filewriter.java

基于JAVA的网络蜘蛛系统,使用JAVA实现抓取网络资源的网络蜘蛛。通过一个入口网址来扫描整个互联网的网址

package issa.webspider;

import java.io.File;
import java.io.IOException;
import java.io.Reader;
import java.net.URI;
import java.net.URISyntaxException;
import java.net.URL;

public class FileWriter {

	URL url;
	String downLoadDir;
	
	public FileWriter(URL url) {
		this.url = url;
		this.downLoadDir = CommonVar.downLoadDir;
	}
	
	public File writeToFile(Reader reader) {
		try {
			String stringFile = makeLocalPath();
			String stringPath = splitPath(stringFile);

			File file = new File(stringFile);
			File dir = new File(stringPath);
			if (!dir.exists()) {
//				System.out.println(dir + " is not exists!");
				dir.mkdirs();
			}
			if (!file.exists()) {
//				System.out.println(file + " is not exists!");
				file.createNewFile();
			}

//			InputStream in = new BufferedInputStream(url.openStream());
//			InputStreamReader reader = new InputStreamReader(in);
			java.io.FileWriter fw = new java.io.FileWriter(file);
			int c;
			while ((c = reader.read()) != -1) {
				fw.write(c);
			}
			fw.flush();
			fw.close();
			return file;
		} catch (IOException e) {
			return null;
		}
	}
	
	private String makeLocalPath() {
		URI parentUri;
		try {
			parentUri = url.toURI();
		} catch (URISyntaxException e) {
			e.printStackTrace();
			return null;
		}
		StringBuilder sb = new StringBuilder();
		sb.append(downLoadDir);
		sb.append("\\");
		sb.append(parentUri.getHost());
		sb.append(parentUri.getPath());
		return replaceSlash(sb.toString());
	}

	private String replaceSlash(String url) {
		char[] temp = url.toCharArray();
		for (int i = 0; i < temp.length; i++) {
			if (temp[i] == '/' || temp[i] == '\\') {
				temp[i] = File.separatorChar;
			}
		}
		String tempString = new String(temp);
		if (tempString.endsWith(File.separator)) {
			return tempString + "noname.html";
		} else {
			return tempString;
		}
	}

	private String splitPath(String url) {
		int slash = url.lastIndexOf(File.separator);
		return url.substring(0, slash + 1);
	}
	
}