Created
November 7, 2012 18:34
-
-
Save flakyfilibuster/4033460 to your computer and use it in GitHub Desktop.
grouphug_nokogiri
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 'rubygems' | |
require 'nokogiri' | |
require 'open-uri' | |
class Grouphug_scraper | |
attr_accessor :confessions, :ids, :title | |
def initialize(url) | |
@confessions = [] | |
@ids = [] | |
@url = url | |
@title = "" | |
@doc = Nokogiri::HTML(open(@url)) | |
end | |
def titlizer | |
@title = doc.at_css("title").text | |
end | |
def scrape_confessions | |
@doc.css("#confessions p").each do |confession| | |
@confessions << confession.text.gsub(/\t/, "") | |
end | |
end | |
def scrape_ids | |
@doc.css(".conf-id a").each do |id| | |
ids << id.text | |
end | |
end | |
def nice_print | |
ids.zip(confessions).each do |id, confession| | |
puts "#{id} : #{confession}\n" | |
end | |
end | |
end | |
scraper_deluxe = Grouphug_scraper.new('http://web.archive.org/web/20071025014638/http://grouphug.us/') | |
scraper_deluxe.scrape_confessions | |
scraper_deluxe.scrape_ids | |
scraper_deluxe.nice_print |
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_grouphug' | |
require 'nokogiri' | |
require 'open-uri' | |
require 'fakeweb' | |
FakeWeb.register_uri(:get, 'http://web.archive.org/web/20071025014638/http://grouphug.us/', :body => "Hello World!") | |
describe "nokogiri extracts data from grouphug and spits it in an array" do | |
let(:scraper) { Grouphug_scraper.new('http://web.archive.org/web/20071025014638/http://grouphug.us/') } | |
let(:doc) {} | |
context "nokogiri instanciates correctly" do | |
it "initiates with an emtpy confessions array" do | |
scraper.confessions.should eql([]) | |
end | |
it "initiates with an empty ids array" do | |
scraper.ids.should == [] | |
end | |
it "puts the 'url' in the instance variable @url" do | |
scraper.stub(:url).and_return ('http://web.archive.org/web/20071025014638/http://grouphug.us/') | |
end | |
it "initializes with an empty title" do | |
scraper.title.should be_empty | |
end | |
xit "assigns a nokogiri object to 'doc'" do | |
scraper.stub(:doc).and_return (Nokogiri::HTML(open('http://web.archive.org/web/20071025014638/http://grouphug.us/'))) | |
scraper.doc.should be_a_kind_of(Nokogiri) | |
end | |
end | |
context "nokogiri titlizer returns correct title" do | |
it "assigns to the instance variable 'title' the correct title" do | |
scraper.stub(:titlizer).and_return ('group hug // anonymous online confessions') | |
scraper.titlizer.should eql('group hug // anonymous online confessions') | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment