stripextraslashes.html
来自「网络爬虫开源代码」· HTML 代码 · 共 60 行
HTML
60 行
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"><html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head><meta http-equiv="content-type" content="text/html; charset=UTF-8" /><title>StripExtraSlashes xref</title><link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" /></head><body><div id="overview"><a href="../../../../../../apidocs/org/archive/crawler/url/canonicalize/StripExtraSlashes.html">View Javadoc</a></div><pre><a name="1" href="#1">1</a> <em class="comment">/*</em><a name="2" href="#2">2</a> <em class="comment"> * Created on 2006-aug-25</em><a name="3" href="#3">3</a> <em class="comment"> *</em><a name="4" href="#4">4</a> <em class="comment"> * Copyright (C) 2006 Royal Library of Sweden.</em><a name="5" href="#5">5</a> <em class="comment"> *</em><a name="6" href="#6">6</a> <em class="comment"> * This program is free software; you can redistribute it and/or</em><a name="7" href="#7">7</a> <em class="comment"> * modify it under the terms of the GNU Lesser General Public License</em><a name="8" href="#8">8</a> <em class="comment"> * as published by the Free Software Foundation; either version 2</em><a name="9" href="#9">9</a> <em class="comment"> * of the License, or (at your option) any later version.</em><a name="10" href="#10">10</a> <em class="comment"> *</em><a name="11" href="#11">11</a> <em class="comment"> * This program is distributed in the hope that it will be useful,</em><a name="12" href="#12">12</a> <em class="comment"> * but WITHOUT ANY WARRANTY; without even the implied warranty of</em><a name="13" href="#13">13</a> <em class="comment"> * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</em><a name="14" href="#14">14</a> <em class="comment"> * GNU Lesser General Public License for more details.</em><a name="15" href="#15">15</a> <em class="comment"> *</em><a name="16" href="#16">16</a> <em class="comment"> * You should have received a copy of the GNU Lesser General Public License</em><a name="17" href="#17">17</a> <em class="comment"> * along with this program; if not, write to the Free Software</em><a name="18" href="#18">18</a> <em class="comment"> * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.</em><a name="19" href="#19">19</a> <em class="comment"> */</em><a name="20" href="#20">20</a> <strong>package</strong> <a href="../../../../../org/archive/crawler/url/canonicalize/package-summary.html">org.archive.crawler.url.canonicalize</a>;<a name="21" href="#21">21</a> <a name="22" href="#22">22</a> <strong>import</strong> java.util.regex.Matcher;<a name="23" href="#23">23</a> <strong>import</strong> java.util.regex.Pattern;<a name="24" href="#24">24</a> <a name="25" href="#25">25</a> <strong>public</strong> <strong>class</strong> <a href="../../../../../org/archive/crawler/url/canonicalize/StripExtraSlashes.html">StripExtraSlashes</a> <strong>extends</strong> <a href="../../../../../org/archive/crawler/url/canonicalize/BaseRule.html">BaseRule</a> {<a name="26" href="#26">26</a> <a name="27" href="#27">27</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String DESCRIPTION = <a name="28" href="#28">28</a> <span class="string">"Strip any extra slashes, '/', found in the path. "</span> +<a name="29" href="#29">29</a> <span class="string">"Use this rule to equate 'http://www.archive.org//A//B/index.html' and "</span> +<a name="30" href="#30">30</a> <span class="string">"'http://www.archive.org/A/B/index.html'."</span>;<a name="31" href="#31">31</a> <a name="32" href="#32">32</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> Pattern REGEX = Pattern.compile(<span class="string">"(^https?://.*?)//+(.*)"</span>);<a name="33" href="#33">33</a> <a name="34" href="#34">34</a> <strong>public</strong> <a href="../../../../../org/archive/crawler/url/canonicalize/StripExtraSlashes.html">StripExtraSlashes</a>(String name) {<a name="35" href="#35">35</a> <strong>super</strong>(name, DESCRIPTION);<a name="36" href="#36">36</a> }<a name="37" href="#37">37</a> <a name="38" href="#38">38</a> <strong>public</strong> String canonicalize(String url, Object context) {<a name="39" href="#39">39</a> Matcher matcher = REGEX.matcher(url);<a name="40" href="#40">40</a> <strong>while</strong> (matcher.matches()) {<a name="41" href="#41">41</a> url = matcher.group(1) + <span class="string">"/"</span> + matcher.group(2);<a name="42" href="#42">42</a> matcher = REGEX.matcher(url);<a name="43" href="#43">43</a> }<a name="44" href="#44">44</a> <strong>return</strong> url;<a name="45" href="#45">45</a> }<a name="46" href="#46">46</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?