-
-
Save abinoam/0d83e2487a0e955411d6 to your computer and use it in GitHub Desktop.
Sybren Kooistra doubt - http://www.ruby-forum.com/topic/4405257
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'nokogiri' | |
require 'open-uri' | |
def get_search_result_links(n_page) | |
links = n_page.css('.linker-kolom li a') | |
puts "** There were #{links.length} links found" | |
links.each do |link| | |
href = link['href'] | |
inner_url = 'https://zoek.officielebekendmakingen.nl' + href | |
puts "\n\n\nFetching page at #{File.basename(inner_url).split('?')[0]}" | |
datalezer = open(inner_url).read | |
lokalenieuwefilenaam = href + ".html" | |
lokalenieuwefile = open(lokalenieuwefilenaam, "w") | |
lokalenieuwefile.write(datalezer) | |
lokalenieuwefile.close | |
end | |
end | |
INITIAL_URL = 'https://zoek.officielebekendmakingen.nl/zoeken/resultaat/?zkt=Uitgebreid&pst=ParlementaireDocumenten' | |
initial_page = Nokogiri::HTML(open(INITIAL_URL)) | |
pagination_links = initial_page.css('.paginering.beneden a') | |
last_page_link = pagination_links[-2] | |
last_page_number = last_page_link.text.to_i | |
(5..last_page_number).each do |page_num| | |
puts "\n\n\n***** Getting page #{page_num}" | |
results_page_url = "#{INITIAL_URL}&_page=#{page_num}" | |
results_page = Nokogiri::HTML(open(results_page_url)) | |
get_search_result_links(results_page) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment