How do I combine this Hash to a single JSON object

问题:

I'm using the following code to generate a JSON file containing all category information for a particular website.

The goal is to have a JSON file with the following format:

[
   {
      "id":"36_17",
      "name":"Diversen Particulier",
      "group":"Diversen",
      "search_attributes":{
         "0":"Prijs van/tot",
         "1":"Groep en Rubriek",
         "2":"Conditie",
      }
   },
   {
      "id":"36_18",
      "name":"Diversen Zakelijk",
      "group":"Diversen",
      "search_attributes":{
         "0":"Prijs van/tot",
         "1":"Groep en Rubriek",
         "2":"Conditie",
      }
   },
   {
      "id":"36_19",
      "name":"Overige Diversen",
      "group":"Diversen",
      "search_attributes":{
         "0":"Prijs van/tot",
         "1":"Groep en Rubriek",
         "2":"Conditie",
      }
   }, {...}
]

But I keep getting this format:

[
   {
      "id":"36_17",
      "name":"Diversen Particulier",
      "group":"Diversen",
      "search_attributes":{"0":"Prijs van/tot"}
   },
  {
     "id":"36_17",
     "name":"Diversen Particulier",
     "group":"Diversen",
     "search_attributes":{"1":"Groep en Rubriek"}
  },
  {
     "id":"36_17",
     "name":"Diversen Particulier",
     "group":"Diversen",
     "search_attributes":{"2":"Conditie"}
  }, {...}
]

The search_attributes are not getting saved correctly.

I'm using the following code:

require 'mechanize'

@hashes = []

# Initialize Mechanize object
a = Mechanize.new

# Begin scraping
a.get('http://www.marktplaats.nl/') do |page|
  groups = page.search('//*[(@id = "navigation-categories")]//a')
  groups.each_with_index do |group, index_1|

    a.get(group[:href]) do |page_2|
      categories = page_2.search('//*[(@id = "category-browser")]//a')
      categories.each_with_index do |category, index_2|

        a.get(category[:href]) do |page_3|
          search_attributes = page_3.search('//*[contains(concat( " ", @class, " " ), concat( " ", "heading", " " ))]')

          search_attributes.each_with_index do |attribute, index_3|
            item = {
              id: "#{index_1}_#{index_2}",
              name: category.text,
              group: group.text,
              :search_attributes => {
                :index_3.to_s => "#{attribute.text unless attribute.text == 'Outlet '}"
              }
            }

            @hashes << item

            puts item

          end
        end
      end
    end
  end
end

# Open file and begin
File.open("json/light/#{Time.now.strftime '%Y%m%d%H%M%S'}_light_categories.json", 'w') do |f|
  puts '# Writing category data to JSON file'
  f.write(@hashes.to_json)
  puts "|-----------> Done. #{@hashes.length} written."
end

puts '# Finished.'

The question is what's causing this and how do I solve it?

Update

A big thanks to arie-shaw for his answer.

Here's the working code:

require 'mechanize'

@hashes = []

# Initialize Mechanize object
a = Mechanize.new

# Begin scraping
a.get('http://www.marktplaats.nl/') do |page|
  groups = page.search('//*[(@id = "navigation-categories")]//a')
  groups.each_with_index do |group, index_1|

    a.get(group[:href]) do |page_2|
      categories = page_2.search('//*[(@id = "category-browser")]//a')
      categories.each_with_index do |category, index_2|

        a.get(category[:href]) do |page_3|
          search_attributes = page_3.search('//*[contains(concat( " ", @class, " " ), concat( " ", "heading", " " ))]')

          attributes_hash = {}

          search_attributes.each_with_index do |attribute, index_3|
            attributes_hash[index_3.to_s] = "#{attribute.text unless attribute.text == 'Outlet '}"
          end

          item = {
            id: "#{index_1}.#{index_2}",
            name: category.text,
            group: group.text,
            :search_attributes => attributes_hash
          }

          @hashes << item

          puts item
        end
      end
    end
  end
end

# Open file and begin
File.open("json/light/#{Time.now.strftime '%Y%m%d%H%M%S'}_light_categories.json", 'w') do |f|
  puts '# Writing category data to JSON file'
  f.write(@hashes.to_json)
  puts "|-----------> Done. #{@hashes.length} written."
end

puts '# Finished.'

回答1:

The most inner each_with_index should be only be used to generate the search_attributes hash, rather than an element hash of the top level array in the result.

# Begin scraping
a.get('http://www.marktplaats.nl/') do |page|
  groups = page.search('//*[(@id = "navigation-categories")]//a')
  groups.each_with_index do |group, index_1|

    a.get(group[:href]) do |page_2|
      categories = page_2.search('//*[(@id = "category-browser")]//a')
      categories.each_with_index do |category, index_2|

        a.get(category[:href]) do |page_3|
          search_attributes = page_3.search('//*[contains(concat( " ", @class, " " ), concat( " ", "heading", " " ))]')

          attributes_hash = {}
          search_attributes.each_with_index do |attribute, index_3|
            attributes_hash[index_3.to_s] = "#{attribute.text unless attribute.text == 'Outlet '}"
          end

          @hashes << {
            id: "#{index_1}_#{index_2}",
            name: category.text,
            group: group.text,
            search_attributes: attributes_hash
          }
        end
      end
    end
  end
end