通过apache.commons.httpclient完成的简单的爬虫工作

package test.app;


import org.apache.commons.httpclient.Cookie;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.HttpMethod;
import org.apache.commons.httpclient.NameValuePair;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.httpclient.methods.PostMethod;
import org.apache.commons.httpclient.params.HttpClientParams;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;


public class WebCrawler {


public static void main(String[] args) {


new WebCrawler().crawlerPost("**********");
}


// 爬网页sUrl
public void crawler(String sUrl) {


HttpClientParams params = new HttpClientParams();
params.setParameter("account", "leo.li");
params.setParameter("password", "****");


HttpClient httpClient = new HttpClient(params);
// httpClient.getHostConfiguration().setProxy("", 0);


HttpMethod method = new GetMethod(sUrl);


method.setRequestHeader("cookie",
"lang=zh-cn; theme=default; lastProject=13; preProjectID=13; moduleBrowseParam=0; productBrowseParam=0; projectTaskOrder=status%2Cid_desc; preProductID=8; preBranch=0; bugModule=0; lastProduct=8; qaBugOrder=idow; windowHeight=925; windowWidth=1026; zentaosid=iss55g3k0do2bdgd9piin2g0p0");


try {
httpClient.executeMethod(method);
System.out.println(method.getStatusLine());
String html = method.getResponseBodyAsString();
method.releaseConnection();


this.parseContext(html);
} catch (Exception e) {
// TODO: handle exception
}


}


// 爬网页sUrl
public void crawlerPost(String sUrl) {


// 设置登陆时要求的信息,用户名和密码
        NameValuePair[] data = { new NameValuePair("account", "leo.li"), new NameValuePair("password", "*****") };


HttpClient httpClient = new HttpClient();
// httpClient.getHostConfiguration().setProxy("", 0);


// HttpMethod method = new PostMethod(sUrl);
PostMethod method = new PostMethod(sUrl);

method.setRequestBody(data);


// method.setRequestHeader("cookie",
// "lang=zh-cn; theme=default; lastProject=13; preProjectID=13; moduleBrowseParam=0; productBrowseParam=0; projectow; windowHeight=925; windowWidth=1026; zentaosid=iss55g3k0do2bdgd9piin2g0p0");


try {
httpClient.executeMethod(method);
System.out.println(method.getStatusLine());




// 获得登陆后的 Cookie
            Cookie[] cookies = httpClient.getState().getCookies();
            StringBuffer tmpcookies = new StringBuffer();
            for (Cookie c : cookies) {
                tmpcookies.append(c.toString() + ";");
                System.out.println("cookies = "+c.toString());
            }
            System.out.println(tmpcookies.toString());

String html = method.getResponseBodyAsString();
method.releaseConnection();


this.parseContext(html);
} catch (Exception e) {
// TODO: handle exception
}


}


// 从context提取url地址
public void parseContext(String context) {
Document document = Jsoup.parse(context);


System.out.println(document.select("a"));


}
}
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值