Class: WebPageParser::GuardianPageParserFactory

Inherits:
ParserFactory show all
Defined in:
lib/web-page-parser/parsers/guardian_page_parser.rb

Constant Summary collapse

URL_RE = 
ORegexp.new("(www\.)?guardian\.co\.uk/[a-z-]+(/[a-z-]+)?/[0-9]{4}/[a-z]{3}/[0-9]{1,2}/[a-z-]{5,200}$")
INVALID_URL_RE = 
ORegexp.new("/cartoon/|/commentisfree/poll/|/video/[0-9]+|/gallery/[0-9]+|/poll/[0-9]+")

Class Method Summary collapse

Methods inherited from ParserFactory

add_factory, #can_parse?, #create, factories, inherited, load, parser_for

Class Method Details

.can_parse?(options) ⇒ Boolean

Returns:

  • (Boolean) 


5
6
7
8
9
 
# File 'lib/web-page-parser/parsers/guardian_page_parser.rb', line 5

def self.can_parse?(options)
  url = options[:url].split('#').first
  return nil if INVALID_URL_RE.match(url)
  URL_RE.match(url)
end

.create(options = {}) ⇒ Object 



11
12
13
 
# File 'lib/web-page-parser/parsers/guardian_page_parser.rb', line 11

def self.create(options = {})
  GuardianPageParserV1.new(options)
end