I have an interesting problem. I wrote the following perl script to recursively loop through a directory and in all html files for img/script/a tags do the following:
Convert the entire url to lowercase
Replace spaces and %20 with underscores
The script works great except when an image tag in wrapped with an anchor tag. Is there a way to modify the current script to also be able to manipulate the links for nested tags that are not on separate lines? Basically if I have <a href="..."><img src="..."></a> the script will only change the link in the anchor tag but
skip the img tag.
#!/usr/bin/perl
use File::Find;
$input="/var/www/tecnew/";
sub process {
if (-T and m/.+\.(htm|html)/i) {
#print "htm/html: $_\n";
open(FILE,"+<$_") or die "couldn't open file $!\n";
$out = '';
while(<FILE>) {
$cur_line = $_;
if($cur_line =~ m/<a.*>/i) {
print "cur_line (unaltered) $cur_line\n";
$cur_line =~ /(^.* href=\")(.+?)(\".*$)/i;
$beg = $1;
$link = html_clean($2);
$end = $3;
$cur_line = $beg.$link.$end;
print "cur_line (altered) $cur_line\n";
}
if($cur_line =~ m/(<img.*>|<script.*>)/i) {
print "cur_line (unaltered) $cur_line\n";
$cur_line =~ /(^.* src=\")(.+?)(\".*$)/i;
$beg = $1;
$link = html_clean($2);
$end = $3;
$cur_line = $beg.$link.$end;
print "cur_line (altered) $cur_line\n";
}
$out .= $cur_line;
}
seek(FILE, 0, 0) or die "can't seek to start of file: $!";
print FILE $out or die "can't print to file: $1";
truncate(FILE, tell(FILE)) or die "can't truncate file: $!";
close(FILE) or die "can't close file: $!";
} } find(\&process, $input);
sub html_clean {
my($input_string) = @_;
$input_string = lc($input_string);
$input_string =~ s/%20|\s/_/g;
return $input_string;
}
