Class: RubyCrawl::Result

Inherits:
Object
  • Object
show all
Defined in:
lib/rubycrawl/result.rb

Overview

Result object with lazy clean_markdown conversion.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(text:, html:, links:, metadata:) ⇒ Result

Returns a new instance of Result.



8
9
10
11
12
13
 
# File 'lib/rubycrawl/result.rb', line 8

def initialize(text:, html:, links:, metadata:)
  @text = text
  @html = html
  @links = links
  @metadata = metadata
end

Instance Attribute Details

#html ⇒ Object (readonly)

Returns the value of attribute html.



6
7
8
 
# File 'lib/rubycrawl/result.rb', line 6

def html
  @html
end

#links ⇒ Object (readonly)

Returns the value of attribute links.



6
7
8
 
# File 'lib/rubycrawl/result.rb', line 6

def links
  @links
end

#metadata ⇒ Object (readonly)

Returns the value of attribute metadata.



6
7
8
 
# File 'lib/rubycrawl/result.rb', line 6

def metadata
  @metadata
end

#text ⇒ Object (readonly)

Returns the value of attribute text.



6
7
8
 
# File 'lib/rubycrawl/result.rb', line 6

def text
  @text
end

Instance Method Details

#clean_markdown ⇒ String

Returns clean markdown converted from the page HTML. Relative URLs are resolved using the page’s final_url.

Returns:

  • (String) —

    Markdown content with absolute URLs



19
20
21
 
# File 'lib/rubycrawl/result.rb', line 19

def clean_markdown
  @clean_markdown ||= MarkdownConverter.convert(html, base_url: final_url)
end

#clean_markdown? ⇒ Boolean

Check if clean_markdown has been computed.

Returns:

  • (Boolean) 


33
34
35
 
# File 'lib/rubycrawl/result.rb', line 33

def clean_markdown?
  !@clean_markdown.nil?
end

#final_url ⇒ String?

The final URL after redirects.

Returns:

  • (String, nil) 


26
27
28
 
# File 'lib/rubycrawl/result.rb', line 26

def final_url
  metadata['final_url']
end

#to_h ⇒ Object 



37
38
39
40
41
42
43
44
45
 
# File 'lib/rubycrawl/result.rb', line 37

def to_h
  {
    text: text,
    html: html,
    links: links,
    metadata: metadata,
    clean_markdown: @clean_markdown
  }
end