Created
August 26, 2013 07:31
-
-
Save ehlyzov/6338857 to your computer and use it in GitHub Desktop.
Parse data from eip.ru using EM Syncrony
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 'bundler' | |
| Bundler.require | |
| require "em-synchrony" | |
| require "em-synchrony/em-http" | |
| require "em-synchrony/fiber_iterator" | |
| agent = Mechanize.new | |
| base_uri = 'http://www.eip.ru/agency/city118/rielt' | |
| page_array = [] | |
| EM.synchrony do | |
| EM::Synchrony::FiberIterator.new( (1..116), 10 ).each do |page| | |
| url = "#{base_uri}/#{page}" | |
| page_array[page] = EventMachine::HttpRequest.new(url).get.response | |
| puts "page #{page}" | |
| end | |
| EventMachine.stop | |
| end | |
| File.open("pages.dump", 'w') do |file| | |
| Marshal.dump(page_array, file) | |
| end |
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 'bundler' | |
| Bundler.require | |
| require 'dm-core' | |
| require 'dm-migrations' | |
| require 'json' | |
| require 'csv' | |
| DataMapper.setup(:default, ENV['DATABASE_URL'] || "sqlite://#{Dir.pwd}/spb.db") | |
| class AgencyCard | |
| include DataMapper::Resource | |
| property :id, Serial | |
| property :title, String | |
| property :ein_url, String | |
| property :email, String | |
| property :phone, String | |
| property :address, String | |
| property :url, String | |
| property :excerpt, Text | |
| end | |
| DataMapper.finalize | |
| DataMapper.auto_upgrade! | |
| dumpfile = "#{Dir.pwd}/pages.dump" | |
| raise "dump before parse!" unless File.exists?(dumpfile) | |
| puts "dump found!" | |
| @pages_array = Marshal.load(File.open(dumpfile,'r').read).compact | |
| @pages_array.each do |page| | |
| doc = Nokogiri::HTML(page) | |
| doc.css('.smallcard').each do |card| | |
| email = card.xpath(".//a[starts-with(@href, 'mailto')]/text()").text | |
| title = card.xpath("./tr[1]/td").text | |
| AgencyCard.create({ | |
| title: title, | |
| email: email, | |
| excerpt: card.inner_html }) | |
| end | |
| end | |
| CSV.open('emails.csv', 'wb') do |csv| | |
| AgencyCard.each do |agency| | |
| csv << [ agency.title, agency.email, agency.id ] | |
| end | |
| end |
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
| source "https://rubygems.org" | |
| gem "sqlite3" | |
| gem "datamapper" | |
| gem "dm-sqlite-adapter" | |
| gem "mechanize" | |
| gem "pry" | |
| gem "em-synchrony" | |
| gem 'em-http-request' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment