Created
October 8, 2010 13:46
-
-
Save sharifulin/616824 to your computer and use it in GitHub Desktop.
Duty clean code and html
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sub clean_code($){ | |
for (my $str = shift) { | |
s/<(xml|style)>.*?<\/\1>//sg; | |
s/<!--.*?-->//sg; | |
s/<\/?([a-z0-9:]+)[^>]*?>/(grep { lc($1) eq $_ } 'p', 'a', 'b', 'strong', 'br', 'img') ? $& : ''/iesg; #tags | |
s/(<img[^>]+class=)("[^"]*"|\S+)/my ($r,$t) = ($1,$2); $r.($t =~ m!^"! ? $t : qq!"$t"!)/iesg; | |
s/(<\/?[a-z0-9]+)\s*([^>]*)>/ $2 ? | |
(join ' ', $1, map { join '=', $_->[0], $_->[1] } grep { my $t = $_; grep { lc($t->[0]) eq $_ } 'href', 'alt', 'src' } map { [ split qr!=!, $_, 2 ] } split qr!(?:(?<=")\s|\s(?="))!, $2).'>' | |
: $1.'>' /iesg; | |
s/(<\/?[a-z0-9]+)\s*([^>]*)>/ $2 ? | |
(join ' ', $1, map { join '=', $_->[0], $_->[1] } grep { my $t = $_; grep { lc($t->[0]) eq $_ } 'href', 'alt', 'src' } map { [ split qr!=!, $_, 2 ] } split qr!(?:(?<=")\s|\s(?="))!, $2).'>' | |
: $1.'>' /iesg; | |
s/(?:\n\s*){2,}/\n/g; | |
s/<([^>]+)><\/\1>//g; | |
s/<![^>]+>//g; | |
#~ s/<img\s+/<img class="img-blog-nowh" /gi; | |
return $_; | |
} | |
} | |
sub clean_html($) { | |
for (my $str = shift) { | |
s{<[^>]+>}{ }sg; | |
return $_; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment