テレビ王国 (tv.so-net.ne.jp) のテレビ番組表から、番組詳細情報を取得する

tv_scraping_1.rb

require 'open-uri'
require 'nokogiri'

# date
date = '20131213'

# open tv.so-net.ne.jp and parse it by Nokogiri
target = 'http://tv.so-net.ne.jp/chart/23.action?head=' + date + '0000&span=24'
doc = Nokogiri::HTML(open(target))

# get links to program detail pages
programs = doc.css('a.schedule-link')
program_detail_links = []

programs.each do |program|
  # url
  program_detail_links.push program.attributes['href'].value
  # title
  # puts program.children.css('span.schedule-title').children.to_s
end

foreach program_links do |program_detail_link|
  Nokogiri::HTML(open(program_detail_link)).css('p.basicTxt').each do |text|
    pp text
  end
end