Created
February 23, 2014 21:41
-
-
Save irmiller22/9177727 to your computer and use it in GitHub Desktop.
Kickstarter_scrape
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
# Kickstarter Project Scrape | |
require 'nokogiri' | |
# HTML, XML parser that allows us to view HTML code as series of nodes; able to highlight elements via CSS selectors | |
require 'open-uri' | |
# Module that allows you to make http request, and returns us the HTML content of a URL via the `open` command | |
require 'pry' | |
# projects | |
# kickstarter.css("li.project.grid_4") | |
# title | |
# project.css("h2.bbcard_name strong a").text | |
# image_link | |
# project.css("div.project-thumbnail a img").attribute("src").value | |
# description | |
# project.css("p.bbcard_blurb").text | |
# location | |
# project.css("ul.project-meta span.location-name").text | |
# percent_funded | |
# project.css("ul.project-stats li.first.funded strong").text --> .gsub("%", "").to_i | |
# 1 - projects hash | |
# 2 - name of project as the key | |
### want this to be converted to a symbol | |
# 3 - project attributes as the values stored within a hash | |
### key stored as a symbol | |
# 4 - image_link setup | |
# 5 - description setup | |
# 6 - location setup | |
# 7 - percent_funded setup | |
# projects = { | |
# :the_penguin_factory => { | |
# :image_link => "http://www.penguins.com/", | |
# :description => "A place where dreams come true", | |
# :location => "Paradise Bay, Antarctica", | |
# :percent_funded => 10 | |
# } | |
# } | |
# projects[:the_penguin_factory][:location] = "Paradise Bay, Antarctica" | |
html = File.read('fixtures/kickstarter.html') | |
kickstarter = Nokogiri::HTML(html) | |
projects = Hash.new | |
kickstarter.css("li.project.grid_4").each do |project| | |
title = project.css("h2.bbcard_name strong a").text.to_sym | |
projects[title] = { | |
:image_link => project.css("div.project-thumbnail a img").attribute("src").value, | |
:description => project.css("p.bbcard_blurb").text, | |
:location => project.css("ul.project-meta span.location-name").text, | |
:percent_funder => project.css("ul.project-stats li.first.funded strong").text.gsub("%", "").to_i | |
} | |
end | |
binding.pry | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment