From: Petter Reinholdtsen Date: Sat, 28 Feb 2009 22:54:03 +0000 (+0000) Subject: Improve HTML. X-Git-Url: http://pere.pagekite.me/gitweb/homepage.git/commitdiff_plain/e8235ae50c510203c61fa611a2f767130d52884b?ds=inline;hp=a93d61e1567d5836402fdadf90f5380108df5d0b Improve HTML. --- diff --git a/blog/data/2009-02-28-hw-support.txt b/blog/data/2009-02-28-hw-support.txt index aeb42fd64d..10ed3a4fd2 100644 --- a/blog/data/2009-02-28-hw-support.txt +++ b/blog/data/2009-02-28-hw-support.txt @@ -37,7 +37,7 @@ scraping was written by me based on the Dell code. I know the HTML parsing could be done using nice libraries, but did not want to introduce more dependencies. This is the current incarnation:

-

+
 use LWP::Simple;
 use POSIX;
 use WWW::Mechanize;
@@ -49,7 +49,7 @@ sub get_support_info {
 
     if ( $model =~ m/^Dell / ) {
         # fetch website from Dell support
-        my $url = "http://support.euro.dell.com/support/topics/topic.aspx/emea/shared/support/my_systems_info/no/details?c=no&cs=nodhs1&l=no&s=dhs&ServiceTag=$serial";
+        my $url = "http://support.euro.dell.com/support/topics/topic.aspx/emea/shared/support/my_systems_info/no/details?c=no&cs=nodhs1&l=no&s=dhs&ServiceTag=$serial";
         my $webpage = get($url);
         return undef unless ($webpage);
 
@@ -57,7 +57,7 @@ sub get_support_info {
         my @lines = split(/\n/, $webpage);
         foreach my $line (@lines) {
             next unless ($line =~ m/Beskrivelse/);
-            $line =~ s/<[^>]+?>/;/gm;
+            $line =~ s/<[^>]+?>/;/gm;
             $line =~ m%;(\d{2})/(\d{2})/(\d{4});+(\d{2})/(\d{2})/(\d{4});%g;
             my $start = "$3-$1-$2";
             my $end = "$6-$4-$5";
@@ -83,7 +83,7 @@ sub get_support_info {
         # Next step is screen scraping
         my $content = $mech->content();
 
-        $content =~ s/<[^>]+?>/;/gm;
+        $content =~ s/<[^>]+?>/;/gm;
         $content =~ s/\s+/ /gm;
         $content =~ s/;\s*;/;;/gm;
         $content =~ s/;[\s;]+/;/gm;
@@ -106,11 +106,11 @@ sub get_support_info {
         }
     } elsif ( $model =~ m/^IBM / ) {
         my ($producttype) = $model =~ m/.*-\[(.{4}).+\]-/;
-        if ($producttype && $serial) {
+        if ($producttype && $serial) {
             my $content =
-                get("http://www-947.ibm.com/systems/support/supportsite.wss/warranty?action=warranty&brandind=5000008&Submit=Submit&type=$producttype&serial=$serial");
+                get("http://www-947.ibm.com/systems/support/supportsite.wss/warranty?action=warranty&brandind=5000008&Submit=Submit&type=$producttype&serial=$serial");
             if ($content) {
-                $content =~ s/<[^>]+?>/;/gm;
+                $content =~ s/<[^>]+?>/;/gm;
                 $content =~ s/\s+/ /gm;
                 $content =~ s/;\s*;/;;/gm;
                 $content =~ s/;[\s;]+/;/gm;
@@ -128,19 +128,19 @@ sub get_support_info {
     }
     return $str;
 }
-

+

Here are some examples on how to use the function, using fake serial numbers. The information passed in as arguments are fetched from dmidecode.

-

+
 print get_support_info("hp.host", "HP ProLiant BL460c G1", "1234567890"
                        "447707-B21");
 print get_support_info("dell.host", "Dell Inc. PowerEdge 2950", "1234567");
 print get_support_info("ibm.host", "IBM eserver xSeries 345 -[867061X]-",
                        "1234567");
-

+

I would recommend this approach for tracking support contracts for everyone with more than a new computers to administer. :)