poj#!perl use strict; use HTML::TreeBuilder 5 -weak; my $tree = HTML::TreeBuilder->new; $tree->parse_file(\*DATA); my @items = $tree->look_down( '_tag', 'meta' ) or die("no items: $!\n"); for my $item (@items) { print $item->attr('itemprop'); print ' = '; print $item->attr('content')."\n"; } __DATA__ <div class="review-content"> <div class="biz-rating biz-rating-very-large clearfix"> <div itemtype="http://schema.org/Rating" itemscope="" itemprop="re +viewRating"> <div class="rating-very-large"> <i title="4.0 star rating" class="star-img stars_4"> <img width="84" height="303" src="http://blah/v2/stars_map +.png" class="offscreen" alt="4.0 star rating"> </i> <meta content="4.0" itemprop="ratingValue"> </div> </div> <span class="rating-qualifier"> <meta content="2011-01-13" itemprop="datePublished"> 1/13/2011 </span> </div> <p lang="en" itemprop="description" class="review_comment ieSucks"> blah!! </p> </div>
In reply to Re: Extracting span and meta content with HTML::TreeBuilder
by poj
in thread Extracting span and meta content with HTML::TreeBuilder
by wrinkles
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |