java爬虫--免登录,通过httpclient模拟登录并获取登录后的信息

以新安人才网为例
1、使用依赖
httpclient 进行http请求
jsoup 对html进行解析

 <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.8.1</version>
        </dependency>
        <dependency>
            <groupId>commons-httpclient</groupId>
            <artifactId>commons-httpclient</artifactId>
            <version>3.0.1</version>
        </dependency>

2、具体实现如下

package com.ssjk.website.service.JsoupHtml;

import org.apache.commons.httpclient.Cookie;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.NameValuePair;
import org.apache.commons.httpclient.cookie.CookiePolicy;
import org.apache.commons.httpclient.cookie.CookieSpec;
import org.apache.commons.httpclient.methods.PostMethod;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

import java.io.IOException;

/**
 * 爬取新安人才网信息
 */
public class XinAnRenCaiWang {
    private static final String SITE = "login.goodjobs.cn";
    private static final int PORT = 80;

    private static final String loginAction = "/index.php/action/UserLogin";
    private static final String forwardURL =
            "http://user.goodjobs.cn/dispatcher.php/module/Personal/";
    private static final String toUrl = "d:\\jsoup_test\\";
    private static final String hostCss = "d:\\jsoup_test\\style.txt";
    private static final String Img = "http://user.goodjobs.cn/images";
    private static final String _JS = "http://user.goodjobs.cn/scripts/fValidate/fValidate.one.js";
    /**
     * 模拟等录
     *
     * @param LOGON_SITE
     * @param LOGON_PORT
     * @param login_Action
     * @param params
     * @throws Exception
     */
    private static String[] loginHtml(String LOGON_SITE, int LOGON_PORT, String
            login_Action, String... params) throws Exception {
        String[] result=null;
        HttpClient client = new HttpClient();
        client.getHostConfiguration().setHost(LOGON_SITE, LOGON_PORT);
// 模拟登录页面
        PostMethod post = new PostMethod(login_Action);
        NameValuePair userName = new NameValuePair("memberName", params[0]);
        NameValuePair password = new NameValuePair("password", params[1]);
        post.setRequestBody(new NameValuePair[]{userName, password});
        client.executeMethod(post);
        System.out.println("执行状态:"+client.getState());
        post.releaseConnection();
// 查看 cookie 信息
        CookieSpec cookiespec = CookiePolicy.getDefaultSpec();
        Cookie[] cookies = cookiespec.match(LOGON_SITE, LOGON_PORT, "/", false,
                client.getState().getCookies());
        if (cookies != null)
            if (cookies.length == 0) {
                System.out.println("Cookies is not Exists ");
            } else {
                for (int i = 0; i < cookies.length; i++) {
                    System.out.println("----------------------------------------------------");
                    System.out.println(cookies[i].toString());
                    result = cookies[i].toString().split("=");
                    System.out.println("----------------------------------------------------");
                }
            }

            return result;
    }

    /**
     *
     * @param cookies
     * @return
     */
    public static Document getHtmlDocument(String[] cookies){
        try {
            Document doc = Jsoup.connect(forwardURL).cookie(cookies[0],cookies[1]).get();
            return doc;
        } catch (IOException e) {
            System.out.println("页面获取异常!");
            e.printStackTrace();
        }
        return null;
    }

    public static void main(String[] args) {
        String[] params = {"job17093123661", "2534133662qq"};
        String[] strings = null;
        try {
            strings = loginHtml(SITE, PORT, loginAction, params);
            if(strings.length>0){
                Document htmlDocument = getHtmlDocument(strings);
                System.out.println(htmlDocument);
            }

        } catch (Exception e) {
            e.printStackTrace();
        }

    }
}
Jsoup+httpclient 模拟登陆和抓取页面 package com.app.html; import java.io.BufferedReader; import java.io.BufferedWriter; import java.io.File; import java.io.FileOutputStream; import java.io.FileReader; import java.io.IOException; import java.io.OutputStreamWriter; import java.io.Writer; import java.text.SimpleDateFormat; import java.util.Date; import org.apache.commons.httpclient.Cookie; import org.apache.commons.httpclient.HttpClient; import org.apache.commons.httpclient.NameValuePair; import org.apache.commons.httpclient.cookie.CookiePolicy; import org.apache.commons.httpclient.cookie.CookieSpec; import org.apache.commons.httpclient.methods.PostMethod; import org.apache.commons.httpclient.params.HttpMethodParams; import org.jsoup.Jsoup; import org.jsoup.nodes.Document; import org.jsoup.nodes.Element; import org.jsoup.select.Elements; import com.app.comom.FileUtil; public class HttpClientHtml { private static final String SITE = "login.goodjobs.cn"; private static final int PORT = 80; private static final String loginAction = "/index.php/action/UserLogin"; private static final String forwardURL = "http://user.goodjobs.cn/dispatcher.php/module/Personal/?skip_fill=1"; private static final String toUrl = "d:\\test\\"; private static final String css = "http://user.goodjobs.cn/personal.css"; private static final String Img = "http://user.goodjobs.cn/images"; private static final String _JS = "http://user.goodjobs.cn/scripts/fValidate/fValidate.one.js"; /** * 模拟等录 * @param LOGON_SITE * @param LOGON_PORT * @param login_Action * @param params * @throws Exception */ private static HttpClient loginHtml(String LOGON_SITE, int LOGON_PORT,String login_Action,String ...params) throws Exception { HttpClient client = new HttpClient(); client.getHostConfiguration().setHost(LOGON_SITE, LOGON_PORT); // 模拟登录页面 PostMethod post = new PostMethod(login_Action); NameValuePair userName = new NameValuePair("memberName",params[0] ); NameValuePair password = new NameValuePair("password",params[1] ); post.setRequestBody(new NameValuePair[] { userName, password }); client.executeMethod(post); post.releaseConnection(); // 查看cookie信息 CookieSpec cookiespec = CookiePolicy.getDefaultSpec(); Cookie[] cookies = cookiespec.match(LOGON_SITE, LOGON_PORT, "/", false, client.getState().getCookies()); if (cookies != null) if (cookies.length == 0) { System.out.println("Cookies is not Exists "); } else { for (int i = 0; i < cookies.length; i++) { System.out.println(cookies[i].toString()); } } return client; } /** * 模拟等录 后获取所需要的页面 * @param client * @param newUrl * @throws Exception */ private static String createHtml(HttpClient client, String newUrl) throws Exception { SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd"); String filePath = toUrl + format.format(new Date() )+ "_" + 1 + ".html"; PostMethod post = new PostMethod(newUrl); client.executeMethod(post); //设置编码 post.getParams().setParameter(HttpMethodParams.HTTP_CONTENT_CHARSET, "GBK"); String content= post.getResponseBodyAsString(); FileUtil.write(content, filePath); System.out.println("\n写入文件成功!"); post.releaseConnection(); return filePath; } /** * 解析html代码 * @param filePath * @param random * @return */ private static String JsoupFile(String filePath, int random) { SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd"); File infile = new File(filePath); String url = toUrl + format.format(new Date()) + "_new_" + random+ ".html"; try { File outFile = new File(url); Document doc = Jsoup.parse(infile, "GBK"); String html="<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Transitional//EN'>"; StringBuffer sb = new StringBuffer(); sb.append(html).append("\n"); sb.append("<html>").append("\n"); sb.append("<head>").append("\n"); sb.append("<title>欢迎使用新安人才网个人专区</title>").append("\n"); Elements meta = doc.getElementsByTag("meta"); sb.append(meta.toString()).append("\n"); ////////////////////////////body////////////////////////// Elements body = doc.getElementsByTag("body"); ////////////////////////////link////////////////////////// Elements links = doc.select("link");//对link标签有href的路径都作处理 for (Element link : links) { String hrefAttr = link.attr("href"); if (hrefAttr.contains("/personal.css")) { hrefAttr = hrefAttr.replace("/personal.css",css); Element hrefVal=link.attr("href", hrefAttr);//修改href的属性值 sb.append(hrefVal.toString()).append("\n"); } } ////////////////////////////script////////////////////////// Elements scripts = doc.select("script");//对script标签 for (Element js : scripts) { String jsrc = js.attr("src"); if (jsrc.contains("/fValidate.one.js")) { String oldJS="/scripts/fValidate/fValidate.one.js";//之前的css jsrc = jsrc.replace(oldJS,_JS); Element val=js.attr("src", jsrc);//修改href的属性值 sb.append(val.toString()).append("\n").append("</head>"); } } ////////////////////////////script////////////////////////// Elements tags = body.select("*");//对所有标签有src的路径都作处理 for (Element tag : tags) { String src = tag.attr("src"); if (src.contains("/images")) { src = src.replace("/images",Img); tag.attr("src", src);//修改src的属性值 } } sb.append(body.toString()); sb.append("</html>"); BufferedReader in = new BufferedReader(new FileReader(infile)); Writer out = new BufferedWriter(new OutputStreamWriter( new FileOutputStream(outFile), "gbk")); String content = sb.toString(); out.write(content); in.close(); System.out.println("页面已经爬完"); out.close(); } catch (IOException e) { e.printStackTrace(); } return url; } public static void main(String[] args) throws Exception { String [] params={"admin","admin123"}; HttpClient client = loginHtml(SITE, PORT, loginAction,params); // 访问所需的页面 String path=createHtml(client, forwardURL); System.out.println( JsoupFile(path,1)); } }
评论 3
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