ZooKeys ORCID Scrape

zookeys_orcid_scrape.rb

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

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

page_range = 0..50

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|
    orcid_urls = get_doc_urls("https://zookeys.pensoft.net/browse_journal_articles.php?journal_name=zookeys&journal_id=2&p=#{i}", "//*[@class=\"inline-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