forums.o.o-topposters.rb

#! /usr/bin/env ruby
# Scrape the user list of forums.opensuse.org to make a list of those
# who have posted at least LIMIT items, for use by the feed filter mentioned in
# http://mvidner.blogspot.com/2010/07/helping-newcomers.html 
require "rubygems"
require "nokogiri"
require "open-uri"

LIMIT = 15
PERPAGE = 50
page = 1
count = nil

begin
  url = "http://forums.opensuse.org/members/list/index#{page}.html?order=desc&sort=posts&pp=#{PERPAGE}"
  $stderr.puts url
  doc = Nokogiri::HTML(open url)

  doc.css("a.username").each do |u|
    count_n = u.at_xpath('../../td[@class="alt1 postcount"]')
    count = count_n.content.tr("^0-9", "").to_i
    break if count <= LIMIT
    $stderr.printf "%5d ", count
    puts u.content
  end
  page += 1
end until count <= LIMIT