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;
/**
* @author Xing,XiuDong
*/
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 : http://www.google.cn/
*/
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");
}
}

/**
* generite html source code
*
* @author Xing,XiuDong
* @date 2009.06.22
* @param request
* @param url
* @param toWebRoot
* @param encoding
* @throws IOException
*/
public void genHtml(HttpServletRequest request, String url, boolean toWebRoot, String encoding) throws IOException {
if (null == url) {
url = request.getRequestURL().toString();
}
String contextPath = request.getContextPath();
String seq = StringUtils.substring(String.valueOf(new Date().getTime()), -6);
String ctxPath = super.getServlet().getServletContext().getRealPath(File.separator);
if (!ctxPath.endsWith(File.separator)) {
ctxPath += File.separator;
}
String filePath = StringUtils.substringAfter(url, contextPath);
filePath = filePath.replaceAll("\\.(do|jsp|html|shtml)$", ".html");
String savePath = "";
String autoCreatedDateDir = "";
if (!toWebRoot) {
savePath = StringUtils.join(new String[] { "files", "history", "" }, File.separator);
String[] folderPatterns = new String[] { "yyyy", "MM", "dd", "" };
autoCreatedDateDir = DateFormatUtils.format(new Date(), StringUtils.join(folderPatterns, File.separator));
filePath = StringUtils.substringBefore(filePath, ".html") + "-" + seq + ".html";
}
File file = new File(ctxPath + savePath + autoCreatedDateDir + filePath);
FileUtils.writeStringToFile(file, HTMLGenerator.generate(url), encoding);
}