HttpClient抓取网页内容简单介绍

下面说的都是HttpClient3.1版本的时候，然后再说HttpClient 4 版本

1、GET方式

第一步、创建一个客户端，类似于你用浏览器打开一个网页

HttpClient httpClient = new HttpClient();

第二步、创建一个GET方法，用来获取到你需要抓取的网页URL

GetMethod getMethod = new GetMethod("http://www.baidu.com");

第三步、获得网址的响应状态码，200表示请求成功

int statusCode = httpClient.executeMethod(getMethod);

第四步、获取网页的源码

byte[] responseBody = getMethod.getResponseBody();

主要就这四步，当然还有其他很多东西，比如网页编码的问题

 HttpClient httpClient = new HttpClient();
        GetMethod getMethod = new GetMethod("http://www.baidu.com/");
        try {
            int statusCode = httpClient.executeMethod(getMethod);
            if (statusCode != HttpStatus.SC_OK) {
                System.err.println("Method failed: "
                        + getMethod.getStatusLine());
            }
            // 读取内容
            byte[] responseBody = getMethod.getResponseBody();
            // 处理内容
　　　　　　String html = new String(responseBody);
　　　　　　System.out.println(html);　
        } catch (Exception e) {
            System.err.println("页面无法访问");
        }finally{
			getMethod.releaseConnection();
		}

2、Post方式

 HttpClient httpClient = new HttpClient();
        PostMethod postMethod = new PostMethod(UrlPath);
        postMethod.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,new DefaultHttpMethodRetryHandler());
        NameValuePair[] postData = new NameValuePair[2];
        postData[0] = new NameValuePair("username", "xkey");
        postData[1] = new NameValuePair("userpass", "********");
        postMethod.setRequestBody(postData);
        try {
            int statusCode = httpClient.executeMethod(postMethod);
            if (statusCode == HttpStatus.SC_OK) {
                byte[] responseBody = postMethod.getResponseBody();
                String html = new String(responseBody);
                System.out.println(html);
            }
        } catch (Exception e) {
            System.err.println("页面无法访问");
        }finally{
			postMethod.releaseConnection();
		}

这个例子传递了两个Post参数：username为xkey，userpass为********，传递给网址UrlPath

如果需要了解获取gzip网页的信息可以参考http://www.cnblogs.com/modou/articles/1325569.html

另外就是获取非字符数据，这样可以使用下面的方法

 HttpClient httpClient = new HttpClient();
        GetMethod getMethod = new GetMethod("http://www.baidu.com");
        try {
            InputStream inputStream = getMethod.getResponseBodyAsStream();
            // 这里处理 inputStream
        } catch (Exception e) {
            System.err.println("页面无法访问");
        }finally{
			getMethod.releaseConnection();
		}

HttpClient4.0（摘录）

class HttpClientTest {

public final static void main(String[] args) throws Exception {

       // 初始化，此处构造函数就与3.1中不同
       HttpClient httpclient = new DefaultHttpClient();

       HttpHost targetHost = new HttpHost("www.google.cn");
       HttpGet httpget = new HttpGet("/");

       // 查看默认request头部信息
       System.out.println("Accept-Charset:" + httpget.getFirstHeader("Accept-Charset"));
       // 以下这条如果不加会发现无论你设置Accept-Charset为gbk还是utf-8，他都会默认返回gb2312（本例针对google.cn来说）
       httpget.setHeader("User-Agent", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.2)");
       // 用逗号分隔显示可以同时接受多种编码
       httpget.setHeader("Accept-Language", "zh-cn,zh;q=0.5");
       httpget.setHeader("Accept-Charset", "GB2312,utf-8;q=0.7,*;q=0.7");
       // 验证头部信息设置生效
       System.out.println("Accept-Charset:" + httpget.getFirstHeader("Accept-Charset").getValue());

       // Execute HTTP request
       System.out.println("executing request " + httpget.getURI());
      
	  HttpResponse response = httpclient.execute(targetHost, httpget);
       //HttpResponse response = httpclient.execute(httpget);

       System.out.println("----------------------------------------");
       System.out.println("Location: " + response.getLastHeader("Location"));
       System.out.println(response.getStatusLine().getStatusCode());
       System.out.println(response.getLastHeader("Content-Type"));
       System.out.println(response.getLastHeader("Content-Length"));
      
       System.out.println("----------------------------------------");

       // 判断页面返回状态判断是否进行转向抓取新链接
       int statusCode = response.getStatusLine().getStatusCode();
       if ((statusCode == HttpStatus.SC_MOVED_PERMANENTLY) ||
            (statusCode == HttpStatus.SC_MOVED_TEMPORARILY) ||
            (statusCode == HttpStatus.SC_SEE_OTHER) ||
            (statusCode == HttpStatus.SC_TEMPORARY_REDIRECT)) {
         // 此处重定向处理   此处还未验证
         String newUri = response.getLastHeader("Location").getValue();
         httpclient = new DefaultHttpClient();
         httpget = new HttpGet(newUri);
         response = httpclient.execute(httpget);
       }

       // Get hold of the response entity
       HttpEntity entity = response.getEntity();
      
       // 查看所有返回头部信息
       Header headers[] = response.getAllHeaders();
       int ii = 0;
       while (ii < headers.length) {
         System.out.println(headers[ii].getName() + ": " + headers[ii].getValue());
         ++ii;
       }
      
       // If the response does not enclose an entity, there is no need
       // to bother about connection release
       if (entity != null) {
         // 将源码流保存在一个byte数组当中，因为可能需要两次用到该流，
          byte[] bytes = EntityUtils.toByteArray(entity);
         String charSet = "";
         
         // 如果头部Content-Type中包含了编码信息，那么我们可以直接在此处获取
          charSet = EntityUtils.getContentCharSet(entity);

         System.out.println("In header: " + charSet);
         // 如果头部中没有，那么我们需要 查看页面源码，这个方法虽然不能说完全正确，因为有些粗糙的网页编码者没有在页面中写头部编码信息
         if (charSet == "") {
            regEx="(?=<meta).*?(?<=charset=[\\'|\\\"]?)([[a-z]|[A-Z]|[0-9]|-]*)";
            p=Pattern.compile(regEx, Pattern.CASE_INSENSITIVE);
            m=p.matcher(new String(bytes));   // 默认编码转成字符串，因为我们的匹配中无中文，所以串中可能的乱码对我们没有影响
            result=m.find();
            if (m.groupCount() == 1) {
                   charSet = m.group(1);
            } else {
                   charSet = "";
            }
         }
         System.out.println("Last get: " + charSet);
         // 至此，我们可以将原byte数组按照正常编码专成字符串输出（如果找到了编码的话）
         System.out.println("Encoding string is: " + new String(bytes, charSet));
       }

       httpclient.getConnectionManager().shutdown();       
}

}