📄 extractorhttp.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>ExtractorHTTP xref</title><link type="text/css" rel="stylesheet" href="../../../../stylesheet.css" /></head><body><div id="overview"><a href="../../../../../apidocs/org/archive/crawler/extractor/ExtractorHTTP.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"> * SimpleHTTPExtractor.java</em><a name="20" href="#20">20</a> <em class="comment"> * Created on Jul 3, 2003</em><a name="21" href="#21">21</a> <em class="comment"> *</em><a name="22" href="#22">22</a> <em class="comment"> * $Header: /cvsroot/archive-crawler/ArchiveOpenCrawler/src/java/org/archive/crawler/extractor/ExtractorHTTP.java,v 1.20 2005/07/27 22:30:55 stack-sf Exp $</em><a name="23" href="#23">23</a> <em class="comment"> */</em><a name="24" href="#24">24</a> <strong>package</strong> <a href="../../../../org/archive/crawler/extractor/package-summary.html">org.archive.crawler.extractor</a>;<a name="25" href="#25">25</a> <a name="26" href="#26">26</a> <strong>import</strong> java.util.logging.Logger;<a name="27" href="#27">27</a> <a name="28" href="#28">28</a> <strong>import</strong> org.apache.commons.httpclient.Header;<a name="29" href="#29">29</a> <strong>import</strong> org.apache.commons.httpclient.HttpMethod;<a name="30" href="#30">30</a> <strong>import</strong> org.apache.commons.httpclient.URIException;<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.framework.Processor;<a name="34" href="#34">34</a> <a name="35" href="#35">35</a> <em>/**<em>*</em></em><a name="36" href="#36">36</a> <em> * Extracts URIs from HTTP response headers.</em><a name="37" href="#37">37</a> <em> * @author gojomo</em><a name="38" href="#38">38</a> <em> */</em><a name="39" href="#39">39</a> <strong>public</strong> <strong>class</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorHTTP.html">ExtractorHTTP</a> <strong>extends</strong> <a href="../../../../org/archive/crawler/framework/Processor.html">Processor</a><a name="40" href="#40">40</a> implements <a href="../../../../org/archive/crawler/datamodel/CoreAttributeConstants.html">CoreAttributeConstants</a> {<a name="41" href="#41">41</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> Logger LOGGER =<a name="42" href="#42">42</a> Logger.getLogger(ExtractorHTTP.<strong>class</strong>.getName());<a name="43" href="#43">43</a> <strong>protected</strong> <strong>long</strong> numberOfCURIsHandled = 0;<a name="44" href="#44">44</a> <strong>protected</strong> <strong>long</strong> numberOfLinksExtracted = 0;<a name="45" href="#45">45</a> <a name="46" href="#46">46</a> <strong>public</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorHTTP.html">ExtractorHTTP</a>(String name) {<a name="47" href="#47">47</a> <strong>super</strong>(name,<a name="48" href="#48">48</a> <span class="string">"HTTP extractor. Extracts URIs from HTTP response headers."</span>);<a name="49" href="#49">49</a> }<a name="50" href="#50">50</a> <a name="51" href="#51">51</a> <strong>public</strong> <strong>void</strong> innerProcess(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="52" href="#52">52</a> <strong>if</strong> (!curi.isHttpTransaction() || curi.getFetchStatus() <= 0) {<a name="53" href="#53">53</a> <em class="comment">// If not http or if an error status code, skip.</em><a name="54" href="#54">54</a> <strong>return</strong>;<a name="55" href="#55">55</a> }<a name="56" href="#56">56</a> numberOfCURIsHandled++;<a name="57" href="#57">57</a> HttpMethod method = (HttpMethod)curi.getObject(A_HTTP_TRANSACTION);<a name="58" href="#58">58</a> addHeaderLink(curi, method.getResponseHeader(<span class="string">"Location"</span>));<a name="59" href="#59">59</a> addHeaderLink(curi, method.getResponseHeader(<span class="string">"Content-Location"</span>));<a name="60" href="#60">60</a> }<a name="61" href="#61">61</a> <a name="62" href="#62">62</a> <strong>protected</strong> <strong>void</strong> addHeaderLink(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi, Header loc) {<a name="63" href="#63">63</a> <strong>if</strong> (loc == <strong>null</strong>) {<a name="64" href="#64">64</a> <em class="comment">// If null, return without adding anything.</em><a name="65" href="#65">65</a> <strong>return</strong>;<a name="66" href="#66">66</a> }<a name="67" href="#67">67</a> <em class="comment">// TODO: consider possibility of multiple headers</em><a name="68" href="#68">68</a> <strong>try</strong> {<a name="69" href="#69">69</a> curi.createAndAddLink(loc.getValue(), loc.getName() + <span class="string">":"</span>,<a name="70" href="#70">70</a> Link.REFER_HOP);<a name="71" href="#71">71</a> numberOfLinksExtracted++;<a name="72" href="#72">72</a> } <strong>catch</strong> (URIException e) {<a name="73" href="#73">73</a> <em class="comment">// There may not be a controller (e.g. If we're being run</em><a name="74" href="#74">74</a> <em class="comment">// by the extractor tool).</em><a name="75" href="#75">75</a> <strong>if</strong> (getController() != <strong>null</strong>) {<a name="76" href="#76">76</a> getController().logUriError(e, curi.getUURI(), loc.getValue());<a name="77" href="#77">77</a> } <strong>else</strong> {<a name="78" href="#78">78</a> LOGGER.info(curi + <span class="string">", "</span> + loc.getValue() + <span class="string">": "</span> +<a name="79" href="#79">79</a> e.getMessage());<a name="80" href="#80">80</a> }<a name="81" href="#81">81</a> }<a name="82" href="#82">82</a> <a name="83" href="#83">83</a> }<a name="84" href="#84">84</a> <a name="85" href="#85">85</a> <strong>public</strong> String report() {<a name="86" href="#86">86</a> StringBuffer ret = <strong>new</strong> StringBuffer();<a name="87" href="#87">87</a> ret.append(<span class="string">"Processor: org.archive.crawler.extractor.ExtractorHTTP\n"</span>);<a name="88" href="#88">88</a> ret.append(<span class="string">" Function: "</span> +<a name="89" href="#89">89</a> <span class="string">"Extracts URIs from HTTP response headers\n"</span>);<a name="90" href="#90">90</a> ret.append(<span class="string">" CrawlURIs handled: "</span> + numberOfCURIsHandled + <span class="string">"\n"</span>);<a name="91" href="#91">91</a> ret.append(<span class="string">" Links extracted: "</span> + numberOfLinksExtracted + <span class="string">"\n\n"</span>);<a name="92" href="#92">92</a> <strong>return</strong> ret.toString();<a name="93" href="#93">93</a> }<a name="94" href="#94">94</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 + -