masayuki5160 · April 21, 2014 23:02 · masayuki5160 · Apr 21, 2014
diff --git a/htmlParserGetLink.pl b/htmlParserGetLink.pl
 use strict;
 use warnings;
 use LWP::UserAgent;
 use HTML::TreeBuilder;

 my $url = "http://www.yahoo.co.jp";
 my $user_agent = "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)";

 my $ua = LWP::UserAgent->new('agent' => $user_agent);
 my $res = $ua->get($url);

 my $content;
 if($res->is_success){
 	$content = $res->content;
 	# print $content;
 }else{
 	die($res->status_line);
 }

 # HTML::TreeBuilderで解析する
 my $tree = HTML::TreeBuilder->new;
 $tree->parse($content);


 # 
 # DOM操作してトピックの部分だけ抜き出す。
 # 

 # <div id='topicsfb'><ul><li>....の部分を抽出する
 my @items =  $tree->look_down('id', 'topicsfb')->find('li');
 print $_->as_text."\n" for @items;

 # <div id='topicsfb'><ul><li><a href>....の部分を抽出する
 my @links =  $tree->look_down('id', 'topicsfb')->find('a');
 print $_->attr('href')."\n" for @links;
	use strict;
	use warnings;
	use LWP::UserAgent;
	use HTML::TreeBuilder;

	my $url = "http://www.yahoo.co.jp";
	my $user_agent = "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)";

	my $ua = LWP::UserAgent->new('agent' => $user_agent);
	my $res = $ua->get($url);

	my $content;
	if($res->is_success){
	$content = $res->content;
	# print $content;
	}else{
	die($res->status_line);
	}

	# HTML::TreeBuilderで解析する
	my $tree = HTML::TreeBuilder->new;
	$tree->parse($content);


	#
	# DOM操作してトピックの部分だけ抜き出す。
	#

	# <div id='topicsfb'><ul><li>....の部分を抽出する
	my @items = $tree->look_down('id', 'topicsfb')->find('li');
	print $_->as_text."\n" for @items;

	# <div id='topicsfb'><ul><li><a href>....の部分を抽出する
	my @links = $tree->look_down('id', 'topicsfb')->find('a');
	print $_->attr('href')."\n" for @links;