Class: Readability::Document

Inherits:
Object
  • Object
show all
Includes:
Cleaner, Metadata, Scoring, Utils
Defined in:
lib/readability/document.rb

Instance Method Summary collapse

Constructor Details

#initialize(doc, url: nil, **options) ⇒ Document

Returns a new instance of Document.



12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
 
# File 'lib/readability/document.rb', line 12

def initialize(doc, url: nil, **options)
  @doc = doc.dup  # Deep clone
  @url = url
  @article_title = nil
  @article_byline = nil
  @article_dir = nil
  @article_site_name = nil
  @article_lang = nil
  @attempts = []
  @metadata = {}
  @candidates = {}
  @data_tables = Set.new

  # Options — from JS constructor lines 49-66
  @debug = !!options[:debug]
  @max_elems_to_parse = options[:max_elems_to_parse] || DEFAULT_MAX_ELEMS_TO_PARSE
  @nb_top_candidates = options[:nb_top_candidates] || DEFAULT_N_TOP_CANDIDATES
  @char_threshold = options[:char_threshold] || DEFAULT_CHAR_THRESHOLD
  @classes_to_preserve = CLASSES_TO_PRESERVE + (options[:classes_to_preserve] || [])
  @keep_classes = !!options[:keep_classes]
  @serializer = options[:serializer] || ->(el) { el.inner_html }
  @disable_json_ld = !!options[:disable_json_ld]
  @allowed_video_regex = options[:allowed_video_regex] || VIDEOS
  @link_density_modifier = options[:link_density_modifier] || 0

  # Flags — all active initially
  @flags = FLAG_STRIP_UNLIKELYS | FLAG_WEIGHT_CLASSES | FLAG_CLEAN_CONDITIONALLY
end

Instance Method Details

#parse ⇒ Object

Port of parse() — JS lines 2747-2805



42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/readability/document.rb', line 42

def parse
  # Avoid parsing too large documents
  if @max_elems_to_parse > 0
    count = 0
    @doc.traverse do |n|
      if n.element?
        count += 1
        if count > @max_elems_to_parse
          raise "Aborting parsing document; #{count} elements found"
        end
      end
    end
  end

  # Unwrap image from noscript
  unwrap_noscript_images(@doc)

  # Extract JSON-LD metadata before removing scripts
  json_ld = @disable_json_ld ? {} : get_json_ld(@doc)

  # Remove script tags from the document
  remove_scripts(@doc)

  prep_document

  # Cache the prepped body HTML for retry re-parsing (avoids innerHTML= cost)
  @prepped_body_html = @doc.at_css("body")&.inner_html

  metadata = get_article_metadata(json_ld)
  @metadata = metadata
  @article_title = metadata["title"]

  article_content = grab_article
  return nil unless article_content

  log("Grabbed: #{article_content.inner_html}")

  post_process_content(article_content)

  # If we haven't found an excerpt in the article's metadata, use the article's
  # first paragraph as the excerpt.
  if !metadata["excerpt"] || metadata["excerpt"].empty?
    paragraphs = article_content.css("p")
    if paragraphs.length > 0
      metadata["excerpt"] = paragraphs[0].text.strip
    end
  end

  text_content = article_content.text

  Result.new(
    title: @article_title,
    byline: (metadata["byline"] && !metadata["byline"].empty? ? metadata["byline"] : nil) || @article_byline,
    dir: @article_dir,
    lang: @article_lang,
    content: @serializer.call(article_content),
    text_content: text_content,
    length: text_content.length,
    excerpt: metadata["excerpt"],
    site_name: metadata["siteName"] || @article_site_name,
    published_time: metadata["publishedTime"]
  )
end