<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
        {font-family:"Cambria Math";
        panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
        {font-family:Calibri;
        panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0cm;
        margin-bottom:.0001pt;
        font-size:11.0pt;
        font-family:"Calibri",sans-serif;
        mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:#0563C1;
        text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
        {mso-style-priority:99;
        color:#954F72;
        text-decoration:underline;}
p.MsoListParagraph, li.MsoListParagraph, div.MsoListParagraph
        {mso-style-priority:34;
        margin-top:0cm;
        margin-right:0cm;
        margin-bottom:0cm;
        margin-left:36.0pt;
        margin-bottom:.0001pt;
        font-size:11.0pt;
        font-family:"Calibri",sans-serif;
        mso-fareast-language:EN-US;}
p.msonormal0, li.msonormal0, div.msonormal0
        {mso-style-name:msonormal;
        mso-margin-top-alt:auto;
        margin-right:0cm;
        mso-margin-bottom-alt:auto;
        margin-left:0cm;
        font-size:12.0pt;
        font-family:"Times New Roman",serif;}
span.E-postmall19
        {mso-style-type:personal;
        font-family:"Calibri",sans-serif;
        color:windowtext;}
span.E-postmall20
        {mso-style-type:personal-reply;
        font-family:"Calibri",sans-serif;
        color:#1F497D;}
.MsoChpDefault
        {mso-style-type:export-only;
        font-size:10.0pt;}
@page WordSection1
        {size:612.0pt 792.0pt;
        margin:70.85pt 70.85pt 70.85pt 70.85pt;}
div.WordSection1
        {page:WordSection1;}
/* List Definitions */
@list l0
        {mso-list-id:463961396;
        mso-list-type:hybrid;
        mso-list-template-ids:-1724738948 69009425 69009433 69009435 69009423 69009433 69009435 69009423 69009433 69009435;}
@list l0:level1
        {mso-level-text:"%1\)";
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level2
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level3
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
@list l0:level4
        {mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level5
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level6
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
@list l0:level7
        {mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level8
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level9
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
ol
        {margin-bottom:0cm;}
ul
        {margin-bottom:0cm;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="SV" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal"><span lang="EN-GB" style="color:#1F497D">After a couple of days of crawling: The number of objects limit trick didn’t work. We have several jobs which remains for days working with just one domain, until reaching the limit (now 50.000 objects).<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="color:#1F497D">How do you solve that? Or is NAS solving it after the first crawl, putting all those domains in the same job (through the ambitious sorting and selection algorithms)?<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="color:#1F497D">Regards,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:black;mso-fareast-language:SV">-----<br>
<br>
</span><span lang="EN-GB" style="font-family:"Arial",sans-serif;color:black;mso-fareast-language:SV">Peter Svanberg</span><span lang="EN-GB" style="color:#1F497D;mso-fareast-language:SV"><br>
</span><span lang="EN-GB" style="font-size:9.0pt;color:#1F497D;mso-fareast-language:SV"><br>
</span><span lang="EN-GB" style="font-family:"Arial",sans-serif;color:#1F497D;mso-fareast-language:SV">National Library of Sweden</span><span lang="EN-GB" style="color:#1F497D;mso-fareast-language:SV"><br>
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#1F497D;mso-fareast-language:SV">Phone: +46 10 709
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:black;mso-fareast-language:SV">32 78</span><span lang="EN-GB" style="font-size:9.0pt;color:#1F497D;mso-fareast-language:SV"><br>
<br>
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#1F497D;mso-fareast-language:SV">E-mail</span><span lang="EN-GB" style="font-size:9.0pt;color:#1F497D;mso-fareast-language:SV">:
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:black;mso-fareast-language:SV">peter.svanberg@kb.se</span><span lang="EN-GB" style="font-size:9.0pt;color:black;mso-fareast-language:SV"><br>
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#1F497D;mso-fareast-language:SV">Web</span><span lang="EN-GB" style="font-size:9.0pt;color:#1F497D;mso-fareast-language:SV">:
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:#1F497D;mso-fareast-language:SV">www.kb.se</span><span lang="EN-GB" style="color:#1F497D;mso-fareast-language:SV"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB" style="color:#1F497D"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal"><b><span style="mso-fareast-language:SV">Från:</span></b><span style="mso-fareast-language:SV"> Peter Svanberg
<br>
<b>Skickat:</b> den 31 januari 2020 11:25<br>
<b>Till:</b> netarchivesuite-users@ml.sbforge.org<br>
<b>Ämne:</b> Cope with product catalogs, large forums; calendars, file structure loops<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Hello,<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><span lang="EN-GB">Two sorts of sites with a lot of potentially unwanted
<a href="URL:s">URL:s</a><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoListParagraph" style="text-indent:-18.0pt;mso-list:l0 level1 lfo2"><![if !supportLists]><span lang="EN-GB"><span style="mso-list:Ignore">1)<span style="font:7.0pt "Times New Roman"">     
</span></span></span><![endif]><span lang="EN-GB">Large product catalogues, large forums etc.<o:p></o:p></span></p>
<p class="MsoListParagraph" style="text-indent:-18.0pt;mso-list:l0 level1 lfo2"><![if !supportLists]><span lang="EN-GB"><span style="mso-list:Ignore">2)<span style="font:7.0pt "Times New Roman"">     
</span></span></span><![endif]><span lang="EN-GB">Calendars (of events, for booking etc.) with no limits, file structure loops<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB">For the first category you can chose to just crawl it – as long as it is finite. But do you, or do you try to limit such sites? How? A problem with crawling it is also that domains with such content often becomes the
 only domain left in a job, occupying it for hours or days with just one URL/s speed.<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-top:12.0pt"><span lang="EN-GB">The second category must be stopped in some way. You can’t safely figure out from the URL what is a calendar, and PathologicalPathDecideRule doesn’t recognize loops in several steps (…/a/b/c/a/b/c…).
 TooManyPathSegmentsDecideRule can be used to stop it eventually but much can happen before that. The least bad way to stop it I can think of is through the number of objects limit. Or do you have other hints?<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB">Regards,<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-bottom:12.0pt"><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:black;mso-fareast-language:SV">-----<br>
<br>
</span><span lang="EN-GB" style="font-family:"Arial",sans-serif;color:black;mso-fareast-language:SV">Peter Svanberg</span><span lang="EN-GB" style="mso-fareast-language:SV"><br>
</span><span lang="EN-GB" style="font-size:9.0pt;mso-fareast-language:SV"><br>
</span><span lang="EN-GB" style="font-family:"Arial",sans-serif;mso-fareast-language:SV">National Library of Sweden</span><span lang="EN-GB" style="mso-fareast-language:SV"><br>
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;mso-fareast-language:SV">Phone: +46 10 709
<span style="color:black">32 78</span></span><span lang="EN-GB" style="font-size:9.0pt;mso-fareast-language:SV"><br>
<br>
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;mso-fareast-language:SV">E-mail</span><span lang="EN-GB" style="font-size:9.0pt;mso-fareast-language:SV">:
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;color:black;mso-fareast-language:SV"><a href="mailto:peter.svanberg@kb.se">peter.svanberg@kb.se</a></span><span lang="EN-GB" style="font-size:9.0pt;color:black;mso-fareast-language:SV"><br>
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;mso-fareast-language:SV">Web</span><span lang="EN-GB" style="font-size:9.0pt;mso-fareast-language:SV">:
</span><span lang="EN-GB" style="font-size:9.0pt;font-family:"Arial",sans-serif;mso-fareast-language:SV"><a href="http://www.kb.se">www.kb.se</a></span><span lang="EN-GB" style="mso-fareast-language:SV"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p> </o:p></span></p>
</div>
</body>
</html>