一:抓取网页中的Email地址
利用正则表达式匹配网页中的文本
[\\w[.-]]+@[\\w[.-]]+\\.[\\w]+
将网页内容分割提取
import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class EmailSpider {
public static void main(String[] args) {
try {
BufferedReader br = new BufferedReader(new FileReader("C:\\emailSpider.html"));
String line = "";
while((line=br.readLine()) != null) {
parse(line);
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
private static void parse(String line) {
Pattern p = Pattern.compile("[\\w[.-]]+@[\\w[.-]]+\\.[\\w]+");
Matcher m = p.matcher(line);
while(m.find()) {
System.out.println(m.group());
}
}
}
打印结果:
867124664@qq.com
260678675@QQ.com
806208721@qq.com
hr_1985@163.com
32575987@qq.com
qingchen0501@126.com
yingyihanxin@foxmail.com
1170382650@qq.com
1170382650@qq.com
yingyihanxin@foxmail.com
qingchen0501@126.com
32575987@qq.com
hr_1985@163.com
现在你找到这么多邮箱地址,用上JavaMail的知识,你可以群发垃圾邮件了,呵呵!!!
二:代码统计
import java.io.BufferedReader;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
public class CodeCounter {
static long normalLines = 0;//正常代码行
static long commentLines = 0;//注释行
static long whiteLines = 0;//空白行
public static void main(String[] args) {
//找到某个文件夹,该文件夹下面在没有文件夹,这里没有写递归处理不在同一文件夹的文件
File f = new File("E:\\Workspaces\\eclipse\\Application\\JavaMailTest\\src\\com\\java\\mail");
File[] codeFiles = f.listFiles();
for(File child : codeFiles){
//只统计java文件
if(child.getName().matches(".*\\.java$")) {
parse(child);
}
}
System.out.println("normalLines:" + normalLines);
System.out.println("commentLines:" + commentLines);
System.out.println("whiteLines:" + whiteLines);
}
private static void parse(File f) {
BufferedReader br = null;
//表示是否为注释开始
boolean comment = false;
try {
br = new BufferedReader(new FileReader(f));
String line = "";
while((line = br.readLine()) != null) {
//去掉注释符/*前面可能出现的空白
line = line.trim();
//空行 因为readLine()将字符串取出来时,已经去掉了换行符\n
//所以不是"^[\\s&&[^\\n]]*\\n$"
if(line.matches("^[\\s&&[^\\n]]*$")) {
whiteLines ++;
} else if (line.startsWith("/*") && !line.endsWith("*/")) {
//统计多行/*****/
commentLines ++;
comment = true;
} else if (line.startsWith("/*") && line.endsWith("*/")) {
//统计一行/**/
commentLines ++;
} else if (true == comment) {
//统计*/
commentLines ++;
if(line.endsWith("*/")) {
comment = false;
}
} else if (line.startsWith("//")) {
commentLines ++;
} else {
normalLines ++;
}
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
if(br != null) {
try {
br.close();
br = null;
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
}