如何将多个哈希合并成一个有效的JSON文件？ [英] How do I merge multiple Hashes into a single valid JSON file?

查看：116
本文介绍了如何将多个哈希合并成一个有效的JSON文件？的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！

问题描述

 需要' mechanize'
 
 @categories_hash = {} 
 @categories_hash ['category'] || = {} 
 @categories_hash ['category'] ['id'] || = {} 
 @categories_hash ['category'] ['name'] || = {} 
 @categories_hash ['category'] ['group'] || = {} 
 @categories_hash ['category'] ['search_attributes'] || = {} 
 
＃初始化机械化对象
a = Mechanize.new 
 
＃打开文件并开始
 File.open（json / booyah /＃{Time.now.strftime'％Y％m％d％H％M％S'} _ booyah_categories.json，'w'）do | f | 
 puts'＃将类别数据写入JSON文件'
 
＃开始刮取
 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 | 
 @categories_hash ['category'] ['id'] =＃{index_1} _＃{index_2}
 @categories_hash ['category'] ['name'] = category.text 
 @categories_hash ['category'] ['group'] = group.text 
 @categories_hash ['category'] ['search_attributes'] [index_3] = attribute.text unless attribute.text =='Outlet' 
 end 
 
＃取消注释如果您想查看正在写入的内容
 puts @categories_hash ['category']。to_json 
 
＃写入转换后的哈希到JSON文件
 f.write（@categories_hash ['category']。to_json）
 end 
 end 
 end 
 end 
 end 
 
 puts'| ----------->完成'
 
 end 
 
 puts'＃Finished。'

此代码产生以下无效 JSON文件。查看完整的JSON文件此处。它看起来像这样：

  {
id：0_0，
name： Boeken en Bijbels，
group：Antiek en Kunst，
search_attributes：{
0：Prijs van / tot，
1 ：Groep en Rubriek，
2：Aangeboden sinds
} 
} {
id：0_1，
name ：电子邮件，
group：Antiek en Kunst，
search_attributes：{
0：Prijs van / tot，
1 ：Groep en Rubriek，
2：Aangeboden sinds
} 
} {
id：0_2，
name： b $ bgroup：Antiek en Kunst，
search_attributes：{
0：Prijs van / tot，
1 ：Groep en Rubriek，
2：Aangeboden sinds
} 
} {...}

我希望输出是有效的JSON，如下所示： 

  [
 {
id：0_0，
name：Boeken en Bijbels，
group：Antiek en Kunst，
搜索h_attributes：{
0：Prijs van / tot，
1：Groep en Rubriek，
2：Aangeboden sinds
} 
}，
 {
id：0_1，
name：Emaille，
group：Antiek en Kunst，
search_attributes：{
0：Prijs van / tot，
1：Groep en Rubriek，
2：Aangeboden sinds
 
 
 
id：0_2，
name：Gereedschap en Instrumenten，
group： Antiek en Kunst，
search_attributes：{
0：Prijs van / tot，
1：Groep en Rubriek，
2 ：Aangeboden sinds
} 
}，
 {...} 
]

问题是，我该如何做到这一点？

更新



非常感谢您为他的 maerics > answer 。



这里是稍微更新，但工作代码：

pre $ require'mechanize'

@categories_hash = {}
@categories_hash ['category'] || = {}
@categories_hash ['category'] ['id'] || = {}
@categories_hash ['category'] ['name '] || = {}
@categories_hash ['category'] ['group'] || = {}
@categories_hash ['category'] ['search_attributes'] || = {}

@hashes = []

＃初始化机械化对象
a = Mechanize.new

＃开始刮取
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<<项目

提取项目

结束
结束
结束
结束
结束
结束

＃打开文件并开始
File.open（json / light /＃{Time.now.strftime'％Y％m％d％H％M％S'} _ light_categories.json，'w '）do | f |
puts'＃将类别数据写入JSON文件'
f.write（@ hashes.to_json）
puts'| ----------->完成'
end

puts'＃Finished。'


解决方案

使用内置 Ruby JSON库：

  require'json'
哈希= [] 
 all_hashes.each {| h |散列 h} 
 print hashes.to_json

或者，在极端情况下，你的哈希将不会适合可用内存（伪代码）：

  print'['
 for each JSON hash H 
打印H 
 print'，'除非H是集合中的最后一个
 print']'


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

require 'mechanize'

@categories_hash = {}
@categories_hash['category'] ||= {}
@categories_hash['category']['id'] ||= {}
@categories_hash['category']['name'] ||= {}
@categories_hash['category']['group'] ||= {}
@categories_hash['category']['search_attributes'] ||= {}

# Initialize Mechanize object
a = Mechanize.new

# Open file and begin
File.open("json/booyah/#{Time.now.strftime '%Y%m%d%H%M%S'}_booyah_categories.json", 'w') do |f|
  puts '# Writing category data to JSON file'

  # 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|
              @categories_hash['category']['id'] = "#{index_1}_#{index_2}"
              @categories_hash['category']['name'] = category.text
              @categories_hash['category']['group'] = group.text
              @categories_hash['category']['search_attributes'][index_3] = attribute.text unless attribute.text == 'Outlet '
            end

            # Uncomment if you want to see what's being written
            puts @categories_hash['category'].to_json

            # Write the converted Hash to the JSON file
            f.write(@categories_hash['category'].to_json)
          end
        end
      end
    end
  end

  puts '|-----------> Done.'

end

puts '# Finished.'

This code produces the following, invalid JSON file. Take a look at the full JSON file here. It looks like this:

{
  "id": "0_0",
  "name": "Boeken en Bijbels",
  "group": "Antiek en Kunst",
  "search_attributes": {
    "0": "Prijs van/tot",
    "1": "Groep en Rubriek",
    "2": "Aangeboden sinds"
  }
}{
  "id": "0_1",
  "name": "Emaille",
  "group": "Antiek en Kunst",
  "search_attributes": {
    "0": "Prijs van/tot",
    "1": "Groep en Rubriek",
    "2": "Aangeboden sinds"
  }
}{
  "id": "0_2",
  "name": "Gereedschap en Instrumenten",
  "group": "Antiek en Kunst",
  "search_attributes": {
    "0": "Prijs van/tot",
    "1": "Groep en Rubriek",
    "2": "Aangeboden sinds"
  }
}{...}

I want the output to be valid JSON and look like this:

[
  {
    "id": "0_0",
    "name": "Boeken en Bijbels",
    "group": "Antiek en Kunst",
    "search_attributes": {
      "0": "Prijs van/tot",
      "1": "Groep en Rubriek",
      "2": "Aangeboden sinds"
    }
  },
  {
    "id": "0_1",
    "name": "Emaille",
    "group": "Antiek en Kunst",
    "search_attributes": {
      "0": "Prijs van/tot",
      "1": "Groep en Rubriek",
      "2": "Aangeboden sinds"
    }
  },
  {
    "id": "0_2",
    "name": "Gereedschap en Instrumenten",
    "group": "Antiek en Kunst",
    "search_attributes": {
      "0": "Prijs van/tot",
      "1": "Groep en Rubriek",
      "2": "Aangeboden sinds"
    }
  },
  {...}
]

The question is, how do I accomplish this?

Update

A big thank you to maerics for his answer.

Here's the slightly updated, but working code:

require 'mechanize'

@categories_hash = {}
@categories_hash['category'] ||= {}
@categories_hash['category']['id'] ||= {}
@categories_hash['category']['name'] ||= {}
@categories_hash['category']['group'] ||= {}
@categories_hash['category']['search_attributes'] ||= {}

@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.'
end

puts '# Finished.'

解决方案

Using the builtin Ruby JSON library:

require 'json'
hashes = []
all_hashes.each { |h| hashes << h }
print hashes.to_json

Or, in the extreme case that your hashes will not fit into the available memory (pseudocode):

print '['
for each JSON hash H
  print H
  print ',' unless H is the last of the set
print ']'

这篇关于如何将多个哈希合并成一个有效的JSON文件？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！

查看全文
相关文章
其他开发最新文章
热门教程
热门工具
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆