extract163mp3.java

一个搜索引擎,希望对大家有用

package com.luceneheritrixbook.extractor.com163;

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.util.Date;

import org.htmlparser.NodeFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.TableColumn;
import org.htmlparser.util.NodeList;

import com.luceneheritrixbook.extractor.Extractor;
import com.luceneheritrixbook.util.StringUtils;

public class Extract163Mp3 extends Extractor {
	public void extract() {
		// TODO Auto-generated method stub
		String filterStr = "td";
		BufferedWriter bw = null;
		NodeFilter filter = new TagNameFilter(filterStr);
		try {
			NodeList nodes = this.getParser().extractAllNodesThatMatch(filter);
			for (int i = 0; i < nodes.size(); i++) {

				TableColumn node = (TableColumn) nodes.elementAt(i);
				String text = node.getChildrenHTML();
				if (node.getAttribute("width") != null
						&& node.getAttribute("width").equals("31%")) {
					String result = getProp(
							"<td width=\"31%\" align=\"left\" bgcolor=\"#F1F1F1\" class=\"fB\">(.*)</td>",
							node.toHtml(), 1);
					TableColumn nodeExt = (TableColumn) node.getNextSibling()
							.getNextSibling();
					bw.write(StringUtils.trim(result) + ":"
							+ StringUtils.trim(nodeExt.getChildrenHTML())
							+ "\n");

					continue;

				} else if (node.getAttribute("class") != null
						&& node.getAttribute("class").equals("f14px fB cWhite")
						&& node.getAttribute("width") != null
						&& node.getAttribute("width").equals("141")) {
					String[] names = node.getChildrenHTML().split(" ");
					StringBuffer title = new StringBuffer();
					for (int k = 0; k < names.length; k++) {
						title.append(names[k]).append("-");
					}
					title.append((new Date()).getTime());
					String title_str = title.toString().replaceAll("/", "_");
					bw = new BufferedWriter(new FileWriter(new File(this
							.getOutputPath()
							+ title_str)));
					int startPos = getInuputFilePath().indexOf("mirror") + 6;
					String url_seg = getInuputFilePath().substring(startPos);
					url_seg = url_seg.replaceAll("\\\\", "/");
					String url = "http:/" + url_seg;
					bw.write(url + "\n");
					bw.write(names[0] + "\n");
				}

			}
			if (bw != null)
				bw.close();
		} catch (Exception e) {
			e.printStackTrace();
		} finally {

		}
	}

}