在用htmlparser解析網(wǎng)頁(yè)內(nèi)容時(shí)，發(fā)現(xiàn)iframe沒有tag類，于是參照源碼自己增加并注冊(cè)使用。

1、創(chuàng)建iFrameTag類：

// HTMLParser Library - A java-based parser for HTML // http://htmlparser.org // Copyright (C) 2006 Somik Raha // // Revision Control Information // // $URL: https://svn.sourceforge.net/svnroot/htmlparser/trunk/parser/src/main/java/org/htmlparser/tags/FrameTag.java $ // $Author: derrickoswald $ // $Date: 2006-09-16 10:44:17 -0400 (Sat, 16 Sep 2006) $ // $Revision: 4 $ // // This library is free software; you can redistribute it and/or // modify it under the terms of the Common Public License; either // version 1.0 of the License, or (at your option) any later version. // // This library is distributed in the hope that it will be useful, // but WITHOUT ANY WARRANTY; without even the implied warranty of // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the // Common Public License for more details. // // You should have received a copy of the Common Public License // along with this library; if not, the license is available from // the Open Source Initiative (OSI) website: // http://opensource.org/licenses/cpl1.0.phppackage an;import org.htmlparser.nodes.TagNode;/*** Identifies a frame tag*/ public class iFrameTagextendsTagNode {/*** The set of names handled by this tag.*/private static final String[] mIds = new String[] {"iframe"};private static final String mEndTagEnders[] = { "iframe" }; /*** Create a new frame tag.*/public iFrameTag (){}/*** Return the set of names handled by this tag.* @return The names to be matched that create tags of this type.*/public String[] getIds (){return (mIds);}public String[] getEndTagEnders() { return mEndTagEnders; } /*** Returns the location of the frame.* @return The contents of the SRC attribute converted to an absolute URL.*/public String getFrameLocation (){String ret;ret = getAttribute ("SRC");if (null == ret)ret = "";else if (null != getPage ())ret = getPage ().getAbsoluteURL (ret);return (ret);}/*** Sets the location of the frame.* @param url The new frame location.*/public void setFrameLocation (String url){setAttribute ("SRC", url);}/*** Get the <code>NAME</code> attribute, if any.* @return The value of the <code>NAME</code> attribute,* or <code>null</code> if the attribute doesn't exist.*/public String getFrameName(){return (getAttribute ("NAME"));}/*** Return a string representation of the contents of this <code>FRAME</code> tag suitable for debugging.* @return A string with this tag's contents.*/public String toString(){return "FRAME TAG : Frame " +getFrameName() + " at "+getFrameLocation()+"; begins at : "+getStartPosition ()+"; ends at : "+getEndPosition ();} } 2、注冊(cè)并使用

package an;import java.net.URL; import java.util.ArrayList; import java.util.List; import org.htmlparser.NodeFilter; import org.htmlparser.Parser; import org.htmlparser.PrototypicalNodeFactory; import org.htmlparser.beans.StringBean; import org.htmlparser.filters.NodeClassFilter; import org.htmlparser.filters.OrFilter; import org.htmlparser.tags.FormTag; import org.htmlparser.tags.FrameSetTag; import org.htmlparser.tags.FrameTag; import org.htmlparser.tags.InputTag; import org.htmlparser.util.NodeList;

/*提取網(wǎng)頁(yè)html源碼中form\frame\iframe\input\frameset，查看表單參數(shù)* iframe要自定義tag類,iFrameTag.java* */public List<String> getHtml(String url) throws Exception{List<String> htmlList=new ArrayList<String>();//初始化//生成一個(gè)解析器對(duì)象，用網(wǎng)頁(yè)的 url 作為參數(shù) Parser parser = new Parser(url);if(parser.getEncoding().equals("ISO-8859-1"))parser.setEncoding("UTF-8"); //設(shè)置節(jié)點(diǎn)過濾NodeFilter formFilter = new NodeClassFilter(FormTag.class); NodeFilter frameFilter = new NodeClassFilter(FrameTag.class); NodeFilter inputFilter = new NodeClassFilter(InputTag.class);NodeFilter framesetFilter = new NodeClassFilter(FrameSetTag.class);//注冊(cè)iframetagPrototypicalNodeFactory p=new PrototypicalNodeFactory();p.registerTag(new iFrameTag()); parser.setNodeFactory(p);NodeFilter iframeFilter = new NodeClassFilter(iFrameTag.class);//添加過濾條件OrFilter lastFilter = new OrFilter(); lastFilter.setPredicates(new NodeFilter[] { formFilter,frameFilter,inputFilter,framesetFilter ,iframeFilter}); NodeList nodeList = parser.parse(lastFilter); for(int i = 0; i <= nodeList.size(); i++) { if(nodeList.elementAt(i) instanceof FormTag) { FormTag tag = (FormTag) nodeList.elementAt(i); htmlList.add(tag.getText()); } if(nodeList.elementAt(i) instanceof InputTag) { InputTag tag = (InputTag) nodeList.elementAt(i); htmlList.add(tag.getText()); }if(nodeList.elementAt(i) instanceof FrameTag){ FrameTag tag = (FrameTag) nodeList.elementAt(i); htmlList.add(tag.getText()); } if(nodeList.elementAt(i) instanceof FrameSetTag){ FrameSetTag tag = (FrameSetTag) nodeList.elementAt(i); htmlList.add(tag.getText());}if(nodeList.elementAt(i) instanceof iFrameTag){ iFrameTag tag = (iFrameTag) nodeList.elementAt(i); htmlList.add(tag.getText());}} return htmlList;} public static void main(String[]args) throws Exception{UrlParser fd=new UrlParser(); List<String> list=fd.getHtml("http://mail.189.cn");for(int i=0;i<list.size();i++){System.out.println(list.get(i));}}

總結(jié)

以上是生活随笔為你收集整理的htmlparser新建tag类(以iframe标签为例）的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。