Javaは正規表現でウェブページの内容をどのように読み取りますか?
javaの正規表現を勉強して、ホームページをキャプチャして、HTML部分の内容を解析します。
package com.xiaofeng.picup;
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.HashMap;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/** *//**
*
* @ ( ) ,
*
*/
public class WebContent ...{
/** *//**
*
*/
public String getOneHtml(String htmlurl) throws IOException...{
URL url;
String temp;
StringBuffer sb = new StringBuffer();
try ...{
url = new URL(htmlurl);
BufferedReader in = new BufferedReader(new InputStreamReader(url
.openStream(), "utf-8"));//
while ((temp = in.readLine()) != null) ...{
sb.append(temp);
}
in.close();
}catch(MalformedURLException me)...{
System.out.println(" URL ! ");
me.getMessage();
throw me;
}catch (IOException e) ...{
e.printStackTrace();
throw e;
}
return sb.toString();
}
/** *//**
*
* @param s
* @return
*/
public String getTitle(String s) ...{
String regex;
String title = "";
List<String> list = new ArrayList<String>();
regex = "<title>.*?</title>";
Pattern pa = Pattern.compile(regex, Pattern.CANON_EQ);
Matcher ma = pa.matcher(s);
while (ma.find()) ...{
list.add(ma.group());
}
for (int i = 0; i < list.size(); i++) ...{
title = title + list.get(i);
}
return outTag(title);
}
/** *//**
*
* @param s
* @return
*/
public List<String> getLink(String s) ...{
String regex;
List<String> list = new ArrayList<String>();
regex = "<a[^>]*href=("([^"]*)"|'([^']*)'|([^s>]*))[^>]*>(.*?)</a>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) ...{
list.add(ma.group());
}
return list;
}
/** *//**
*
* @param s
* @return
*/
public List<String> getScript(String s) ...{
String regex;
List<String> list = new ArrayList<String>();
regex = "<script.*?</script>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) ...{
list.add(ma.group());
}
return list;
}
/** *//**
*
* @param s
* @return CSS
*/
public List<String> getCSS(String s) ...{
String regex;
List<String> list = new ArrayList<String>();
regex = "<style.*?</style>";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) ...{
list.add(ma.group());
}
return list;
}
/** *//**
*
* @param s
* @return
*/
public String outTag(String s) ...{
return s.replaceAll("<.*?>", "");
}