网络爬虫httpclient与jsoup解析

模拟爬取51job网站的信息

//爬取对象
HttpClient httpClient = new HttpClient();
//创建爬取方法
GetMethod method= new GetMethod("http://www.51job.com/");
//开始爬取
httpClient.executeMethod(method);
//获取一个页面返回的字符串,即html标签
String html = method.getResponseBodyAsString();
//System.out.println(html);
//停止爬取,关闭连接
method.releaseConnection();
//将返回的页面存放在F的doc目录下
FileUtil util = new FileUtil();
String path="F:\\doc\\51job.html";
util.file(path,html);
//Jsoup类解析html,返回一个文档对象
Document doc = Jsoup.parse(html);


//模拟登陆请求
HttpClient httpClient = new HttpClient();
PostMethod method= new PostMethod("http://www.51job.com/");