简单爬虫的实现原理

本文介绍了一个使用Java实现的简单网页抓取程序,该程序能够从指定的URL抓取网页内容,并通过正则表达式匹配来提取网页中的链接。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

import java.io.BufferedReader;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Test {
/**
* *
*
* @param args
*/
public static void main(String[] args) {
try {
URL url = new URL("http://www.sina.com.cn");
URLConnection conn = url.openConnection();
conn.setDoOutput(true);
InputStream in = null;
in = url.openStream();
String content = pipe(in, "gbk");
System.out.println(content);

String regex = "<(a|A)(\\s|\\w|\\.|/|#|\\?|\\&|\\=|%|:|,|;|-|\\)|\\(|\'|\")*>";
java.util.regex.Pattern pattern = Pattern.compile(regex);

Matcher matcher = pattern.matcher(content);

while(matcher.find()) {
System.out.println(matcher.group());
System.out.println(getURL(matcher.group()));
}



} catch (Exception e) {
e.printStackTrace();
}
}


public static String getURL(String content) {
String result = "";

int l = 0;
int s = 0;
int e = 0;

l = content.length();

content = content.toLowerCase();
s = content.indexOf("href=\"") + 6;

e = content.indexOf("\" ", s);
if(e == -1) {
e = content.indexOf("\">", s);
}

if(s > 0 && e > s) {
result = content.substring(s, e);
}

return result;
}


public static String pipe(InputStream in, String charset) throws IOException {
StringBuffer s = new StringBuffer();
if (charset == null || "".equals(charset)) {
charset = "utf-8";
}
String rLine = null;
BufferedReader bReader = new BufferedReader(new InputStreamReader(in,
charset));
PrintWriter pw = null;
FileOutputStream fo = new FileOutputStream("../index.html");
OutputStreamWriter writer = new OutputStreamWriter(fo, "utf-8");
pw = new PrintWriter(writer);
while ((rLine = bReader.readLine()) != null) {
String tmp_rLine = rLine;
int str_len = tmp_rLine.length();
if (str_len > 0) {
s.append(tmp_rLine);
pw.println(tmp_rLine);
pw.flush();
s.append("\n");
}
tmp_rLine = null;
}
in.close();
pw.close();
return s.toString();
}
}

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值