Check Resource Counts

Gemfile

# frozen_string_literal: true

source "https://rubygems.org"

git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }

gem "mechanize"
gem 'progress_bar'
gem 'terminal-table'

Rakefile

require 'colorize'
require 'mechanize'
require 'progress_bar'
require 'terminal-table'

@base_url = 'https://dlmenetwork.org/library/browse'
@agent = Mechanize.new

namespace :test do
  desc 'Test landing page item counts'
  task :landing_page do

    rows = []
    bar = ProgressBar.new(categories.size)

    @page = @agent.get(@base_url)
    categories = @page.search("//div[contains(@class, 'category')]")

    categories.each do |category|
      # extract items
      count = category.search('small').text.gsub(/item?(s?)/, '').strip.to_i
      label = category.search('span[@class="title"]').text

      link = category.search('a').first
      # go to page
      view = @agent.click(link)
      page_count = view.search('small').text.gsub(/item?(s?)/, '').strip.to_i

      difference = page_count - count
      bar.puts "Checking #{label}".green
      bar.increment!

      rows << [label, count, page_count, difference]

    end

    table = Terminal::Table.new headings: ['Category', 'Index Count', 'Page Count', 'Difference'], rows: rows

    puts table
  end
end

results.txt

+--------------------------------------------------------------+-------------+------------+------------+
| Category                                                     | Index Count | Page Count | Difference |
+--------------------------------------------------------------+-------------+------------+------------+
| Manuscripts from the Free Library of Philadelphia            | 87          | 87         | 0          |
| Abdul-Hamid II Books and Serials, Library of Congress        | 321         | 3414       | 3093       |
| Manuscripts from the University of Pennsylvania Libraries    | 692         | 692        | 0          |
| Persian Language Rare Materials, Library of Congress         | 5232        | 5232       | 0          |
| Manuscripts from Haveford College                            | 32          | 32         | 0          |
| Manuscripts from Bryn Mawr College                           | 22          | 22         | 0          |
| Rare Books & Manuscripts, Columbia University Library        | 220         | 220        | 0          |
| Manuscripts from the Library Company of Philadelphia         | 4           | 4          | 0          |
| Sakip Sabanci Museum's Emirgân Archive                       | 305         | 3515       | 3210       |
| Abdul Hamid II Photograph Collection, Library of Congress    | 1817        | 1818       | 1          |
| Manuscripts from the American Philosophical Society          | 4           | 4          | 0          |
| Libraries of the Greek & Armenian Patriarchates in Jerusalem | 1002        | 1002       | 0          |
| Manuscripts from the Philadelphia Museum of Art              | 1           | 1          | 0          |
| Muhammad Ali Eltaher Collection, Library of Congress         | 105         | 5232       | 5127       |
| Manuscripts from St. Catherine's Monastery, Mt. Sinai        | 1687        | 1687       | 0          |
| Medical Manuscripts                                          | 189         | 31386      | 31197      |
| Qur'an Manuscripts                                           | 186         | 141285     | 141099     |
| Persian Manuscripts                                          | 677         | 677        | 0          |
| Manuscripts in Naskh Script                                  | 1472        | 69247      | 67775      |
| Mathematical Manuscripts                                     | 183         | 31386      | 31203      |
| Manuscripts in Muhaqqaq Script                               | 18          | 69247      | 69229      |
| Cairo Genizah Manuscripts                                    | 22743       | 31386      | 8643       |
| Richard B. Parker Nile Watercraft Photographs                | 75          | 5705       | 5630       |
| Arabic Manuscripts                                           | 7211        | 7211       | 0          |
| Manuscripts in Riqa Script                                   | 10          | 69247      | 69237      |
| Émile Béchard's Oriental Studies Photographs                 | 90          | 5705       | 5615       |
| Astronomy Manuscripts                                        | 130         | 31386      | 31256      |
| Ottoman Turkish Manuscripts                                  | 182         | 182        | 0          |
| Manuscripts in Thuluth Script                                | 84          | 69247      | 69163      |
| Manuscripts in Nastaliq Script                               | 515         | 69247      | 68732      |
| Turkish Painting: Ottoman Reformation to the Republic        | 492         | 3515       | 3023       |
| Abidin Dino Archive                                          | 2118        | 141285     | 139167     |
| Hassan Fathy Architectural Archives                          | 56          | 3931       | 3875       |
| Ramses Wissa Wassef Architectural Drawings                   | 48          | 5705       | 5657       |
| K.A.C. Creswell Photographs of Islamic Architecture          | 1006        | 5705       | 4699       |
+--------------------------------------------------------------+-------------+------------+------------+