Class: Wiki::Yggdrasil::Article

Inherits:
Object
  • Object
show all
Defined in:
lib/wiki/article.rb

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(uri:) ⇒ Article

Returns a new instance of Article.

Raises:

  • (ArgumentError) 


9
10
11
12
13
14
15
 
# File 'lib/wiki/article.rb', line 9

def initialize(uri:)
  raise ArgumentError unless Wiki::Yggdrasil::Article.is_valid_wiki_article?(uri: uri)
  @uri         = uri
  @summary     = nil
  @child_links = nil
  @name        = nil
end

Instance Attribute Details

#uri ⇒ Object (readonly)

Returns the value of attribute uri.



7
8
9
 
# File 'lib/wiki/article.rb', line 7

def uri
  @uri
end

Class Method Details

.is_valid_wiki_article?(uri:) ⇒ Boolean

Returns:

  • (Boolean) 


44
45
46
47
 
# File 'lib/wiki/article.rb', line 44

def self.is_valid_wiki_article?(uri:)
  ## Is this URI a wikipedia article?
  uri =~ /.*wikipedia\.org\/wiki\/.+/ ? true : false
end

Instance Method Details



21
22
23
24
25
 
# File 'lib/wiki/article.rb', line 21

def child_links
  formatted_links = format_links
  validated_links =  formatted_links.select { |uri| Wiki::Yggdrasil::Article.is_valid_wiki_article?(uri: uri) }
  @child_links  ||= validated_links
end

#format_links(anchors: self.scrape_all_summary_links) ⇒ Object 



36
37
38
39
40
41
42
 
# File 'lib/wiki/article.rb', line 36

def format_links(anchors: self.scrape_all_summary_links)
  uris = anchors.map do |anchor|
    anchor.nil? || anchor['href'].nil? ? next : 'https://en.wikipedia.org' << anchor['href'] ## nil href attributes are often self refs (but possibly not always). Ignore them.
  end

  uris.compact
end

#name ⇒ Object 



31
32
33
34
 
# File 'lib/wiki/article.rb', line 31

def name
  @name ||= Nokogiri::HTML(open(self.uri)).css('#firstHeading').inner_html
  ## TODO: Cleanup
end

#scrape_all_summary_links ⇒ Object 



27
28
29
 
# File 'lib/wiki/article.rb', line 27

def scrape_all_summary_links
  self.summary.css('p a')
end

#summary ⇒ Object 



17
18
19
 
# File 'lib/wiki/article.rb', line 17

def summary
  @summary ||= Nokogiri::HTML(Nokogiri::HTML(open(self.uri)).to_s.split('<div id="toc" class="toc">')[0]).css('p') ## TODO: Cleanup
end