Last active
January 2, 2016 18:59
-
-
Save kamui/8347721 to your computer and use it in GitHub Desktop.
A ruby script to scrape a site for a specific dom node change. It will email you if you choose when the content changes and what the new node content changed into. Require `nokogiri` and `pony` gems. http://jackchu.com/articles/2014/01/10/web-scraping-content-changes-with-nokogiri/
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' | |
require 'pony' | |
require 'digest' | |
URL = 'https://encrypted.google.com/'.freeze | |
CSS_SELECTOR = '#lga'.freeze | |
INTERVAL = 600.freeze | |
USER_AGENT = "Ruby/#{RUBY_VERSION}".freeze | |
SEND_EMAIL = false | |
MAIL_FROM = '[email protected]'.freeze | |
MAIL_TO = '[email protected]'.freeze | |
MAIL_OPTIONS = { | |
address: 'smtp.gmail.com', | |
port: '587', | |
enable_starttls_auto: true, | |
user_name: 'user', | |
password: 'password', | |
authentication: :plain, # :plain, :login, :cram_md5, no auth by default | |
domain: "localhost.localdomain" # the HELO domain provided by the client to the server | |
}.freeze | |
Pony.options = { | |
from: MAIL_FROM, | |
via: :smtp, | |
via_options: MAIL_OPTIONS | |
} | |
target_digest = nil | |
while(true) do | |
doc = Nokogiri::HTML(open(URL, 'User-Agent' => USER_AGENT)) | |
content = doc.css(CSS_SELECTOR).first | |
content_digest = Digest::MD5.new.digest(content.to_s) | |
if target_digest.nil? | |
target_digest = content_digest | |
puts "#{Time.now}: Seeded content: #{content}" | |
elsif content_digest.strip != target_digest.strip | |
puts "#{Time.now}: #{content}" | |
Pony.mail({ | |
to: MAIL_TO, | |
subject: "Web Scrape Script: Target website has been updated!", | |
body: "Target URL: #{URL}\n\nChange: #{content}" | |
}) if SEND_EMAIL | |
target_digest = content_digest | |
else | |
puts "#{Time.now}: No change" | |
end | |
sleep INTERVAL | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment