Module: Metapage

Defined in:
lib/metapage.rb,
lib/metapage/version.rb

Defined Under Namespace

Classes: ContentTypeError, HTTPResponseError, Metadata, ResolveError

Constant Summary collapse

ERROR_CLASSES =
[ResolveError, HTTPResponseError, ContentTypeError]
VERSION =
"0.3.0"

Class Method Summary collapse

Class Method Details

.extract(text) ⇒ Object



27
28
29
# File 'lib/metapage.rb', line 27

def extract(text)
  extract_urls(text).map {|url| fetch(url.gsub(/[\.\,]+\Z/, '')) }.compact
end

.extract!(text) ⇒ Object



31
32
33
# File 'lib/metapage.rb', line 31

def extract!(text)
  extract_urls(text).map {|url| fetch!(url.gsub(/[\.\,]+\Z/, '')) }.compact
end

.extract_urls(text) ⇒ Object



35
36
37
38
39
40
# File 'lib/metapage.rb', line 35

def extract_urls(text)
  processed_text = text.
    gsub(/([^\/])www\./, '\1http://www.').
    gsub(/\Awww\./, 'http://www.')
  URI.extract processed_text, ['http', 'https']
end

.fetch(url) ⇒ Object



17
18
19
20
21
# File 'lib/metapage.rb', line 17

def fetch(url)
  fetch! url
rescue *ERROR_CLASSES => err
  nil
end

.fetch!(url) ⇒ Object



23
24
25
# File 'lib/metapage.rb', line 23

def fetch!(url)
  Metadata.new(url)
end