diff options
author | Lorry Tar Creator <lorry-tar-importer@lorry> | 2013-05-08 22:21:52 +0000 |
---|---|---|
committer | Lorry Tar Creator <lorry-tar-importer@lorry> | 2013-05-08 22:21:52 +0000 |
commit | 2f253cfc85ffd55a8acb988e91f0bc5ab348124c (patch) | |
tree | 4734ccd522c71dd455879162006742002f8c1565 /eg/hanchors | |
download | HTML-Parser-tarball-2f253cfc85ffd55a8acb988e91f0bc5ab348124c.tar.gz |
HTML-Parser-3.71HEADHTML-Parser-3.71master
Diffstat (limited to 'eg/hanchors')
-rwxr-xr-x | eg/hanchors | 48 |
1 files changed, 48 insertions, 0 deletions
diff --git a/eg/hanchors b/eg/hanchors new file mode 100755 index 0000000..c7693fd --- /dev/null +++ b/eg/hanchors @@ -0,0 +1,48 @@ +#!/usr/bin/perl -w + +# This program will print out all <a href=".."> links in a +# document together with the text that goes with it. +# +# See also HTML::LinkExtor + +use HTML::Parser; + +my $p = HTML::Parser->new(api_version => 3, + start_h => [\&a_start_handler, "self,tagname,attr"], + report_tags => [qw(a img)], + ); +$p->parse_file(shift || die) || die $!; + +sub a_start_handler +{ + my($self, $tag, $attr) = @_; + return unless $tag eq "a"; + return unless exists $attr->{href}; + print "A $attr->{href}\n"; + + $self->handler(text => [], '@{dtext}' ); + $self->handler(start => \&img_handler); + $self->handler(end => \&a_end_handler, "self,tagname"); +} + +sub img_handler +{ + my($self, $tag, $attr) = @_; + return unless $tag eq "img"; + push(@{$self->handler("text")}, $attr->{alt} || "[IMG]"); +} + +sub a_end_handler +{ + my($self, $tag) = @_; + my $text = join("", @{$self->handler("text")}); + $text =~ s/^\s+//; + $text =~ s/\s+$//; + $text =~ s/\s+/ /g; + print "T $text\n"; + + $self->handler("text", undef); + $self->handler("start", \&a_start_handler); + $self->handler("end", undef); +} + |