Created
November 4, 2012 22:08
-
-
Save krtx/4013980 to your computer and use it in GitHub Desktop.
langrid scraper for back-translation
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
# coding: utf-8 | |
require 'watir' | |
require 'pp' | |
# !!! EDIT HERE !!! | |
userid = '' | |
password = '' | |
language = 'ja' # 'ja' or 'en' | |
topic_id = | |
# !!! KOKOMADE !!! | |
navi = {'ja' => ['原文編集', '翻訳'], 'en' => ['Pre-edit', 'Translate']} | |
browser = Watir::Browser.new | |
browser.goto 'http://langrid.org/tools/toolbox' | |
browser.text_field(:name => 'uname').set userid | |
browser.text_field(:name => 'pass').set password | |
browser.form(:name => 'login_form').submit | |
browser.goto "http://langrid.org/tools/toolbox/modules/forum/?topicId=#{topic_id.to_s}&lang=#{language}&ml_lang=#{language}" | |
loop do | |
links = browser.links(:text => navi[language][0]).length | |
links.times do |i| | |
browser.link(:text => navi[language][0], :index => i).click | |
browser.button(:text => navi[language][1], :index => 0).click | |
text = '' | |
loop do | |
sleep 2 | |
text = browser.div(:class => 'bbs-preview-back-translation-area').text | |
break if text != '' | |
end | |
puts text | |
browser.back | |
sleep 2 | |
end | |
begin | |
browser.link(:text => 'Next >>').click | |
rescue Watir::Exception::UnknownObjectException | |
break | |
end | |
sleep 2 | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment