mql_write2file.java

用于抽取网页文本评论的源程序

package cn.casia.ailab.ldy.cmt;

import java.io.BufferedOutputStream;
import java.io.BufferedWriter;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.util.zip.GZIPOutputStream;
/* This Class is citing Thunder's work*/
public class Mql_Write2File {

	// private String fileName = new String();
	// private String fileName = ;

	private String fileName = new String();
	private String encoding = "gb2312";
	public Mql_Write2File(String fileName) {
		this.fileName = fileName;
	}

	/**
	 * 将网页的内容存入文件夹中
	 * 
	 * @param urlName
	 * @param htmlContent
	 * @throws IOException
	 */
	public void writeWebDownFile(String htmlContent) throws IOException {

		BufferedWriter successFileWrite = null;
		try {
			successFileWrite = new BufferedWriter(new OutputStreamWriter(
					new FileOutputStream(fileName, true), encoding));
			// 注意，FileOutputStream的构造参数中必须含有true，这样才能续写文件。

			// 下载的网页内容
			successFileWrite.write(htmlContent);
			// 表示这一下载网页的HTML代码已经结束
			// String separateMark =
			// "\r\n--------######END######--------\r\n\r\n";
			// successFileWrite.write(separateMark);
			successFileWrite.close();

		} catch (IOException ex) {
			throw new RuntimeException(ex);
		} finally {
			if (successFileWrite != null) {
				successFileWrite.close();
			}
		}
	}// writeSuccessFile ends.
	public void writeNewFile(String htmlContent) throws IOException {

		BufferedWriter successFileWrite = null;
		try {
			successFileWrite = new BufferedWriter(new OutputStreamWriter(
					new FileOutputStream(fileName, false), encoding));
			// 注意，FileOutputStream的构造参数中必须含有true，这样才能续写文件。

			// 下载的网页内容
			successFileWrite.write(htmlContent);
			// 表示这一下载网页的HTML代码已经结束
			// String separateMark =
			// "\r\n--------######END######--------\r\n\r\n";
			// successFileWrite.write(separateMark);
			successFileWrite.close();

		} catch (IOException ex) {
			throw new RuntimeException(ex);
		} finally {
			if (successFileWrite != null) {
				successFileWrite.close();
			}
		}
	}// writeSuccessFile ends.

	/**
	 * 将网页内容采用GZIP压缩形式存入文件中
	 * 
	 * @param urlName
	 *            URL's name
	 * @param htmlContent
	 *            下载的网页内容
	 * @param encoding
	 *            gzip压缩的编码格式
	 * @throws IOException
	 */
	public void writeGZIP(String urlName, String htmlContent, String encoding)
			throws IOException {

		BufferedOutputStream gzipWrite = null;
		try {
			gzipWrite = new BufferedOutputStream(new GZIPOutputStream(
					new FileOutputStream(fileName, true)));
			// 注意，FileOutputStream的构造参数中必须含有true，这样才能续写文件。
			// 用下面的字符串分割下载文件中的多个HTML网页代码
			String separateMark = "\r\n<url>" + urlName + "</url>\r\n";

			// 注意：要将字符串写入压缩文件中，需要先将其转换为byte数组。
			byte[] url2Byte = separateMark.getBytes("UTF-8");
			gzipWrite.write(url2Byte);

			try {
				// 将网页内容转换为byte数组，写入压缩文件中
				byte[] htmlContent2Byte = htmlContent.getBytes(encoding);
				gzipWrite.write(htmlContent2Byte);
			} catch (UnsupportedOperationException ex) {// 遇到Sting.getBytes不支持的编码方式
				// 按照“UTF-8”编码将网页内容转换为byte数组，写入压缩文件中
				byte[] htmlContent2Byte = htmlContent.getBytes("UTF-8");
				gzipWrite.write(htmlContent2Byte);
			}

			// 表示这一下载网页的HTML代码已经结束
			separateMark = "\r\n--------######END######--------\r\n\r\n";
			byte[] separateMark2Byte = separateMark.getBytes();
			gzipWrite.write(separateMark2Byte);

			gzipWrite.close();
		} catch (IOException ex) {
			throw new RuntimeException(ex);
		} finally {
			if (gzipWrite != null) {
				gzipWrite.close();
			}
		}
	}// writeGZIP ends.

}