⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 linkregexfilter.java

📁 本程序用于对页面信息进行提取并分析
💻 JAVA
字号:
// HTMLParser Library $Name: v1_6_20060319 $ - A java-based parser for HTML// http://sourceforge.org/projects/htmlparser// Copyright (C) 2005 John Derrick//// Revision Control Information//// $Source: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/filters/LinkRegexFilter.java,v $// $Author: derrickoswald $// $Date: 2005/09/18 23:40:44 $// $Revision: 1.4 $//// This library is free software; you can redistribute it and/or// modify it under the terms of the GNU Lesser General Public// License as published by the Free Software Foundation; either// version 2.1 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 GNU// Lesser General Public License for more details.//// You should have received a copy of the GNU Lesser General Public// License along with this library; if not, write to the Free Software// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA//package org.htmlparser.filters;import java.util.regex.Matcher;import java.util.regex.Pattern;import org.htmlparser.Node;import org.htmlparser.NodeFilter;import org.htmlparser.tags.LinkTag;/** * This class accepts tags of class LinkTag that contain a link matching a given * regex pattern. Use this filter to extract LinkTag nodes with URLs that match * the desired regex pattern. */public class LinkRegexFilter implements NodeFilter{    /**     * The regular expression to use on the link.     */    protected Pattern mRegex;    /**     * Creates a LinkRegexFilter that accepts LinkTag nodes containing     * a URL that matches the supplied regex pattern.     * The match is case insensitive.     * @param regexPattern The pattern to match.     */    public LinkRegexFilter (String regexPattern)    {        this (regexPattern, true);    }    /**     * Creates a LinkRegexFilter that accepts LinkTag nodes containing     * a URL that matches the supplied regex pattern.     * @param regexPattern The regex pattern to match.     * @param caseSensitive Specifies case sensitivity for the matching process.     */    public LinkRegexFilter (String regexPattern, boolean caseSensitive)    {        if (caseSensitive)            mRegex = Pattern.compile (regexPattern);        else            mRegex = Pattern.compile (regexPattern,                Pattern.CASE_INSENSITIVE | Pattern.UNICODE_CASE);    }    /**     * Accept nodes that are a LinkTag and have a URL     * that matches the regex pattern supplied in the constructor.     * @param node The node to check.     * @return <code>true</code> if the node is a link with the pattern.     */    public boolean accept (Node node)    {        boolean ret;        ret = false;        if (LinkTag.class.isAssignableFrom (node.getClass ()))        {            String link = ((LinkTag)node).getLink ();            Matcher matcher = mRegex.matcher (link);            ret = matcher.find ();        }        return (ret);    }}

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -