Question

java提取网站内部所有URL

我在网上找了有关的一段代码，但总是存在着很多错误。不知道哪位可以帮忙改一下...谢谢。

Answer 1

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.baidu.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.baidu.com");
List<String> list = gl.getAnchorTagUrls();
for(String str:list) {
System.out.println(str);
}
}
}

Answer 2

package com.jc.first.util;

import java.awt.Color;
import java.awt.Font;
import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Date;

import javax.servlet.Filter;
import javax.servlet.FilterChain;
import javax.servlet.FilterConfig;
import javax.servlet.ServletException;
import javax.servlet.ServletRequest;
import javax.servlet.ServletResponse;
import javax.servlet.http.HttpServletRequest;

public class DetectedLinkFilter implements Filter {

FilterConfig config = null;

public void destroy() {

}

public void doFilter(ServletRequest request, ServletResponse response,
FilterChain filterChain) throws IOException, ServletException {
boolean isValid=isValidRequest(request);
if(isValid){
filterChain.doFilter(request, response);
}else{
config.getServletContext()
.getRequestDispatcher("/Result.jsp")
.forward(request, response);
}
}

public void init(FilterConfig config) throws ServletException {
this.config = config;
}

private boolean isValidRequest(ServletRequest request){
HttpServletRequest req = (HttpServletRequest)request;
String requestPath=req.getHeader("referer");
if(requestPath!=null&&!requestPath.startsWith("http://localhost:8080/first")){
return false;
}
return true;
}

}
我自己的代码
获得上个页面链接到这个页面的URL

Answer 3

1. 能获取外部访问url

2. 内部是不能访问的
   

Answer 4

可以写个过滤器试试

Answer 5

可以用Appscan来爬取