How to convert Nokogiri Document object into JSON

This one works for me:

Hash.from_xml(@nokogiri_object.to_xml).to_json

This method is using active support, so if you are not using rails then include active support core extensions manually:

require 'active_support/core_ext/hash'

Here's one way to do it. As noted by my comment, the 'right' answer depends on what your output should be. There is no canonical representation of XML nodes in JSON, and hence no such capability is built into the libraries involved:

require 'nokogiri'
require 'json'
class Nokogiri::XML::Node
  def to_json(*a)
    {"$name"=>name}.tap do |h|
      kids = children.to_a
      h.merge!(attributes)
      h.merge!("$text"=>text) unless text.empty?
      h.merge!("$kids"=>kids) unless kids.empty?
    end.to_json(*a)
  end
end
class Nokogiri::XML::Document
  def to_json(*a); root.to_json(*a); end
end
class Nokogiri::XML::Text
  def to_json(*a); text.to_json(*a); end
end
class Nokogiri::XML::Attr
  def to_json(*a); value.to_json(*a); end
end

xml = Nokogiri::XML '<root a="b" xmlns:z="zzz">
  <z:a>Hello <b z:x="y">World</b>!</z:a>
</root>'
puts xml.to_json
{
  "$name":"root",
  "a":"b",
  "$text":"Hello World!",
  "$kids":[
    {
      "$name":"a",
      "$text":"Hello World!",
      "$kids":[
        "Hello ",
        {
          "$name":"b",
          "x":"y",
          "$text":"World",
          "$kids":[
            "World"
          ]
        },
        "!"
      ]
    }
  ]
}

Note that the above completely ignores namespaces, which may or may not be what you want.


Converting to JsonML

Here's another alternative that converts to JsonML. While this is a lossy conversion (it does not support comment nodes, DTDs, or namespace URLs) and the format is a little bit "goofy" by design (the first child element is at [1] or [2] depending on whether or not attributes are present), it does indicate namespace prefixes for elements and attributes:

require 'nokogiri'
require 'json'
class Nokogiri::XML::Node
  def namespaced_name
    "#{namespace && "#{namespace.prefix}:"}#{name}"
  end
end
class Nokogiri::XML::Element
  def to_json(*a)
    [namespaced_name].tap do |parts|
      unless attributes.empty?
        parts << Hash[ attribute_nodes.map{ |a| [a.namespaced_name,a.value] } ]
      end
      parts.concat(children.select{|n| n.text? ? (n.text=~/\S/) : n.element? })
    end.to_json(*a)
  end
end
class Nokogiri::XML::Document
  def to_json(*a); root.to_json(*a); end
end
class Nokogiri::XML::Text
  def to_json(*a); text.to_json(*a); end
end
class Nokogiri::XML::Attr
  def to_json(*a); value.to_json(*a); end
end

xml = Nokogiri::XML '<root a="b" xmlns:z="zzz">
  <z:a>Hello <b z:x="y">World</b>!</z:a>
</root>'
puts xml.to_json
#=> ["root",{"a":"b"},["z:a","Hello ",["b",{"z:x":"y"},"World"],"!"]]