Zero=, One=Monday, Two=Tuesday, Three=Wednesday, Four=Thursday, Five=FridaySaturday, Foo=xA0Sunda121bbbdddeeeggg

##</code><code>##

use warnings;
use strict;

our $XML_SPE;
{ no strict 'vars';
# copied from http://www.cs.sfu.ca/~cameron/REX.html#AppA
# REX/Perl 1.0 
# Robert D. Cameron "REX: XML Shallow Parsing with Regular Expressions",
# Technical Report TR 1998-17, School of Computing Science, Simon Fraser 
# University, November, 1998.
# Copyright (c) 1998, Robert D. Cameron. 
# The following code may be freely used and distributed provided that
# this copyright and citation notice remains intact and that modifications
# or additions are clearly identified.

$TextSE = "[^<]+";
$UntilHyphen = "[^-]*-";
$Until2Hyphens = "$UntilHyphen(?:[^-]$UntilHyphen)*-";
$CommentCE = "$Until2Hyphens>?";
$UntilRSBs = "[^\\]]*](?:[^\\]]+])*]+";
$CDATA_CE = "$UntilRSBs(?:[^\\]>]$UntilRSBs)*>";
$S = "[ \\n\\t\\r]+";
$NameStrt = "[A-Za-z_:]|[^\\x00-\\x7F]";
$NameChar = "[A-Za-z0-9_:.-]|[^\\x00-\\x7F]";
$Name = "(?:$NameStrt)(?:$NameChar)*";
$QuoteSE = "\"[^\"]*\"|'[^']*'";
$DT_IdentSE = "$S$Name(?:$S(?:$Name|$QuoteSE))*";
$MarkupDeclCE = "(?:[^\\]\"'><]+|$QuoteSE)*>";
$S1 = "[\\n\\r\\t ]";
$UntilQMs = "[^?]*\\?+";
$PI_Tail = "\\?>|$S1$UntilQMs(?:[^>?]$UntilQMs)*>";
$DT_ItemSE = "<(?:!(?:--$Until2Hyphens>|[^-]$MarkupDeclCE)|\\?$Name(?:$PI_Tail))|%$Name;|$S";
$DocTypeCE = "$DT_IdentSE(?:$S)?(?:\\[(?:$DT_ItemSE)*](?:$S)?)?>?";
$DeclCE = "--(?:$CommentCE)?|\\[CDATA\\[(?:$CDATA_CE)?|DOCTYPE(?:$DocTypeCE)?";
$PI_CE = "$Name(?:$PI_Tail)?";
$EndTagCE = "$Name(?:$S)?>?";
$AttValSE = "\"[^<\"]*\"|'[^<']*'";
$ElemTagCE = "$Name(?:$S$Name(?:$S)?=(?:$S)?(?:$AttValSE))*(?:$S)?/?>?";
$MarkupSPE = "<(?:!(?:$DeclCE)?|\\?(?:$PI_CE)?|/(?:$EndTagCE)?|(?:$ElemTagCE)?)";
$XML_SPE = "$TextSE|$MarkupSPE";

}

my $xml = do { open my $fh, '<', $ARGV[0] or die $!; local $/; <$fh> };

# Not tested and assumes proper nesting of <div> elements (and valid XML syntax)
# (Warning: Messy hack. Read at your own risk.)
my $nest = 0;
my $out = '';
my @elements = $xml =~ /$XML_SPE/g; # see http://www.cs.sfu.ca/~cameron/REX.html#AppA
for (@elements)
{
    if (/^<div/)
    {
        $nest++ if ($nest > 0); # only increment if inside an interesting <div>
        next unless (/class\h*=\h*['"]data['"]/); # \h is horizontal white space
        next unless (/id\h*=\h*['"](\w+)['"]/);
        $out .= ", $1=";
        $nest = 1 if ($nest == 0); # if this is the outer most interesting <div>
        next;
    }
    $nest--, next if (/^<\/div/);
    next if (/^[<]/); # skip other mark-up
    s/\W+//g;
    $out .= $_ if ($nest > 0);
}
$out =~ s/^, //;
print "$out\n";