Last active
August 29, 2015 14:05
-
-
Save jrmehle/b306bb6c743edc58cc4e to your computer and use it in GitHub Desktop.
A script to quickly see if any bikes I'm interested in are in stock on my favorite site to buy bikes from.
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 'colorize' | |
class BikeScraper | |
BIKES_DIRECT_URL = 'http://www.bikesdirect.com/products/cross_bikes.htm' | |
TARGET_BIKE_SIZE_REGEX = /56cm/ | |
TARGET_BIKE_NAME = 'Fantom' | |
def execute | |
bikes_index_page = open_page(BIKES_DIRECT_URL) | |
target_bikes = bikes_index_page.css("a:contains(\"#{TARGET_BIKE_NAME}\")") | |
bike_urls = target_bikes.collect { |node| { title: sanitize_title(node.css('strong').text), url: node.attributes['href'].value } }.uniq | |
bike_urls.each do |link| | |
bike_page = open_page(link[:url]) | |
puts | |
puts "### #{link[:title]} ###" | |
puts link[:url] | |
puts bike_sizes(bike_page) | |
end | |
end | |
private | |
def bike_sizes(bike_page) | |
bike_page.css('select').collect do |bike_size_selector| | |
bike_sizes = bike_size_selector.children.select { |node| node['value'] if node['value'] =~ /\d+cm/ } | |
next if bike_sizes.empty? | |
bike_sizes.collect { |s| s.attributes['value'].value =~ TARGET_BIKE_SIZE_REGEX ? s.attributes['value'].value.red : s.attributes['value'].value } | |
end.compact.join("\t\n") | |
end | |
def sanitize_title(title) | |
title.gsub(/NEW|CLEARANCE|SALE|SaleSave Thousands|,* Save Up To 60\%|Save Over \d+\%|Sale2014,/, '') | |
.gsub('PROFINAL', 'PRO') | |
.gsub('UNOOnly', 'UNO') | |
.strip | |
end | |
def open_page(url) | |
Nokogiri::HTML(open(url)) | |
end | |
end | |
BikeScraper.new.execute |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment