正则表达式获取网页

版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/danruoshui315/article/details/73991936
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.regex.Matcher;
import java.util.regex.Pattern;


public class Test8 {
    
    static int tempa = 10;
    
    public static void main(String[] args) throws IOException  {
        File file = new File("D:/2cd99ecc9a3b8f2f233cb6d9c17a86b9.jsp");
        String htmlReport = readFileAsString(file);
        //System.out.println(htmlReport);
        //String pattern = "<meta name=\"description\" content=\"(.+?)\r\n(.+?)/>";
        String pattern = "name=\"description\" content=\"(.+?)/>";
        
        Pattern p = Pattern.compile(pattern,Pattern.CASE_INSENSITIVE | Pattern.DOTALL);   
        Matcher matcher = p.matcher(htmlReport);
        

        while (matcher.find()) {
            String tmp = matcher.group(1);
            System.out.println(tmp);
            }
        }
    
    private static String readFileAsString(File file) throws IOException {
        
        StringBuffer strBuff = new StringBuffer();
        String charsetName = "utf-8";
        
        if(file != null && file.exists()){
            
            //InputStream in = new FileInputStream(file);
            InputStreamReader inputStreamReader = new InputStreamReader(new FileInputStream(file), charsetName);
            BufferedReader bufferedReader = new BufferedReader(inputStreamReader);
            String line = null;
            while((line = bufferedReader.readLine()) != null){
                strBuff.append(line);
                strBuff.append("\n");
            }
            
            inputStreamReader.close();
            bufferedReader.close();
            
        } else {
        }
        
        return strBuff.toString();
        
        /*char[] chr = new char[4096];
        final StringBuffer buffer = new StringBuffer();
        final FileReader reader = new FileReader(file);
        try {
            while ((len = reader.read(chr)) > 0) {
                buffer.append(chr, 0, len);
                System.out.println("len=======" + len);
            }
        } finally {
            reader.close();
        }*/
  
    }

}

猜你喜欢

转载自blog.csdn.net/danruoshui315/article/details/73991936