java获取url源代码 java获取url文件名
java获取URL
import java.io.BufferedReader;
郾城ssl适用于网站、小程序/APP、API接口等需要进行数据传输应用场景，ssl证书未来市场广阔！成为创新互联的ssl证书销售渠道，可以享受市场价格4-6折优惠！如果有意向欢迎电话联系或者加微信：18980820575（备注：SSL证书合作）期待与您的合作！
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);
}
}
}
java程序读取一个url页面的源代码
传入一个url，返回源代码； public static String getHTML(String url){// 获取指定URL的网页，返回网页内容的字符串，然后将此字符串存到文件即可 try { URL newUrl = new URL(url); URLConnection connect = newUrl.openConnection(); connect.setRequestProperty("User-Agent","Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)"); DataInputStream dis = new DataInputStream(connect.getInputStream()); BufferedReader in = new BufferedReader(new InputStreamReader(dis,"UTF-8")); String html = ""; String readLine = null; while((readLine = in.readLine()) != null) { html = html + readLine; } in.close(); return html; }catch (MalformedURLException me){ System.out.println("MalformedURLException" + me); }catch (IOException ioe){ System.out.println("ioeException" + ioe); } return null; }
Java访问指定URL并获取网页源代码
1．编写useSourceViewer 类的基本框架，该类仅包括无返回值的main ()方法，该方法从参数中获取URL，通过输入缓冲和输出缓冲将该URL 原码输出。
2．编写useSourceViewer 类，代码如下：
import java.net.*;
import java.io.*;
public class useSourceViewer
{
public static void main (String[] args)
{
if (args.length 0)
{
try
{
//读入URL
URL u = new URL(args[0]);
InputStream in = u.openStream( );
// 为增加性能存储输入流
in = new BufferedInputStream(in);
// 将输入流连接到阅读器
Reader r = new InputStreamReader(in);
int c;
while ((c = r.read( )) != -1)
{
System.out.print((char) c);
}
Object o = u.getContent( );
System.out.println("I got a " + o.getClass().getName( ));
}
catch (MalformedURLException e)
{
System.err.println(args[0] + " is not a parseable URL");
}
catch (IOException e)
{
System.err.println(e);
}
} // end if
} // end main
} // end SourceViewer}
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("", "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);
}
}
}
根据具体问题类型，进行步骤拆解／原因原理分析／内容拓展等。
具体步骤如下：／导致这种情况的原因主要是……
网页题目：java获取url源代码 java获取url文件名
文章位置：http://scjbc.cn/article/doscghh.html
