crawl/crawlSingleTask_list.html">单本采集管理</a></li>
+                <li><a class="link_1" href="/crawl/crawlSource_test.html" target="_blank" >规则测试</a></li>
+                <!--<li><a class="link_1 " href="/user/userinfo.html">批量小说爬取</a></li>
+                <li><a class="link_4 " href="/user/favorites.html">单本小说爬取</a></li>-->
+            </ul>
+
+        </div>
+        <div class="my_r">
+            <div class="my_bookshelf">
+
+                <div class="userBox cf">
+                    <form method="post" action="./register.html" id="form2">
+                        <div class="aspNetHidden">
+                            <input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE"
+                                   value="/wEPDwUKLTIzNjMxNDQxNw9kFgJmD2QWAmYPFgIeBFRleHQFqAE8YSBocmVmPSIvc2VhcmNoLmFzcHg/c2VhcmNoS2V5PeWWu+Wuiembr++8jOeLhOazve+8jOeBteW8gu+8jOWJjeS4luS7iueUn++8jOWGpeeOi+msvOWkqyIgdGFyZ2V0PSJfYmxhbmsiPuWWu+Wuiembr++8jOeLhOazve+8jOeBteW8gu+8jOWJjeS4luS7iueUn++8jOWGpeeOi+msvOWkqzwvYT5kZOquoASBvnvPbc/TYIQiLhSPJ8GKnYQrmk7jGhb5AC5Q">
+                        </div>
+
+                        <div class="aspNetHidden">
+
+                            <input type="hidden" name="__VIEWSTATEGENERATOR" id="__VIEWSTATEGENERATOR" value="23AA6834">
+                            <input type="hidden" name="__EVENTVALIDATION" id="__EVENTVALIDATION"
+                                   value="/wEdAAVece19BIZ9HiByRfHz3pfnqKSXUE1UN51mNFrIuw38c3Y2+Mc6SrnAqio3oCKbxYZZ1lS+gZUZKpbsAea8j7ASAv40DHFcQ/NE7tJUnABeyQ3d9sFDIcFCYNqlVtprfLoh4JFy0U+R/CcMuyAiWTz7">
+                        </div>
+                        <div class="user_l">
+                            <div></div>
+                            <h3>爬虫源信息填写（示例均为顶点小说网：dingdiann.com）</h3>
+                            <ul class="log_list">
+                                <li><span id="LabErr"></span></li>
+                                示例：<b>http://m.xdingdiann.com/sort/{catId}/{page}.html</b> ({catId}代表分类ID，{page}代表分页页码)
+                                <li><input type="text" id="url" class="s_input icon_key"
+                                           placeholder="url"></li>
+
+                                示例：<b>value=\"(\\d+)/\\d+\"</b>
+                                <li><input type="text" id="rule" class="s_input icon_name" placeholder="规则"></li>
+                                示例：<b>1强制刷新 空或0使用缓存</b>
+                                <li><input type="text" id="isRefresh" class="s_input icon_name" placeholder="是否强制刷新"></li>
+
+                                <li><textarea rows="20" cols="100" id="resultMap"></textarea></li>
+
+
+
+                                <li><input type="button" onclick="testCrawlSource()" name="btnRegister" value="测试"
+                                           id="btnRegister" class="btn_red"></li>
+                            </ul>
+                        </div>
+                    </form>
+                </div>
+                <!--<div id="divData" class="updateTable">
+                    <table cellpadding="0" cellspacing="0">
+                        <thead>
+                        <tr>
+
+                            <th class="name">
+                                爬虫源（已开启的爬虫源）
+                            </th>
+                            <th class="chapter">
+                                成功爬取数量（websocket实现）
+                            </th>
+                            <th class="time">
+                            目标爬取数量
+                            </th>
+                            <th class="goread">
+                                状态（正在运行，已停止）（一次只能运行一个爬虫源）
+                            </th>
+                            <th class="goread">
+                                操作（启动，停止）
+                            </th>
+                        </tr>
+                        </thead>
+                        <tbody id="bookShelfList">
+
+
+
+                        </tbody>
+                    </table>
+                    <div class="pageBox cf" id="shellPage">
+                    </div>
+                </div>-->
+            </div>
+        </div>
+    </div>
+</div>
+
+
+</body>
+<script src="/javascript/jquery-1.8.0.min.js" type="text/javascript"></script>
+<script src="/layui/layui.all.js" type="text/javascript"></script>
+<script src="/javascript/header.js" type="text/javascript"></script>
+<script src="/javascript/user.js" type="text/javascript"></script>
+<script language="javascript" type="text/javascript">
+    function load() {
+       var testParseUrl= localStorage.getItem("testParseUrl");
+       $("#url").val(testParseUrl);
+        var testParseRule=localStorage.getItem("testParseRule");
+        $("#rule").val(testParseRule);
+    }
+    function testCrawlSource() {
+
+        var data = {};
+
+
+        var isRefresh = $("#isRefresh").val();
+        data.isRefresh = isRefresh;
+        var rule = $("#rule").val();
+        if (rule.length == 0) {
+            layer.alert("正则必填");
+            return false;
+        }
+        data.rule = rule;
+        var url = $("#url").val();
+        if (url.length == 0) {
+            layer.alert("url必填");
+            return false;
+        }
+        data.url = url;
+
+        localStorage.setItem("testParseUrl",url);
+        localStorage.setItem("testParseRule",rule);
+        $.ajax({
+            type: "POST",
+            url: "/crawl/testParse",
+            data: data,
+            dataType: "json",
+            success: function (data) {
+                if (data.code == 200) {
+                    $("#resultMap").val(JSON.stringify(data.data));
+                } else {
+                    layer.alert(data.msg);
+                }
+
+            },
+            error: function () {
+                layer.alert('网络异常');
+            }
+        })
+
+    }
+
+</script>
+</html>

novel-crawl/src/main/resources/templates/crawl/crawlSource_update.html

@@ -0,0 +1,522 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+        "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+    <head>
+        <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
+        <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"/>
+        <title>爬虫管理系统-小说精品屋</title>
+        <link rel="stylesheet" href="/css/base.css?v=1"/>
+        <link rel="stylesheet" href="/css/user.css"/>
+    </head>
+</head>
+<body class="">
+
+<div class="header">
+    <div class="mainNav" id="mainNav">
+        <div class="box_center cf"
+             style="text-align: center;height: 44px;line-height: 48px;color: #fff;font-size: 16px;">
+
+            小说精品屋爬虫管理
+
+        </div>
+    </div>
+</div>
+
+<div class="main box_center cf">
+    <div class="userBox cf">
+        <div class="my_l">
+
+            <ul class="log_list">
+                <li><a class="link_1 on" href="/">爬虫源管理</a></li>
+                <li><a class="link_1" href="/crawl/crawlSingleTask_list.html">单本采集管理</a></li>
+                <li><a class="link_1" href="/crawl/crawlSource_test.html" target="_blank" >规则测试</a></li>
+                <!--<li><a class="link_1 " href="/user/userinfo.html">批量小说爬取</a></li>
+                <li><a class="link_4 " href="/user/favorites.html">单本小说爬取</a></li>-->
+            </ul>
+
+        </div>
+        <div class="my_r">
+            <div class="my_bookshelf">
+
+                <div class="userBox cf">
+                    <form method="post" action="./register.html" id="form2">
+                        <input type="hidden" name="id" id="sourceId"/>
+                        <div class="aspNetHidden">
+                            <input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE"
+                                   value="/wEPDwUKLTIzNjMxNDQxNw9kFgJmD2QWAmYPFgIeBFRleHQFqAE8YSBocmVmPSIvc2VhcmNoLmFzcHg/c2VhcmNoS2V5PeWWu+Wuiembr++8jOeLhOazve+8jOeBteW8gu+8jOWJjeS4luS7iueUn++8jOWGpeeOi+msvOWkqyIgdGFyZ2V0PSJfYmxhbmsiPuWWu+Wuiembr++8jOeLhOazve+8jOeBteW8gu+8jOWJjeS4luS7iueUn++8jOWGpeeOi+msvOWkqzwvYT5kZOquoASBvnvPbc/TYIQiLhSPJ8GKnYQrmk7jGhb5AC5Q">
+                        </div>
+
+                        <div class="aspNetHidden">
+
+                            <input type="hidden" name="__VIEWSTATEGENERATOR" id="__VIEWSTATEGENERATOR" value="23AA6834">
+                            <input type="hidden" name="__EVENTVALIDATION" id="__EVENTVALIDATION"
+                                   value="/wEdAAVece19BIZ9HiByRfHz3pfnqKSXUE1UN51mNFrIuw38c3Y2+Mc6SrnAqio3oCKbxYZZ1lS+gZUZKpbsAea8j7ASAv40DHFcQ/NE7tJUnABeyQ3d9sFDIcFCYNqlVtprfLoh4JFy0U+R/CcMuyAiWTz7">
+                        </div>
+                        <div class="user_l">
+                            <div></div>
+                            <h3>爬虫源信息填写（示例均为顶点小说网：dingdiann.com）</h3>
+                            <ul class="log_list">
+                                <li><span id="LabErr"></span></li>
+                                示例：<b>新顶点小说网</b>
+                                <li><input type="text" id="sourceName" class="s_input icon_name" placeholder="源站名"></li>
+                                <!--示例：<b>https://m.xdingdiann.com/sort/0/1.html</b>
+                                <li><input type="text" id="updateBookListUrl" class="s_input icon_key"
+                                           placeholder="小说更新列表url"></li>-->
+                                示例：<b>http://m.xdingdiann.com/sort/{catId}/{page}.html</b> ({catId}代表分类ID，{page}代表分页页码)
+                                <li><input type="text" id="bookListUrl" class="s_input icon_key"
+                                           placeholder="分类列表页URL规则"></li>
+                                示例：<b>1</b>
+                                <li><input type="text" id="catId1" class="s_input icon_key" placeholder="玄幻奇幻分类ID"></li>
+                                示例：<b>2</b>
+                                <li><input type="text" id="catId2" class="s_input icon_key" placeholder="武侠仙侠分类ID"></li>
+                                示例：<b>3</b>
+                                <li><input type="text" id="catId3" class="s_input icon_key" placeholder="都市言情分类ID"></li>
+                                示例：<b>4</b>
+                                <li><input type="text" id="catId4" class="s_input icon_key" placeholder="历史军事分类ID"></li>
+                                示例：<b>5</b>
+                                <li><input type="text" id="catId5" class="s_input icon_key" placeholder="科幻灵异分类ID"></li>
+                                示例：<b>6</b>
+                                <li><input type="text" id="catId6" class="s_input icon_key" placeholder="网游竞技分类ID"></li>
+                                示例：<b>7</b>
+                                <li><input type="text" id="catId7" class="s_input icon_key" placeholder="女生频道分类ID"></li>
+                                示例：<b>href="/ddk(\d+)/"</b>
+                                <li><input type="text" id="bookIdPatten" class="s_input icon_key"
+                                           placeholder="列表页小说ID正则表达式："></li>
+                                <b>value="(\d+)/\d+"</b>
+                                <li><input type="text" id="pagePatten" class="s_input icon_key"
+                                           placeholder="列表页当前分页页码正则表达式："></li>
+                                <b>value="\d+/(\d+)"</b>
+                                <li><input type="text" id="totalPagePatten" class="s_input icon_key"
+                                           placeholder="列表页分页总页数正则表达式："></li>
+                                <b>http://m.xdingdiann.com/ddk{bookId}</b> (bookId代表小说ID)
+                                <li><input type="text" id="bookDetailUrl" class="s_input icon_key"
+                                           placeholder="详情页URL规则："></li>
+                                示例：<b>&lt;p class="title"&gt;([^/]+)&lt;/p&gt;</b>
+                                <li><input type="text" id="bookNamePatten" class="s_input icon_key"
+                                           placeholder="小说名的正则表达式："></li>
+                                示例：<b>作者：([^/]+)<</b>
+                                <li><input type="text" id="authorNamePatten" class="s_input icon_key"
+                                           placeholder="小说作者的正则表达式："></li>
+                                示例：<b>&lt;img src="([^>]+)"\s+onerror="this.src=</b>
+                                <li><input type="text" id="picUrlPatten" class="s_input icon_key"
+                                           placeholder="小说图片路径的正则表达式："></li>
+                                <b>可空，适用于图片路径为相对路径的源站，加上小说图片路径，则为完整的可访问的图片路径</b>
+                                <li><input type="text" id="picUrlPrefix" class="s_input icon_key"
+                                           placeholder="小说图片访问路径前缀："></li>
+                                示例：<b>状态：([^/]+)&lt;/li&gt;</b>
+                                <li><input type="text" id="statusPatten" class="s_input icon_key"
+                                           placeholder="小说状态的正则表达式："></li>
+                                示例：<b>连载</b>
+                                <li><input type="text" id="bookStatus0" class="s_input icon_key"
+                                           placeholder="连载中的小说在此网站的具体表现值："></li>
+                                示例：<b>完结</b>
+                                <li><input type="text" id="bookStatus1" class="s_input icon_key"
+                                           placeholder="全本小说在此网站的具体表现值："></li>
+                                示例：<b>&lt;div\s+class="score"&gt;(\d+\.\d+)分&lt;/div&gt;</b>
+                                <li><input type="text" id="scorePatten" class="s_input icon_key"
+                                           placeholder="小说评分的正则表达式："></li>
+                                示例：<b></b>
+                                <li><input type="text" id="visitCountPatten" class="s_input icon_key"
+                                           placeholder="小说点击量的正则表达式："></li>
+                                示例：<b>&lt;p class="review"&gt;</b>
+                                <li><input type="text" id="descStart" class="s_input icon_key"
+                                           placeholder="小说简介开始截取字符串："></li>
+                                示例：<b>&lt;/p&gt;</b>
+                                <li><input type="text" id="descEnd" class="s_input icon_key" placeholder="小说简介结束截取字符串：">
+                                </li>
+                                示例：<b>更新：(\d+-\d+-\d+\s\d+:\d+:\d+)&lt;/a&gt;</b>
+                                <li><input type="text" id="upadateTimePatten" class="s_input icon_key"
+                                           placeholder="小说更新时间的正则表达式："></li>
+                                示例：<b>yyyy-MM-dd HH:mm:ss</b>
+                                <li><input type="text" id="upadateTimeFormatPatten" class="s_input icon_key"
+                                           placeholder="小说更新时间在此网站的显示模式："></li>
+                                示例：<b>http://m.xdingdiann.com/ddk{bookId}/all.html</b> (bookId代表小说ID)
+                                <li><input type="text" id="bookIndexUrl" class="s_input icon_key"
+                                           placeholder="小说目录页的URL规则："></li>
+                                <b>可空，适用于最新章节列表和全部章节列表在同一个页面的源站</b>
+                                <li><input type="text" id="bookIndexStart" class="s_input icon_key"
+                                           placeholder="小说目录页内容开始截取字符串："></li>
+                                示例：<b>&lt;a\s+style=""\s+href="/ddk\d+/(\d+)\.html"&gt;[^/]+&lt;/a&gt;</b>
+                                <li><input type="text" id="indexIdPatten" class="s_input icon_key"
+                                           placeholder="目录页目录ID正则表达式："></li>
+                                示例：<b>&lt;a\s+style=""\s+href="/ddk\d+/\d+\.html"&gt;([^/]+)&lt;/a&gt;</b>
+                                <li><input type="text" id="indexNamePatten" class="s_input icon_key"
+                                           placeholder="目录页目录名的正则表达式："></li>
+                                示例：<b>http://m.xdingdiann.com/ddk{bookId}/{indexId}.html</b>
+                                (bookId代表小说ID,{indexId}代表目录ID)
+                                <li><input type="text" id="bookContentUrl" class="s_input icon_key"
+                                           placeholder="小说内容页的URL规则："></li>
+                                示例：<b>id="content"></b>
+                                <li><input type="text" id="contentStart" class="s_input icon_key"
+                                           placeholder="小说内容开始截取字符串："></li>
+                                示例：<b>&lt;script&gt;</b>
+                                <li><input type="text" id="contentEnd" class="s_input icon_key"
+                                           placeholder="小说内容结束截取字符串："></li>
+
+                                <li><input type="button" onclick="updateCrawlSource()" name="btnRegister" value="提交"
+                                           id="btnRegister" class="btn_red"></li>
+                            </ul>
+                        </div>
+                    </form>
+                </div>
+                <!--<div id="divData" class="updateTable">
+                    <table cellpadding="0" cellspacing="0">
+                        <thead>
+                        <tr>
+
+                            <th class="name">
+                                爬虫源（已开启的爬虫源）
+                            </th>
+                            <th class="chapter">
+                                成功爬取数量（websocket实现）
+                            </th>
+                            <th class="time">
+                            目标爬取数量
+                            </th>
+                            <th class="goread">
+                                状态（正在运行，已停止）（一次只能运行一个爬虫源）
+                            </th>
+                            <th class="goread">
+                                操作（启动，停止）
+                            </th>
+                        </tr>
+                        </thead>
+                        <tbody id="bookShelfList">
+
+
+
+                        </tbody>
+                    </table>
+                    <div class="pageBox cf" id="shellPage">
+                    </div>
+                </div>-->
+            </div>
+        </div>
+    </div>
+</div>
+
+
+</body>
+<script src="/javascript/jquery-1.8.0.min.js" type="text/javascript"></script>
+<script src="/layui/layui.all.js" type="text/javascript"></script>
+<script src="/javascript/header.js" type="text/javascript"></script>
+<script src="/javascript/user.js" type="text/javascript"></script>
+<script language="javascript" type="text/javascript">
+
+    function load(){
+        var crawlSourceId = localStorage.getItem("crawlSourceId")
+        if(crawlSourceId!=null){
+            $.ajax({
+                type: "GET",
+                url: "/crawl/getCrawlSource/"+crawlSourceId,
+                dataType: "json",
+                success: function (data) {
+                    if (data.code == 200) {
+                        loadPage(data.data);
+                    } else if (data.code == 1001) {
+                        //未登录
+                        location.href = '/user/login.html?originUrl=' + decodeURIComponent(location.href);
+
+                    }else {
+                        layer.alert(data.msg);
+                    }
+
+                },
+                error: function () {
+                    layer.alert('网络异常');
+                }
+            })
+        }
+    }
+    function loadPage(data){
+        $("#sourceId").val(data.id);
+        $("#sourceName").val(data.sourceName);
+        if(data.crawlRule){
+
+
+            var crawlRule= JSON.parse(data.crawlRule);
+            $("#bookListUrl").val(crawlRule.bookListUrl);
+            var catIdRule = crawlRule.catIdRule;
+            try{
+                for (var i = 1; i <= 7; i++) {
+                    $("#catId" + i).val(catIdRule["catId" + i]);
+                }
+            }catch(e){
+            }
+            $("#bookIdPatten").val(crawlRule.bookIdPatten);
+            $("#pagePatten").val(crawlRule.pagePatten);
+            $("#totalPagePatten").val(crawlRule.totalPagePatten);
+            $("#bookDetailUrl").val(crawlRule.bookDetailUrl);
+            $("#bookNamePatten").val(crawlRule.bookNamePatten);
+            $("#authorNamePatten").val(crawlRule.authorNamePatten);
+            $("#picUrlPatten").val(crawlRule.picUrlPatten);
+            $("#picUrlPrefix").val(crawlRule.picUrlPrefix);
+            $("#statusPatten").val(crawlRule.statusPatten);
+            try{
+                var bookStatusRule = crawlRule.bookStatusRule;
+                var i=0;
+                for(var key in bookStatusRule){
+                    $("#bookStatus" + i).val(key);
+                    i++;
+                }
+            }catch (e) {
+
+            }
+            $("#scorePatten").val(crawlRule.scorePatten);
+            $("#visitCountPatten").val(crawlRule.visitCountPatten);
+            $("#descStart").val(crawlRule.descStart);
+            $("#descEnd").val(crawlRule.descEnd);
+            $("#upadateTimePatten").val(crawlRule.upadateTimePatten);
+            $("#upadateTimeFormatPatten").val(crawlRule.upadateTimeFormatPatten);
+            $("#bookIndexUrl").val(crawlRule.bookIndexUrl);
+            $("#bookIndexStart").val(crawlRule.bookIndexStart);
+            $("#indexIdPatten").val(crawlRule.indexIdPatten);
+            $("#indexNamePatten").val(crawlRule.indexNamePatten);
+            $("#bookContentUrl").val(crawlRule.bookContentUrl);
+            $("#contentStart").val(crawlRule.contentStart);
+            $("#contentEnd").val(crawlRule.contentEnd);
+
+        }
+    }
+    load();
+
+    function updateCrawlSource() {
+
+        var crawlRule = {};
+        var sourceId =$("#sourceId").val();
+
+        var sourceName = $("#sourceName").val();
+        if (sourceName.length == 0) {
+            layer.alert("源站名必填");
+            return false;
+        }
+
+        var bookListUrl = $("#bookListUrl").val();
+        if (bookListUrl.length == 0) {
+            layer.alert("分类列表页URL规则必填");
+            return false;
+        }
+        crawlRule.bookListUrl = bookListUrl;
+
+        var catIdRule = {};
+
+        for (var i = 1; i <= 7; i++) {
+            var catId = $("#catId" + i).val();
+            if (catId.length > 0) {
+                catIdRule["catId" + i] = catId;
+            }
+        }
+
+        if (Object.keys(catIdRule).length == 0) {
+            layer.alert("分类ID至少要填一项");
+            return false;
+        }
+        crawlRule.catIdRule = catIdRule;
+
+
+        var bookIdPatten = $("#bookIdPatten").val();
+
+
+        if (bookIdPatten.length == 0) {
+            layer.alert("列表页小说ID正则表达式必填");
+            return false;
+        }
+
+        crawlRule.bookIdPatten = bookIdPatten;
+
+        var pagePatten = $("#pagePatten").val();
+
+        if (pagePatten.length > 0) {
+            crawlRule.pagePatten = pagePatten;
+        }
+
+        var totalPagePatten = $("#totalPagePatten").val();
+
+        if (totalPagePatten.length > 0) {
+            crawlRule.totalPagePatten = totalPagePatten;
+        }
+
+        var bookDetailUrl = $("#bookDetailUrl").val();
+
+        if (bookDetailUrl.length == 0) {
+            layer.alert("详情页URL规则必填");
+            return false;
+        }
+
+        crawlRule.bookDetailUrl = bookDetailUrl;
+
+        var bookNamePatten = $("#bookNamePatten").val();
+
+        if (bookNamePatten.length == 0) {
+            layer.alert("小说名的正则表达式必填");
+            return false;
+        }
+
+        crawlRule.bookNamePatten = bookNamePatten;
+
+        var authorNamePatten = $("#authorNamePatten").val();
+
+        if (authorNamePatten.length == 0) {
+            layer.alert("小说作者的正则表达式必填");
+            return false;
+        }
+
+        crawlRule.authorNamePatten = authorNamePatten;
+
+        var picUrlPatten = $("#picUrlPatten").val();
+
+        if (picUrlPatten.length > 0) {
+            crawlRule.picUrlPatten = picUrlPatten;
+        }
+
+        var picUrlPrefix = $("#picUrlPrefix").val();
+
+        if (picUrlPrefix.length > 0) {
+            crawlRule.picUrlPrefix = picUrlPrefix;
+        }
+
+        var statusPatten = $("#statusPatten").val();
+        if (statusPatten.length > 0) {
+            crawlRule.statusPatten = statusPatten;
+        }
+
+        var bookStatusRule = {};
+
+        for (var i = 0; i <= 1; i++) {
+            var bookStatus = $("#bookStatus" + i).val();
+            if (bookStatus.length > 0) {
+                bookStatusRule[bookStatus] = i;
+            }
+        }
+
+        crawlRule.bookStatusRule = bookStatusRule;
+
+        var scorePatten = $("#scorePatten").val();
+
+        if (scorePatten.length > 0) {
+            crawlRule.scorePatten = scorePatten;
+        }
+
+        var visitCountPatten = $("#visitCountPatten").val();
+
+        if (visitCountPatten.length > 0) {
+            crawlRule.visitCountPatten = visitCountPatten;
+        }
+
+        var descStart = $("#descStart").val();
+
+        if (descStart.length == 0) {
+            layer.alert("小说简介开始截取字符串必填");
+            return false;
+        }
+
+        crawlRule.descStart = descStart;
+
+        var descEnd = $("#descEnd").val();
+
+        if (descEnd.length == 0) {
+            layer.alert("小说简介结束截取字符串必填");
+            return false;
+        }
+
+        crawlRule.descEnd = descEnd;
+
+        var upadateTimePatten = $("#upadateTimePatten").val();
+
+        if (upadateTimePatten.length > 0) {
+            crawlRule.upadateTimePatten = upadateTimePatten;
+        }
+
+        var upadateTimeFormatPatten = $("#upadateTimeFormatPatten").val();
+
+        if (upadateTimeFormatPatten.length > 0) {
+            crawlRule.upadateTimeFormatPatten = upadateTimeFormatPatten;
+        }
+
+        var bookIndexUrl = $("#bookIndexUrl").val();
+
+        if (bookIndexUrl.length == 0) {
+            layer.alert("小说目录页的URL规则必填");
+            return false;
+        }
+
+        crawlRule.bookIndexUrl = bookIndexUrl;
+
+
+        var bookIndexStart = $("#bookIndexStart").val();
+
+        if (bookIndexStart.length > 0) {
+            crawlRule.bookIndexStart = bookIndexStart;
+        }
+
+        var indexIdPatten = $("#indexIdPatten").val();
+
+        if (indexIdPatten.length == 0) {
+            layer.alert("小说目录页的目录ID正则表达式必填");
+            return false;
+        }
+
+        crawlRule.indexIdPatten = indexIdPatten;
+
+        var indexNamePatten = $("#indexNamePatten").val();
+
+        if (indexNamePatten.length == 0) {
+            layer.alert("小说目录页的目录名正则表达式必填");
+            return false;
+        }
+
+        crawlRule.indexNamePatten = indexNamePatten;
+
+        var bookContentUrl = $("#bookContentUrl").val();
+
+        if (bookContentUrl.length == 0) {
+            layer.alert("小说内容页的URL规则必填");
+            return false;
+        }
+
+        crawlRule.bookContentUrl = bookContentUrl;
+
+        var contentStart = $("#contentStart").val();
+
+        if (contentStart.length == 0) {
+            layer.alert("小说内容开始截取字符串必填");
+            return false;
+        }
+        crawlRule.contentStart = contentStart;
+
+        var contentEnd = $("#contentEnd").val();
+
+        if (contentEnd.length == 0) {
+            layer.alert("小说内容结束截取字符串必填");
+            return false;
+        }
+
+        crawlRule.contentEnd = contentEnd;
+
+
+        $.ajax({
+            type: "POST",
+            url: "/crawl/updateCrawlSource",
+            data: {'id':sourceId,'sourceName': sourceName, 'crawlRule': JSON.stringify(crawlRule)},
+            dataType: "json",
+            success: function (data) {
+                if (data.code == 200) {
+
+                    window.location.href = '/crawl/crawlSource_list.html';
+
+
+                } else {
+                    layer.alert(data.msg);
+                }
+
+            },
+            error: function () {
+                layer.alert('网络异常');
+            }
+        })
+
+    }
+
+</script>
+</html>

novel-front/pom.xml

@@ -87,14 +87,92 @@
         </dependency>
     </dependencies>
 
+<!--    <build>-->
+<!--        <plugins>-->
+<!--            <plugin>-->
+<!--                <groupId>org.springframework.boot</groupId>-->
+<!--                <artifactId>spring-boot-maven-plugin</artifactId>-->
+<!--            </plugin>-->
+<!--        </plugins>-->
+<!--    </build>-->
     <build>
         <plugins>
             <plugin>
+                <!--打包时去除第三方依赖-->
                 <groupId>org.springframework.boot</groupId>
                 <artifactId>spring-boot-maven-plugin</artifactId>
+                <configuration>
+                    <layout>ZIP</layout>
+                    <includes>
+                        <include>
+                            <groupId>non-exists</groupId>
+                            <artifactId>non-exists</artifactId>
+                        </include>
+                    </includes>
+                </configuration>
+            </plugin>
+            <!--拷贝第三方依赖文件到指定目录-->
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-dependency-plugin</artifactId>
+                <executions>
+                    <execution>
+                        <id>copy-dependencies</id>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>copy-dependencies</goal>
+                        </goals>
+                        <configuration>
+                            <!--target/lib是依赖jar包的输出目录，根据自己喜好配置-->
+                            <outputDirectory>target/lib</outputDirectory>
+                            <excludeTransitive>false</excludeTransitive>
+                            <stripVersion>false</stripVersion>
+                            <includeScope>runtime</includeScope>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+            <plugin>
+                <artifactId>maven-antrun-plugin</artifactId>
+                <version>1.8</version>
+                <executions>
+                    <execution>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>run</goal>
+                        </goals>
+                        <configuration>
+                            <tasks>
+                                <!-- 文件夹 -->
+                                <copy todir="${project.build.directory}/build/conf" overwrite="true">
+                                    <fileset dir="${basedir}/src/main/resources">
+                                        <include name="**/*.*"/>
+                                        <exclude name="mybatis/*/*.*"/>
+                                    </fileset>
+                                </copy>
+                                <move todir="${project.build.directory}/build/lib">
+                                    <fileset dir="target/lib"/>
+                                </move>
+                                <copy file="${project.build.directory}/${project.artifactId}-${project.version}.jar"
+                                      tofile="${project.build.directory}/build/${project.artifactId}.jar" />
+
+                                <fixcrlf srcdir="${basedir}/src/main/build/scripts" eol="unix"/>
+                                <copy todir="${project.build.directory}/build/bin">
+                                    <fileset dir="${basedir}/src/main/build/scripts">
+                                        <include name="*.sh" />
+                                        <include name="*.txt" />
+                                        <include name="*.bat" />
+                                    </fileset>
+                                </copy>
+                                <zip destfile='${project.build.directory}/build/${project.artifactId}.zip'>
+                                    <zipfileset filemode="755" dir= '${project.build.directory}/build/' />
+                                </zip>
+                            </tasks>
+                        </configuration>
+                    </execution>
+                </executions>
             </plugin>
         </plugins>
     </build>
 
-
+</project>
-</project>

novel-front/src/main/build/scripts/readme.txt

@@ -0,0 +1,8 @@
+1：linux启动环境
+sh start.sh
+
+3：windows启动环境
+windows-start.bat
+
+3：linux停止应用
+sh stop.sh

novel-front/src/main/build/scripts/start.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+ENGINE=novel-front.jar
+cd ../
+
+#部署目路
+DEPLOY_DIR=`pwd`
+#获取到当前目录的名称
+SERVER_NAME=`basename $DEPLOY_DIR`
+
+#应用进程
+PIDS=`ps -ef | grep java | grep "$ENGINE" |awk '{print $2}'`
+#设置日志文件的输出目录
+LOGS_DIR=$DEPLOY_DIR/logs
+if [ ! -d $LOGS_DIR ]; then
+    mkdir $LOGS_DIR
+fi
+#日志
+STDOUT_FILE=$LOGS_DIR/stdout.log
+#JAVA 环境配置
+JAVA_OPTS=" -Djava.net.preferIPv4Stack=true -Dlog.home=$LOGS_DIR"
+
+JAVA_MEM_OPTS=" -server -Xms1024m -Xmx1024m -XX:MetaspaceSize=64m -XX:MaxMetaspaceSize=256m  -XX:+UseG1GC -XX:MaxGCPauseMillis=100 -XX:InitiatingHeapOccupancyPercent=50 -XX:+PrintGCApplicationStoppedTime -XX:+PrintGCApplicationConcurrentTime -XX:+PrintGCDateStamps -verbose:gc -XX:+PrintGCDetails -XX:+PrintHeapAtGC -Xloggc:$LOGS_DIR/gc.log -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=10 -XX:GCLogFileSize=100M -XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=dump.hprof "
+#退出标志
+RETVAL="0"
+
+if [ -n "$PIDS" ]; then
+		echo "ERROR: The $SERVER_NAME already started!"
+		echo "PID: $PIDS"
+		exit $RETVAL
+fi
+
+nohup java -jar  $JAVA_OPTS $JAVA_MEM_OPTS  -Dloader.path=conf,lib $ENGINE > $STDOUT_FILE 2>&1 &
+COUNT=0
+	while [ $COUNT -lt 1 ]; do
+		echo -e ".\c"
+		sleep 1
+		COUNT=`ps -f | grep java | grep "$DEPLOY_DIR" | awk '{print $2}' | wc -l`
+		if [ $COUNT -gt 0 ]; then
+			break
+		fi
+	done
+
+	echo "OK!"
+	PIDS=`ps -f | grep java | grep "$DEPLOY_DIR" | awk '{print $2}'`
+	echo "PID: $PIDS"
+	echo "STDOUT: $STDOUT_FILE"

novel-front/src/main/build/scripts/stop.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+SERVER_NAME=novel-front.jar
+
+#应用进程
+PIDS=`ps -ef | grep java | grep "$SERVER_NAME" |awk '{print $2}'`
+if [ -z "$PIDS" ]; then
+    		echo "ERROR: The $SERVER_NAME does not started!"
+    	exit 1
+	fi
+
+	echo -e "Stopping the $SERVER_NAME ...\c"
+	for PID in $PIDS ; do
+    		kill $PID > /dev/null 2>&1
+	done
+
+	COUNT=0
+	while [ $COUNT -lt 1 ]; do
+    		echo -e ".\c"
+    		sleep 1
+    		COUNT=1
+    		for PID in $PIDS ; do
+        	PID_EXIST=`ps -f -p $PID | grep java`
+        	if [ -n "$PID_EXIST" ]; then
+            		COUNT=0
+            		break
+        	fi
+    		done
+	done
+
+	echo "OK!"
+	echo "PID: $PIDS"
+	PIDS=""
+

novel-front/src/main/build/scripts/windows-start.bat

@@ -0,0 +1,10 @@
+@echo off
+setlocal enabledelayedexpansion
+set JAVA=java
+
+set OPTS=-XX:MetaspaceSize=128m -XX:MaxMetaspaceSize=128m -Xms1024m -Xmx1024m -Xmn256m -Xss256k -XX:SurvivorRatio=8 -XX:+UseConcMarkSweepGC
+set ENGINE=novel-front.jar
+cd ../
+java -jar %OPTS%   -Dloader.path=conf,lib %ENGINE%
+pause
+

novel-front/src/main/resources/logback-boot.xml

@@ -57,8 +57,8 @@
     <!-- 指定项目中某个包，当有日志操作行为时的日志记录级别 -->
     <!-- com.maijinjie.springboot 为根包，也就是只要是发生在这个根包下面的所有日志操作行为的权限都是DEBUG -->
     <!-- 级别依次为【从高到低】：FATAL > ERROR > WARN > INFO > DEBUG > TRACE -->
-    <logger name="com.java2nb" level="DEBUG">
+    <logger name="com.java2nb" level="DEBUG"  additivity="false">
         <appender-ref ref="STDOUT" />
         <appender-ref ref="FILE" />
     </logger>
-</configuration>
+</configuration>

pom.xml

@@ -30,7 +30,7 @@
         <java.version>1.8</java.version>
         <maven.test.skip>true</maven.test.skip>
         <mysql.version>8.0.11</mysql.version>
-        <mybatis.version>1.3.2</mybatis.version>
+        <mybatis.version>2.1.4</mybatis.version>
         <mybatis-generator.version>1.4.0</mybatis-generator.version>
         <mybatis-dynamic-sql.version>1.1.4</mybatis-dynamic-sql.version>
         <pagehelper.version>1.2.5</pagehelper.version>
@@ -112,4 +112,4 @@
             </snapshots>
         </pluginRepository>
     </pluginRepositories>
-</project>
+</project>