共计 1296 个字符，预计需要花费 4 分钟才能阅读完成。
用 Java 中 URLConnection 抓取某个 URL 网页源码（这是原理核心）生成 html 文件，就是这么简单！就是这么 Easy！
需要 commons.io 和 commons.lang 两个包
import java.io.BufferedReader;
import java.io.File;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.io.FileUtils;
import org.apache.commons.lang.StringUtils;
/**
*/
public class HTMLGenerator {
public static final String generate(final String url) {
if (StringUtils.isBlank(url)) {
return null;
}
Pattern pattern = Pattern.compile(“(http://|https://){1}[\\w\\.\\-/:]+”);
Matcher matcher = pattern.matcher(url);
if (!matcher.find()) {
return null;
}
StringBuffer sb = new StringBuffer();
try {
URL _url = new URL(url);
URLConnection urlConnection = _url.openConnection();
BufferedReader in = new BufferedReader(new InputStreamReader(urlConnection.getInputStream()));
String inputLine;
while ((inputLine = in.readLine()) != null) {
sb.append(inputLine);
}
} catch (MalformedURLException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return sb.toString();
}
/**
* Test Code
* Target :
*/
public static void main(String[] args) throws IOException {
String src = HTMLGenerator.generate(“http://www.google.cn/”);
File file = new File(“C:” + File.separator + “index.html”);
FileUtils.writeStringToFile(file, src, “UTF-8”);
}
}