in reply to Re: Convert html table to text
in thread Convert html table to text

Not really, this is the best I could come up with
#!/usr/bin/perl -- use strict; use warnings; use HTML::TreeBuilder; use Text::ASCIITable; use List::Util qw(max); my $html = q~ <table border=1> <tr><th>header1</th><th>header2</th></tr> <tr> <Td> tr 1, td 1 </td> <td> tr 1, td 2</td> </tr> <tr> <td> tr 3, td 1 <table border=0><tr><td>00</td></tr><tr><td>0</td></tr +><tr><td> Yes, a Lone Table Cell</td></tr></table> </td> <td> tr2 td2 </td> </tr> </table>~; my $t = HTML::TreeBuilder->new(); $t->parse($html); $t->eof; print DumpTable( $_ ), $/, $/ for $t->find_by_tag_name('table') ; sub DumpTable { my($ht, $depth) = (@_,0); # warn "$ht depth $depth"; die "$ht is not a table" unless $ht->tag eq 'table'; my $tt = Text::ASCIITable::->new; my @co; my @da; my $da = []; for my $ro ( @{ $ht->content() } ) { if( $ro->tag eq 'tr' ) { push @da, $da if @$da; $da = []; for my $ce ( @{ $ro->content() } ) { if( $ce->tag eq 'td' ) { if( $ce->look_down( '_tag', 'table' ) ) { my $string = ''; for my $i ( @{ $ce->content() } ) { if( not ref $i ) { $string .= $i; } elsif( $i->tag eq 'table' ) { $string .= "\n"; $string .= DumpTable($i,$depth+1); $string .= "\n"; } else { $string .= $i->as_text; } } push @$da, $string; } else { push @$da, $ce->as_text; } } elsif( $ce->tag eq 'th' ) { push @co, $ce->as_text; } } } } push @da, $da if @$da; unless(@co) { use List::Util qw(max); my $max = 1 + max( 0, map { $#$_ } @da ); ( @co ) = (' ') x $max ; $tt->setOptions( hide_HeadRow => 1 ); $tt->setOptions( hide_HeadLine => 1 ); } # warn " co ", map {"{$_}"} @co; $tt->setCols( @co ); if( $depth == 0 ){ my $maxcolwidth = 120; $maxcolwidth -= 1 for split //, '.==.'; # bad guesstimation $maxcolwidth -= 2 for @co; # '| ' and '| ' $tt->setColWidth( $_, $maxcolwidth/(0+@co), 1) for @co; } $tt->addRow($_) for @da; $tt->setOptions( 'drawRowLine', 1) if $ht->attr('border'); # return $tt->draw(); return $tt->draw( [ '.=', '=.', '-', '-' ], # .=-----------=. [ '|', '|', '|' ], # | info | info | [ '|-', '-|', '=', '=' ], # |-===========-| [ '|', '|', '|' ], # | info | info | [ "'=", "='", '-', '-' ], # '=-----------=' [ '|=', '=|', '-', '*' ] # rowseperator ); } __END__