Created
October 11, 2013 15:55
-
-
Save TrevMcKendrick/6937239 to your computer and use it in GitHub Desktop.
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
class StudentScraper | |
attr_accessor :main_index_url | |
def initialize(main_index_url) | |
@main_index_url = main_index_url | |
end | |
def call | |
require 'nokogiri' | |
require 'open-uri' | |
index_page = Nokogiri::HTML(open("#{self.main_index_url}")) | |
students_array = index_page.css('li.home-blog-post div.blog-thumb a').collect do |link| | |
link.attr('href') | |
end | |
students = [] | |
begin | |
students_array.each do |student| | |
student_website = "#{self.main_index_url}/#{student}" | |
student_page = Nokogiri::HTML(open("#{student_website}")) | |
name = student_page.css('h4.ib_main_header').text | |
social_media = student_page.css('div.social-icons a').collect do |link| | |
link.attr('href') | |
end | |
quote = student_page.css('div.textwidget h3').text | |
text = student_page.css('div.services p').collect do |link| | |
link.content.strip if link.element_children.empty? | |
end | |
text = text.compact | |
# Insert data stored in variables into student_hash | |
student = {} | |
student[:name] = name | |
student[:twitter] = social_media[0] | |
student[:linkedin] = social_media[1] | |
student[:github] = social_media[2] | |
student[:facebook] = social_media[3] | |
student[:website] = student_website | |
student[:quote] = quote | |
student[:bio] = text[0] | |
student[:work] = text[1] | |
students << student | |
end | |
rescue | |
end | |
students | |
end | |
end | |
#puts StudentScraper.new("http://students.flatironschool.com").call |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment