Created
May 18, 2014 03:31
-
-
Save gryftir/2b15c2d62c70d8431e4c to your computer and use it in GitHub Desktop.
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
#!/usr/bin/env perl | |
use warnings; | |
use strict; | |
use WWW::Mechanize; | |
use HTML::TreeBuilder; | |
my $url = "http://www.google.com"; | |
my $mech = WWW::Mechanize->new(); | |
$mech->get($url); | |
my $tree = HTML::TreeBuilder->new_from_content($mech->content()); | |
print $tree->as_text(); | |
print "\n\n"; | |
print as_text($tree, delimiter => " "); | |
sub as_text { | |
# Yet another iteratively implemented traverser | |
my ( $this, %options ) = @_; | |
my $skip_dels = $options{'skip_dels'} || 0; | |
my (@pile) = ($this); | |
my $tag; | |
my $text = ''; | |
my $delimiter = $options{delimiter} || undef; | |
my $nillio = []; | |
while (@pile) { | |
if ( !defined( $pile[0] ) ) { # undef! | |
shift @pile; # how did that get in here? | |
} | |
elsif ( !ref( $pile[0] ) ) { # text bit! save it! | |
$text .= shift @pile; | |
$text .= $delimiter if defined ($delimiter); | |
} | |
else { # it's a ref -- traverse under it | |
unshift @pile, @{ $this->{'_content'} || $nillio } | |
unless ( $tag = ( $this = shift @pile )->{'_tag'} ) eq 'style' | |
or $tag eq 'script' | |
or ( $skip_dels and $tag eq 'del' ); | |
} | |
} | |
return $text; | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment