Method: Spidr::Page#to_absolute

Defined in:
lib/spidr/page/html.rb

#to_absolute(link) ⇒ URI::HTTP

Normalizes and expands a given link into a proper URI.

Parameters:

  • link (String) —

    The link to normalize and expand.

Returns:

  • (URI::HTTP) —

    The normalized URI.


267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
 
# File 'lib/spidr/page/html.rb', line 267

def to_absolute(link)
  link    = link.to_s
  new_url = begin
              url.merge(link)
            rescue URI::Error
              return
            end

  if (!new_url.opaque) && (path = new_url.path)
    # ensure that paths begin with a leading '/' for URI::FTP
    if (new_url.scheme == 'ftp' && !path.start_with?('/'))
      path.insert(0,'/')
    end

    # make sure the path does not contain any .. or . directories,
    # since URI::Generic#merge cannot normalize paths such as
    # "/stuff/../"
    new_url.path = URI.expand_path(path)
  end

  return new_url
end