-
-
Save statianzo/1886365 to your computer and use it in GitHub Desktop.
export google history
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 'mechanize' | |
require 'logger' | |
require 'date' | |
## Call: | |
## $ ruby export.rb <gmail> <password> | |
caFile = File.join(File.dirname(__FILE__), 'cacert.pem') | |
if not File.exists? caFile | |
require 'net/http' | |
puts 'Getting cacert.pem' | |
Net::HTTP.start('curl.haxx.se') do |http| | |
resp = http.get '/ca/cacert.pem' | |
open(caFile, 'w') { |f| f.write resp.body } | |
end | |
end | |
agent = Mechanize.new do |a| | |
a.user_agent_alias = 'Linux Mozilla' | |
a.log = Logger.new(STDOUT) | |
a.log.level = Logger::WARN | |
a.ca_file = caFile | |
end | |
puts 'Logging in...' | |
login_page = agent.get('http://www.google.com/history') | |
success_page = login_page.form_with(:action => 'https://accounts.google.com/ServiceLoginAuth') do |f| | |
f.Email = ARGV[0] | |
f.Passwd = ARGV[1] | |
end.click_button | |
puts 'Getting history...' | |
feedURL = 'http://www.google.com/history/lookup?output=rss&num=9999' | |
prevDate = nil | |
d = nil | |
loop do | |
rss = agent.get(feedURL) | |
rssXml = Nokogiri::XML(rss.body) | |
pubDates = rssXml.xpath('//pubDate') | |
d = DateTime.parse(pubDates.last.inner_text) | |
# end if the last date | |
break if prevDate == d | |
prevDate = d | |
firstDate = DateTime.parse(pubDates.first.inner_text) | |
fileName = "#{firstDate.year}#{'%02d' % firstDate.month}#{'%02d' % firstDate.day}.xml" | |
rss.save(fileName) | |
puts 'Saved ' + fileName | |
feedURL = "http://www.google.com/history/lookup?output=rss&num=9999&month=#{d.month}&day=#{d.day}&yr=#{d.year}" | |
end | |
puts 'Last item: ' + d.to_s | |
puts 'Done' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment