本文目录一览:
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 ListString getAnchorTagUrls() {
if (webSource == null) {
System.out.println("没有网页源代码");
return null;
}
ArrayListString list = new ArrayListString();
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=
//
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("");
ListString list = gl.getAnchorTagUrls();
for(String str:list) {
System.out.println(str);
}
}
}
请问java如何获取当前url路径?
1、利用System.getProperty()函数获取当前路径:
System.out.println(System.getProperty("user.dir"));//user.dir指定了当前的路径
2、使用File提供的函数获取当前路径:
File directory = new File("");//设定为当前文件夹
try{
System.out.println(directory.getCanonicalPath());//获取标准的路径
System.out.println(directory.getAbsolutePath());//获取绝对路径
}catch(Exceptin e){}
File.getCanonicalPath()和File.getAbsolutePath()大约只是对于new File(".")和new File("..")两种路径有所区别。
# 对于getCanonicalPath()函数,“."就表示当前的文件夹,而”..“则表示当前文件夹的上一级文件夹
# 对于getAbsolutePath()函数,则不管”.”、“..”,返回当前的路径加上你在new File()时设定的路径
# 至于getPath()函数,得到的只是你在new File()时设定的路径
java怎样获取url参数
如果是javaweb 项目,那么非常简单,直接调用 HttpServletRequest 对象的 .getParamter("参数名称") 方法即可得到。
如果是普通java 项目:
/**
* 获取网址的指定参数值
*
* @param url
* 网址
* @param parameter
* 参数名称
* @author cevencheng
* @return
*/
public static String getParameter(String url, String parameter, String defaultValue) {
try {
final String charset = "utf-8";
url = URLDecoder.decode(url, charset);
if (url.indexOf('?') != -1) {
final String contents = url.substring(url.indexOf('?') + 1);
HashMapString, String map = new HashMapString, String();
String[] keyValues = contents.split("");
for (int i = 0; i keyValues.length; i++) {
String key = keyValues[i].substring(0, keyValues[i].indexOf("="));
String value = keyValues[i].substring(keyValues[i].indexOf("=") + 1);
if (key.equals(parameter)) {
if (value == null || "".equals(value.trim())) {
return defaultValue;
}
return value;
}
map.put(key, value);
}
}
return null;
} catch (Exception e) {
e.printStackTrace();
}
return null;
}
java怎么获取url上的参数
解析url,本想用正则表达式处理,但正则表达式速度较慢。用split处理一下就可以了。
package RequestPackage;
import java.util.HashMap;
import java.util.Map;
public class CRequest {
/**
* 解析出url请求的路径,包括页面
* @param strURL url地址
* @return url路径
*/
public static String UrlPage(String strURL)
{
String strPage=null;
String[] arrSplit=null;
strURL=strURL.trim().toLowerCase();
arrSplit=strURL.split("[?]");
if(strURL.length()0)
{
if(arrSplit.length1)
{
if(arrSplit[0]!=null)
{
strPage=arrSplit[0];
}
}
}
return strPage;
}
/**
* 去掉url中的路径,留下请求参数部分
* @param strURL url地址
* @return url请求参数部分
*/
private static String TruncateUrlPage(String strURL)
{
String strAllParam=null;
String[] arrSplit=null;
strURL=strURL.trim().toLowerCase();
arrSplit=strURL.split("[?]");
if(strURL.length()1)
{
if(arrSplit.length1)
{
if(arrSplit[1]!=null)
{
strAllParam=arrSplit[1];
}
}
}
return strAllParam;
}
/**
* 解析出url参数中的键值对
* 如 "index.jsp?Action=delid=123",解析出Action:del,id:123存入map中
* @param URL url地址
* @return url请求参数部分
*/
public static MapString, String URLRequest(String URL)
{
MapString, String mapRequest = new HashMapString, String();
String[] arrSplit=null;
String strUrlParam=TruncateUrlPage(URL);
if(strUrlParam==null)
{
return mapRequest;
}
//每个键值为一组
arrSplit=strUrlParam.split("[]");
for(String strSplit:arrSplit)
{
String[] arrSplitEqual=null;
arrSplitEqual= strSplit.split("[=]");
//解析出键值
if(arrSplitEqual.length1)
{
//正确解析
mapRequest.put(arrSplitEqual[0], arrSplitEqual[1]);
}
else
{
if(arrSplitEqual[0]!="")
{
//只有参数没有值,不加入
mapRequest.put(arrSplitEqual[0], "");
}
}
}
return mapRequest;
}
}
测试类
package RequestPackage;
import java.util.Map;
public class TestCRequest {
/**用于测试CRequest类
* @param args
*/
public static void main(String[] args) {
// 请求url
String str = "index.jsp?Action=delid=123sort=";
//url页面路径
System.out.println(CRequest.UrlPage(str));
//url参数键值对
String strRequestKeyAndValues="";
MapString, String mapRequest = CRequest.URLRequest(str);
for(String strRequestKey: mapRequest.keySet()) {
String strRequestValue=mapRequest.get(strRequestKey);
strRequestKeyAndValues+="key:"+strRequestKey+",Value:"+strRequestValue+";";
}
System.out.println(strRequestKeyAndValues);
//获取无效键时,输出null
System.out.println(mapRequest.get("page"));
}
}