📄 extractorhtmltest.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=UTF-8" /><title>ExtractorHTMLTest xref</title><link type="text/css" rel="stylesheet" href="../../../../stylesheet.css" /></head><body><div id="overview"><a href="../../../../../apidocs/org/archive/crawler/extractor/ExtractorHTMLTest.html">View Javadoc</a></div><pre><a name="1" href="#1">1</a> <em class="comment">/*<em class="comment"> ExtractorHTMLTest</em></em><a name="2" href="#2">2</a> <em class="comment"> *</em><a name="3" href="#3">3</a> <em class="comment"> * Created on May 19, 2004</em><a name="4" href="#4">4</a> <em class="comment"> *</em><a name="5" href="#5">5</a> <em class="comment"> * Copyright (C) 2004 Internet Archive.</em><a name="6" href="#6">6</a> <em class="comment"> *</em><a name="7" href="#7">7</a> <em class="comment"> * This file is part of the Heritrix web crawler (crawler.archive.org).</em><a name="8" href="#8">8</a> <em class="comment"> *</em><a name="9" href="#9">9</a> <em class="comment"> * Heritrix is free software; you can redistribute it and/or modify</em><a name="10" href="#10">10</a> <em class="comment"> * it under the terms of the GNU Lesser Public License as published by</em><a name="11" href="#11">11</a> <em class="comment"> * the Free Software Foundation; either version 2.1 of the License, or</em><a name="12" href="#12">12</a> <em class="comment"> * any later version.</em><a name="13" href="#13">13</a> <em class="comment"> *</em><a name="14" href="#14">14</a> <em class="comment"> * Heritrix is distributed in the hope that it will be useful,</em><a name="15" href="#15">15</a> <em class="comment"> * but WITHOUT ANY WARRANTY; without even the implied warranty of</em><a name="16" href="#16">16</a> <em class="comment"> * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</em><a name="17" href="#17">17</a> <em class="comment"> * GNU Lesser Public License for more details.</em><a name="18" href="#18">18</a> <em class="comment"> *</em><a name="19" href="#19">19</a> <em class="comment"> * You should have received a copy of the GNU Lesser Public License</em><a name="20" href="#20">20</a> <em class="comment"> * along with Heritrix; if not, write to the Free Software</em><a name="21" href="#21">21</a> <em class="comment"> * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA</em><a name="22" href="#22">22</a> <em class="comment"> */</em><a name="23" href="#23">23</a> <strong>package</strong> <a href="../../../../org/archive/crawler/extractor/package-summary.html">org.archive.crawler.extractor</a>;<a name="24" href="#24">24</a> <a name="25" href="#25">25</a> <strong>import</strong> java.io.File;<a name="26" href="#26">26</a> <strong>import</strong> java.io.FileOutputStream;<a name="27" href="#27">27</a> <strong>import</strong> java.io.IOException;<a name="28" href="#28">28</a> <strong>import</strong> java.net.URL;<a name="29" href="#29">29</a> <strong>import</strong> java.util.Collection;<a name="30" href="#30">30</a> <strong>import</strong> java.util.Iterator;<a name="31" href="#31">31</a> <a name="32" href="#32">32</a> <strong>import</strong> javax.management.AttributeNotFoundException;<a name="33" href="#33">33</a> <strong>import</strong> javax.management.InvalidAttributeValueException;<a name="34" href="#34">34</a> <strong>import</strong> javax.management.MBeanException;<a name="35" href="#35">35</a> <strong>import</strong> javax.management.ReflectionException;<a name="36" href="#36">36</a> <a name="37" href="#37">37</a> <strong>import</strong> org.apache.commons.collections.CollectionUtils;<a name="38" href="#38">38</a> <strong>import</strong> org.apache.commons.collections.Predicate;<a name="39" href="#39">39</a> <strong>import</strong> org.apache.commons.httpclient.URIException;<a name="40" href="#40">40</a> <strong>import</strong> org.archive.crawler.datamodel.CoreAttributeConstants;<a name="41" href="#41">41</a> <strong>import</strong> org.archive.crawler.datamodel.CrawlOrder;<a name="42" href="#42">42</a> <strong>import</strong> org.archive.crawler.datamodel.CrawlURI;<a name="43" href="#43">43</a> <strong>import</strong> org.archive.crawler.settings.MapType;<a name="44" href="#44">44</a> <strong>import</strong> org.archive.crawler.settings.SettingsHandler;<a name="45" href="#45">45</a> <strong>import</strong> org.archive.crawler.settings.XMLSettingsHandler;<a name="46" href="#46">46</a> <strong>import</strong> org.archive.net.UURI;<a name="47" href="#47">47</a> <strong>import</strong> org.archive.net.UURIFactory;<a name="48" href="#48">48</a> <strong>import</strong> org.archive.util.HttpRecorder;<a name="49" href="#49">49</a> <strong>import</strong> org.archive.util.TmpDirTestCase;<a name="50" href="#50">50</a> <a name="51" href="#51">51</a> <a name="52" href="#52">52</a> <em>/**<em>*</em></em><a name="53" href="#53">53</a> <em> * Test html extractor.</em><a name="54" href="#54">54</a> <em> *</em><a name="55" href="#55">55</a> <em> * @author stack</em><a name="56" href="#56">56</a> <em> * @version $Revision: 1.20 $, $Date: 2005/09/22 23:03:11 $</em><a name="57" href="#57">57</a> <em> */</em><a name="58" href="#58">58</a> <strong>public</strong> <strong>class</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorHTMLTest.html">ExtractorHTMLTest</a><a name="59" href="#59">59</a> <strong>extends</strong> <a href="../../../../org/archive/util/TmpDirTestCase.html">TmpDirTestCase</a><a name="60" href="#60">60</a> implements <a href="../../../../org/archive/crawler/datamodel/CoreAttributeConstants.html">CoreAttributeConstants</a> {<a name="61" href="#61">61</a> <strong>private</strong> <strong>final</strong> String ARCHIVE_DOT_ORG = <span class="string">"archive.org"</span>;<a name="62" href="#62">62</a> <strong>private</strong> <strong>final</strong> String LINK_TO_FIND = <span class="string">"http://www.hewlett.org/"</span>;<a name="63" href="#63">63</a> <strong>private</strong> <a href="../../../../org/archive/util/HttpRecorder.html">HttpRecorder</a> recorder = <strong>null</strong>;<a name="64" href="#64">64</a> <strong>private</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorHTML.html">ExtractorHTML</a> extractor = <strong>null</strong>;<a name="65" href="#65">65</a> <a name="66" href="#66">66</a> <strong>protected</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorHTML.html">ExtractorHTML</a> createExtractor()<a name="67" href="#67">67</a> throws InvalidAttributeValueException, AttributeNotFoundException,<a name="68" href="#68">68</a> MBeanException, ReflectionException {<a name="69" href="#69">69</a> <em class="comment">// Hack in a settings handler. Do this by adding this extractor</em><a name="70" href="#70">70</a> <em class="comment">// to the order file (I'm adding it to a random MapType; seemingly</em><a name="71" href="#71">71</a> <em class="comment">// can only add to MapTypes post-construction). This takes care</em><a name="72" href="#72">72</a> <em class="comment">// of setting a valid SettingsHandler into the ExtractorHTML (This</em><a name="73" href="#73">73</a> <em class="comment">// shouldn't be so difficult). Of note, the order file below is</em><a name="74" href="#74">74</a> <em class="comment">// not written to disk.</em><a name="75" href="#75">75</a> <strong>final</strong> String name = <strong>this</strong>.getClass().getName();<a name="76" href="#76">76</a> <a href="../../../../org/archive/crawler/settings/SettingsHandler.html">SettingsHandler</a> handler = <strong>new</strong> <a href="../../../../org/archive/crawler/settings/XMLSettingsHandler.html">XMLSettingsHandler</a>(<a name="77" href="#77">77</a> <strong>new</strong> File(getTmpDir(), name + <span class="string">".order.xml"</span>));<a name="78" href="#78">78</a> handler.initialize();<a name="79" href="#79">79</a> <strong>return</strong> (ExtractorHTML)((MapType)handler.getOrder().<a name="80" href="#80">80</a> getAttribute(CrawlOrder.ATTR_RULES)).addElement(handler.<a name="81" href="#81">81</a> getSettingsObject(<strong>null</strong>), <strong>new</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorHTML.html">ExtractorHTML</a>(name));<a name="82" href="#82">82</a> }<a name="83" href="#83">83</a> <a name="84" href="#84">84</a> <strong>protected</strong> <strong>void</strong> setUp() throws Exception {<a name="85" href="#85">85</a> <strong>super</strong>.setUp();<a name="86" href="#86">86</a> <strong>this</strong>.extractor = createExtractor();<a name="87" href="#87">87</a> <strong>final</strong> <strong>boolean</strong> USE_NET = false;<a name="88" href="#88">88</a> URL url = <strong>null</strong>;<a name="89" href="#89">89</a> <strong>if</strong> (USE_NET) {<a name="90" href="#90">90</a> url = <strong>new</strong> URL(<span class="string">"http://"</span> + <strong>this</strong>.ARCHIVE_DOT_ORG);<a name="91" href="#91">91</a> } <strong>else</strong> {<a name="92" href="#92">92</a> File f = <strong>new</strong> File(getTmpDir(), <strong>this</strong>.ARCHIVE_DOT_ORG + <span class="string">".html"</span>);<a name="93" href="#93">93</a> url = <strong>new</strong> URL(<span class="string">"file://"</span> + f.getAbsolutePath());<a name="94" href="#94">94</a> FileOutputStream fos = <strong>new</strong> FileOutputStream(f);<a name="95" href="#95">95</a> fos.write((<span class="string">"<html><head><title>test</title><body>"</span> +<a name="96" href="#96">96</a> <span class="string">"<a href="</span> + <strong>this</strong>.LINK_TO_FIND + <span class="string">">Hewlett Foundation</a>"</span> +<a name="97" href="#97">97</a> <span class="string">"</body></html>"</span>).getBytes());<a name="98" href="#98">98</a> fos.flush();<a name="99" href="#99">99</a> fos.close();<a name="100" href="#100">100</a> }<a name="101" href="#101">101</a> <strong>this</strong>.recorder = HttpRecorder.wrapInputStreamWithHttpRecord(getTmpDir(),⌨️ 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 + -