Class: ReadabilityJs::Nodo

Inherits:
Nodo::Core
  • Object
show all
Defined in:
lib/readability_js/nodo.rb

Class Method Summary collapse

Class Method Details

.is_probably_readerable(html, min_content_length: 140, min_score: 20, visibility_checker: nil) ⇒ Object

instance wrapper method, as nodo does not support class methods



28
29
30
31
32
33
34
35
36
 
# File 'lib/readability_js/nodo.rb', line 28

def self.is_probably_readerable(html, min_content_length: 140, min_score: 20, visibility_checker: nil)
  begin
    # remove style tags from html, so jsdom does not need to process css and its warnings are not shown
    html = html.gsub(/<style[^>]*>.*?<\/style>/m, '')
    self.new.is_probably_readerable html, min_content_length, min_score, visibility_checker
  rescue ::Nodo::JavaScriptError => e
    raise ReadabilityJs::Error.new "#{e.message}"
  end
end

.parse(html, url: nil, debug: false, max_elems_to_parse: 0, nb_top_candidates: 5, char_threshold: 500, classes_to_preserve: [], keep_classes: false, disable_json_ld: false, serializer: nil, allow_video_regex: nil, link_density_modifier: 0) ⇒ Object

instance wrapper method, as nodo does not support class methods



15
16
17
18
19
20
21
22
23
 
# File 'lib/readability_js/nodo.rb', line 15

def self.parse(html, url: nil, debug: false, max_elems_to_parse: 0, nb_top_candidates: 5, char_threshold: 500, classes_to_preserve: [], keep_classes: false, disable_json_ld: false, serializer: nil, allow_video_regex: nil, link_density_modifier: 0)
  begin
    # remove style tags from html, so jsdom does not need to process css and its warnings are not shown
    html = html.gsub(/<style[^>]*>.*?<\/style>/m, '')
    self.new.parse html, url, debug, max_elems_to_parse, nb_top_candidates, char_threshold, classes_to_preserve, keep_classes, disable_json_ld, serializer, allow_video_regex, link_density_modifier
  rescue ::Nodo::JavaScriptError => e
    raise ReadabilityJs::Error.new "#{e.message}"
  end
end

.probably_readerable(html) ⇒ Object 



38
39
40
 
# File 'lib/readability_js/nodo.rb', line 38

def self.probably_readerable(html)
  self.is_probably_readerable(html)
end