HttpClient+Jericho HTML Parser 实现网页的抓取

Jericho HTML Parser是一个简单而功能强大的Java HTML解析器库，可以分析和处理HTML文档的一部分，包括一些通用的服务器端标签，同时也可以重新生成无法识别的或无效的HTML。它也提供了一个有用的HTML表单分析器。
  下载地址:http://sourceforge.net/project/showfiles.php?group_id=101067

  HttpClient作为HTTP客户端组件与服务器进行通讯，同时使用了jdom进行XML数据的解析。

    * HttpClient 可以在http://jakarta.apache.org/commons/httpclient/downloads.html下载
    * HttpClient 用到了 Apache Jakarta common 下的子项目 logging，你可以从这个地址http://jakarta.apache.org/site/downloads/downloads_commons-logging.cgi下载到 common logging，从下载后的压缩包中取出 commons-logging.jar 加到 CLASSPATH 中
    * HttpClient 用到了 Apache Jakarta common 下的子项目 codec，你可以从这个地址http://jakarta.apache.org/site/downloads/downloads_commons-codec.cgi 下载到最新的 common codec，从下载后的压缩包中取出 commons-codec-1.x.jar 加到 CLASSPATH 中


在对网页信息进行抓取时,主要会用到GET 方法

使用 HttpClient 需要以下 6 个步骤：

1. 创建 HttpClient 的实例

2. 创建某种连接方法的实例，在这里是 GetMethod。在 GetMethod 的构造函数中传入待连接的地址

3. 调用第一步中创建好的实例的 execute 方法来执行第二步中创建好的 method 实例

4. 读 response

5. 释放连接。无论执行方法是否成功，都必须释放连接

6. 对得到后的内容进行处理
在eclipse下建立工程 -->snatch
将上面下载的四个jar文件导入到项目路径中.
环境搭建完成

现在,首先介绍一下HttpClient的使用
在工程目录下创建test包,在包中创建Httpclient Test类

package test;
import java.io.IOException;
import org.apache.commons.httpclient.*;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.httpclient.params.HttpMethodParams;
public class HttpClientTest...{
  public static void main(String[] args) {
  //构造HttpClient的实例
  HttpClient httpClient = new HttpClient();
  //创建GET方法的实例
  GetMethod getMethod = new GetMethod("http://www.google.com.cn");
  //使用系统提供的默认的恢复策略
  getMethod.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,
    new DefaultHttpMethodRetryHandler());
  try {
   //执行getMethod
   int statusCode = httpClient.executeMethod(getMethod);
   if (statusCode != HttpStatus.SC_OK) {
    System.err.println("Method failed: "
      + getMethod.getStatusLine());
   }
   //读取内容
   byte[] responseBody = getMethod.getResponseBoy();
   //处理内容
   System.out.println(new String(responseBody));
  } catch (HttpException e) {
   //发生致命的异常，可能是协议不对或者返回的内容有问题
   System.out.println("Please check your provided http address!");
   e.printStackTrace();
  } catch (IOException e) {
   //发生网络异常
   e.printStackTrace();
  } finally {
   //释放连接
   getMethod.releaseConnection();
  }
 }
}

package test;
import java.io.IOException;
import org.apache.commons.httpclient.*;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.httpclient.params.HttpMethodParams;
public class HttpClientTest...{
  public static void main(String[] args) {
  //构造HttpClient的实例
  HttpClient httpClient = new HttpClient();
  //创建GET方法的实例
  GetMethod getMethod = new GetMethod("http://www.google.com.cn");
  //使用系统提供的默认的恢复策略
  getMethod.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,
    new DefaultHttpMethodRetryHandler());
  try {
   //执行getMethod
   int statusCode = httpClient.executeMethod(getMethod);
   if (statusCode != HttpStatus.SC_OK) {
    System.err.println("Method failed: "
      + getMethod.getStatusLine());
   }
   //读取内容 
   byte[] responseBody = getMethod.getResponseBoy();
   //处理内容
   System.out.println(new String(responseBody));
  } catch (HttpException e) {
   //发生致命的异常，可能是协议不对或者返回的内容有问题
   System.out.println("Please check your provided http address!");
   e.printStackTrace();
  } catch (IOException e) {
   //发生网络异常
   e.printStackTrace();
  } finally {
   //释放连接
   getMethod.releaseConnection();
  }
 }
}

这样得到的是页面的源代码.
这里 byte[] responseBody = getMethod.getResponseBoy();是读取内容
除此之外,我们还可以这样读取:
InputStream inputStream=   getMethod.getResponseBodyAsStream();
String responseBody = getMethod.getResponseBodyAsString();


下面结合两者给个事例
取出http://www.ahcourt.gov.cn/gb/ahgy_2004/fyxw/index.html
中"信息快递"栏的前几条信息.
新建类CourtNews

package test;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

import org.apache.commons.httpclient.DefaultHttpMethodRetryHandler;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.HttpException;
import org.apache.commons.httpclient.HttpStatus;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.httpclient.params.HttpMethodParams;

import au.id.jericho.lib.html.Element;
import au.id.jericho.lib.html.HTMLElementName;
import au.id.jericho.lib.html.Segment;
import au.id.jericho.lib.html.Source;

/** *//**
 * @author oscar 07-5-17
 *
 */
public class CourtNews {
    private int newsCount = 3;

    private List newsList = new ArrayList();

    public int getNewsCount() {
        return newsCount;
    }

    public void setNewsCount(int newsCount) {
        this.newsCount = newsCount;
    }

    public List getNewsList() {
        HttpClient httpClient = new HttpClient();
        GetMethod getMethod = new GetMethod(
                "http://www.ahcourt.gov.cn/gb/ahgy_2004/fyxw/index.html");
        getMethod.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,
                new DefaultHttpMethodRetryHandler());

        try {
            int statusCode = httpClient.executeMethod(getMethod);
            if (statusCode != HttpStatus.SC_OK) {
                System.err
                        .println("Method failed:" + getMethod.getStatusLine());
            }

            String responseBody = getMethod.getResponseBodyAsString();
            responseBody = new String(responseBody.getBytes("ISO-8859-1"),
                    "GB2312");
            Source source = new Source(responseBody);

            int tableCount = 0;

            for (Iterator i = source.findAllElements(HTMLElementName.TABLE)
                    .iterator(); i.hasNext(); tableCount++) {

                Segment segment = (Segment) i.next();

                if (tableCount == 13) {

                    int hrefCount = 0;
                    for (Iterator j = segment
                            .findAllElements(HTMLElementName.A).iterator(); j
                            .hasNext();) {
                        Segment childsegment = (Segment) j.next();
                        String title = childsegment.extractText();
                        title.replace(" ", " ");
                        title = trimTitle(title);
                        Element childelement = (Element) childsegment;
                        if (hrefCount < newsCount) {

                            String[] news = new String[] {
                                    title,
                                    "http://www.ahcourt.gov.cn"
                                            + childelement
                                                    .getAttributeValue("href") };
                            newsList.add(news);
                            hrefCount++;
                        }
                    }

                }
            }
        } catch (HttpException e) {
            System.out.println("please check your provided http address!");
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            getMethod.releaseConnection();
        }
        return newsList;
    }

    private String trimTitle(String title) {
        String titlenew = "";

        for (int i = 0; i < title.length(); i++) {

            if (Character.isSpaceChar(title.charAt(i)))
                titlenew += " ";
            else {
                titlenew += title.charAt(i);
            }

        }
        return titlenew;
    }
    public static void main(String[] args) {
        // TODO Auto-generated method stub
        CourtNews justice = new CourtNews();
        justice.setNewsCount(4);
        List list = justice.getNewsList();
        Iterator it = list.iterator();
        while (it.hasNext()) {
            String[] news = (String[]) it.next();
            System.out.println(news[0]);
            System.out.println(news[1]);
    }
    }

}