Scrape Zootaxa Issues for ORCID IDs

zootaxa_orcid_scrape.rb

#!/usr/bin/env ruby
# encoding: utf-8

require 'rest_client'
require 'csv'
require 'nokogiri'
require 'colorize'

page_range = 1..10

def get_doc_urls(url, xpath)
  html = RestClient.get(url)
  doc = Nokogiri::HTML.parse(html)
  doc.xpath(xpath).map{|a| a.attributes["href"].value}
end

CSV.open("orcids.csv", "w") do |csv|
  page_range.each do |i|
    issue_urls = get_doc_urls("https://www.mapress.com/j/zt/issue/archive?issuesPage=#{i}", "//*[@id=\"issues\"]//h4/a")
    issue_urls.each do |url|
      toc_urls = get_doc_urls(url, "//*[@class=\"tocTitle\"]/a")
      toc_urls.each do |url|
        orcid_urls = get_doc_urls(url, "//a[contains(@href, 'orcid')]")
        orcids = orcid_urls.map{|o| o.sub!("https://orcid.org/", "")}
        orcids.each do |orcid|
          if orcid
            csv << [orcid]
            puts orcid.green
          end
        end
      end
    end
  end
end