If your list of PMIDs is in a file, pmids.txt with one PMID per line, here's a shell script with TogoWS solution:

for i in `cat pmids.txt`; do echo -n $i;ruby -e 'print "\t"'; curl "http://togows.dbcls.jp/entry/ncbi-pubmed/$i/ab"; done

Once you get all your articles, click on the button send-to /File/XML and save the articles as XML.

Then apply this XSLT-stylesheet ( xsltproc --novalid stylesheet.xsl pubmed_result.txt )

<xsl:stylesheet version="1.0" xmlns:xsl="&lt;a href=" http:="" www.w3.org="" 1999="" XSL="" Transform"="" rel="nofollow">http://www.w3.org/1999/XSL/Transform" 
    >

<xsl:output method="text"/>
<xsl:template match="/">
    <xsl:for-each select="/PubmedArticleSet/PubmedArticle">
        <xsl:value-of select="MedlineCitation/PMID"/>
        <xsl:text>  </xsl:text>
        <xsl:value-of select="normalize-space(MedlineCitation/Article/Abstract)"/>
        <xsl:text>
</xsl:text>
    </xsl:for-each>
</xsl:template>

</xsl:stylesheet>

Some parsing is required in cases like this.

If your list of PMIDs is in a file, pmids.txt with one PMID per line, here's a BioRuby solution:

#!/usr/bin/ruby

require "rubygems" # ruby1.8
require "bio"

Bio::NCBI.default_email = "me@me.com"

File.read("pmids.txt").each do |line|
  article = Bio::PubMed.query(line)
  medline = Bio::MEDLINE.new(article)
  puts "#{medline.pmid}\t#{medline.ab}"
end