Created
June 3, 2023 06:24
-
-
Save denpatin/24360e025c958805b8e3256a71772c5d to your computer and use it in GitHub Desktop.
Download all MS StyleGuides from https://www.microsoft.com/en-us/language/StyleGuides
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
# frozen_string_literal: true | |
source 'https://rubygems.org' | |
gem 'nokogiri' | |
gem 'rubocop', require: false |
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
#!/usr/bin/env ruby | |
# frozen_string_literal: true | |
require 'nokogiri' | |
require 'open-uri' | |
URL = 'https://www.microsoft.com/en-us/language/StyleGuides' | |
PDF_FOLDER = 'pdf_files' | |
html = URI.parse(URL).open.read | |
doc = Nokogiri::HTML(html) | |
pdf_list = doc.at_css('#ddlStyleGuideLanguage') | |
options = pdf_list.css('option') | |
Dir.mkdir(PDF_FOLDER) unless Dir.exist?(PDF_FOLDER) | |
mutex = Mutex.new | |
threads = [] | |
options.each do |option| | |
value = option['value'] | |
next if value.nil? || !value.end_with?('.pdf') | |
file_name = "#{option.text.strip}.pdf" | |
file_path = File.join(PDF_FOLDER, file_name) | |
threads << Thread.new do | |
mutex.synchronize do | |
URI.parse(value).open do |pdf_file| | |
File.open(file_path, 'wb') do |file| | |
file.write(pdf_file.read) | |
end | |
end | |
end | |
puts "#{file_name} downloaded successfully." | |
rescue StandardError => e | |
warn "Failed to download #{file_name}: #{e.message}" | |
end | |
end | |
threads.each(&:join) | |
puts 'All PDF files downloaded.' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment