网络爬虫之获取图片到本地.docxVIP

/* Created on Aug 26, 2011 2:41:26 PM * HtmlSourceGetter.java * NOTICE OF PROPRIETARY RIGHTS * This program is a confidential trade secret and the property of author. Use, examination, reproduction, disassembly, decompiling, transfer and/or disclosure to others of all or any part of this software program are strictly prohibited except by express written agreement with author. * * Modification History * Date Author Version Description * Aug 26, 2011 Cross 1.0 New * */ package com.cross.tools; import java.io.BufferedInputStream; import java.io.File; import java.io.FileOutputStream; import java.io.IOException; import java.io.OutputStream; import .HttpURLConnection; import .URL; import org.htmlparser.Node; import org.htmlparser.NodeFilter; import org.htmlparser.Parser; import org.htmlparser.filters.NodeClassFilter; import org.htmlparser.tags.ImageTag; import org.htmlparser.tags.LinkTag; import org.htmlparser.util.NodeList; import org.htmlparser.util.ParserException; import org.htmlparser.util.SimpleNodeIterator; public class HtmlSourceGetter { private static HttpURLConnection con = null; private static BufferedInputStream bis = null; private static OutputStream out = null; public static void getSource(String url) { public static void parseHTML(String url, String keyword) { private static void processNodeList(NodeList list, String keyword) { public static void extractLinks(String url) { try { Parser parser = new Parser(url); parser.setEncoding(UTF-8); // frame filter NodeFilter frameFilter = new NodeFilter() { @Override public boolean accept(Node node) { if(node.getText().startsWith(frame src=)) { return true; } return false; } }; // image filter; NodeFilter imageFilter = new NodeClassFilter(ImageTag.class); // href filter; NodeFilter linkFilter = new NodeClassFilter(LinkTag.class); // link or image filter // OrFilter orFilter = new OrFilter(new NodeClassFilter(LinkTag.class),new NodeClassFilter(ImageTag.class)); // link or image or frame filter // OrFilter allFilt