--- trunk/feeds/sciencedirect2.pl	2003/07/05 18:26:40	70
+++ trunk/feeds/sciencedirect2.pl	2004/06/10 22:05:38	338
@@ -14,6 +14,11 @@
 
 my $debug=1;
 
+my $file;
+
+# uncomment following line if you want to use file instead of http connection
+#$file="list.html";
+
 # configure ScienceDirect CVS files location
 my $csv_dir="/data/isis_data/sciencedirect";
 my $j_holdings="sd_JournalHoldingsRpt.txt";
@@ -69,8 +74,8 @@
 	}
 
 	foreach my $i (4, 6, 8, 10) {
+		push @{$journal->{$key}},$data[$i] || "";
 		if ($data[$i]) {
-			push @{$journal->{$key}},$data[$i];
 			$c_nr++;
 		}
 	}
@@ -81,35 +86,46 @@
 
 $debug++ if (lc($ARGV[0]) eq "-d");
 
-my $ua = new LWP::UserAgent;
-$ua->agent("Mjesec educational harvester -- contact mglavica\@ffzg.hr 0.0");
-$ua->timeout(60);
-#$ua->env_proxy();
-#$ua->proxy(['http', 'ftp'], 'http://proxy.carnet.hr:8001/');
-
-print STDERR "getting '$url'...\n" if ($debug);
-my $req = HTTP::Request->new(GET => $url);
 
-my @out;
+my $res;
+if (! $file) {
+	my $ua = new LWP::UserAgent;
+	$ua->agent("Mjesec educational harvester -- contact mglavica\@ffzg.hr 0.0");
+	$ua->timeout(60);
+	#$ua->env_proxy();
+	#$ua->proxy(['http', 'ftp'], 'http://proxy.carnet.hr:8001/');
+
+	print STDERR "getting '$url'...\n" if ($debug);
+	my $req = HTTP::Request->new(GET => $url);
+
+	$res = $ua->request($req);
+} elsif (! -e $file) {
+	die "can't find feed file '$file'";
+}
 
-my $res = $ua->request($req);
-if ($res->is_success) {
+if ($file || $res->is_success) {
 	print STDERR "parsing html...\n" if ($debug);
 	my $tree = HTML::TreeBuilder->new;
-#	$tree->parse_file("list.html");   # !
-	$tree->parse($res->content);
+	if ($file) {
+		$tree->parse_file("list.html");
+	} else {
+		$tree->parse($res->content);
+	}
 
 	foreach my $tr ($tree->look_down('_tag', 'tr')) {
 		my $link;
-		if ($link = $tr->look_down('_tag','a')) {
+		foreach my $link ($tr->look_down('_tag','a')) {
 			if ($link->attr('href') =~ m{/science\?_ob=JournalURL}) {
 				my $j=nuc($link->as_text);
 				if ($journal->{$j}) {
-					print join("\n",@{$journal->{$j}});
+					my $i=0;
+					foreach my $line (@{$journal->{$j}}) {
+						print $i++,": $line\n";
+					}
 					$j_detailed++;
 				} else {
-					print $link->attr('href')."\n";
-					print $link->as_text."\n";
+					print "0: ",$link->as_text."\n";
+					print "7: http://www.sciencedirect.com",$link->attr('href')."\n";
 					$j_basic++;
 					print STDERR "can't find details for $j\n" if ($debug);
 				}