Module: ReadabilityJs

Defined in:
lib/readability_js.rb,
lib/custom_errors/error.rb,
lib/readability_js/nodo.rb,
lib/readability_js/version.rb,
lib/readability_js/extended.rb

Overview

ReadabilityJs

Defined Under Namespace

Classes: Error, Extended, Nodo

Constant Summary collapse

VERSION = 
'0.0.7'.freeze

Class Method Summary collapse

Class Method Details

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

Decides whether a document is probably readerable without parsing the whole document.

Only ‘html’ is a required parameter, all others are optional.

html = “<html>…</html>”

visibility_checker = <<~JS

(node) => {
 const style = node.ownerDocument.defaultView.getComputedStyle(node);
 return (style && style.display !== 'none' && style.visibility !== 'hidden' && parseFloat(style.opacity) > 0);
}

JS

ReadabilityJs.is_probably_readerable(html, min_content_length: 200, min_score: 25, visibility_checker: visibility_checker)

Raises:



103
104
105
106
107
108
109
 
# File 'lib/readability_js.rb', line 103

def self.is_probably_readerable(html, min_content_length: 140, min_score: 20, visibility_checker: nil)
  begin
    ReadabilityJs::Nodo.is_probably_readerable(html, min_content_length: min_content_length, min_score: min_score, visibility_checker: visibility_checker)
  rescue => e
    raise ReadabilityJs::Error.new e.message
  end
end

.normalize_result(result) ⇒ Hash

Normalize result keys to snake_case for ruby style



150
151
152
153
154
155
 
# File 'lib/readability_js.rb', line 150

def self.normalize_result(result)
  result["text_content"] = result.delete("textContent") if result.key?("textContent")
  result["site_name"] = result.delete("siteName") if result.key?("siteName")
  result["published_time"] = result.delete("publishedTime") if result.key?("publishedTime")
  result
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) ⇒ Hash

Parse a HTML document and extract its main content using Mozilla’s Readability library.

‘html’ is a required parameters, all others are optional.

Raises:



40
41
42
43
44
45
46
47
 
# File 'lib/readability_js.rb', line 40

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
    result = ReadabilityJs::Nodo.parse(html, url: url, debug: debug, max_elems_to_parse: max_elems_to_parse, nb_top_candidates: nb_top_candidates, char_threshold: char_threshold, classes_to_preserve: classes_to_preserve, keep_classes: keep_classes, disable_json_ld: disable_json_ld, serializer: serializer, allow_video_regex: allow_video_regex, link_density_modifier: link_density_modifier)
    normalize_result(result)
  rescue => e
    raise ReadabilityJs::Error.new e.message
  end
end

.parse_extended(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, blacklist_selectors: []) ⇒ Hash

Like #parse but with additional pre- and post-processing to enhance content extraction.

‘html’ is a required parameters, all others are optional.

Raises:



71
72
73
74
75
 
# File 'lib/readability_js.rb', line 71

def self.parse_extended(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, blacklist_selectors: [])
  result = Extended::before_cleanup html, blacklist_selectors: blacklist_selectors
  result = parse result, url: url, debug: debug, max_elems_to_parse: max_elems_to_parse, nb_top_candidates: nb_top_candidates, char_threshold: char_threshold, classes_to_preserve: classes_to_preserve, keep_classes: keep_classes, disable_json_ld: disable_json_ld, serializer: serializer, allow_video_regex: allow_video_regex, link_density_modifier: link_density_modifier
  Extended::after_cleanup result, html
end

.probably_readerable?(html, min_content_length: 140, min_score: 20, visibility_checker: nil) ⇒ Boolean

Decides whether a document is probably readerable without parsing the whole document.

Only ‘html’ is a required parameter, all others are optional.

html = “<html>…</html>”

visibility_checker = <<~JS

(node) => {
 const style = node.ownerDocument.defaultView.getComputedStyle(node);
 return (style && style.display !== 'none' && style.visibility !== 'hidden' && parseFloat(style.opacity) > 0);
}

JS

ReadabilityJs.probably_readerable?(html, min_content_length: 200, min_score: 25, visibility_checker: visibility_checker)

Raises:



138
139
140
 
# File 'lib/readability_js.rb', line 138

def self.probably_readerable?(html, min_content_length: 140, min_score: 20, visibility_checker: nil)
  self.is_probably_readerable(html, min_content_length: min_content_length, min_score: min_score, visibility_checker: visibility_checker)
end