Created
January 1, 2011 20:57
-
-
Save ashaw/762004 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 'rest_client' | |
require 'nokogiri' | |
require 'pp' | |
def escape_csv(string) | |
string.gsub(/,/,'/') | |
end | |
class Crunch | |
attr_reader :company_data | |
def initialize(page) | |
@crunch = Nokogiri::HTML(RestClient.get("http://www.crunchbase.com/search/advanced/companies/605026?page=#{page}")) | |
@company_data = [] | |
end | |
def parse | |
@crunch.css(".search_result_name a").each do |company_link| | |
crunch_link = "http://crunchbase.com" + company_link.attr("href") | |
company = {:name => escape_csv(company_link.content), :url => crunch_link, :employees => company_people(crunch_link)} | |
@company_data << company | |
puts company_link.content | |
end | |
end | |
def company_people(company_link) | |
employees = [] | |
titles = [] | |
company_page = Nokogiri::HTML(RestClient.get(company_link)) | |
company_page.css(".col1_people_name a").each do |person| | |
employees << escape_csv(person.content) | |
end | |
company_page.css(".col1_people_title").each do |title| | |
titles << escape_csv(title.content) | |
end | |
employees_with_titles = [] | |
(0..employees.length).each do |number| | |
employees_with_titles << {employees[number], titles[number]} | |
end | |
p employees_with_titles | |
employees_with_titles | |
end | |
end | |
class CSVBuilder | |
FIELDS = "name,url,employees" | |
attr_reader :doc | |
def initialize(company_array) | |
@doc = "" | |
doc << FIELDS + "\n" | |
company_array.each do |company| | |
employees = "" | |
company[:employees].each do |employee| | |
employee.each do |name,title| | |
employees << "#{name}" | |
p "#{name}" | |
if title && !title.strip.empty? | |
employees << " (#{title})" | |
p " (#{title})" | |
end | |
employees << "," | |
end | |
end | |
doc << "#{company[:name]},#{company[:url]},#{employees}\n" | |
end | |
@doc | |
end | |
end | |
master_company_data = [] | |
(1..2).each do |page| | |
c = Crunch.new(page) | |
c.parse | |
master_company_data << c.company_data | |
end | |
csv = CSVBuilder.new(master_company_data.flatten) | |
f = File.open('crunchbase.csv', 'w+') do |data| | |
data.write csv.doc | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment