java取网址

1. java获取URL

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;

public class GetLinks {
private String webSource;
private String url;

public GetLinks(String url) throws MalformedURLException, IOException {
this.url = Complete(url);
webSource = getWebCon(this.url);
}

private String getWebCon(String strURL) throws MalformedURLException,
IOException {
StringBuffer sb = new StringBuffer();
java.net.URL url = new java.net.URL(strURL);
BufferedReader in = new BufferedReader(new InputStreamReader(url
.openStream()));
String line;
while ((line = in.readLine()) != null) {
sb.append(line);
}
in.close();
return sb.toString();
}

private String Complete(String link)throws MalformedURLException{
URL url1 = new URL(link);
URL url2 = new URL(link+"/");
String handledUrl = link;
try{
StringBuffer sb1 = new StringBuffer();
BufferedReader in1 = new BufferedReader(new InputStreamReader(url1
.openStream()));
String line1;
while ((line1 = in1.readLine()) != null) {
sb1.append(line1);
}
in1.close();

StringBuffer sb2 = new StringBuffer();
BufferedReader in2 = new BufferedReader(new InputStreamReader(url2
.openStream()));
String line2;
while ((line2 = in2.readLine()) != null) {
sb2.append(line2);
}
in1.close();

if(sb1.toString().equals(sb2.toString())){
handledUrl = link+"/";
}
}catch(Exception e){
handledUrl = link;
}
return handledUrl;

}

/**
* 处理链接的相对路径
* @param link 相对路径或绝对路径
* @return 绝对路径
*/
private String urlHandler(String link) {
if (link == null)
return null;
link = link.trim();

if (link.toLowerCase().startsWith("http://")
|| link.toLowerCase().startsWith("https://")) {
return link;
}
String pare = url.trim();
if (!link.startsWith("/")) {
if (pare.endsWith("/")) {
return pare + link;
}

if (url.lastIndexOf("/") == url.indexOf("//") + 1 || url.lastIndexOf("/") == url.indexOf("//") + 2) {
return pare + "/" + link;
} else {
int lastSeparatorIndex = url.lastIndexOf("/");
return url.substring(0, lastSeparatorIndex + 1) + link;
}
}else{
if (url.lastIndexOf("/") == url.indexOf("//") + 1 || url.lastIndexOf("/") == url.indexOf("//") + 2) {
return pare + link;
}else{
return url.substring(0,url.indexOf("/", url.indexOf("//")+3)) + link;
}
}
}

public List<String> getAnchorTagUrls() {
if (webSource == null) {
System.out.println("没有网页源代码");
return null;
}
ArrayList<String> list = new ArrayList<String>();
int index = 0;
while (index != -1) {
index = webSource.toLowerCase().indexOf("<a ", index);
if (index != -1) {
int end = webSource.indexOf(">", index);
String str = webSource.substring(index, end == -1 ? webSource
.length() : end);
str = str.replaceAll("\\s*=\\s*", "=");
if (str.toLowerCase().matches("^<a.*href\\s*=\\s*[\'|\"]?.*")) {// "^<a\\s+\\w*\\s*href\\s*=\\s*[\'|\"]?.*"
int hrefIndex = str.toLowerCase().indexOf("href=");
int leadingQuotesIndex = -1;
if ((leadingQuotesIndex = str.indexOf("\"", hrefIndex
+ "href=".length())) != -1) { // 形如<a
// href=".....">
int TrailingQuotesIndex = str.indexOf("\"",
leadingQuotesIndex + 1);
TrailingQuotesIndex = TrailingQuotesIndex == -1 ? str
.length() : TrailingQuotesIndex;
str = str.substring(leadingQuotesIndex + 1,
TrailingQuotesIndex);
str = urlHandler(str);
list.add(str);
System.out.println(str);
index += "<a ".length();
continue;
}

if ((leadingQuotesIndex = str.indexOf("\'", hrefIndex
+ "href=".length())) != -1) { // 形如<a
// href='.....'>
int TrailingQuotesIndex = str.indexOf("\'",
leadingQuotesIndex + 1);
TrailingQuotesIndex = TrailingQuotesIndex == -1 ? str
.length() : TrailingQuotesIndex;
str = str.substring(leadingQuotesIndex + 1,
TrailingQuotesIndex);
str = urlHandler(str);
System.out.println(str);
list.add(str);
index += "<a ".length();
continue;
}

int whitespaceIndex = str.indexOf(" ", hrefIndex
+ "href=".length()); // 形如<a href=
// http://www..com >
whitespaceIndex = whitespaceIndex == -1 ? str.length()
: whitespaceIndex;
str = str.substring(hrefIndex + "href=".length(),
whitespaceIndex);
str = urlHandler(str);
list.add(str);
System.out.println(str);

}
index += "<a ".length();
}
}
return list;
}

public static void main(String[] args) throws Exception {
GetLinks gl = new GetLinks("http://www..com");
List<String> list = gl.getAnchorTagUrls();
for(String str:list) {
System.out.println(str);
}
}
}

2. java怎么获得web应用的网址

比如这个路径

http://localhost/servlet/DemoServlet？name=test
String scheme = request.getScheme();//获取请求协议-http
int serverPort = request.getServerPort();//获取服务端口号 -8080
String serverName = request.getServerName();//获取服务域名(主机名) -localhost
String requestURI = request.getRequestURI();//获取请求uri路径 -/servlet/DemoServlet
String servletPath = request.getServletPath();//获取servlet路径 -/DemoServlet
String contextPath = request.getContextPath();//获取上下文路径 -/servlet
String queryString = request.getQueryString();//获取uri请求参数 -/name=test
StringBuffer requestURL = request.getRequestURL();//获取url路径 -http://localhost/servlet/DemoServlet

3. 用java实现获取当前网址的来路(即是访问当前网址是从哪里接入的)

有两种方式：
一种是通过后台请求获取：request.getHeader("referer");
另一种是通过脚本js获取：document.referrer

4. java中如何根据一个网址获得该网页的源代码

package test;

import java.io.BufferedReader;

import java.io.InputStreamReader;

import java.net.HttpURLConnection;

import java.net.URL;

public class HttpTest {

private String u;

private String encoding;

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

HttpTest client = new HttpTest("http://www..com/", "UTF-8");

client.run();

}

public HttpTest(String u, String encoding) {

this.u = u;

this.encoding = encoding;

}

public void run() throws Exception {

URL url = new URL(u);// 根据链接（字符串格式），生成一个URL对象

HttpURLConnection urlConnection = (HttpURLConnection) url

.openConnection();// 打开URL

BufferedReader reader = new BufferedReader(new InputStreamReader(

urlConnection.getInputStream(), encoding));// 得到输入流，即获得了网页的内容

String line; // 读取输入流的数据，并显示

while ((line = reader.readLine()) != null) {

System.out.println(line);

}

}

}

5. java如何获取浏览器的访问网址及其内容

通过request俩获取，以下是request的方法介绍：
getParameterNames():取得客户端所发出的请求参数名称.
getParameter():可以让您指定请求参数名称，以取得对应的设定值.
getServerName():请求的服务器.
getProtocol():使用协议.
getMethod():请求方法.
getServerPort():请求端口号.
getContextPath():Context路径.
getServletPath(): Servlet路径.
getRequestURI():URI路径.
getQueryString():查询字符串.
getRemoteAddr():使用者主机IP.
getRemotePort():使用者使用端口号.

6. java正则表达式提取网址

1. 用字符串的split方法

   var ip = '127.111.1.112:8080';

   var addr = ip.split(':')[0];

   var port = ip.split(':')[1];
   

2. 用正则

   var reg=/(d{1,3}.d{1,3}.d{1,3}.d{1,3}):(d{1,4})/;

   var ip = '127.111.1.112:8080';

   var addr = ip.replace(reg,'$1');

   var port = ip.replace(reg,'$2');

3. 还可以间接使用字符串其他的方法，或者是数组的
   

7. java中怎样获取百度短网址

HtmlParser hp=new HtmlParser("www.sina.com.cn");