commit 38b01c17db70af16c70b9b75000b302494d3c18f
parent 60346754980b30e22c556d2b580674f3e29e2b5d
Author: kyle <kyle@getaddrinfo.net>
Date: Sun, 6 Mar 2016 10:57:37 -0700
memexp: add product page description scraping support.
Diffstat:
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/PS/MemoryExpress.pm b/PS/MemoryExpress.pm
@@ -91,6 +91,12 @@ sub scrape_price {
}
sub scrape_description {
+ my ($self, $resp) = @_;
+ my $dom = HTML::Grabber->new( html => $resp->decoded_content );
+
+ # Product page description is inside <h1> tags
+ my $description = $dom->find(".PDH_HeaderBlock h1")->text();
+ return $description;
}
sub find_product_page {
diff --git a/t/memory_express.t b/t/memory_express.t
@@ -4,7 +4,7 @@ use PS::MemoryExpress;
use Log::Log4perl qw(:easy);
use Test;
-BEGIN { plan tests => 17 }
+BEGIN { plan tests => 18 }
Log::Log4perl->easy_init($INFO);
@@ -36,6 +36,9 @@ ok(@others == 0);
ok($price > 200.0);
ok($price < 400.0);
+my $descr = $me->scrape_description($resp);
+ok($descr, "8TB Archive HDD, SATA III w/ 128MB Cache");
+
# Search for something I know has multiple results
#