您的位置:首页 > 理论基础 > 计算机网络

编写爬虫(spider)的预备知识:用java发送HTTP请求

2015-11-02 00:10 561 查看
  使用原生API来发送http请求,而不是使用apache的库,原因在于这个第三方库变化实在太快了,每个版本都有不小的变化。对于程序员来说,使用它反而会有很多麻烦,比如自己曾经写过的代码将无法复用。

原理简介

使用Java发送这两种请求的代码大同小异,只是一些参数设置的不同。步骤如下:
1.生成统一资源定位器(java.net.URL),并据此生成一个连接(java.net.URLConnection)
2.设置请求的参数
3.发送请求(get和post有区别)
4.以输入流的形式获取返回内容
5.关闭输入流

抓取百度网页

上代码:

package test;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.PrintWriter;
import java.net.URL;
import java.net.URLConnection;
import java.util.List;
import java.util.Map;

public class HttpRequest {
/**
* 向指定URL发送GET方法的请求
*
* @param url
*            发送请求的URL
* @param param
*            请求参数,请求参数应该是 name1=value1&name2=value2 的形式。
* @return URL 所代表远程资源的响应结果
*/
public static String sendGet(String url, String param) {
String result = "";
BufferedReader in = null;
try {
String urlNameString = url + "?" + param;
URL realUrl = new URL(urlNameString);
// 打开和URL之间的连接
URLConnection connection = realUrl.openConnection();
// 设置通用的请求属性
connection.setRequestProperty("accept", "*/*");
connection.setRequestProperty("connection", "Keep-Alive");
connection.setRequestProperty("user-agent",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
// 建立实际的连接
connection.connect();
// 获取所有响应头字段
Map<String, List<String>> map = connection.getHeaderFields();
// 遍历所有的响应头字段
for (String key : map.keySet()) {
System.out.println(key + "--->" + map.get(key));
}
// 定义 BufferedReader输入流来读取URL的响应
in = new BufferedReader(new InputStreamReader(
connection.getInputStream()));
String line;
while ((line = in.readLine()) != null) {
result += line;
System.out.println("@2" + line);
}
} catch (Exception e) {
System.out.println("发送GET请求出现异常!" + e);
e.printStackTrace();
}
// 使用finally块来关闭输入流
finally {
try {
if (in != null) {
in.close();
}
} catch (Exception e2) {
e2.printStackTrace();
}
}
return result;
}

/**
* 向指定 URL 发送POST方法的请求
*
* @param url
*            发送请求的 URL
* @param param
*            请求参数,请求参数应该是 name1=value1&name2=value2 的形式。
* @return 所代表远程资源的响应结果
*/
public static String sendPost(String url, String param) {
PrintWriter out = null;
BufferedReader in = null;
String result = "";
try {
URL realUrl = new URL(url);
// 打开和URL之间的连接
URLConnection conn = realUrl.openConnection();
// 设置通用的请求属性
conn.setRequestProperty("accept", "*/*");
conn.setRequestProperty("connection", "Keep-Alive");
conn.setRequestProperty("user-agent",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
// 发送POST请求必须设置如下两行
conn.setDoOutput(true);
conn.setDoInput(true);
// 获取URLConnection对象对应的输出流
out = new PrintWriter(conn.getOutputStream());
// 发送请求参数
out.print(param);
// flush输出流的缓冲
out.flush();
// 定义BufferedReader输入流来读取URL的响应
in = new BufferedReader(
new InputStreamReader(conn.getInputStream()));
String line;
while ((line = in.readLine()) != null) {
result += line;
}
} catch (Exception e) {
System.out.println("发送 POST 请求出现异常!"+e);
e.printStackTrace();
}
//使用finally块来关闭输出流、输入流
finally{
try{
if(out!=null){
out.close();
}
if(in!=null){
in.close();
}
}
catch(IOException ex){
ex.printStackTrace();
}
}
return result;
}

public static void main(String[] args) {
//发送 GET 请求
//String s=HttpRequest.sendGet("https://www.baidu.com", "key=123&v=456");
String s=HttpRequest.sendPost("https://www.baidu.com", "");
System.out.println("@1" + s);

//发送 POST 请求
//String sr=HttpRequest.sendPost("https://www.baidu.com", "key=123&v=456");
//System.out.println(sr);
}
}


  两种方法在控制台中的输出是不同的,用post请求才能得到整个html。原因是,如果用get方法发送请求,会被服务器要求重定向到http协议的url:

  <noscript><meta http-equiv="refresh" content="0;url=http://www.baidu.com/"></noscript>

tip:

httpUrlConnection.setDoOutput(true);以后就可以使用conn.getOutputStream().write()
httpUrlConnection.setDoInput(true);以后就可以使用conn.getInputStream().read();

get请求用不到conn.getOutputStream(),因为参数直接追加在地址后面,因此默认是false。
post请求(比如:文件上传)需要往服务区传输大量的数据,这些数据是放在http的body里面的,因此需要在建立连接以后,往服务端写数据。

因为总是使用conn.getInputStream()获取服务端的响应,因此默认值是true。

下面分别详细介绍。

使用Get方法:

package test;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.net.HttpURLConnection;
import java.net.InetSocketAddress;
import java.net.Proxy;
import java.net.URL;
import java.net.URLConnection;
import java.util.Iterator;
import java.util.Map;

public class HttpRequestor {

private String charset = "utf-8";
private Integer connectTimeout = null;
private Integer socketTimeout = null;
private String proxyHost = null;
private Integer proxyPort = null;

/**
* Do GET request
* @param url
* @return
* @throws Exception
* @throws IOException
*/
public String doGet(String url) throws Exception {

URL localURL = new URL(url);

URLConnection connection = openConnection(localURL);
HttpURLConnection httpURLConnection = (HttpURLConnection)connection;

httpURLConnection.setRequestProperty("Accept-Charset", charset);
httpURLConnection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");

InputStream inputStream = null;
InputStreamReader inputStreamReader = null;
BufferedReader reader = null;
StringBuffer resultBuffer = new StringBuffer();
String tempLine = null;

if (httpURLConnection.getResponseCode() >= 300) {
throw new Exception("HTTP Request is not success, Response code is " + httpURLConnection.getResponseCode());
}

try {
inputStream = httpURLConnection.getInputStream();
inputStreamReader = new InputStreamReader(inputStream);
reader = new BufferedReader(inputStreamReader);

while ((tempLine = reader.readLine()) != null) {
resultBuffer.append(tempLine);
}

} finally {

if (reader != null) {
reader.close();
}

if (inputStreamReader != null) {
inputStreamReader.close();
}

if (inputStream != null) {
inputStream.close();
}

}

return resultBuffer.toString();
}

/**
* Do POST request
* @param url
* @param parameterMap
* @return
* @throws Exception
*/
public String doPost(String url, Map parameterMap) throws Exception {

/* Translate parameter map to parameter date string */
StringBuffer parameterBuffer = new StringBuffer();
if (parameterMap != null) {
Iterator iterator = parameterMap.keySet().iterator();
String key = null;
String value = null;
while (iterator.hasNext()) {
key = (String)iterator.next();
if (parameterMap.get(key) != null) {
value = (String)parameterMap.get(key);
} else {
value = "";
}

parameterBuffer.append(key).append("=").append(value);
if (iterator.hasNext()) {
parameterBuffer.append("&");
}
}
}

System.out.println("POST parameter : " + parameterBuffer.toString());

URL localURL = new URL(url);

URLConnection connection = openConnection(localURL);
HttpURLConnection httpURLConnection = (HttpURLConnection)connection;

httpURLConnection.setDoOutput(true);
httpURLConnection.setRequestMethod("POST");
httpURLConnection.setRequestProperty("Accept-Charset", charset);
httpURLConnection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
httpURLConnection.setRequestProperty("Content-Length", String.valueOf(parameterBuffer.length()));

OutputStream outputStream = null;
OutputStreamWriter outputStreamWriter = null;
InputStream inputStream = null;
InputStreamReader inputStreamReader = null;
BufferedReader reader = null;
StringBuffer resultBuffer = new StringBuffer();
String tempLine = null;

try {
outputStream = httpURLConnection.getOutputStream();
outputStreamWriter = new OutputStreamWriter(outputStream);

outputStreamWriter.write(parameterBuffer.toString());
outputStreamWriter.flush();

if (httpURLConnection.getResponseCode() >= 300) {
throw new Exception("HTTP Request is not success, Response code is " + httpURLConnection.getResponseCode());
}

inputStream = httpURLConnection.getInputStream();
inputStreamReader = new InputStreamReader(inputStream);
reader = new BufferedReader(inputStreamReader);

while ((tempLine = reader.readLine()) != null) {
resultBuffer.append(tempLine);
}

} finally {

if (outputStreamWriter != null) {
outputStreamWriter.close();
}

if (outputStream != null) {
outputStream.close();
}

if (reader != null) {
reader.close();
}

if (inputStreamReader != null) {
inputStreamReader.close();
}

if (inputStream != null) {
inputStream.close();
}

}

return resultBuffer.toString();
}

private URLConnection openConnection(URL localURL) throws IOException {
URLConnection connection;
if (proxyHost != null && proxyPort != null) {
Proxy proxy = new Proxy(Proxy.Type.HTTP, new InetSocketAddress(proxyHost, proxyPort));
connection = localURL.openConnection(proxy);
} else {
connection = localURL.openConnection();
}
return connection;
}

/**
* Render request according setting
* @param request
*/
private void renderRequest(URLConnection connection) {

if (connectTimeout != null) {
connection.setConnectTimeout(connectTimeout);
}

if (socketTimeout != null) {
connection.setReadTimeout(socketTimeout);
}

}

/*
* Getter & Setter
*/
public Integer getConnectTimeout() {
return connectTimeout;
}

public void setConnectTimeout(Integer connectTimeout) {
this.connectTimeout = connectTimeout;
}

public Integer getSocketTimeout() {
return socketTimeout;
}

public void setSocketTimeout(Integer socketTimeout) {
this.socketTimeout = socketTimeout;
}

public String getProxyHost() {
return proxyHost;
}

public void setProxyHost(String proxyHost) {
this.proxyHost = proxyHost;
}

public Integer getProxyPort() {
return proxyPort;
}

public void setProxyPort(Integer proxyPort) {
this.proxyPort = proxyPort;
}

public String getCharset() {
return charset;
}

public void setCharset(String charset) {
this.charset = charset;
}

}

HttpRequestor


View Code

HttpRequestor的测试代码

客户端代码:

package test;

import java.util.HashMap;
import java.util.Map;

public class Call {

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

/* Post Request */
Map dataMap = new HashMap();
dataMap.put("username", "Nick Huang");
dataMap.put("blog", "IT");
System.out.println(new HttpRequestor().doPost("http://localhost:8080/OneHttpServer/", dataMap));

/* Get Request */
System.out.println(new HttpRequestor().doGet("http://localhost:8080/OneHttpServer/"));
}

}

Call


服务端代码:

import java.io.IOException;
import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

public class LoginServlet extends HttpServlet {
private static final long serialVersionUID = 1L;

public LoginServlet() {
super();
}

protected void doGet(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
this.doPost(request, response);
}

protected void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
String username = request.getParameter("username");
String blog = request.getParameter("blog");

System.out.println(username);
System.out.println(blog);

response.setContentType("text/plain; charset=UTF-8");
response.setCharacterEncoding("UTF-8");
response.getWriter().write("It is ok!");
}

}

LoginServlet


web.xml

<?xml version="1.0" encoding="UTF-8"?>
<web-app xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://java.sun.com/xml/ns/javaee" xmlns:web="http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd" xsi:schemaLocation="http://java.sun.com/xml/ns/javaee http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd" id="WebApp_ID" version="2.5">
<display-name>OneHttpServer</display-name>
<welcome-file-list>
<welcome-file>LoginServlet</welcome-file>
</welcome-file-list>

<servlet>
<description></description>
<display-name>LoginServlet</display-name>
<servlet-name>LoginServlet</servlet-name>
<servlet-class>LoginServlet</servlet-class>
</servlet>
<servlet-mapping>
<servlet-name>LoginServlet</servlet-name>
<url-pattern>/LoginServlet</url-pattern>
</servlet-mapping>

</web-app>

web.xml
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: