Server IP : 85.214.239.14 / Your IP : 3.146.178.220 Web Server : Apache/2.4.62 (Debian) System : Linux h2886529.stratoserver.net 4.9.0 #1 SMP Tue Jan 9 19:45:01 MSK 2024 x86_64 User : www-data ( 33) PHP Version : 7.4.18 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals,pcntl_unshare, MySQL : OFF | cURL : OFF | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : OFF Directory : /usr/share/doc/libhtml-parser-perl/examples/ |
Upload File : |
#!/usr/bin/perl # This script cleans up an HTML document use strict; use warnings; use HTML::Parser (); # configure these values my @ignore_attr = qw(bgcolor background color face style link alink vlink text onblur onchange onclick ondblclick onfocus onkeydown onkeyup onload onmousedown onmousemove onmouseout onmouseover onmouseup onreset onselect onunload ); my @ignore_tags = qw(font big small b i); my @ignore_elements = qw(script style); # make it easier to look up attributes my %ignore_attr = map { $_ => 1 } @ignore_attr; sub tag { my ($pos, $text) = @_; if (@$pos >= 4) { # kill some attributes my ($k_offset, $k_len, $v_offset, $v_len) = @{$pos}[-4 .. -1]; my $next_attr = $v_offset ? $v_offset + $v_len : $k_offset + $k_len; my $edited; while (@$pos >= 4) { ($k_offset, $k_len, $v_offset, $v_len) = splice @$pos, -4; if ($ignore_attr{lc substr($text, $k_offset, $k_len)}) { substr($text, $k_offset, $next_attr - $k_offset) = ""; $edited++; } $next_attr = $k_offset; } # if we killed all attributed, kill any extra whitespace too $text =~ s/^(<\w+)\s+>$/$1>/ if $edited; } print $text; } sub decl { my $type = shift; print shift if $type eq "doctype"; } sub text { print shift; } HTML::Parser->new( api_version => 3, start_h => [\&tag, "tokenpos, text"], process_h => ["", ""], comment_h => ["", ""], declaration_h => [\&decl, "tagname, text"], default_h => [\&text, "text"], ignore_tags => \@ignore_tags, ignore_elements => \@ignore_elements, )->parse_file(shift) || die "Can't open file: $!\n";