⭐ 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

📄 extractorswf.html

📁 用JAVA编写的,在做实验的时候留下来的,本来想删的,但是传上来,大家分享吧
💻 HTML
📖 第 1 页 / 共 2 页
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>ExtractorSWF 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"> * Heritrix</em><a name="3" href="#3">3</a>   <em class="comment"> *</em><a name="4" href="#4">4</a>   <em class="comment"> * $Id: ExtractorSWF.java,v 1.22 2006/04/29 00:41:12 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 March 19, 2004</em><a name="7" href="#7">7</a>   <em class="comment"> *</em><a name="8" href="#8">8</a>   <em class="comment"> * Copyright (C) 2003 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/crawler/extractor/package-summary.html">org.archive.crawler.extractor</a>;<a name="28" href="#28">28</a>  <a name="29" href="#29">29</a>  <strong>import</strong> java.io.IOException;<a name="30" href="#30">30</a>  <strong>import</strong> java.io.InputStream;<a name="31" href="#31">31</a>  <strong>import</strong> java.util.Enumeration;<a name="32" href="#32">32</a>  <strong>import</strong> java.util.Vector;<a name="33" href="#33">33</a>  <strong>import</strong> java.util.logging.Logger;<a name="34" href="#34">34</a>  <a name="35" href="#35">35</a>  <strong>import</strong> org.archive.crawler.datamodel.CoreAttributeConstants;<a name="36" href="#36">36</a>  <strong>import</strong> org.archive.crawler.datamodel.CrawlURI;<a name="37" href="#37">37</a>  <a name="38" href="#38">38</a>  <strong>import</strong> com.anotherbigidea.flash.interfaces.SWFTagTypes;<a name="39" href="#39">39</a>  <strong>import</strong> com.anotherbigidea.flash.interfaces.SWFVectors;<a name="40" href="#40">40</a>  <strong>import</strong> com.anotherbigidea.flash.readers.SWFReader;<a name="41" href="#41">41</a>  <strong>import</strong> com.anotherbigidea.flash.readers.TagParser;<a name="42" href="#42">42</a>  <strong>import</strong> com.anotherbigidea.flash.structs.Rect;<a name="43" href="#43">43</a>  <strong>import</strong> com.anotherbigidea.io.InStream;<a name="44" href="#44">44</a>  <a name="45" href="#45">45</a>  <em>/**<em>*</em></em><a name="46" href="#46">46</a>  <em> * Extracts URIs from SWF (flash/shockwave) files.</em><a name="47" href="#47">47</a>  <em> * </em><a name="48" href="#48">48</a>  <em> * To test, here is a link to an swf that has links</em><a name="49" href="#49">49</a>  <em> * embedded inside of it: <a href="http://www.hitspring.com/index.swf." target="alexandria_uri">http://www.hitspring.com/index.swf.</a></em><a name="50" href="#50">50</a>  <em> *</em><a name="51" href="#51">51</a>  <em> * @author Igor Ranitovic</em><a name="52" href="#52">52</a>  <em> */</em><a name="53" href="#53">53</a>  <strong>public</strong> <strong>class</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorSWF.html">ExtractorSWF</a><a name="54" href="#54">54</a>  <strong>extends</strong> <a href="../../../../org/archive/crawler/extractor/Extractor.html">Extractor</a><a name="55" href="#55">55</a>  implements <a href="../../../../org/archive/crawler/datamodel/CoreAttributeConstants.html">CoreAttributeConstants</a> {<a name="56" href="#56">56</a>      <strong>private</strong> <strong>static</strong> Logger logger =<a name="57" href="#57">57</a>          Logger.getLogger(ExtractorSWF.<strong>class</strong>.getName());<a name="58" href="#58">58</a>      <strong>protected</strong> <strong>long</strong> numberOfCURIsHandled = 0;<a name="59" href="#59">59</a>      <strong>protected</strong> <strong>long</strong> numberOfLinksExtracted = 0;<a name="60" href="#60">60</a>      <em class="comment">// TODO: consider if this should be even smaller, because anything </em><a name="61" href="#61">61</a>      <em class="comment">// containing URLs wouldn't be this big</em><a name="62" href="#62">62</a>      <strong>private</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> MAX_READ_SIZE = 1024 * 1024; <em class="comment">// 1MB</em><a name="63" href="#63">63</a>  <a name="64" href="#64">64</a>      <em>/**<em>*</em></em><a name="65" href="#65">65</a>  <em>     * @param name</em><a name="66" href="#66">66</a>  <em>     */</em><a name="67" href="#67">67</a>      <strong>public</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorSWF.html">ExtractorSWF</a>(String name) {<a name="68" href="#68">68</a>          <strong>super</strong>(name, <span class="string">"Flash extractor. Extracts URIs from SWF "</span> +<a name="69" href="#69">69</a>              <span class="string">"(flash/shockwave) files."</span>);<a name="70" href="#70">70</a>      }<a name="71" href="#71">71</a>  <a name="72" href="#72">72</a>      <strong>protected</strong> <strong>void</strong> extract(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="73" href="#73">73</a>          <strong>if</strong> (!isHttpTransactionContentToProcess(curi)) {<a name="74" href="#74">74</a>              <strong>return</strong>;<a name="75" href="#75">75</a>          }<a name="76" href="#76">76</a>  <a name="77" href="#77">77</a>          String contentType = curi.getContentType();<a name="78" href="#78">78</a>          <strong>if</strong> (contentType == <strong>null</strong>) {<a name="79" href="#79">79</a>              <strong>return</strong>;<a name="80" href="#80">80</a>          }<a name="81" href="#81">81</a>          <strong>if</strong> ((contentType.toLowerCase().indexOf(<span class="string">"x-shockwave-flash"</span>) &lt; 0)<a name="82" href="#82">82</a>                  &amp;&amp; (!curi.toString().toLowerCase().endsWith(<span class="string">".swf"</span>))) {<a name="83" href="#83">83</a>              <strong>return</strong>;<a name="84" href="#84">84</a>          }<a name="85" href="#85">85</a>  <a name="86" href="#86">86</a>          numberOfCURIsHandled++;<a name="87" href="#87">87</a>  <a name="88" href="#88">88</a>          InputStream documentStream = <strong>null</strong>;<a name="89" href="#89">89</a>          <em class="comment">// Get the SWF file's content stream.</em><a name="90" href="#90">90</a>          <strong>try</strong> {<a name="91" href="#91">91</a>              documentStream = curi.getHttpRecorder().getRecordedInput().<a name="92" href="#92">92</a>                  getContentReplayInputStream();<a name="93" href="#93">93</a>              <strong>if</strong> (documentStream == <strong>null</strong>) {<a name="94" href="#94">94</a>                  <strong>return</strong>;<a name="95" href="#95">95</a>              }<a name="96" href="#96">96</a>  <a name="97" href="#97">97</a>              <em class="comment">// Create SWF action that will add discoved URIs to CrawlURI</em><a name="98" href="#98">98</a>              <em class="comment">// alist(s).</em><a name="99" href="#99">99</a>              <a href="../../../../org/archive/crawler/extractor/CrawlUriSWFAction.html">CrawlUriSWFAction</a> curiAction = <strong>new</strong> <a href="../../../../org/archive/crawler/extractor/CrawlUriSWFAction.html">CrawlUriSWFAction</a>(curi,<a name="100" href="#100">100</a>                     getController());<a name="101" href="#101">101</a>             <em class="comment">// Overwrite parsing of specific tags that might have URIs.</em><a name="102" href="#102">102</a>             <a href="../../../../org/archive/crawler/extractor/CustomSWFTags.html">CustomSWFTags</a> customTags = <strong>new</strong> <a href="../../../../org/archive/crawler/extractor/CustomSWFTags.html">CustomSWFTags</a>(curiAction);<a name="103" href="#103">103</a>             <em class="comment">// Get a SWFReader instance.</em><a name="104" href="#104">104</a>             SWFReader reader =<a name="105" href="#105">105</a>                 <strong>new</strong> SWFReader(getTagParser(customTags), documentStream) {<a name="106" href="#106">106</a>                 <em>/**<em>*</em></em><a name="107" href="#107">107</a> <em>                 * Override because a corrupt SWF file can cause us to try</em><a name="108" href="#108">108</a> <em>                 * read lengths that are hundreds of megabytes in size</em><a name="109" href="#109">109</a> <em>                 * causing us to OOME.</em><a name="110" href="#110">110</a> <em>                 * </em><a name="111" href="#111">111</a> <em>                 * Below is copied from SWFReader parent class.</em><a name="112" href="#112">112</a> <em>                 */</em><a name="113" href="#113">113</a>                 <strong>public</strong> <strong>int</strong> readOneTag() throws IOException {<a name="114" href="#114">114</a>                     <strong>int</strong> header = mIn.readUI16();<a name="115" href="#115">115</a>                     <strong>int</strong>  type   = header >> 6;    <em class="comment">//only want the top 10 bits</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 + -