response = httpclient.execute(httpost); //执行
entity = response.getEntity(); //返回服务器响应
try{
System.out.println("----------------------------------------");
System.out.println(response.getStatusLine()); //服务器返回状态
Header[] headers = response.getAllHeaders(); //返回的HTTP头信息
for (int i=0; i<headers.length; i++) {
System.out.println(headers[i]);
}
System.out.println("----------------------------------------");
String responseString = null;
if (response.getEntity() != null) {
responseString = EntityUtils.toString(response.getEntity()); / /返回服务器响应的HTML代码
System.out.println(responseString); //打印出服务器响应的HTML代码
}
} finally {
if (entity != null)
entity.consumeContent(); // release connection gracefully
}
System.out.println("Login form get: " + response.getStatusLine());
if (entity != null) {
entity.consumeContent();
}
}
}
HttpClient4.0 学习实例 - 页面获取
HttpClient 4.0出来不久,所以网络上面相关的实例教程不多,搜httpclient得到的大部分都是基于原 Commons HttpClient 3.1 (legacy) 包的,官网下载页面:,如果大家看了官网说明就明白httpclient4.0是从原包分支出来独立成包的,以后原来那个包中的httpclient不会再升级,所以以后我们是用httpclient新分支,由于4.0与之前的3.1包结构以及接口等都有较大变化,所以网上搜到的实例大部分都是不适合4.0的,当然,我们可以通过那些实例去琢磨4.0的用法,我也是新手,记录下学习过程方便以后检索
本实例我们来获取抓取网页编码,内容等信息
默认情况下,服务器端会根据客户端的请求头信息来返回服务器支持的编码,像google.cn他本身支持utf-8,gb2312等编码,所以如果你在头部中不指定任何头部信息的话他默认会返回gb2312编码,而如果我们在浏览器中直接访问google.cn,通过httplook,或者firefox 的firebug插件查看返回头部信息的话会发现他返回的是UTF-8编码
下面我们还是看实例来解说吧,注释等我也放代码里面解释,放完整代码,方便新手理解
本实例将
使用的httpclient相关包
httpclient-4.0.jar
httpcore-4.0.1.jar
httpmime-4.0.jar
commons-logging-1.0.4.jar等其它相关包
// HttpClientTest.java
package com.baihuo.crawler.test;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.http.Header;
import org.apache.http.HttpEntity;
import org.apache.http.HttpHost;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;
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("http://www.apache.org/");
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();