Class: WebPageParser::BbcNewsPageParserFactory

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

Constant Summary collapse

URL_RE = 
ORegexp.new("(www|news)\.bbc\.co\.uk/.+/([a-z-]+-)?[0-9-]+(\.stm)?$")
INVALID_URL_RE = 
ORegexp.new("in_pictures|pop_ups|sport1")

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) 


8
9
10
11
12
13
14
15
 
# File 'lib/web-page-parser/parsers/bbc_news_page_parser.rb', line 8

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

.create(options = {}) ⇒ Object 



17
18
19
 
# File 'lib/web-page-parser/parsers/bbc_news_page_parser.rb', line 17

def self.create(options = {})
  BbcNewsPageParserV5.new(options)
end