You have an off-by-one error in your data, your expectations are wrong

This is actually row 5 column 4 not column 1  <td class=3Dxl32 x:num=3D"7258831">R5Col1</td>

thus this is column 7 so its dropped <td class=3Dxl29>TSH5555 this data gets dropped but should not</td>

So fix your data or work around it or something else entirely

Here is how I found out 

#!/usr/bin/perl --
use strict;
use warnings;
use Data::Dump qw/ dd /;
use HTML::TableExtract;
Main( @ARGV );
exit( 0 );
sub Main {
    my $te = HTML::TableExtract->new();
    $te->parse( SkewHtml() );
    $te->eof;
    $te->tables_dump('show_content', ',' );
    dd( $te->rows );
} ## end of Main

sub SkewHtml {
    my $html= q{
<html><head><title>skew test 2</title></head>
<body>
<table border=1>
<tr>
    <td>head0</td>
    <td>head1</td>
    <td>head2</td>
    <td>head3</td>
</tr>
<tr>
    <td colspan=4> <b>0/0</b>  colspan=4 <br>  0/0 undef undef undef <
+br> "0/0"  "0/0"  "0/0"  "0/0" </td>
</tr>
<tr>
    <td rowspan=2> <b>1/0</b>  rowspan=2 <br> 1/0 1/1 1/2 1/3 </td>
    <td> 1/1 </td>
    <td> 1/2  </td>
    <td> 1/3  </td>
</tr>
<tr>
    <td colspan=2 rowspan=3> <b>2/1</b> colspan=2 rowspan=3 <br> undef
+ 2/1 undef 2/3 <br> "1/0" "2/1" "2/1" "2/3"  </td>
    <td> 2/3 </td>
</tr>
<tr>
    <td> <b>3/0</b> <br> 3/0 undef undef 3/3 <br>  "3/0" "2/1"  "2/1" 
+ "3/3"  </td>
    <td> 3/3 </td>
</tr>
<tr>
    <td> <b>4/0</b> <br> 4/0 undef undef 4/3 <br>  "4/0" "2/1"  "2/1" 
+ "4/3"   </td>
    <td> 4/3 </td>
</tr>
<tr>
    <td colspan=2> <b>5/0</b> colspan=2 <br> 5/0 undef 5/2 5/3 <br> "5
+/0" "5/0" "5/2" "5/3" </td>
    <td> 5/2 </td>
    <td> 5/3 </td>
</tr>
</table>
<pre>
TABLE(0, 0):
head0,head1,head2,head3
 0/0  colspan=4  ,,,
 1/0  rowspan=2  , 1/1 , 1/2  , 1/3  
, 2/1 colspan=2 rowspan=3  ,, 2/3 
 3/0  ,,, 3/3 
 4/0  ,,, 4/3 
 5/0 colspan=2  ,, 5/2 , 5/3 
(
  ["head0", "head1", "head2", "head3"],
  [" 0/0  colspan=4  ", undef, undef, undef],
  [" 1/0  rowspan=2  ", " 1/1 ", " 1/2  ", " 1/3  "],
  [undef, " 2/1 colspan=2 rowspan=3  ", undef, " 2/3 "],
  [" 3/0  ", undef, undef, " 3/3 "],
  [" 4/0  ", undef, undef, " 4/3 "],
  [" 5/0 colspan=2  ", undef, " 5/2 ", " 5/3 "],
)
</pre>
</body>
</html>
    };
    $html =~ s{^\s+|\s+$}{}gm;
    $html =~ s{(<br>.+?)</td>}{<!-- $1 --> </td>}gm;
    $html =~ s{rowspan=3}{rowspan=3D2}g;
    return $html;
} ## end of SkewHtml

__END__
TABLE(0, 0):
head0,head1,head2,head3
 0/0  colspan=4  ,,,
 1/0  rowspan=2  , 1/1 , 1/2  , 1/3  
, 2/1 colspan=2 rowspan=3D2  ,, 2/3 
 3/0  ,,, 3/3 
 4/0  ,,, 4/3 
 5/0 colspan=2  ,, 5/2 , 5/3 
(
  ["head0", "head1", "head2", "head3"],
  [" 0/0  colspan=4  ", undef, undef, undef],
  [" 1/0  rowspan=2  ", " 1/1 ", " 1/2  ", " 1/3  "],
  [undef, " 2/1 colspan=2 rowspan=3D2  ", undef, " 2/3 "],
  [" 3/0  ", undef, undef, " 3/3 "],
  [" 4/0  ", undef, undef, " 4/3 "],
  [" 5/0 colspan=2  ", undef, " 5/2 ", " 5/3 "],
)

[download]
head0 head1 head2 head3
0/0 colspan=4
0/0 undef undef undef
"0/0" "0/0" "0/0" "0/0"
1/0 rowspan=2
1/0 1/1 1/2 1/3 		1/1 1/2 1/3
2/1 colspan=2 rowspan=3
undef 2/1 undef 2/3
"1/0" "2/1" "2/1" "2/3" 		2/3
3/0
3/0 undef undef 3/3
"3/0" "2/1" "2/1" "3/3" 		3/3
4/0
4/0 undef undef 4/3
"4/0" "2/1" "2/1" "4/3" 		4/3
5/0 colspan=2
5/0 undef 5/2 5/3
"5/0" "5/0" "5/2" "5/3" 		5/2 5/3 
TABLE(0, 0):
head0,head1,head2,head3
 0/0  colspan=4  ,,,
 1/0  rowspan=2  , 1/1 , 1/2  , 1/3  
, 2/1 colspan=2 rowspan=3  ,, 2/3 
 3/0  ,,, 3/3 
 4/0  ,,, 4/3 
 5/0 colspan=2  ,, 5/2 , 5/3 
(
  ["head0", "head1", "head2", "head3"],
  [" 0/0  colspan=4  ", undef, undef, undef],
  [" 1/0  rowspan=2  ", " 1/1 ", " 1/2  ", " 1/3  "],
  [undef, " 2/1 colspan=2 rowspan=3  ", undef, " 2/3 "],
  [" 3/0  ", undef, undef, " 3/3 "],
  [" 4/0  ", undef, undef, " 4/3 "],
  [" 5/0 colspan=2  ", undef, " 5/2 ", " 5/3 "],
)

[download]

In reply to Re: HTML::TableExtract problem handling merged cells across rows (OBO rowspan colspan) by Anonymous Monk
in thread HTML::TableExtract problem handling merged cells across rows by jtravillian

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.