class TaiwaneseNewsParser::Parser::LibertyTimesBig5
Public Class Methods
applicable?(url)
click to toggle source
# File lib/taiwanese_news_parser/parser/liberty_times_big5.rb, line 10 def self.applicable?(url) url.match(%r{libertytimes\.com\.tw/\d+/\w+/\w+/\d+/.+\.htm}) end
domain()
click to toggle source
# File lib/taiwanese_news_parser/parser/liberty_times_big5.rb, line 2 def self.domain 'libertytimes.com.tw' end
names()
click to toggle source
# File lib/taiwanese_news_parser/parser/liberty_times_big5.rb, line 6 def self.names %{自由時報} end
parse_url_id(url)
click to toggle source
# File lib/taiwanese_news_parser/parser/liberty_times_big5.rb, line 48 def self.parse_url_id(url) url[%r{http://www\.libertytimes\.com\.tw/(.*)\.htm},1] end
Public Instance Methods
clean_url()
click to toggle source
# File lib/taiwanese_news_parser/parser/liberty_times_big5.rb, line 43 def clean_url cleaner = TaiwaneseNewsParser::UrlCleaner.new('') @article[:url] = cleaner.clean(@article[:url]) end
parse()
click to toggle source
url = 'www.libertytimes.com.tw/2013/new/apr/13/today-sp2.htm'
# File lib/taiwanese_news_parser/parser/liberty_times_big5.rb, line 15 def parse @article[:title] = doc.at_css('#newtitle').text @article[:company_name] = parse_company_name @article[:content] = doc.css('#newsContent>span:not(#newtitle)>p:not(.picture)').text @article[:reporter_name] = parse_reporter_name() @article[:published_at] = Time.parse(doc.at_css('#date').text) clean_up @article end
parse_company_name()
click to toggle source
# File lib/taiwanese_news_parser/parser/liberty_times_big5.rb, line 39 def parse_company_name '自由時報' end
parse_reporter_name()
click to toggle source
# File lib/taiwanese_news_parser/parser/liberty_times_big5.rb, line 28 def parse_reporter_name if match = @article[:content].match(%r{〔(.*?)[//╱](.*?)〕}) reporter_name = match[1][%r{記者(.+)},1] elsif match = @article[:content].match(%r{記者(.+?)[//╱]}) reporter_name = match[1] elsif match = @article[:content].match(%r{(文/(.*?))}) reporter_name = match[1] end reporter_name end