#!/usr/bin/perl -w $inputfile="test.htm"; $outputfile=">outfile2.html"; $numofTables=1; open(INFILE, $inputfile) or die ("no file $inputfile"); $filesize = -s INFILE; read(INFILE, $thispage, $filesize); close(INFILE); #this removes anypage breaks $thispage=~s/<BR>/ /g; $thispage=~s/<\/BR>/ /g; @myarray=split("\s", $thispage); open(OUTFILE, $outputfile); $start=0; foreach(@myarray){ #this is not to clean but the ASP that wrote the HTML #put the table tags and script tags on their own line if(($_ =~ m/<TABLE/)||($_ =~ m/<SCRIPT/)) { $start++; } if($start<=$numofTables){ print OUTFILE "$_\s"; } if($_ =~ m/<\/TABLE>/) { $start--; print OUTFILE "</TR><TR>\n<TD>"; }elsif($_ =~ m/<\/SCRIPT>/){ $start--; } } close(OUTFILE);
In reply to embedded table remover by BigJoe
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |