HttpUtil-优快云博客

本文介绍了一个实用的HTTP工具类，该工具类提供了多种方法来发送HTTP请求（包括GET和POST），处理URL连接，并从响应中提取有用信息如Cookies等。此外，还提供了字符串拼接、HTML过滤等功能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import org.apache.commons.lang.StringUtils;
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLConnection;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class HttpUtils {
public static URLConnection getUrlConnection(String url) throws IOException {
URL obj = new URL(url);
URLConnection conn = obj.openConnection();
String host = getHostByUrl(url);
conn.setRequestProperty("Host", host);
conn.setRequestProperty("Referer", "http://" + host);
return conn;
}

public static URLConnection getUrlConnection(String url, String encode, String cookie)
throws IOException {
URL obj = new URL(url);
URLConnection conn = obj.openConnection();
setProperty(encode, conn, cookie);
String host = getHostByUrl(url);
conn.setRequestProperty("Host", host);
conn.setRequestProperty("Referer", "http://" + host);
return conn;
}

public static Map<String, List<String>> getHeaderFields(String url) throws IOException {
URLConnection conn = getUrlConnection(url);
Map<String, List<String>> map = conn.getHeaderFields();
return map;
}

public static String getCookieByHeaders(Map<String, List<String>> headers) {
String mcookie = "";
List<String> server = headers.get("Set-Cookie");
if (server == null) {
System.err.println("Key 'Cookie' is not found!");
} else {
StringBuilder sb = new StringBuilder();
for (String values : server) {
sb.append(values);
}
mcookie = sb.toString();
}
return mcookie;
}

public static String streamToString(InputStream inStream) throws IOException {
BufferedReader in = new BufferedReader(new InputStreamReader(inStream));
String line;
StringBuilder sb = new StringBuilder();
while ((line = in.readLine()) != null) {
sb.append(line);
}
String result = sb.toString();
in.close();
return result;
}

/**
* 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。
* @param encoding 使用编码.
* @return URL 所代表远程资源的响应结果
*/
public static String sendGet(String url, String param, String encoding) {
return sendGet(url, param, encoding, "");
}

public static String sendGet(String url, String param, String encoding, String cookie) {
String result = "";
BufferedReader in = null;
try {
String urlNameString = concatUrl(url, param);
// System.err.println("urlNameString-------------");
// System.err.println(urlNameString);

URL realUrl = new URL(urlNameString);
HttpURLConnection conn = (HttpURLConnection) realUrl.openConnection();
setProperty(encoding, conn, cookie);
String host = getHostByUrl(url);
conn.setRequestProperty("Host", host);
conn.setRequestProperty("Referer", "http://" + host);
conn.setRequestMethod("GET");
conn.connect();
result = streamToString(conn.getInputStream());
} catch (Exception e) {
e.printStackTrace();
System.err.println("Send GET http request exception！" + e.getMessage());
} finally {
try {
if (in != null) {
in.close();
}
} catch (Exception e2) {
System.err.println(e2.getMessage());
}
}
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。
* @param encoding 使用编码.
* @return URL 所代表远程资源的响应结果
*/
public static String sendPost(String url, String param, String encoding) throws IOException {
return sendPost(url, param, encoding, "");
}

public static String sendPost(String url, String param, String encoding, String cookie)
throws IOException {
PrintWriter out = null;
BufferedReader in = null;
String result = "";
if (StringUtils.isEmpty(url)) {
throw new IOException("The request url is not allow empty or null!");
}
try {
URL realUrl = new URL(url);
HttpURLConnection conn = (HttpURLConnection) realUrl.openConnection();
setProperty(encoding, conn, cookie);
String host = getHostByUrl(url);
conn.setRequestProperty("Host", host);
conn.setRequestProperty("Referer", "http://" + host);
conn.setRequestMethod("POST");
conn.setDoOutput(true);
conn.setDoInput(true);
out = new PrintWriter(new OutputStreamWriter(conn.getOutputStream(), encoding));
out.print(param);
out.flush();
result = streamToString(conn.getInputStream());
} catch (Exception e) {
System.err.println("Send http post method exception！" + e);
throw new IOException(e);
} finally {
try {
if (out != null) {
out.close();
}
if (in != null) {
in.close();
}
} catch (IOException ex) {
throw ex;
}
}
return result;
}

private static String getHostByUrl(String url) {
int index = url.indexOf(":");
String temp = url.substring(index + 3);
int end = temp.indexOf("/");
if (end <= 0) {
end = temp.length();
}
String host = temp.substring(0, end);
System.out.println("host---------->" + host);
return host;
}

private static void setProperty(String encoding, URLConnection conn, String cookie) {
conn.setRequestProperty("Accept-Charset", encoding);
conn.setRequestProperty(
"Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8");
conn.setRequestProperty("Connection", "keep-alive");
// conn.setRequestProperty("Content-Type",
// "application/x-www-form-urlencoded");
// "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:43.0) Gecko/20100101
// Firefox/43.0"
// Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.2)
// Gecko/20090729 Firefox/3.5.2
// conn.setRequestProperty("user-agent", "Mozilla/5.0 (Windows; U;
// Windows NT 5.1; zh-CN; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2");
conn.setRequestProperty("user-agent", "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 5.1;SV1)");
if (StringUtils.isNotBlank(cookie)) {
conn.setRequestProperty("Cookie", cookie);
}
// conn.setRequestProperty("Access-Control-Allow-Origin", "*");
}

/**
* 向指定URL发送GET方法的请求，默认编码：gb2312
*
* @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) {
return sendGet(url, param, "gb2312");
}

/**
* 向指定 URL 发送POST方法的请求,默认编码：gb2312
*
* @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) throws IOException {
return sendPost(url, param, "gb2312");
}

/**
* Format money to fen unit as 12 bit,if not enough pending left by 0.
*
* @param input the money input source
* @return
*/
public static String toFenAndPending(float input) {
int money = (int) (input * 100);
String ret = String.valueOf(money);
if (ret.length() < 12) {
while (12 > ret.length()) {
ret = "0" + ret;
}
}
return ret;
}

public static String filterHtml(String input, String pattern) {
Matcher m = Pattern.compile(pattern, 2 | Pattern.DOTALL).matcher(input);
int i = m.groupCount();
while (m.find()) {
return m.group(i);
}
return input;
}

public static String getFormTagHtml(String result) {
return HttpUtils.filterHtml(result, "<form [\\s\\S]*</form>");
}

/**
* Filter HTML with pattern for specific given input tag(name="key").
*
* @param input the source of HTML.
* @param key the input name.
* @return the given name input of value.
*/
public static String getHtmlInput(String input, String key) {
String pattern = "<input\\s*(?=[^>]*name=\"" + key + "\")(?=[^>]*value=\"([^\"]+)\")[^>]+>";
Matcher m = Pattern.compile(pattern, 2 | Pattern.DOTALL).matcher(input);
int i = m.groupCount();
while (m.find()) {
return m.group(i);
}
return input;
}

// "<a[^>]*>(.*?)</a>"
// String pattern= "href=\"([^\"]*)\"";
public static String filterAhref(String input) {
Pattern pattern = Pattern.compile("<a\\s*href=\"([^<>\"]*)\"[^<>]*>", 2 | Pattern.DOTALL);
Matcher m = pattern.matcher(input);
if (m.find()) {
return m.group(1);
}
return input;
}

public static String concatUrl(String url, String param) {
if (StringUtils.isNotBlank(param)) {
if (url.indexOf("?") > -1) {
url += "&" + param;
} else {
url += "?" + param;
}
}
return url;
}

public static String getRequestParam(Map<String, Object> maps) {
StringBuilder sb = new StringBuilder();
if (maps != null && maps.size() > 0) {
Iterator<Map.Entry<String, Object>> entries = maps.entrySet().iterator();
while (entries.hasNext()) {
Map.Entry<String, Object> entry = entries.next();
sb.append(entry.getKey());
sb.append("=");
sb.append(entry.getValue());
sb.append("&");
}
return sb.substring(0, sb.length() - 1);
}
return null;
}

/*
* public static void main(String[] args) { String str =
* " <div style=\"height:500px;\"><div class=\"list\"> <ul> " +
* "" +
* "<li class=\"font16\"><a href=\"/ECPS_HB/businessPublicity.jspx?id=1E14F35079882995E1A21BDC5EB022F0\">武汉闻广资讯有限公司</a></li>"
* +
* " <li class=\"font14\">注册号/统一社会信用代码：<span>420103000168755</span>   法定代表人:"
* +
* "<span>狄刚</span>   登记机关:<span>武汉市工商行政管理局江汉分局</span>  成立日期:<span>2011年8月5日</span></li></ul> </div> </div>"
* ;
*
* // Matcher m = //
* Pattern.compile("<div.+?class=.*?list.+?>(.*)</div>").matcher(str); //
* <div.+?class=.*?list.+?>(.*)</div> // <div.+?class=.*?list.+?>(.*)</div>
* // while (m.find()) { // String temp = m.group(m.groupCount()); //
* System.out.println(temp); // String result = HttpUtil.filterAhref(temp);
* // System.out.println(result); // // } String result =
* HttpUtil.filterHtml(str,
* "<div\\s*style=\"height:500px;\">\\s*<div.+?class=.*?list.+?>(.*)</div>")
* ; System.out.println(result); }
*/

/* public static void main(String[] args) {
String url = "http://www.qichacha.com/search?key=%E7%80%9A%E6%99%96&index=0";

// http://www.qichacha.com/firm_GD_2bf17e4f0cd4bc67706d3471faa8b1aa.shtml#touzi
// url ="http://www.qixin.com";
String result;
try {
String url1 = "http://www.qichacha.com/";
URLConnection conn = HttpUtils.getUrlConnection(url1);

result = HttpUtils.getCookieByHeaders(conn.getHeaderFields());

result = HttpUtils.sendGet(url, "", "utf-8", result);

System.out.println("=====" + result);
} catch (Exception e) {
e.printStackTrace();
}

}*/
}