java判断中文英文_用java判断英文网页中是否存在中文字符

//【原创】本程序是把网页(php)源代码读取后，以文件txt格式存入指定路径下；然后通过批量读取txt文件，判断是否存在中文字符，若是中文字符，则会打印出来。

注：php

的url需要手动保存到AA.txt里面，也可以用自动抓取url方式，那样就方便多了。对于打印出来的中文字符，也可以以日志方法保存到文件里，方便查看。

package html;

import java.io.BufferedReader;

import java.io.BufferedWriter;

import java.io.File;

import java.io.FileReader;

import java.io.FileWriter;

import java.io.IOException;

import java.io.InputStreamReader;

import java.net.MalformedURLException;

import java.net.URL;

import java.net.URLConnection;

public class source_html {

static StringBuffer document = new

StringBuffer();

public static void main(String[] args)

{

String url =

"c://mytino//AA.txt"; // 英文网页的URL存放文件

String url_log =

"c://mytino//log//"; // 英文网页源代码存放目录

String fileURL = null;

BufferedReader in;

try {

in = new

BufferedReader(new FileReader(url));

while

((fileURL = in.readLine()) != null) {

System.out.println(fileURL);

write_log(fileURL,

url_log);

}

in.close();

} catch (IOException e) {

// TODO

Auto-generated catch block

e.printStackTrace();

}

try {

getDir(url_log);

} catch (Exception e) {

// TODO

Auto-generated catch block

e.printStackTrace();

}

}

public static void write_log(String fileURL,

String url_log)

{ // 把网页的源码文件读取出来，放入到指定目录里

try {

URL url = new

URL(fileURL);

URLConnection

conn = url.openConnection();

BufferedReader

reader = new BufferedReader(new InputStreamReader(

conn.getInputStream(),

"utf-8"));

String

newFileName = fileURL.replace("/", "!");

BufferedWriter

out = new BufferedWriter(new FileWriter(url_log

+

newFileName.substring(7) + ".txt"));

String line =

null;

while ((line

= reader.readLine()) != null) {

line

= new String(line.getBytes("utf-8"), "utf-8");

out.write(line

+ "\r\n");

}

out.close();

reader.close();

} catch (MalformedURLException

e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

}

}

static void getDir(String url_log) throws

Exception

{ // 获取所有源文件的文件名列表

try {

File f = new

File(url_log);

File[] fList

= f.listFiles();

for (int j =

0; j < fList.length; j++) {

if

(fList[j].isDirectory()) {

System.out.println("Directory

is: " + fList[j].getPath());

getDir(fList[j].getPath());

}

else {

String

name = fList[j].getPath().toString();

System.out.println("filename is: " + name);

isChinese(name);

System.out.println();

}

}

} catch (Exception e)

{

System.out.println("Error：

" + e);

}

}

private static void isChinese(String name)

throws IOException

{

String str;

String subStr1;

BufferedReader in = new

BufferedReader(new FileReader(name));

while ((str = in.readLine()) !=

null) {

for (int i

= 0; i < str.length(); i++) {

// if (str.substring(i, i + 1).matches("[\u4e00-\u9fa5]+"))

//

{ System.out.print(str.substring(i, i + 1));

// } else { System.out.println("非汉字");

} //取中文在Unicode中的编码区间判断

if(str.contains("//")

|| str.startsWith("/*" )||

str.endsWith("*")) //第二个“*”补上"/"

break; subStr1 = str.substring(i, i + 1);

if

(subStr1.getBytes().length == 2) {

System.out.print(subStr1

+ "+");

}

}

}

}

}