黑马程序员技术交流社区
标题:
请各位帮忙看下我的爬虫小程序，求解答,谢谢
[打印本页]
作者:
wyy666
时间:
2014-6-1 23:07
标题:
请各位帮忙看下我的爬虫小程序，求解答,谢谢
package regex;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.InputStreamReader;
import java.io.PrintWriter;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
//爬虫小程序
public class Carwler {
public static void main (String[] args) throws Exception{
URL url = new URL("http://tieba.baidu.com/p/2711844440");
URLConnection urlcon = url.openConnection();
BufferedReader br = new BufferedReader(new InputStreamReader(urlcon.getInputStream()));
PrintWriter pw = new PrintWriter(new File("E:\\carwler.txt"));
String regex="\\w+@\\w+(\\.\\w+)+";
Pattern p = Pattern.compile(regex);
String line=null;
while((line=br.readLine())!=null){
Matcher mm = p.matcher(line);
while(mm.find()){
//System.out.println(mm.group()); <font color="#ff0000">//这里出现了一点问题，可以直接在控制台上打印，可以为什么不能写入到一个文件中呢？？</font>
作者:
pk49800
时间:
2014-6-2 00:29
这样写，可以写到TXT里面，你试试
import java.io.BufferedReader;
import java.io.File;
import java.io.FileWriter;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Carwler {
public static void main(String[] args) throws Exception {
URL url = new URL("http://tieba.baidu.com/p/2711844440");
URLConnection urlcon = url.openConnection();
BufferedReader br = new BufferedReader(new InputStreamReader(
urlcon.getInputStream()));
FileWriter fw = new FileWriter(new File("D:\\carwler.txt"));
String regex = "\\w+@\\w+(\\.\\w+)+";
Pattern p = Pattern.compile(regex);
String line = null;
while ((line = br.readLine()) != null) {
Matcher mm = p.matcher(line);
while (mm.find()) {
fw.write(mm.group()+"\r\n");
System.out.println(mm.group());
}
}
fw.close();
}
}
复制代码
欢迎光临 黑马程序员技术交流社区 (http://bbs.itheima.com/)
黑马程序员IT技术论坛 X3.2