读取多目录下的文件

public class simpleRegex {

	public static void main(String[] args) throws IOException {
		processFile("C:\\Users\\tianjun\\Desktop\\search\\ch10\\heritrixproject\\jobs\\xiaoxue-20150314050416274\\mirror\\");
	}

	public static void processFile(String path) throws IOException {
		File[] files = new File(path).listFiles();
		for (int i = 0; i < files.length; i++) {
			if (files[i].isDirectory() == true) {
				processFile(files[i].getAbsolutePath());
			} else {
				try {
					BufferedReader reader = new BufferedReader(new FileReader(
							files[i].getAbsoluteFile()));
					StringBuffer sb = new StringBuffer();
					String line = null;
					while ((line = reader.readLine()) != null) {
						sb.append(line);
						sb.append("\n");
					}
					reader.close();
				} catch (IOException e) {
					e.printStackTrace();
				} finally {
					Extractor extractor = new Extractor();
					extractor.extract(files[i].getAbsolutePath());
				}
			}

		}
	}
}

这个是对目录及文件的处理，接下来就是对具体处理的实现的一个例子的函数

	public void extract(String filename) throws IOException {
		String web = readFileByLines(filename);
		web = new String(web.getBytes("utf-8"), "utf-8");
		title = MatchStr("<h1 id=\"detail_article_title\">([\\w\\W]*?)</h1>",
				web);
		yd = MatchStr("<span class=\"view_count\">([\\w\\W]*?)</span>", web);
		bjdp = MatchStr("<strong>[\\w\\W]*?</strong>([\\w\\W]*?)<br />", web);
		zw = MatchStr("<div id=\"article\">([\\s\\S]*?)<div class=\"clear\">",
				web);
		lj = filename.substring(filename.indexOf("mirror") + 7,
				filename.lastIndexOf("\\"));
		lj = lj.replaceAll("\\\\", "/");
		md5 = MD5.MD5EnCode(lj);
		run();
		if (this.user != null) {

		}
	}