Java Regular Expressions Use an _ regular expression

One: Crawl the email address in the webpage

Using regular expressions to match text in a Web page

Copy Code code as follows:

[\\w[.-]]+@[\\w[.-]]+\\. [\\w]+

Split the page content to extract

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 Bufferedread ER (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 ());
    }
}}

Print results:

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

Now you find so many email addresses, with the knowledge of JavaMail, you can send mass spam, hehe!!!

Two: Code statistics

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;//Normal code line static long Commentlines = 0;//Comment Line static long Whitel Ines = 0;//blank line public static void main (string[] args) {//Find a folder in which there is no folder, no write recursive processing files in the same folder file F = new
    File ("E:\\workspaces\\eclipse\\application\\javamailtest\\src\\com\\java\\mail");
    file[] Codefiles = F.listfiles ();
      for (file child:codefiles) {///Statistics only Java file if (Child.getname (). Matches (". *\\.java$")) {parse (child);
    } System.out.println ("Normallines:" + normallines);
    System.out.println ("Commentlines:" + commentlines);
  System.out.println ("Whitelines:" + whitelines);
    private static void Parse (File f) {bufferedreader br = null;
    Indicates whether to start Boolean comment = False for the comment;
      try {br = new BufferedReader (new FileReader (f)); String Line = "";
        while (line = Br.readline ())!= null) {//Remove the blank line = Line.trim () that may appear before the annotation character/*; Empty line because ReadLine () has removed the string, the newline character \ n//So is not "^[\\s&&[^\\n]]*\\n$" if (line.matches) ("^[\\s&&[
        ^\\n]]*$ ")) {whitelines + +;
          else if (Line.startswith ("*") &&!line.endswith ("* *")) {//statistic multiline/*****/Commentlines + +;  
        Comment = true;
        else if (Line.startswith ("*") && line.endswith ("* *")) {//statistic row/**/Commentlines + +;
          else if (true = = comment) {//Statistics */commentlines + +;
          if (Line.endswith ("* *")) {comment = false;
        } else if (Line.startswith ("//)") {commentlines + +;
        else {normallines + +;
    A catch (FileNotFoundException e) {e.printstacktrace ());
    catch (IOException e) {e.printstacktrace (); finally {if (BR != null) {try {br.close ();
        br = NULL;
        catch (IOException e) {e.printstacktrace (); }
      }
    }
  }
}

The above content is this article to share Java in the regular expression of the use, I hope you like.