class DiffNews::Tagesanzeiger
Public Class Methods
base_url()
click to toggle source
# File lib/news_service/tagesanzeiger.rb, line 15 def self.base_url 'http://www.tagesanzeiger.ch/' end
new(url)
click to toggle source
Calls superclass method
# File lib/news_service/tagesanzeiger.rb, line 7 def initialize url super normalize_url(url) end
provider()
click to toggle source
# File lib/news_service/tagesanzeiger.rb, line 11 def self.provider 'tagesanzeiger.ch' end
valid_url()
click to toggle source
# File lib/news_service/tagesanzeiger.rb, line 19 def self.valid_url /^https?:\/\/(www.)?tagesanzeiger.ch/ end
Private Instance Methods
normalize_url(url)
click to toggle source
Remove the SEO parts, making the URL more unique
# File lib/news_service/tagesanzeiger.rb, line 26 def normalize_url url parts = url.split('/') if parts.count > 5 (parts.first(4) + parts.last(2)).join('/') else url end end
text()
click to toggle source
# File lib/news_service/tagesanzeiger.rb, line 47 def text content = @doc.css("#mainContent").first content.css('script').remove content.css('.inlinePoll').remove normalize_text(strip_html(content)) rescue '' end
title()
click to toggle source
# File lib/news_service/tagesanzeiger.rb, line 35 def title normalize_text(strip_html(@doc.css("h1").first)) rescue '' end