http://qs321.pair.com?node_id=589103


in reply to Process a HTML file to get information from it.

here's my go
#!/usr/bin/perl use strict; use warnings; use HTML::TokeParser::Simple; my $html = q{ <a name="a"></a> <h2>A</h2> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td> <table width="100%" cellpadding="5" cellspacing="0" border="1"> <tr> <td width="33%" valign="top" class="clsTableBody"> <a href="pdf\c76b834e-36e1-497b-b13e-eba2348dc044.pdf" targe +t="_blank"> Abbott, Evelyn </a><br /> <span>110136892</span><br /> <a href="pdf\8a956f66-1c60-48fc-905c-b49d617aa6c5.pdf" targe +t="_blank"> Agnew, Thomas </a><br /> <span>110377660</span><br /> </td> <td width="34%" valign="top" class="clsTableBodyClear"> <a href="pdf\37d3e78b-1adb-458b-9e89-0df780909f08.pdf" targe +t="_blank"> Allison, David </a><br /> <span>108116112</span><br /> <a href="pdf\6c0a5bb4-143d-4305-957b-796c8193d07a.pdf" targe +t="_blank"> Allison, Gary Owen </a><br /> <span>116815754</span><br /> </td> <td width="33%" valign="top" class="clsTableBody"> <a href="pdf\ae8d51e0-005b-44be-84cb-3c9b57335755.pdf" targe +t="_blank"> Arsenault, Michael </a><br /> <span>108318866</span><br /> <a href="pdf\e646f948-f78d-4463-a01d-0261aebf70dc.pdf" targe +t="_blank"> Arsenault, Normand A. </a><br /> <span>113069066</span><br /> </td> </tr> </table> </td> </tr> </table> }; my $p = HTML::TokeParser::Simple->new(\$html); # parse until second table my $table_count = 2; while (my $t = $p->get_tag('table')){ last unless --$table_count; } my (%href, $this_href, $number); while (my $t = $p->get_token){ if ($t->is_start_tag('a')){ $this_href = $t->get_attr('href'); next; } if ($t->is_start_tag('span')){ $number = $p->get_trimmed_text('/span'); $href{$this_href} = $number; next; } last if $t->is_end_tag('table'); } for my $key (keys %href){ print "$key -> $href{$key}\n"; }
output:
---------- Capture Output ---------- > "C:\Perl\bin\perl.exe" _new.pl pdf\8a956f66-1c60-48fc-905c-b49d617aa6c5.pdf -> 110377660 pdf\c76b834e-36e1-497b-b13e-eba2348dc044.pdf -> 110136892 pdf\ae8d51e0-005b-44be-84cb-3c9b57335755.pdf -> 108318866 pdf\37d3e78b-1adb-458b-9e89-0df780909f08.pdf -> 108116112 pdf\e646f948-f78d-4463-a01d-0261aebf70dc.pdf -> 113069066 pdf\6c0a5bb4-143d-4305-957b-796c8193d07a.pdf -> 116815754 > Terminated with exit code 0.