<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Good text book on extracting data from HTML(Web) in SAS Procedures</title>
    <link>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27689#M6341</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Then you want to look into proc html and proc soap.&amp;nbsp; Do a search on the discussion forums for either.&amp;nbsp; If you include my id or friedeggs id in the search, I'm sure that will help to eliminate much of the noise.&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Wed, 11 Jan 2012 04:08:28 GMT</pubDate>
    <dc:creator>art297</dc:creator>
    <dc:date>2012-01-11T04:08:28Z</dc:date>
    <item>
      <title>Good text book on extracting data from HTML(Web)</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27686#M6338</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;I need to extract messy data from the website. Could anyone recommend a good textbook that covers how to extract data efficiently from the web, plz?&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Thank you.&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 11 Jan 2012 02:10:31 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27686#M6338</guid>
      <dc:creator>VX_Xc</dc:creator>
      <dc:date>2012-01-11T02:10:31Z</dc:date>
    </item>
    <item>
      <title>Good text book on extracting data from HTML(Web)</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27687#M6339</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Seunghoon,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Do you mean automatically or as in copy/paste?&amp;nbsp; If it is the latter, I'll be doing an SGF presentation on the topic in April, titled 'Copy and Paste Almost Anything'.&amp;nbsp; I already presented a draft of the paper at one of my local user group meetings and you can find it at:&lt;/P&gt;&lt;P&gt;&lt;A href="http://torsas.ca/page18.php"&gt;http://torsas.ca/page18.php&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;HTH,&lt;/P&gt;&lt;P&gt;Art&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 11 Jan 2012 03:48:14 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27687#M6339</guid>
      <dc:creator>art297</dc:creator>
      <dc:date>2012-01-11T03:48:14Z</dc:date>
    </item>
    <item>
      <title>Good text book on extracting data from HTML(Web)</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27688#M6340</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;I meant automatically. For example I would like to learn PROC (with many optional statements) that extracts data from the HTML file if I give it a address of a website or .html file directory.&lt;/P&gt;&lt;P&gt;maybe there isn't one? Then I would have to use DATA steps with a lot of @&amp;lt;tag&amp;gt; arguments in INPUT statement, which would not be very practical. &lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;But thanks for the link. I will have a look, looks promising.&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 11 Jan 2012 04:05:35 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27688#M6340</guid>
      <dc:creator>VX_Xc</dc:creator>
      <dc:date>2012-01-11T04:05:35Z</dc:date>
    </item>
    <item>
      <title>Good text book on extracting data from HTML(Web)</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27689#M6341</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Then you want to look into proc html and proc soap.&amp;nbsp; Do a search on the discussion forums for either.&amp;nbsp; If you include my id or friedeggs id in the search, I'm sure that will help to eliminate much of the noise.&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 11 Jan 2012 04:08:28 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27689#M6341</guid>
      <dc:creator>art297</dc:creator>
      <dc:date>2012-01-11T04:08:28Z</dc:date>
    </item>
    <item>
      <title>Good text book on extracting data from HTML(Web)</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27690#M6342</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Yes. You can do it.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;PRE&gt;filename x url 'http://www.sas.com';
data want(where=(line is not missing));
infile x dsd dlm='&amp;lt;&amp;gt;' lrecl=32767;
input @ '&amp;gt;' line : $400. @@;
run;


&lt;/PRE&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Ksharp&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 11 Jan 2012 05:06:45 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Good-text-book-on-extracting-data-from-HTML-Web/m-p/27690#M6342</guid>
      <dc:creator>Ksharp</dc:creator>
      <dc:date>2012-01-11T05:06:45Z</dc:date>
    </item>
  </channel>
</rss>

