📄 extractoruniversal.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>ExtractorUniversal xref</title><link type="text/css" rel="stylesheet" href="../../../../stylesheet.css" /></head><body><div id="overview"><a href="../../../../../apidocs/org/archive/crawler/extractor/ExtractorUniversal.html">View Javadoc</a></div><pre><a name="1" href="#1">1</a> <em class="comment">/*<em class="comment"> Copyright (C) 2003 Internet Archive.</em></em><a name="2" href="#2">2</a> <em class="comment"> *</em><a name="3" href="#3">3</a> <em class="comment"> * This file is part of the Heritrix web crawler (crawler.archive.org).</em><a name="4" href="#4">4</a> <em class="comment"> *</em><a name="5" href="#5">5</a> <em class="comment"> * Heritrix is free software; you can redistribute it and/or modify</em><a name="6" href="#6">6</a> <em class="comment"> * it under the terms of the GNU Lesser Public License as published by</em><a name="7" href="#7">7</a> <em class="comment"> * the Free Software Foundation; either version 2.1 of the License, or</em><a name="8" href="#8">8</a> <em class="comment"> * any later version.</em><a name="9" href="#9">9</a> <em class="comment"> *</em><a name="10" href="#10">10</a> <em class="comment"> * Heritrix is distributed in the hope that it will be useful,</em><a name="11" href="#11">11</a> <em class="comment"> * but WITHOUT ANY WARRANTY; without even the implied warranty of</em><a name="12" href="#12">12</a> <em class="comment"> * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</em><a name="13" href="#13">13</a> <em class="comment"> * GNU Lesser Public License for more details.</em><a name="14" href="#14">14</a> <em class="comment"> *</em><a name="15" href="#15">15</a> <em class="comment"> * You should have received a copy of the GNU Lesser Public License</em><a name="16" href="#16">16</a> <em class="comment"> * along with Heritrix; if not, write to the Free Software</em><a name="17" href="#17">17</a> <em class="comment"> * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA</em><a name="18" href="#18">18</a> <em class="comment"> *</em><a name="19" href="#19">19</a> <em class="comment"> * Created on Jan 15, 2004</em><a name="20" href="#20">20</a> <em class="comment"> *</em><a name="21" href="#21">21</a> <em class="comment"> */</em><a name="22" href="#22">22</a> <strong>package</strong> <a href="../../../../org/archive/crawler/extractor/package-summary.html">org.archive.crawler.extractor</a>;<a name="23" href="#23">23</a> <a name="24" href="#24">24</a> <strong>import</strong> java.io.IOException;<a name="25" href="#25">25</a> <strong>import</strong> java.io.InputStream;<a name="26" href="#26">26</a> <strong>import</strong> java.util.logging.Logger;<a name="27" href="#27">27</a> <strong>import</strong> java.util.regex.Matcher;<a name="28" href="#28">28</a> <a name="29" href="#29">29</a> <strong>import</strong> javax.management.AttributeNotFoundException;<a name="30" href="#30">30</a> <a name="31" href="#31">31</a> <strong>import</strong> org.archive.crawler.datamodel.CoreAttributeConstants;<a name="32" href="#32">32</a> <strong>import</strong> org.archive.crawler.datamodel.CrawlURI;<a name="33" href="#33">33</a> <strong>import</strong> org.archive.crawler.settings.SimpleType;<a name="34" href="#34">34</a> <strong>import</strong> org.archive.crawler.settings.Type;<a name="35" href="#35">35</a> <strong>import</strong> org.archive.net.UURI;<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> * A last ditch extractor that will look at the raw byte code and try to extract</em><a name="40" href="#40">40</a> <em> * anything that <i>looks</i> like a link.</em><a name="41" href="#41">41</a> <em> *</em><a name="42" href="#42">42</a> <em> * If used, it should always be specified as the last link extractor in the</em><a name="43" href="#43">43</a> <em> * order file.</em><a name="44" href="#44">44</a> <em> * <p></em><a name="45" href="#45">45</a> <em> * To accomplish this it will scan through the bytecode and try and build up</em><a name="46" href="#46">46</a> <em> * strings of consecutive bytes that all represent characters that are valid</em><a name="47" href="#47">47</a> <em> * in a URL (see #isURLableChar(int) for details).</em><a name="48" href="#48">48</a> <em> * Once it hits the end of such a string (i.e. finds a character that</em><a name="49" href="#49">49</a> <em> * should not be in a URL) it will try to determine if it has found a URL.</em><a name="50" href="#50">50</a> <em> * This is done be seeing if the string is an IP address prefixed with</em><a name="51" href="#51">51</a> <em> * http(s):// or contains a dot followed by a Top Level Domain and end of</em><a name="52" href="#52">52</a> <em> * string or a slash.</em><a name="53" href="#53">53</a> <em> *</em><a name="54" href="#54">54</a> <em> * @author Kristinn Sigurdsson</em><a name="55" href="#55">55</a> <em> */</em><a name="56" href="#56">56</a> <strong>public</strong> <strong>class</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorUniversal.html">ExtractorUniversal</a> <strong>extends</strong> <a href="../../../../org/archive/crawler/extractor/Extractor.html">Extractor</a><a name="57" href="#57">57</a> implements <a href="../../../../org/archive/crawler/datamodel/CoreAttributeConstants.html">CoreAttributeConstants</a> {<a name="58" href="#58">58</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> Logger logger =<a name="59" href="#59">59</a> Logger.getLogger(ExtractorUniversal.<strong>class</strong>.getName());<a name="60" href="#60">60</a> <a name="61" href="#61">61</a> <strong>private</strong> <strong>static</strong> String ATTR_MAX_DEPTH_BYTES = <span class="string">"max-depth-bytes"</span>;<a name="62" href="#62">62</a> <a name="63" href="#63">63</a> <em>/**<em>* Default value for how far into an unknown document we should scan</em></em><a name="64" href="#64">64</a> <em> * - 10k. A value of 0 or lower will disable this.</em><a name="65" href="#65">65</a> <em> */</em><a name="66" href="#66">66</a> <strong>private</strong> <strong>static</strong> <strong>long</strong> DEFAULT_MAX_DEPTH_BYTES = 10240;<a name="67" href="#67">67</a> <a name="68" href="#68">68</a> <strong>private</strong> <strong>static</strong> String ATTR_MAX_URL_LENGTH = <span class="string">"max-url-length"</span>;<a name="69" href="#69">69</a> <a name="70" href="#70">70</a> <em>/**<em>* Maximum length for a URI that we try to match.*/</em></em><a name="71" href="#71">71</a> <strong>private</strong> <strong>static</strong> <strong>long</strong> DEFAULT_MAX_URL_LENGTH = UURI.MAX_URL_LENGTH;<a name="72" href="#72">72</a> <a name="73" href="#73">73</a> <em>/**<em>*</em></em><a name="74" href="#74">74</a> <em> * Matches any string that begins with <a href="http://" target="alexandria_uri">http://</a> or https:// followed by</em><a name="75" href="#75">75</a> <em> * something that looks like an ip address (four numbers, none longer then</em><a name="76" href="#76">76</a> <em> * 3 chars seperated by 3 dots). Does <b>not</b> ensure that the numbers are</em><a name="77" href="#77">77</a> <em> * each in the range 0-255.</em><a name="78" href="#78">78</a> <em> */</em><a name="79" href="#79">79</a> <strong>static</strong> <strong>final</strong> String IP_ADDRESS =<a name="80" href="#80">80</a> <span class="string">"((http://)|(https://))(//d(//d)?(//d)?//.//d(//d)?(//d)?//.//d(//d)?(//d)?//.//d(//d)?(//d)?)"</span>;<a name="81" href="#81">81</a> <a name="82" href="#82">82</a> <em>/**<em>*</em></em><a name="83" href="#83">83</a> <em> * Matches any string that begins with a TLD (no .) followed by a '/' slash</em><a name="84" href="#84">84</a> <em> * or end of string. If followed by slash then nothing after the slash is</em><a name="85" href="#85">85</a> <em> * of consequence.</em><a name="86" href="#86">86</a> <em> */</em><a name="87" href="#87">87</a> <strong>public</strong> <strong>static</strong> <strong>final</strong> String TLDs =<a name="88" href="#88">88</a> <span class="string">"(ac(/.*)?)"</span> <em class="comment">// ac Ascension Island</em><a name="89" href="#89">89</a> + <span class="string">"|(ad(/.*)?)"</span> <em class="comment">// ad Andorra</em><a name="90" href="#90">90</a> + <span class="string">"|(ae(/.*)?)"</span> <em class="comment">// ae United Arab Emirates</em><a name="91" href="#91">91</a> + <span class="string">"|(af(/.*)?)"</span> <em class="comment">// af Afghanistan</em><a name="92" href="#92">92</a> + <span class="string">"|(ag(/.*)?)"</span> <em class="comment">// ag Antigua and Barbuda</em><a name="93" href="#93">93</a> + <span class="string">"|(ai(/.*)?)"</span> <em class="comment">// ai Anguilla</em><a name="94" href="#94">94</a> + <span class="string">"|(al(/.*)?)"</span> <em class="comment">// al Albania</em><a name="95" href="#95">95</a> + <span class="string">"|(am(/.*)?)"</span> <em class="comment">// am Armenia</em><a name="96" href="#96">96</a> + <span class="string">"|(an(/.*)?)"</span> <em class="comment">// an Netherlands Antilles</em><a name="97" href="#97">97</a> + <span class="string">"|(ao(/.*)?)"</span> <em class="comment">// ao Angola</em><a name="98" href="#98">98</a> + <span class="string">"|(aero(/.*)?)"</span> <em class="comment">// aero Air-transport industry</em><a name="99" href="#99">99</a> + <span class="string">"|(aq(/.*)?)"</span> <em class="comment">// aq Antarctica</em><a name="100" href="#100">100</a> + <span class="string">"|(ar(/.*)?)"</span> <em class="comment">// ar Argentina</em><a name="101" href="#101">101</a> + <span class="string">"|(as(/.*)?)"</span> <em class="comment">// as American Samoa</em><a name="102" href="#102">102</a> + <span class="string">"|(at(/.*)?)"</span> <em class="comment">// at Austria</em><a name="103" href="#103">103</a> + <span class="string">"|(au(/.*)?)"</span> <em class="comment">// au Australia</em><a name="104" href="#104">104</a> + <span class="string">"|(aw(/.*)?)"</span> <em class="comment">// aw Aruba</em><a name="105" href="#105">105</a> + <span class="string">"|(az(/.*)?)"</span> <em class="comment">// az Azerbaijan</em><a name="106" href="#106">106</a> + <span class="string">"|(ba(/.*)?)"</span> <em class="comment">// ba Bosnia Hercegovina</em>⌨️ 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 + -