You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yacy_search_server/htroot/CrawlStartSite.html

117 lines
7.2 KiB

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >
<head>
<title>YaCy '#[clientname]#': Crawl Start</title>
#%env/templates/metas.template%#
<script type="text/javascript" src="js/ajax.js"></script>
<script type="text/javascript" src="js/IndexCreate.js"></script>
<script type="text/javascript">
function check(key){
document.getElementById(key).checked = 'checked';
}
</script>
<style type="text/css">
.nobr {
white-space: nowrap;
}
</style>
</head>
<body id="IndexCreate">
#%env/templates/header.template%#
#%env/templates/submenuCrawler.template%#
<div id="api"></div>
<h2>Site Crawling</h2>
<p id="startCrawling">
<strong>Site Crawler:</strong>&nbsp;
Download all web pages from a given domain or base URL.
</p>
<fieldset>
<legend>Site Crawl Start</legend>
<form id="Crawler" method="post" action="Crawler_p.html" enctype="multipart/form-data" accept-charset="UTF-8">
<dl>
<dt><label>Site</label></dt>
<dd>
<table border="0" cellpadding="0" cellspacing="0"><tr valign="top">
<td valign="top"><input type="radio" name="crawlingMode" id="url" value="url" checked="checked"
onmousedown="document.getElementById('rangeDomain').disabled=false;document.getElementById('rangeSubpath').disabled=false;document.getElementById('crawlingDomMaxCheck').disabled=false;document.getElementById('crawlingDomMaxPages').disabled=false;"/>Start URL&nbsp;(must start with<br/>http:// https:// ftp:// smb:// file://)</td>
<td valign="top">
<input name="crawlingURL" id="crawlingURL" type="text" size="50" maxlength="256" value="#[starturl]#" onkeypress="changed()" onfocus="check('url')" style="font-size:16px"/><br/>
<input name="bookmarkTitle" id="bookmarkTitle" type="text" size="50" maxlength="256" value="" readonly="readonly" style="background:transparent; border:0px"/>
</td>
<td>
<span id="robotsOK"></span>
<img id="ajax" src="env/grafics/empty.gif" alt="empty" style="vertical-align: top;" />
</td>
</tr><tr>
<td><input type="radio" name="crawlingMode" id="sitelist" value="sitelist" disabled="disabled" />Link-List of URL</td>
<td>
<div id="sitelistURLs"></div>
<button id="expandSiteListBtn" style="visibility:hidden" type="button" onclick="this.disabled = true;loadInfos(true);" class="btn btn-default btn-xs" title="Show all links">
<span class="glyphicon glyphicon-option-horizontal"/>
</button>
</td>
</tr><tr>
<td><input type="radio" name="crawlingMode" id="sitemap" value="sitemap" disabled="disabled"
onmousedown="document.getElementById('rangeDomain').disabled=true;document.getElementById('rangeSubpath').disabled=true;document.getElementById('crawlingDomMaxCheck').disabled=true;document.getElementById('crawlingDomMaxPages').disabled=true;"/>Sitemap URL</td>
<td><input name="sitemapURL" type="text" size="41" maxlength="256" value="" readonly="readonly" style="background:transparent; border:0px"/></td>
</tr>
</table><br/>
<input type="hidden" name="crawlingDepth" id="crawlingDepth" value="99" />
</dd>
<dt><label>Path</label></dt>
<dd>
<input type="radio" name="range" id="rangeDomain" value="domain" checked="checked"/>load all files in domain<br />
<input type="radio" name="range" id="rangeSubpath" value="subpath" />load only files in a sub-path of given url
<input type="hidden" name="deleteold" id="deleteold" value="on" />
<input type="hidden" name="mustnotmatch" id="mustnotmatch" value="" />
<input type="hidden" name="crawlingDomFilterCheck" id="crawlingDomFilterCheck" value="off" />
</dd>
<dt><label>Limitation</label></dt>
<dd><table border="0" cellpadding="0" cellspacing="0"><tr valign="top">
<td valign="top"><input type="checkbox" name="crawlingDomMaxCheck" id="crawlingDomMaxCheck" #(crawlingDomMaxCheck)#::checked="checked"#(/crawlingDomMaxCheck)# /> not more than </td>
<td valign="top"><input name="crawlingDomMaxPages" id="crawlingDomMaxPages" type="text" size="6" maxlength="6" value="#[crawlingDomMaxPages]#" /></td>
<td valign="top">documents</td>
</tr></table>
</dd>
<dt><label>Collection</label></dt>
<dd>
<input name="collection" id="collection" type="text" size="60" maxlength="100" value="#[collection]#" #(collectionEnabled)#disabled="disabled"::#(/collectionEnabled)# />
</dd>
<dt><label>Start</label></dt>
<dd>
<input type="hidden" name="directDocByURL" id="directDocByURL" value="off" />
<input type="hidden" name="recrawl" id="recrawl" value="reload" />
<input type="hidden" name="reloadIfOlderNumber" id="reloadIfOlderNumber" value="3" />
<input type="hidden" name="reloadIfOlderUnit" id="reloadIfOlderUnit" value="day" />
<input type="hidden" name="deleteold" id="deleteold" value="on" />
<input type="hidden" name="storeHTCache" id="storeHTCache" value="on" />
<input type="hidden" name="cachePolicy" id="cachePolicy" value="iffresh" />
<input type="hidden" name="crawlingQ" id="crawlingQ" value="on" />
<input type="hidden" name="followFrames" id="followFrames" value="on" />
<input type="hidden" name="obeyHtmlRobotsNoindex" id="obeyHtmlRobotsNoindex" value="on" />
<input type="hidden" name="indexText" id="indexText" value="on" />
<input type="hidden" name="indexMedia" id="indexMedia" value="on" />
<input type="hidden" name="intention" id="intention" value="" />
<input id="timezoneOffset" type="hidden" name="timezoneOffset" value=""><script>document.getElementById("timezoneOffset").value = new Date().getTimezoneOffset();</script>
<input type="submit" name="crawlingstart" value="Start New Crawl" class="btn btn-primary"/>
</dd>
</dl>
</form>
</fieldset>
<h3>Hints</h3>
<ul>
<li><h4>Crawl Speed Limitation</h4> No more that two pages are loaded from the same host in one second (not more that 120 document per minute) to limit the load on the target server.</li>
<li><h4>Target Balancer</h4> A second crawl for a different host increases the throughput to a maximum of 240 documents per minute since the crawler balances the load over all hosts.</li>
<li><h4>High Speed Crawling</h4> A 'shallow crawl' which is not limited to a single host (or site)
can extend the pages per minute (ppm) rate to unlimited documents per minute when the number of target hosts is high.
This can be done using the <a href="CrawlStartExpert.html">Expert Crawl Start</a> servlet.</li>
<li><h4>Scheduler Steering</h4> The scheduler on crawls can be changed or removed using the <a href="Table_API_p.html">API Steering</a>.</li>
</ul>
#%env/templates/footer.template%#
</body>
</html>