📄 regexpcsslinkextractor.html
字号:
<!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=ISO-8859-1" /><title>RegexpCSSLinkExtractor xref</title><link type="text/css" rel="stylesheet" href="../../../stylesheet.css" /></head><body><pre><a name="1" href="#1">1</a> <em class="comment">/*</em><a name="2" href="#2">2</a> <em class="comment"> * ExtractorCSS</em><a name="3" href="#3">3</a> <em class="comment"> *</em><a name="4" href="#4">4</a> <em class="comment"> * $Id: RegexpCSSLinkExtractor.java,v 1.5 2005/11/11 22:29:53 gojomo Exp $</em><a name="5" href="#5">5</a> <em class="comment"> *</em><a name="6" href="#6">6</a> <em class="comment"> * Created on Mar 29, 2005</em><a name="7" href="#7">7</a> <em class="comment"> *</em><a name="8" href="#8">8</a> <em class="comment"> * Copyright (C) 2005 Internet Archive.</em><a name="9" href="#9">9</a> <em class="comment"> *</em><a name="10" href="#10">10</a> <em class="comment"> * This file is part of the Heritrix web crawler (crawler.archive.org).</em><a name="11" href="#11">11</a> <em class="comment"> *</em><a name="12" href="#12">12</a> <em class="comment"> * Heritrix is free software; you can redistribute it and/or modify</em><a name="13" href="#13">13</a> <em class="comment"> * it under the terms of the GNU Lesser Public License as published by</em><a name="14" href="#14">14</a> <em class="comment"> * the Free Software Foundation; either version 2.1 of the License, or</em><a name="15" href="#15">15</a> <em class="comment"> * any later version.</em><a name="16" href="#16">16</a> <em class="comment"> *</em><a name="17" href="#17">17</a> <em class="comment"> * Heritrix is distributed in the hope that it will be useful,</em><a name="18" href="#18">18</a> <em class="comment"> * but WITHOUT ANY WARRANTY; without even the implied warranty of</em><a name="19" href="#19">19</a> <em class="comment"> * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</em><a name="20" href="#20">20</a> <em class="comment"> * GNU Lesser Public License for more details.</em><a name="21" href="#21">21</a> <em class="comment"> *</em><a name="22" href="#22">22</a> <em class="comment"> * You should have received a copy of the GNU Lesser Public License</em><a name="23" href="#23">23</a> <em class="comment"> * along with Heritrix; if not, write to the Free Software</em><a name="24" href="#24">24</a> <em class="comment"> * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA</em><a name="25" href="#25">25</a> <em class="comment"> */</em><a name="26" href="#26">26</a> <a name="27" href="#27">27</a> <strong>package</strong> <a href="../../../org/archive/extractor/package-summary.html">org.archive.extractor</a>;<a name="28" href="#28">28</a> <a name="29" href="#29">29</a> <strong>import</strong> java.util.logging.Logger;<a name="30" href="#30">30</a> <strong>import</strong> java.util.regex.Matcher;<a name="31" href="#31">31</a> <a name="32" href="#32">32</a> <strong>import</strong> org.apache.commons.httpclient.URIException;<a name="33" href="#33">33</a> <strong>import</strong> org.archive.crawler.extractor.Link;<a name="34" href="#34">34</a> <strong>import</strong> org.archive.net.UURIFactory;<a name="35" href="#35">35</a> <strong>import</strong> org.archive.util.DevUtils;<a name="36" href="#36">36</a> <strong>import</strong> org.archive.util.TextUtils;<a name="37" href="#37">37</a> <a name="38" href="#38">38</a> <em>/**<em>*</em></em><a name="39" href="#39">39</a> <em> * This extractor is parsing URIs from CSS type files.</em><a name="40" href="#40">40</a> <em> * The format of a CSS URL value is 'url(' followed by optional white space</em><a name="41" href="#41">41</a> <em> * followed by an optional single quote (') or double quote (") character</em><a name="42" href="#42">42</a> <em> * followed by the URL itself followed by an optional single quote (') or</em><a name="43" href="#43">43</a> <em> * double quote (") character followed by optional white space followed by ')'.</em><a name="44" href="#44">44</a> <em> * Parentheses, commas, white space characters, single quotes (') and double</em><a name="45" href="#45">45</a> <em> * quotes (") appearing in a URL must be escaped with a backslash:</em><a name="46" href="#46">46</a> <em> * '\(', '\)', '\,'. Partial URLs are interpreted relative to the source of</em><a name="47" href="#47">47</a> <em> * the style sheet, not relative to the document. <a href="<a href="http://www.w3.org/TR/REC-CSS1" target="alexandria_uri">http://www.w3.org/TR/REC-CSS1</a>#url"></em><a name="48" href="#48">48</a> <em> * Source: www.w3.org</a></em><a name="49" href="#49">49</a> <em> *</em><a name="50" href="#50">50</a> <em> * ROUGH DRAFT IN PROGRESS / incomplete... untested... major changes likely</em><a name="51" href="#51">51</a> <em> *</em><a name="52" href="#52">52</a> <em> * @author igor gojomo</em><a name="53" href="#53">53</a> <em> *</em><a name="54" href="#54">54</a> <em> **/</em><a name="55" href="#55">55</a> <a name="56" href="#56">56</a> <strong>public</strong> <strong>class</strong> <a href="../../../org/archive/extractor/RegexpCSSLinkExtractor.html">RegexpCSSLinkExtractor</a> <strong>extends</strong> <a href="../../../org/archive/extractor/CharSequenceLinkExtractor.html">CharSequenceLinkExtractor</a> {<a name="57" href="#57">57</a> <strong>private</strong> <strong>static</strong> Logger logger =<a name="58" href="#58">58</a> Logger.getLogger(RegexpCSSLinkExtractor.<strong>class</strong>.getName());<a name="59" href="#59">59</a> <a name="60" href="#60">60</a> <strong>private</strong> <strong>static</strong> String ESCAPED_AMP = <span class="string">"&amp"</span>;<a name="61" href="#61">61</a> <em class="comment">// CSS escapes: "Parentheses, commas, whitespace characters, single</em><a name="62" href="#62">62</a> <em class="comment">// quotes (') and double quotes (") appearing in a URL must be</em><a name="63" href="#63">63</a> <em class="comment">// escaped with a backslash"</em><a name="64" href="#64">64</a> <strong>static</strong> <strong>final</strong> String CSS_BACKSLASH_ESCAPE = <span class="string">"////([,'\"//(//)//s])"</span>;<a name="65" href="#65">65</a> <a name="66" href="#66">66</a> <strong>protected</strong> Matcher uris;<a name="67" href="#67">67</a> <a name="68" href="#68">68</a> <em>/**<em>*</em></em><a name="69" href="#69">69</a> <em> * CSS URL extractor pattern.</em><a name="70" href="#70">70</a> <em> *</em><a name="71" href="#71">71</a> <em> * This pattern extracts URIs for CSS files</em><a name="72" href="#72">72</a> <em> **/</em><a name="73" href="#73">73</a> <strong>static</strong> <strong>final</strong> String CSS_URI_EXTRACTOR =<a name="74" href="#74">74</a> <span class="string">"(?:@import (?:url[(]|)|url[(])//s*([//\"\']?)([^//\"\'].*?)//1//s*[);]"</span>;<a name="75" href="#75">75</a> <a name="76" href="#76">76</a> <strong>protected</strong> <strong>boolean</strong> findNextLink() {<a name="77" href="#77">77</a> <strong>if</strong> (uris == <strong>null</strong>) {<a name="78" href="#78">78</a> uris = TextUtils.getMatcher(CSS_URI_EXTRACTOR, sourceContent);<a name="79" href="#79">79</a> <em class="comment">// NOTE: this matcher can't be recycled in this method because</em><a name="80" href="#80">80</a> <em class="comment">// it is reused on rentry</em><a name="81" href="#81">81</a> }<a name="82" href="#82">82</a> String cssUri;<a name="83" href="#83">83</a> <strong>try</strong> {<a name="84" href="#84">84</a> <strong>while</strong> (uris.find()) {<a name="85" href="#85">85</a> cssUri = uris.group(2);<a name="86" href="#86">86</a> <em class="comment">// TODO: Escape more HTML Entities.</em><a name="87" href="#87">87</a> cssUri = TextUtils.replaceAll(ESCAPED_AMP, cssUri, <span class="string">"&"</span>);<a name="88" href="#88">88</a> <em class="comment">// Remove backslashes when used as escape character in CSS URL</em><a name="89" href="#89">89</a> cssUri = TextUtils.replaceAll(CSS_BACKSLASH_ESCAPE, cssUri, <span class="string">"$1"</span>);<a name="90" href="#90">90</a> <em class="comment">// TODO: handle relative URIs?</em><a name="91" href="#91">91</a> <strong>try</strong> {<a name="92" href="#92">92</a> <a href="../../../org/archive/crawler/extractor/Link.html">Link</a> link = <strong>new</strong> <a href="../../../org/archive/crawler/extractor/Link.html">Link</a>(source, UURIFactory.getInstance(base,<a name="93" href="#93">93</a> cssUri), Link.EMBED_MISC, Link.EMBED_HOP);<a name="94" href="#94">94</a> next.addLast(link);<a name="95" href="#95">95</a> } <strong>catch</strong> (URIException e) {<a name="96" href="#96">96</a> extractErrorListener.noteExtractError(e, source, cssUri);<a name="97" href="#97">97</a> }<a name="98" href="#98">98</a> <strong>return</strong> <strong>true</strong>;<a name="99" href="#99">99</a> }<a name="100" href="#100">100</a> } <strong>catch</strong> (StackOverflowError e) {<a name="101" href="#101">101</a> DevUtils.warnHandle(e, <span class="string">"RegexpCSSLinkExtractor StackOverflowError"</span>);<a name="102" href="#102">102</a> }<a name="103" href="#103">103</a> <strong>return</strong> false;<a name="104" href="#104">104</a> }<a name="105" href="#105">105</a> <a name="106" href="#106">106</a> <strong>public</strong> <strong>void</strong> reset() {<a name="107" href="#107">107</a> <strong>super</strong>.reset();<a name="108" href="#108">108</a> TextUtils.recycleMatcher(uris);<a name="109" href="#109">109</a> uris = <strong>null</strong>;<a name="110" href="#110">110</a> }<a name="111" href="#111">111</a> <a name="112" href="#112">112</a> <strong>protected</strong> <strong>static</strong> <a href="../../../org/archive/extractor/CharSequenceLinkExtractor.html">CharSequenceLinkExtractor</a> newDefaultInstance() {<a name="113" href="#113">113</a> <strong>return</strong> <strong>new</strong> <a href="../../../org/archive/extractor/RegexpCSSLinkExtractor.html">RegexpCSSLinkExtractor</a>();<a name="114" href="#114">114</a> }<a name="115" href="#115">115</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
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -