Question

如何使用Java语言实现一个网页爬虫

Answer 1

我给你代码
public class DEmo {
public static void match(String s1) {
Pattern p = Pattern.compile("<a(.*)>.*</a>");
Matcher m = p.matcher(s1);
while (m.find()) {
System.out.println(m.group(1));
}
}

public static void main(String args[]) {
URL url;
int responsecode;
HttpURLConnection urlConnection;
BufferedReader reader;
String line;
try {
// 生成一个URL对象，要获取源代码的网页地址为：http://www.sina.com.cn
url = new URL("http://www.jb51.net/article/97787.htm");
// 打开URL
urlConnection = (HttpURLConnection) url.openConnection();
// 获取服务器响应代码
responsecode = urlConnection.getResponseCode();
String temp = "";
if (responsecode == 200) {
// 得到输入流，即获得了网页的内容
reader = new BufferedReader(new InputStreamReader(
urlConnection.getInputStream(), "GBK"));
while ((line = reader.readLine()) != null) {
temp = temp + line;
}
System.out.println(temp);
match(temp);

} else {
System.out.println("获取不到网页的源码，服务器响应代码为：" + responsecode);
}
} catch (Exception e) {
System.out.println("获取不到网页的源码,出现异常：" + e);
}

}
}