【Java】基于jsoup爬虫实现（从智联获取工作信息）

这几天在学习Java解析xml&＃xff0c;突然想到Dom能不能解析html&＃xff0c;结果试了半天行不通&＃xff0c;然后就去查了一些资料&＃xff0c;发现很多人都在用Jsoup解析html文件&＃xff0c;然后研究了一下&＃xff0c;写了一个简单的实例&＃xff0c;感觉还有很多地方需要润色&＃xff0c;在这里分享一下我的实例&＃xff0c;欢迎交流指教&＃xff01;后续想通过Java把数据导入到Excel或者生成一个报表&＃xff01;

import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;/**从智联招聘获取招聘信息* &＃64;url 智联招聘网站链接&＃xff08;建议不要更改&＃xff09;* &＃64;city 搜索工作的城市* &＃64;keywrods 搜索工作的相关关键字*/public class JsoupHtml {private String url&＃61;"http://sou.zhaopin.com/jobs/searchresult.ashx?jl&＃61;"; //智联招聘网站private String city&＃61;"西安"; //搜索工作的城市private String keywords&＃61;"java"; //搜索工作的关键字public JsoupHtml(String city,String keywords){ this.city&＃61;city;this.keywords &＃61;keywords;}public void getZhiLianWork(){try {for (int i&＃61;0;i<10;i&＃43;&＃43;) {System.out.println("*********开始遍历第"&＃43;(i&＃43;1)&＃43;"页的求职信息*********");Document doc &＃61; Jsoup.connect(url&＃43;city&＃43;"&kw&＃61;"&＃43;keywords&＃43;"&p&＃61;"&＃43;(i&＃43;1)&＃43;"&isadv&＃61;0").get(); Element content &＃61; doc.getElementById("newlist_list_content_table"); Elements zwmcEls &＃61; content.getElementsByClass("zwmc");Elements gsmcEls &＃61; content.getElementsByClass("gsmc"); Elements zwyxEls &＃61; content.getElementsByClass("zwyx"); Elements gzddEls &＃61; content.getElementsByClass("gzdd"); Elements gxsjEls &＃61; content.getElementsByClass("gxsj");for(int j &＃61; 0;j

更新源代码&＃xff0c;支持生成html表格&＃xff1a;

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;public class JsoupHtml {public static void main(String[] args) { try {String url &＃61;"http://sou.zhaopin.com/jobs/searchresult.ashx?";String city &＃61;"西安";String keywords &＃61; "java";BufferedWriter bWriter &＃61; new BufferedWriter(new OutputStreamWriter(new FileOutputStream("output.html"),"utf-8"));bWriter.write("");File input &＃61; new File("input.html");Document doc2 &＃61; Jsoup.parse(input, "UTF-8", "");Element table &＃61; doc2.getElementById("workinfo");table.text("");Element theader &＃61; table.appendElement("tr");theader.appendElement("th").text("序号");theader.appendElement("th").text("职位名称");theader.appendElement("th").text("公司名称");theader.appendElement("th").text("职位月薪");theader.appendElement("th").text("工作地点");theader.appendElement("th").text("发布日期"); for(int page&＃61;0;page<10;page&＃43;&＃43;){ Document doc &＃61; Jsoup.connect(url&＃43;city&＃43;"&kw&＃61;"&＃43;keywords&＃43;"&p&＃61;"&＃43;page).get(); Element content &＃61; doc.getElementById("newlist_list_content_table"); Elements zwmcEls &＃61; content.getElementsByClass("zwmc");Elements gsmcEls &＃61; content.getElementsByClass("gsmc"); Elements zwyxEls &＃61; content.getElementsByClass("zwyx"); Elements gzddEls &＃61; content.getElementsByClass("gzdd"); Elements gxsjEls &＃61; content.getElementsByClass("gxsj");for(int i &＃61; 1;i

output.html模板&＃xff1a;