advait has asked for the wisdom of the Perl Monks concerning the following question:

Hi All,
I need help in parsing a xml document. 
experiments total-hybs="629" total-samples="733" total="21" to="21" fr
+om="1">
−
    <experiment accnum="E-GEOD-8918" array="Agilent Human Genome CGH M
+icroarray 44B [G4410B]" biosamples-png="download/mageml/E-GEOD-8918.b
+iosamples.png" biosamples-svg="download/mageml/E-GEOD-8918.biosamples
+.svg" fgem="download/mageml/E-GEOD-8918.processed.zip" fgem-count="87
+" hybs="87" id="1636341195" name="CGH profiling of 87 indolent non-ho
+dgkin   s lymphoma (NHL)" releasedate="2008-06-19" samples="174" sdrf
+="download/mageml/E-GEOD-8918.sdrf.txt" species="Homo sapiens" two-co
+lumns="download/mageml/E-GEOD-8918.2columns.txt">
&#8722;
    <users>
<user id="1"/>
</users>
&#8722;
    <secondaryaccessions>
<secondaryaccession>GSE8918</secondaryaccession>
</secondaryaccessions>
&#8722;
    
    
</experiment>

[download]
Can anyone please suggest how can I retrieve accnum in experiment. Using XML twig I could retrieve secondaryaccession.
perl script is as follow
 use strict;
use XML::Twig;

my $t= new XML::Twig( TwigHandlers=> { experiment => \&experiment});
$t->parsefile( '/home/adi/lwp_cgh_hs.xml');
exit;

sub experiment
  { my ($t, $experiment)= @_;
    my %experiment;
    $experiment{secondaryaccessions}= $experiment->field( 'secondaryac
+cessions');
   # $experiment{name}= $experiment->field( 'experimentName');
    #$experiment{description}= $experiment->field( 'Description');

    $experiment{secondaryaccession}= join ':', 
                        map {$_->text || ''}   
                        @{[$experiment->children( 'secondaryaccession'
+)]};
    print "$experiment\n";
    print "$experiment{secondaryaccessions}: \n";
    print "        : $experiment{secondaryaccession}\n";
    $experiment->delete;
  }

[download]
Thank you

Replies are listed 'Best First'.
Re: XML parsing
by toolic (Bishop) on Jul 07, 2008 at 16:29 UTC
    Can anyone please suggest how can I retrieve accnum in experiment.
    Here is one way to do it, after cleaning up what I think is the XML you want: 
    use strict;
use warnings;
use XML::Twig;

my $xfile = <<EOF;
<experiment accnum="E-GEOD-8918" array="Agilent Human Genome CGH Micro
+array 44B [G4410B]" biosamples-png="download/mageml/E-GEOD-8918.biosa
+mples.png" biosamples-svg="download/mageml/E-GEOD-8918.biosamples.svg
+" fgem="download/mageml/E-GEOD-8918.processed.zip" fgem-count="87" hy
+bs="87" id="1636341195" name="CGH profiling of 87 indolent non-hodgki
+n   s lymphoma (NHL)" releasedate="2008-06-19" samples="174" sdrf="do
+wnload/mageml/E-GEOD-8918.sdrf.txt" species="Homo sapiens" two-column
+s="download/mageml/E-GEOD-8918.2columns.txt">
    <users>
        <user id="1"/>
    </users>
    <secondaryaccessions>
        <secondaryaccession>GSE8918</secondaryaccession>
    </secondaryaccessions>
</experiment>
EOF

my $t= new XML::Twig();
$t->parse($xfile);
my $experiment = $t->root();
print 'accnum = ', $experiment->att('accnum'), "\n";

    [download]

    prints: 

    accnum = E-GEOD-8918

    [download]
[reply]
[d/l]
[select]
Re: XML parsing
by Your Mother (Archbishop) on Jul 08, 2008 at 00:21 UTC

    And one more since I've become the chapter secretary for the XML::LibXML fan club (I like Twig too). 

    use strict;
use warnings;
use XML::LibXML;

my $doc = XML::LibXML->new->parse_fh(\*DATA);

for my $node ( $doc->findnodes('//experiment[@accnum]') ){
    print $node->getAttribute("accnum"), "\n";
}

__DATA__
<?xml version="1.0" encoding="UTF-8"?>
<experiments total-hybs="629" total-samples="733" total="21" to="21" f
+rom="1">
  <experiment accnum="E-GEOD-8918" array="Agilent Human Genome CGH Mic
+roarray 44B [G4410B]" biosamples-png="download/mageml/E-GEOD-8918.bio
+samples.png" biosamples-svg="download/mageml/E-GEOD-8918.biosamples.s
+vg" fgem="download/mageml/E-GEOD-8918.processed.zip" fgem-count="87" 
+hybs="87" id="1636341195" name="CGH profiling of 87 indolent non-hodg
+kin s lymphoma (NHL)" releasedate="2008-06-19" samples="174" sdrf="do
+wnload/mageml/E-GEOD-8918.sdrf.txt" species="Homo sapiens" two-column
+s="download/mageml/E-GEOD-8918.2columns.txt">
    <users>
      <user id="1"/>
    </users>
    <secondaryaccessions>
      <secondaryaccession>GSE8918</secondaryaccession>
    </secondaryaccessions>
  </experiment>
</experiments>

    [download]
[reply]
[d/l]
Re: XML parsing
by Anonymous Monk on Jul 07, 2008 at 16:29 UTC 
    #!/usr/bin/perl --

use strict;
use warnings;

use XML::Twig;

my $t = new XML::Twig(
    TwigHandlers=> {
        experiment => sub {
            use Data::Dumper;
            print join $/, @_,$_,$/;
            print $_->{att}->{accnum},$/;
            print $_->{'att'}->{'accnum'},$/;
            print $_->att('accnum'),$/;
            print $_->_dump;
            
        }
    }
);

my $xml = q~<experiment accnum="E-GEOD-8918">
<users><user id="1"/></users>
</experiment>~;

$t->parse($xml);


__END__

XML::Twig=HASH(0x19140c0)
XML::Twig::Elt=HASH(0x1ea55b8)
XML::Twig::Elt=HASH(0x1ea55b8)

E-GEOD-8918
E-GEOD-8918
E-GEOD-8918
|-experiment accnum="E-GEOD-8918"
| |-users
| | |-user id="1"

    [download]
[reply]
[d/l]
A reply falls below the community's threshold of quality. You may see it by logging in.

Back to Seekers of Perl Wisdom