增加新源，过滤简介中的特殊字符，提高爬虫兼容性

novel-crawl/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <artifactId>novel</artifactId>
         <groupId>com.java2nb</groupId>
-        <version>2.5.0</version>
+        <version>2.5.1</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 

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

@@ -96,8 +96,12 @@ public class CrawlParser {
 
                     String desc = bookDetailHtml.substring(bookDetailHtml.indexOf(ruleBean.getDescStart()) + ruleBean.getDescStart().length());
                     desc = desc.substring(0, desc.indexOf(ruleBean.getDescEnd()));
-                    //过滤掉简介中的a标签
-                    desc = desc.replaceAll("<a[^<]+</a>","");
+                    //过滤掉简介中的特殊标签
+                    desc = desc.replaceAll("<a[^<]+</a>","")
+                            .replaceAll("<font[^<]+</font>","")
+                            .replaceAll("<p>\\s*</p>","")
+                            .replaceAll("<p>","")
+                            .replaceAll("</p>","<br/>");
                     //设置书籍简介
                     book.setBookDesc(desc);
                     if (StringUtils.isNotBlank(ruleBean.getStatusPatten())) {