HttpClient的简略封装,静态调用,自动识别网页字符集,伪装火狐/IE浏览器
HttpClient的简单封装,静态调用,自动识别网页字符集,伪装火狐/IE浏览器
HttpClient是一个非常好用的java开源项目,其作用是对用java程序对网站发起Http请求。
下面是鲁炬对HttpClient进行的简单封装,主要优点是,静态调用,自动识别网页字符集,伪装火狐/IE浏览器。
为什么不使用单例。以前是用单例模式,只创建一个HttpClient示例,后来发现用单例在并发情况下会出现bug,所以改为了每次调用都新建一个。
import java.io.IOException; import org.apache.commons.httpclient.HttpClient; import org.apache.commons.httpclient.HttpException; import org.apache.commons.httpclient.HttpMethod; import org.apache.commons.httpclient.methods.GetMethod; import org.apache.commons.lang.StringUtils; /** * @author 鲁炬 * */ public class HttpClientUtil { public static HttpClient getClient() { HttpClient client = new HttpClient(); return client; } public static String getHtml(String url) throws HttpException, IOException { return getHtml(url, 80, null, null, 0, null); } public static String getHtml(String url, String cookie) throws HttpException, IOException { return getHtml(url, 80, null, null, 0, cookie); } public static String getHtml(String url, int port, String cookie) throws HttpException, IOException { return getHtml(url, port, null, null, 0, cookie); } public static String getHtml(String url, int port, String encoding, String proxyHost, int proxyPort, String cookie) throws HttpException, IOException { HttpClient httpClient = getClient(); String rest = null; if(proxyHost != null && proxyPort != 0) httpClient.getHostConfiguration().setProxy(proxyHost, proxyPort); HttpMethod method = new GetMethod(url); if(!StringUtils.isBlank(cookie)) { method.addRequestHeader("Cookie", cookie); } method.addRequestHeader("User-Agent", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 2.0.50727"); //Mozilla/5.0 (Windows NT 6.1; rv:7.0.1) Gecko/20100101 Firefox/7.0.1 httpClient.executeMethod(method); //根据http头解析正确的字符集 String header = method.getResponseHeader("Content-Type").getValue(); if(header.contains("charset=")) { encoding = header.substring(header.indexOf("charset=") + "charset=".length(), header.length()); } if(encoding == null) encoding = "GBK"; rest = new String(method.getResponseBody(), encoding); method.releaseConnection(); return rest; } public static void main(String[] args) throws HttpException, IOException { String url = "http://www.ccb.com"; System.out.println(getHtml(url)); } }