Class: Crawlscope::StructuredData::Document

Inherits:
Object
  • Object
show all
Defined in:
lib/crawlscope/structured_data/document.rb

Defined Under Namespace

Classes: Item

Instance Method Summary collapse

Constructor Details

#initialize(html:) ⇒ Document

Returns a new instance of Document.



11
12
13
# File 'lib/crawlscope/structured_data/document.rb', line 11

def initialize(html:)
  @doc = Nokogiri::HTML(html.to_s)
end

Instance Method Details

#itemsObject



15
16
17
# File 'lib/crawlscope/structured_data/document.rb', line 15

def items
  @items ||= extract_json_ld_items + extract_microdata_items
end

#json_ld_itemsObject



19
20
21
22
23
24
25
26
27
# File 'lib/crawlscope/structured_data/document.rb', line 19

def json_ld_items
  items.filter_map do |item|
    next unless item.source == "json-ld"
    next unless item.data.is_a?(Hash)
    next if item.data.key?(:error)

    item.data
  end
end