📄 webcrawler.java
字号:
package chapter2;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.InetSocketAddress;
import java.net.Proxy;
import java.net.URL;
import java.net.URLConnection;
import java.net.UnknownHostException;
public class WebCrawler {
private static String Text_File_Path = "c:\\workshop\\ch2\\htmlsrc.html";
public static void main(String[] args) throws IOException {
try {
File file = new File(Text_File_Path);
FileWriter fpWriter = new FileWriter(file);
// 生成下载对象
URL url = new URL("http://www.bnu.edu.cn");
// 创建代理服务器
InetSocketAddress addr = new InetSocketAddress("172.17.18.84",
8080);
Proxy proxy = new Proxy(Proxy.Type.HTTP, addr); // http 代理
// 如果我们知道代理server的名字, 可以直接使用
// 结束
URLConnection conn = url.openConnection(proxy);
InputStream in = conn.getInputStream();
//Socket webclient = new Socket("www.bnu.edu.cn", 80);
//PrintWriter result = new PrintWriter(webclient.getOutputStream(), true);
//BufferedReader receiver = new BufferedReader(new InputStreamReader(webclient.getInputStream()));
BufferedReader receiver = new BufferedReader(new InputStreamReader(in));
//发送HTTP request请求
/*result.println("GET / HTTP/1.1");
result.println("Host: bnu.edu.cn");
result.println("Connection: Close");
result.println();*/
//接收HTTP Response 返回的结果信息
boolean bRet = true;
StringBuffer sBuffer = new StringBuffer(8096);
while (bRet) {
if (receiver.ready()) {
int idx = 0;
while (idx != -1) {
idx = receiver.read();
if(idx == '<')
break;
}
while (idx != -1) {
sBuffer.append((char) idx);
idx = receiver.read();
}
bRet = false;
}
}
// 显示获得的网页正文,打印到控制台
System.out.println(sBuffer.toString());
fpWriter.write(sBuffer.toString());
//webclient.close();
fpWriter.close();
} catch (UnknownHostException e) {
System.err.println("无法访问指定主机.");
System.exit(1);
} catch (IOException e) {
System.err.println("下载失败,请检查输入地址是否正确。");
System.exit(1);
}
}
}
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -