| Server IP : 127.0.0.2 / Your IP : 18.117.166.111 Web Server : Apache/2.4.18 (Ubuntu) System : User : www-data ( ) PHP Version : 7.0.33-0ubuntu0.16.04.16 Disable Function : disk_free_space,disk_total_space,diskfreespace,dl,exec,fpaththru,getmyuid,getmypid,highlight_file,ignore_user_abord,leak,listen,link,opcache_get_configuration,opcache_get_status,passthru,pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,php_uname,phpinfo,posix_ctermid,posix_getcwd,posix_getegid,posix_geteuid,posix_getgid,posix_getgrgid,posix_getgrnam,posix_getgroups,posix_getlogin,posix_getpgid,posix_getpgrp,posix_getpid,posix,_getppid,posix_getpwnam,posix_getpwuid,posix_getrlimit,posix_getsid,posix_getuid,posix_isatty,posix_kill,posix_mkfifo,posix_setegid,posix_seteuid,posix_setgid,posix_setpgid,posix_setsid,posix_setuid,posix_times,posix_ttyname,posix_uname,pclose,popen,proc_open,proc_close,proc_get_status,proc_nice,proc_terminate,shell_exec,source,show_source,system,virtual MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /usr/share/doc/libhtml-parser-perl/examples/ |
Upload File : |
#!/usr/bin/perl -w
# This script cleans up an HTML document.
# Specifically it removes deprecated styling and scripting tags.
use strict;
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";