Created
July 29, 2008 10:44
-
-
Save kirel/3060 to your computer and use it in GitHub Desktop.
Scraping ugly tables...
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/ruby | |
require 'rubygems' | |
gem 'RubyInline', '=3.6.3' | |
require 'scrubyt' | |
bus_data = Scrubyt::Extractor.define do | |
fetch 'http://rvm-online.de' | |
route = { :place_origin => "everswinkel", | |
:name_origin => "mitte", | |
:place_destination => "münster (westf)", | |
:name_destination => "hbf", } | |
now = Time.now | |
time = { :itdTimeHour => now.hour, | |
:itdTimeMinute => now.min, | |
:itdDateDay => now.day, | |
:itdDateMonth => now.mon, | |
:itdDateYear => now.year, } | |
route.each { |field,value| fill_textfield field, value } | |
time.each { |field,value| fill_textfield field, value } | |
submit | |
# scrape result | |
fahrten "//table//table[2]//tr[15]//table" do | |
fahrt "//" do | |
ab "//tr[3]//td[2]//span" | |
an "//tr[4]//td[2]//span" | |
bus "//tr[3]//td[8]//span" | |
end | |
fahrt "//" do | |
ab "//tr[11]//td[2]//span" | |
an "//tr[12]//td[2]//span" | |
bus "//tr[11]//td[8]//span" | |
end | |
fahrt "//" do | |
ab "//tr[19]//td[2]//span" | |
an "//tr[20]//td[2]//span" | |
bus "//tr[19]//td[8]//span" | |
end | |
end | |
end | |
puts bus_data.to_xml |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment