in reply to Problem with parsing HTML with Regex's
local $/; my $data = <DATA>; my @img = $data =~ m/<\s*img[^>]*?src\s*=\s*['"]?([^"' >\n]+)/gi; my @css = $data =~ m/<\s*link[^>]*?href\s*=\s*['"]?([^"' >\n]+)/gi; my @lnk = $data =~ m/<\s*a[^>]*?href\s*=\s*['"]?([^"' >\n]+)/gi; use Data::Dumper; print Dumper \@img, \@css, \@lnk; __DATA__ <img src="img.link1"> <img src="img.link2" alt="foo"> <img height=20 width=25 src=img.link3 > <IMG src='img.link4'> <link href="css.link1"> <a class=foo href="normal.link1"> <A href=normal.link2 class="foo" > <a href="normal.link3"> <a class=foo href='normal.link4'> <a Href='normal.link5'> __END__ $VAR1 = [ 'img.link1', 'img.link2', 'img.link3', 'img.link4' ]; $VAR2 = [ 'css.link1' ]; $VAR3 = [ 'normal.link1', 'normal.link2', 'normal.link3', 'normal.link4', 'normal.link5' ];
|
|---|