<?xml version="1.0" encoding="utf-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: The Whitehouse.gov Website&#8217;s Robots.txt File Has 1839 Lines In It</title>
	<atom:link href="http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/feed" rel="self" type="application/rss+xml" />
	<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it</link>
	<description>grep understanding</description>
	<lastBuildDate>Sun, 29 Jan 2012 20:44:46 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
	<item>
		<title>By: Deepak</title>
		<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/comment-page-1#comment-27624</link>
		<dc:creator>Deepak</dc:creator>
		<pubDate>Thu, 08 Feb 2007 13:38:06 +0000</pubDate>
		<guid isPermaLink="false">http://dmiessler.com/archives/1083#comment-27624</guid>
		<description>&lt;p&gt;Yup, even I noted it sometime back as an excellent sitemap. ;-)&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Yup, even I noted it sometime back as an excellent sitemap. ;-)</p>]]></content:encoded>
	</item>
	<item>
		<title>By: Deepak</title>
		<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/comment-page-1#comment-246735</link>
		<dc:creator>Deepak</dc:creator>
		<pubDate>Thu, 08 Feb 2007 13:38:00 +0000</pubDate>
		<guid isPermaLink="false">http://dmiessler.com/archives/1083#comment-246735</guid>
		<description>&lt;p&gt;Yup, even I noted it sometime back as an excellent sitemap. ;-)&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Yup, even I noted it sometime back as an excellent sitemap. ;-)</p>]]></content:encoded>
	</item>
	<item>
		<title>By: ghost16825</title>
		<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/comment-page-1#comment-25176</link>
		<dc:creator>ghost16825</dc:creator>
		<pubDate>Fri, 26 Jan 2007 10:03:46 +0000</pubDate>
		<guid isPermaLink="false">http://dmiessler.com/archives/1083#comment-25176</guid>
		<description>&lt;p&gt;Ooooh, /secret/ directories. &lt;em&gt;nods head&lt;/em&gt;&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Ooooh, /secret/ directories. <em>nods head</em></p>]]></content:encoded>
	</item>
	<item>
		<title>By: ghost16825</title>
		<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/comment-page-1#comment-246734</link>
		<dc:creator>ghost16825</dc:creator>
		<pubDate>Fri, 26 Jan 2007 10:03:00 +0000</pubDate>
		<guid isPermaLink="false">http://dmiessler.com/archives/1083#comment-246734</guid>
		<description>&lt;p&gt;Ooooh, /secret/ directories. &lt;em&gt;nods head&lt;/em&gt;&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Ooooh, /secret/ directories. <em>nods head</em></p>]]></content:encoded>
	</item>
	<item>
		<title>By: sergei</title>
		<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/comment-page-1#comment-25038</link>
		<dc:creator>sergei</dc:creator>
		<pubDate>Thu, 25 Jan 2007 18:11:44 +0000</pubDate>
		<guid isPermaLink="false">http://dmiessler.com/archives/1083#comment-25038</guid>
		<description>&lt;p&gt;Search in Google for &#039;robots.txt&#039; shows whitehouse.gov at position 5&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Search in Google for &#8216;robots.txt&#8217; shows whitehouse.gov at position 5</p>]]></content:encoded>
	</item>
	<item>
		<title>By: sergei</title>
		<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/comment-page-1#comment-246733</link>
		<dc:creator>sergei</dc:creator>
		<pubDate>Thu, 25 Jan 2007 18:11:00 +0000</pubDate>
		<guid isPermaLink="false">http://dmiessler.com/archives/1083#comment-246733</guid>
		<description>&lt;p&gt;Search in Google for &#039;robots.txt&#039; shows whitehouse.gov at position 5&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Search in Google for &#8216;robots.txt&#8217; shows whitehouse.gov at position 5</p>]]></content:encoded>
	</item>
	<item>
		<title>By: Some Joker</title>
		<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/comment-page-1#comment-24755</link>
		<dc:creator>Some Joker</dc:creator>
		<pubDate>Tue, 23 Jan 2007 22:06:03 +0000</pubDate>
		<guid isPermaLink="false">http://dmiessler.com/archives/1083#comment-24755</guid>
		<description>&lt;p&gt;Looking at most of those entries, it looks like they&#039;re excluding pages which look to be designed for text only browsers/screen readers.. nearly every directory ends in /text&lt;/p&gt;

&lt;p&gt;Disallow:   /asia/2005/photoessay/china/text
Disallow:   /asia/2005/photoessay/japan/text
Disallow:   /asia/2005/photoessay/korea/text
Disallow:   /asia/2005/photoessay/mongolia/text
Disallow:   /asia/2005/photoessay/mrsbush1/text
Disallow:   /asia/2005/photoessay/mrsbush2/text&lt;/p&gt;

&lt;p&gt;and if you browse up one directory, you get the same story with pictures..&lt;/p&gt;

&lt;p&gt;I&#039;d say it looks like they are doing it to work around for a poor file structure or possibly to keep search engines from finding duplicate text (although without pictures)&lt;/p&gt;

&lt;p&gt;&lt;em&gt;shrugs&lt;/em&gt; I&#039;m all for pointing out when the administration does something crooked, but I can&#039;t see fault in this one.. (granted, I&#039;ve only checked out 20 or so of the links.. the only one that didn&#039;t go anywhere for me was /video/text )&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Looking at most of those entries, it looks like they&#8217;re excluding pages which look to be designed for text only browsers/screen readers.. nearly every directory ends in /text</p>

<p>Disallow:   /asia/2005/photoessay/china/text
Disallow:   /asia/2005/photoessay/japan/text
Disallow:   /asia/2005/photoessay/korea/text
Disallow:   /asia/2005/photoessay/mongolia/text
Disallow:   /asia/2005/photoessay/mrsbush1/text
Disallow:   /asia/2005/photoessay/mrsbush2/text</p>

<p>and if you browse up one directory, you get the same story with pictures..</p>

<p>I&#8217;d say it looks like they are doing it to work around for a poor file structure or possibly to keep search engines from finding duplicate text (although without pictures)</p>

<p><em>shrugs</em> I&#8217;m all for pointing out when the administration does something crooked, but I can&#8217;t see fault in this one.. (granted, I&#8217;ve only checked out 20 or so of the links.. the only one that didn&#8217;t go anywhere for me was /video/text )</p>]]></content:encoded>
	</item>
	<item>
		<title>By: Some Joker</title>
		<link>http://danielmiessler.com/blog/the-whitehousegov-websites-robotstxt-file-has-1839-lines-in-it/comment-page-1#comment-246732</link>
		<dc:creator>Some Joker</dc:creator>
		<pubDate>Tue, 23 Jan 2007 22:06:00 +0000</pubDate>
		<guid isPermaLink="false">http://dmiessler.com/archives/1083#comment-246732</guid>
		<description>&lt;p&gt;Looking at most of those entries, it looks like they&#039;re excluding pages which look to be designed for text only browsers/screen readers.. nearly every directory ends in /text&lt;/p&gt;

&lt;p&gt;Disallow:   /asia/2005/photoessay/china/text
Disallow:   /asia/2005/photoessay/japan/text
Disallow:   /asia/2005/photoessay/korea/text
Disallow:   /asia/2005/photoessay/mongolia/text
Disallow:   /asia/2005/photoessay/mrsbush1/text
Disallow:   /asia/2005/photoessay/mrsbush2/text&lt;/p&gt;

&lt;p&gt;and if you browse up one directory, you get the same story with pictures..&lt;/p&gt;

&lt;p&gt;I&#039;d say it looks like they are doing it to work around for a poor file structure or possibly to keep search engines from finding duplicate text (although without pictures)&lt;/p&gt;

&lt;p&gt;&lt;em&gt;shrugs&lt;/em&gt; I&#039;m all for pointing out when the administration does something crooked, but I can&#039;t see fault in this one.. (granted, I&#039;ve only checked out 20 or so of the links.. the only one that didn&#039;t go anywhere for me was /video/text )&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Looking at most of those entries, it looks like they&#8217;re excluding pages which look to be designed for text only browsers/screen readers.. nearly every directory ends in /text</p>

<p>Disallow:   /asia/2005/photoessay/china/text
Disallow:   /asia/2005/photoessay/japan/text
Disallow:   /asia/2005/photoessay/korea/text
Disallow:   /asia/2005/photoessay/mongolia/text
Disallow:   /asia/2005/photoessay/mrsbush1/text
Disallow:   /asia/2005/photoessay/mrsbush2/text</p>

<p>and if you browse up one directory, you get the same story with pictures..</p>

<p>I&#8217;d say it looks like they are doing it to work around for a poor file structure or possibly to keep search engines from finding duplicate text (although without pictures)</p>

<p><em>shrugs</em> I&#8217;m all for pointing out when the administration does something crooked, but I can&#8217;t see fault in this one.. (granted, I&#8217;ve only checked out 20 or so of the links.. the only one that didn&#8217;t go anywhere for me was /video/text )</p>]]></content:encoded>
	</item>
</channel>
</rss>

