201206030/novel-plus
1
0
Fork 0
mirror of https://github.com/201206030/novel-plus.git synced 2025-06-24 12:46:38 +00:00
Code Issues Packages Releases Wiki Activity

增加新源，过滤简介中的特殊字符，提高爬虫兼容性

Browse Source
This commit is contained in:
xiongxiaoyang
2020-06-08 16:54:58 +08:00
parent f8a669eb01
commit 0e2e6229cd
6 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
novel-crawl/src/main/java/com/java2nb/novel/core/crawl/CrawlParser.java
View File

@ -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())) {