Module: Miteru::Mixins::URL

Included in:
Feeds::Feed
Defined in:
lib/miteru/mixin.rb

Constant Summary collapse

IGNORE_EXTENSIONS =
%w[.htm .html .php .asp .aspx .exe .txt].freeze

Instance Method Summary collapse

Instance Method Details

#breakdown(url, enable_directory_traveling) ⇒ Array<String>

Breakdown a URL into URLs

Parameters:

  • url (String)
  • enable_directory_traveling (Boolean)

Returns:

  • (Array<String>)


25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
# File 'lib/miteru/mixin.rb', line 25

def breakdown(url, enable_directory_traveling)
  begin
    uri = URI.parse(url)
  rescue URI::InvalidURIError => _e
    return []
  end

  base = "#{uri.scheme}://#{uri.hostname}"
  return [base] unless enable_directory_traveling

  segments = uri.path.split("/")
  return [base] if segments.length.zero?

  urls = (0...segments.length).map { |idx| "#{base}#{segments[0..idx].join("/")}" }

  urls.reject do |breakdowned_url|
    # Reject a url which ends with specific extension names
    invalid_extension? breakdowned_url
  end
end

#invalid_extension?(url) ⇒ Boolean

Validate extension of a URL

Parameters:

  • url (String)

Returns:

  • (Boolean)


13
14
15
# File 'lib/miteru/mixin.rb', line 13

def invalid_extension?(url)
  IGNORE_EXTENSIONS.any? { |ext| url.end_with? ext }
end