Java实例——基于jsoup的简单爬虫实现（从智联获取工作信息）
这几天在学习Java解析xml，突然想到Dom能不能解析html，结果试了半天行不通，然后就去查了一些资料，发现很多人都在用Jsoup解析html文件，然后研究了一下，写了一个简单的实例，感觉还有很多地方需要润色，在这里分享一下我的实例，欢迎交流指教！
后续想通过Java把数据导入到Excel或者生成一个报表！
1 package gethtml; 2 3 4 5 import java.io.IOException; 6 import org.jsoup.Jsoup; 7 import org.jsoup.nodes.Document; 8 import org.jsoup.nodes.Element; 9 import org.jsoup.select.Elements; 10 11 /**从智联招聘获取招聘信息 12 * @author syskey 13 * @url 智联招聘网站链接（建议不要更改） 14 * @city 搜索工作的城市 15 * @keywrods 搜索工作的相关关键字 16 */ 17 18 public class JsoupHtml { 19 20 private String url="http://sou.zhaopin.com/jobs/searchresult.ashx?jl="; //智联招聘网站 21 private String city="西安"; //搜索工作的城市 22 private String keywords="java"; //搜索工作的关键字 23 public JsoupHtml(String city,String keywords){ 24 this.city=city; 25 this.keywords =keywords; 26 27 } 28 29 public void getZhiLianWork(){ 30 try { 31 for (int i=0;i<10;i++) { 32 System.out.println("*********开始遍历第"+(i+1)+"页的求职信息*********"); 33 Document doc = Jsoup.connect(url+city+"&kw="+keywords+"&p="+(i+1)+"&isadv=0").get(); 34 Element content = doc.getElementById("newlist_list_content_table"); 35 Elements zwmcEls = content.getElementsByClass("zwmc"); 36 Elements gsmcEls = content.getElementsByClass("gsmc"); 37 Elements zwyxEls = content.getElementsByClass("zwyx"); 38 Elements gzddEls = content.getElementsByClass("gzdd"); 39 Elements gxsjEls = content.getElementsByClass("gxsj"); 40 for(int j = 0;j<zwmcEls .size();j++){ 41 42 System.out.println( 43 zwmcEls.get(j).tagName("a").text()+"*****"+gsmcEls.get(j).tagName("a").text()+ 44 "*****"+zwyxEls.get(j).tagName("a").text()+"*****"+gzddEls.get(j).tagName("a").text()+ 45 "*****"+gxsjEls.get(j).tagName("a").text()); 46 System.out.println(); 47 } 48 System.out.println("*********结束遍历第"+(i+1)+"页的求职信息*********"); 49 50 } 51 52 } catch (IOException e) { 53 // TODO Auto-generated catch block 54 e.printStackTrace(); 55 } 56 } 57 public static void main(String[] args) { 58 59 JsoupHtml jHtml = new JsoupHtml("上海", "java"); 60 jHtml.getZhiLianWork(); 61 62 } 63 64 }
更新源代码，支持生成html表格：
package jsouphtml;
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 ="http://sou.zhaopin.com/jobs/searchresult.ashx?";
String city ="西安";
String keywords = "java";
BufferedWriter bWriter = new BufferedWriter(
new OutputStreamWriter(
new FileOutputStream("output.html"),"utf-8"));
bWriter.write("");
File input = new File("input.html");
Document doc2 = Jsoup.parse(input, "UTF-8", "");
Element table = doc2.getElementById("workinfo");
table.text("");
Element theader = 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=0;page<10;page++){
Document doc = Jsoup.connect(url+city+"&kw="+keywords+"&p="+page).get();
Element content = doc.getElementById("newlist_list_content_table");
Elements zwmcEls = content.getElementsByClass("zwmc");
Elements gsmcEls = content.getElementsByClass("gsmc");
Elements zwyxEls = content.getElementsByClass("zwyx");
Elements gzddEls = content.getElementsByClass("gzdd");
Elements gxsjEls = content.getElementsByClass("gxsj");
for(int i = 1;i<zwmcEls .size();i++){
Element tr =table.appendElement("tr");
tr.appendElement("td").text((page+1)+"-"+i);
tr.appendElement("td").text(zwmcEls.get(i).tagName("a").text());
tr.appendElement("td").text(gsmcEls.get(i).tagName("a").text());
tr.appendElement("td").text(zwyxEls.get(i).tagName("a").text());
tr.appendElement("td").text(gzddEls.get(i).tagName("a").text());
tr.appendElement("td").text(gxsjEls.get(i).tagName("a").text());
}
}
System.out.println(doc2.html());
bWriter.write(doc2.html());
bWriter.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
output.html模板：
<!doctype html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="Generator" content="EditPlus®">
<meta name="Author" content="">
<meta name="Keywords" content="">
<meta name="Description" content="">
<title>智联工作信息</title>
<style>
body{margin:0;padding:0;}
.header{height:100px;width:100%;background:#39c;color:#fff;text-align:center;line-height:100px;font-size:40px;
font-family:"微软雅黑";}
.body{width:100%;background:#fff;}
.body table{width:90%;margin:0 auto;color:#2e2e2e;border:1px solid #cad9ea; border-collapse: collapse; }
.body table th,td{min-width:50px;max-width:300px;}
.feeter{height:30px;width:100%;background:#39c;color:#fff;text-align:center;line-height:30px;font-size:14px;
font-family:"微软雅黑";}
</style>
</head>
<body>
<div class="header">智联工作信息</div>
<div class="body">
<table class="work" border="1">
<tbody id="workinfo">
</tbody>
</table>
</div>
<div class="feeter">版权所有 翻版必究@2017 sysker</div>
</body>
</html>
