blob: 351beacc358b7ef45228bc7e0187d1d275b75597 [file] [log] [blame]
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html style="font-size: 16px;"><head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<meta content="Apache Forrest" name="Generator">
<meta name="Forrest-version" content="0.9">
<meta name="Forrest-skin-name" content="nutch">
<title>About Apache Nutch</title>
<link type="text/css" href="about_files/basic.css" rel="stylesheet">
<link media="screen" type="text/css" href="about_files/screen.css" rel="stylesheet">
<link media="print" type="text/css" href="about_files/print.css" rel="stylesheet">
<link type="text/css" href="about_files/profile.css" rel="stylesheet">
<script src="about_files/getBlank.js" language="javascript" type="text/javascript"></script><script src="about_files/getMenu.js" language="javascript" type="text/javascript"></script><style type="text/css">.menuitemgroup{display: none;}</style><script src="about_files/fontsize.js" language="javascript" type="text/javascript"></script>
<link rel="shortcut icon" href="http://nutch.apache.org/images/favicon.ico">
</head>
<body style="font-size: 16px;" onload="init()">
<script type="text/javascript">ndeSetTextSize();</script>
<div id="top">
<!--+
|breadtrail
+-->
<div class="breadtrail">
<a href="http://www.apache.org/">Apache</a> &gt; <a href="http://nutch.apache.org/">Nutch</a> &gt; <a href="http://nutch.apache.org/">Home</a><script src="about_files/breadcrumbs.js" language="JavaScript" type="text/javascript"></script> &gt;
</div>
<!--+
|header
+-->
<div class="header">
<!--+
|start group logo
+-->
<div class="grouplogo">
<a href="http://www.apache.org/"><img class="logoImage" alt="Apache" src="about_files/feather-small.gif" title="Apache Software Foundation "></a>
</div>
<!--+
|end group logo
+-->
<!--+
|start Project Logo
+-->
<div class="projectlogo">
<a href="http://nutch.apache.org/"><img class="logoImage" alt="Nutch" src="about_files/nutch_logo_tm.gif" title="Open Source Web Search Software"></a>
</div>
<!--+
|end Project Logo
+-->
<!--+
|start Search
+-->
<div class="searchbox">
<script type="text/javascript">
function selectProvider(form) {
provider = form.elements['searchProvider'].value;
if (provider == "any") {
if (Math.random() > 0.5) {
provider = "lucid";
} else {
provider = "sl";
}
}
if (provider == "lucid") {
form.action = "http://search.lucidimagination.com/p:nutch";
} else if (provider == "sl") {
form.action = "http://search-lucene.com/nutch";
}
days = 90; // cookie will be valid for 90 days
date = new Date();
date.setTime(date.getTime() + (days * 24 * 60 * 60 * 1000));
expires = "; expires=" + date.toGMTString();
document.cookie = "searchProvider=" + provider + expires + "; path=/";
}
</script>
<form id="searchform" action="http://search.lucidimagination.com/p:nutch" method="get" class="roundtopsmall">
<input onfocus="getBlank (this, 'Search the site with Solr');" size="25" name="q" id="query" value="Search the site with Solr" type="text">&nbsp;
<input onclick="selectProvider(this.form)" name="Search" value="Search" type="submit">
@
<select id="searchProvider" name="searchProvider"><option selected="selected" value="any">select provider</option><option value="lucid">Lucid Find</option><option value="sl">Search-Lucene</option></select><script type="text/javascript">
if (document.cookie.length>0) {
cStart=document.cookie.indexOf("searchProvider=");
if (cStart!=-1) {
cStart=cStart + "searchProvider=".length;
cEnd=document.cookie.indexOf(";", cStart);
if (cEnd==-1) {
cEnd=document.cookie.length;
}
provider = unescape(document.cookie.substring(cStart,cEnd));
document.forms['searchform'].elements['searchProvider'].value = provider;
}
}
</script>
</form>
</div>
<!--+
|end search
+-->
<!--+
|start Tabs
+-->
<ul id="tabs">
<li class="current">
<a class="selected" href="http://nutch.apache.org/index.html">Main</a>
</li>
<li>
<a class="unselected" href="http://nutch.apache.org/wiki.html">Wiki</a>
</li>
<li>
<a class="unselected" href="http://issues.apache.org/jira/browse/NUTCH">Jira</a>
</li>
</ul>
<!--+
|end Tabs
+-->
</div>
</div>
<div id="main">
<div id="publishedStrip">
<!--+
|start Subtabs
+-->
<div id="level2tabs"></div>
<!--+
|end Endtabs
+-->
<script type="text/javascript"><!--
document.write("Last Published: " + document.lastModified);
// --></script>Last Published: 07/10/2012 15:39:10
</div>
<!--+
|breadtrail
+-->
<div class="breadtrail">
&nbsp;
</div>
<!--+
|start Menu, mainarea
+-->
<!--+
|start Menu
+-->
<div id="menu">
<div onclick="SwitchMenu('menu_selected_1.1', 'skin/')" id="menu_selected_1.1Title" class="menutitle" style="background-image: url('skin/images/chapter_open.gif');">Project</div>
<div id="menu_selected_1.1" class="selectedmenuitemgroup" style="display: block;">
<div class="menuitem">
<a href="http://nutch.apache.org/index.html">News</a>
</div>
<div class="menupage">
<div class="menupagetitle">About</div>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/credits.html">Credits</a>
</div>
<div class="menuitem">
<a href="http://www.apache.org/foundation/thanks.html">Thanks</a>
</div>
<div class="menuitem">
<a href="http://www.cafepress.com/nutch/">Buy Stuff</a>
</div>
<div class="menuitem">
<a href="http://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
</div>
<div class="menuitem">
<a href="http://www.apache.org/licenses/">License</a>
</div>
<div class="menuitem">
<a href="http://www.apache.org/security/">Security</a>
</div>
</div>
<div onclick="SwitchMenu('menu_1.2', 'skin/')" id="menu_1.2Title" class="menutitle">Documentation</div>
<div id="menu_1.2" class="menuitemgroup">
<div class="menuitem">
<a href="http://nutch.apache.org/faq.html">FAQ</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/wiki.html">Wiki</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/tutorial.html">Tutorial</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/bot.html">Robot </a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/apidocs-2.0/index.html">API Docs (2.0)</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/apidocs-1.5/index.html">API Docs (1.5.1)</a>
</div>
<div class="menuitem">
<a href="https://builds.apache.org/job/Nutch-trunk/javadoc/">API Docs (trunk-nightly)</a>
</div>
<div class="menuitem">
<a href="https://builds.apache.org/job/Nutch-nutchgora/javadoc/">API Docs (2.0-Dev-nightly)</a>
</div>
</div>
<div onclick="SwitchMenu('menu_1.3', 'skin/')" id="menu_1.3Title" class="menutitle">Resources</div>
<div id="menu_1.3" class="menuitemgroup">
<div class="menuitem">
<a href="http://www.apache.org/dyn/closer.cgi/nutch/">Download</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/nightly.html">Nightly builds</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/sonar.html">Sonar Analysis</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/mailing_lists.html">Mailing Lists</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/issue_tracking.html">Issue Tracking</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/version_control.html">Version Control</a>
</div>
<div class="menuitem">
<a href="http://nutch.apache.org/old_downloads.html">Older Downloads</a>
</div>
</div>
<div onclick="SwitchMenu('menu_1.4', 'skin/')" id="menu_1.4Title" class="menutitle">Related Projects</div>
<div id="menu_1.4" class="menuitemgroup">
<div class="menuitem">
<a href="http://lucene.apache.org/java/">Lucene</a>
</div>
<div class="menuitem">
<a href="http://hadoop.apache.org/">Hadoop</a>
</div>
<div class="menuitem">
<a href="http://lucene.apache.org/solr/">Solr</a>
</div>
<div class="menuitem">
<a href="http://tika.apache.org/">Tika</a>
</div>
<div class="menuitem">
<a href="http://gora.apache.org/">Gora</a>
</div>
</div>
<div id="credit"></div>
<div id="roundbottom">
<img style="display: none" class="corner" alt="" src="about_files/rc-b-l-15-1body-2menu-3menu.png" height="15" width="15"></div>
<!--+
|alternative credits
+-->
<div id="credit2"></div>
</div>
<!--+
|end Menu
+-->
<!--+
|start content
+-->
<div id="content">
<div title="Portable Document Format" class="pdflink">
<a class="dida" href="http://nutch.apache.org/about.pdf"><img alt="PDF -icon" src="about_files/pdfdoc.gif" class="skin"><br>
PDF</a>
</div>
<h1>About Apache Nutch</h1>
<div id="minitoc-area">
<ul class="minitoc">
<li>
<a href="#Overview">Overview</a>
</li>
</ul>
</div>
<a name="N1000E"></a><a name="Overview"></a>
<h2 class="h3">Overview</h2>
<div class="section">
<p>Apache Nutch is an open source web-search
software project. Stemming from <a href="http://lucene.apache.org/java/">Apache Lucene</a>, it now builds
on <a href="http://lucene.apache.org/solr/">Apache Solr</a> adding web-specifics, such as a crawler,
a link-graph database and parsing support handled by <a href="http://tika.apache.org/">Apache Tika</a>
for HTML and and array other document formats.</p>
<p>Apache Nutch can run on a single machine, but gains a lot of its
strength from running in a <a href="http://hadoop.apache.org/">Hadoop cluster</a>
</p>
<p>The system can be enhanced (eg other document formats can be
parsed) using a highly flexible, easily extensible and thoroughly maintained
plugin infrastructure.</p>
<p>For more information about Apache Nutch, please see the <a href="http://wiki.apache.org/nutch/">Nutch wiki.</a>
</p>
</div>
</div>
<!--+
|end content
+-->
<div class="clearboth">&nbsp;</div>
</div>
<div id="footer">
<!--+
|start bottomstrip
+-->
<div class="lastmodified">
<script type="text/javascript"><!--
document.write("Last Published: " + document.lastModified);
// --></script>Last Published: 07/10/2012 15:39:10
</div>
<div class="copyright">
Copyright ©
2005-2011 <a href="http://www.apache.org/licenses/">The Apache
Software Foundation.
Apache Nutch, Nutch, Apache, the Apache feather logo, and the Apache
Nutch project logo are trademarks of The Apache Software Foundation.
</a>
</div>
<!--+
|end bottomstrip
+-->
</div>
</body></html>