count blog sites from blog list.
# count blogsites from blog list.
# Usage:
# ./count_blogs.pl blog_500.txt
while(<>){
# print $_;
next unless /http:/;
@url = split(/\//, $_);
# print join(":", @url);
$servername = $url[2];
# print $servername, "\n";
$servername = "fc2.com" if $servername =~ /.*\.fc2\.com/o;
$servername = "dtiblog.com" if $servername =~ /.*\.dtiblog\.com/o;
$servername = "exblog.jp" if $servername =~ /.*\.exblog\.jp/o;
$servername = "livedoor.biz" if $servername =~ /.*\.livedoor\.biz/o;
$servername = "at.webry.info" if $servername =~ /.*\.at.webry\.info/o;
$servername = "seesaa.net" if $servername =~ /.*\.seesaa\.net/o;
$servername = "jugem.jp" if $servername =~ /.*\.jugem\.jp/o;
$servername = "blog.ocn.ne.jp" if $servername =~ /.*\.blog\.ocn\.ne\.jp/o;
$servername = "cocolog-nifty.com" if $servername =~ /.*\.cocolog-nifty\.com/o;
$servername = "blogspot.com" if $servername =~ /.*\.blogspot\.com/o;
$servername = "sakura.ne.jp" if $servername =~ /.*\.sakura\.ne\.jp/o;
$servername = "blog.so-net.ne.jp" if $servername =~ /.*\.blog\.so-net\.ne\.jp/o;
$servername = "ap.teacup.com" if $servername =~ /.*\.ap\.teacup\.com/o;
$servers{$servername}++;
}
foreach $servername (sort {$servers{$b} <=> $servers{$a}} keys %servers){
print $servername, ":", $servers{$servername}, "\n";
}