Untitled

How to crawl the right way?
require 'rubygems'
require 'nokogiri'
require 'open-uri'
require 'rexml/document'
require 'csv'
include REXML

@urls = Array.new
@ID = Array.new
@titleSv = Array.new
@titleEn = Array.new
@identifier = Array.new
@typeOfLevel = Array.new

htmldoc = Nokogiri::HTML(open('http://testnavet.skolverket.se/SusaNavExport/EmilExporter?GetEvent&EMILVersion=1.1&NotExpired&EEFormOfStudy=normal&EIAcademicType=UoH&SelectEI'))

htmldoc.xpath('//a/@href').each do |links|
  @urls << links.content
end

@urls.each do |url|
  # Loop throw the XML files and grab element nodes
  xmldoc = REXML::Document.new(open(url).read)
  # Root element
  root = xmldoc.root
  # Hämtar info-id
  @ID << root.attributes["id"]
  # TitleSv
  xmldoc.elements.each("/educationInfo/titles/title[1] | /ns:educationInfo/ns:titles/ns:title[1]"){
    |e| m = e.text
        m = m.to_s
        next if m.empty?
        @titleSv << m
  }

CSV.open("eduction_normal.csv", "wb") do |row|
    (0..@ID.length - 1).each do |index|
      row << [@ID[index], @titleSv[index], @titleEn[index], @identifier[index], @typeOfLevel[index], @typeOfResponsibleBody[index], @courseTyp[index], @credits[index], @degree[index], @preAcademic[index], @subjectCodeVhs[index], @descriptionSv[index], @lastedited[index], @expires[index]]
    end
  end

items = Set.new

doc.xpath('//a/@href').each do |url|
  item = {}
  item[:url] = url.content
  items << item
end

items.each do |item|
  xml = Nokogiri::XML(open(item[:url]))

  item[:id] = xml.root['id']
  ...
end

xmldoc.elements.each("/educationInfo/titles/title[1] | /ns:educationInfo/ns:titles/ns:title[1]"){
    |e| m = e.text
     m = m.to_s
     next if m.empty?
     @titleSv << m
}

def get_value(xml, path)
   str = ''
   xml.elements.each(path) do |e|
     str = e.text.to_s
     next if str.empty?
   end

   str
end

xml_paths = {
  :title_sv => "/educationInfo/titles/title[1] | /ns:educationInfo/ns:titles/ns:title[1]",
  :title_en => "/educationInfo/titles/title[2] | /ns:educationInfo/ns:titles/ns:title[2]",
  ...
}

item[:title_sv] = get_value(xml, xml_paths[:title_sv])
item[:title_en] = get_value(xml, xml_paths[:title_en])

require 'rubygems'
require 'pioneer'
require 'nokogiri'
require 'rexml/document'
require 'csv'

class Links < Pioneer::Base
  include REXML
  def locations
    ["http://testnavet.skolverket.se/SusaNavExport/EmilExporter?GetEvent&EMILVersion=1.1&NotExpired&EEFormOfStudy=normal&EIAcademicType=UoH&SelectEI"]
  end

  def processing(req)
    doc = Nokogiri::HTML(req.response.response)
    htmldoc.xpath('//a/@href').map do |links|
      links.content
    end
  end
end

class Crawler < Pioneer::Base
  include REXML
  def locations
    Links.new.start.flatten
  end

  def processing(req)
    xmldoc = REXML::Document.new(req.respone.response)
    root = xmldoc.root
    id = root.attributes["id"]
    xmldoc.elements.each("/educationInfo/titles/title[1] | /ns:educationInfo/ns:titles/ns:title[1]") do |e|
      title = e.text.to_s
      CSV.open("eduction_normal.csv", "a") do |f|
        f << [id, title ...]
      end
    end
  end
end

Crawler.start
# or you can run 100 concurrent processes
Crawler.start(concurrency: 100)