赞
踩
首先是两个正则表达式:
1.]+>:这个正则表达式可以匹配所有html标签,可以100%匹配(注意页面编码方式和读取的编码方式)。
2.>[^
下面上程序:
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class URLTest {
/**
* @param args
* @throws URISyntaxException
*/
public static void main(String[] args) throws Exception {
URL url = new URL("http://www.ascii-code.com/");
InputStreamReader reader = new InputStreamReader(url.openStream());
BufferedReader br = new BufferedReader(reader);
String s = null;
while((s=br.readLine())!=null){
s = GetLabel(s);
if(s!=null){
System.out.println(s);
}
}
br.close();
reader.close();
}
public static String GetContent(String html) {
//String html = "
String ss = ">[^
String temp = null;
Pattern pa = Pattern.compile(ss);
Matcher ma = null;
ma = pa.matcher(html);
String result = null;
while(ma.find()){
temp = ma.group();
if(temp!=null){
if(temp.startsWith(">")){
temp = temp.substring(1);
}
if(temp.endsWith("
temp = temp.substring(0, temp.length()-1);
}
if(!temp.equalsIgnoreCase("")){
if(result==null){
result = temp;
}
else{
result+="____"+temp;
}
}
}
}
return result;
}
public static String GetLabel(String html) {
//String html = "
String ss = "]+>";
String temp = null;
Pattern pa = Pattern.compile(ss);
Matcher ma = null;
ma = pa.matcher(html);
String result = null;
while(ma.find()){
temp = ma.group();
if(temp!=null){
if(temp.startsWith(">")){
temp = temp.substring(1);
}
if(temp.endsWith("
temp = temp.substring(0, temp.length()-1);
}
if(!temp.equalsIgnoreCase("")){
if(result==null){
result = temp;
}
else{
result+="____"+temp;
}
}
}
}
return result;
}
}
GetContent用来获取标签内容。
GetLabel用来获取标签。
赞
踩
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。