siuying

<root>
  <schedule>
    <cinema>奧海城</cinema>
    <house>1</house>
    <movie>未來戰士2018</movie>
    <cat>IIB</cat>
    <time>Jun 03 2009 (Wed) 10:20PM</time>
  </schedule>
</root>

siuying

require 'rubygems'
require 'scrubyt'
require 'nokogiri'
require 'iconv'

# Fetch the seatplan for the schedule
movies = Scrubyt::Extractor.define do
  # use a proper schedule link here
  fetch "http://www2.cinema.com.hk/revamp/html/show_seat.php?lang=c&show_id=13105241"

siuying

require 'rubygems'
require 'scrubyt'
require 'nokogiri'
require 'iconv'

# Fetch the seatplan for the schedule
movies = Scrubyt::Extractor.define do
  # use a proper schedule link here
  fetch "http://www2.cinema.com.hk/revamp/html/show_seat.php?lang=c&show_id=13105241"

siuying

<?xml version="1.0"?>
<root>
  <schedule>
    <cinema>&#x5967;&#x6D77;&#x57CE;</cinema>
    <house>1</house>
    <movie>&#x672A;&#x4F86;&#x6230;&#x58EB;2018</movie>
    <cat>IIB</cat>
    <time>Jun 03 2009 (Wed) 10:20PM</time>
  <seats>210</seats></schedule>
  

siuying

require 'rubygems'
require 'scrubyt'

# Find avaliable schedules
schedules = Scrubyt::Extractor.define do
  fetch "http://www.cinema.com.hk/revamp/html/movie_ticketing.php?lang=c&mode=ticketing"
  cinema "//select[@class='show_pulldown']" do
    schedule "//option/@value"
  end
end

siuying

<root>
  <cinema>
    <schedule>10065063</schedule>
    <schedule>0</schedule>
    <schedule>10065064</schedule>
    <schedule>10065065</schedule>
    <schedule>10065066</schedule>
    <schedule>10065067</schedule>
  </cinema>
  <cinema>

siuying

@xml = Hpricot.XML(doc)
items = (@xml/"//item")

items.to_a.first(@item_limit).each do |item|
  link = (item/"link")
  desc = (item/"description")
  guid = (item/"guid")

  # fetch content using the link
  # replace the item description with content of the link

siuying

# link is the link to full text article
doc = open(link).read
hdoc = Hpricot(doc)
text = (hdoc.search(".livewords")).inner_html

siuying

module Fullfeed
  module Extractor
    class YahooNewsHongKongExtractor < XpathExtractor
      # register this extractor to the system
      register

      def initialize
        super(%r{http://hk\.rd\.yahoo.com/news/rss/\*http://.+\.html}, ".livewords")
      end
    end

siuying

require "rubygems"
require "fullfeed"
require "yahoo_news_hong_kong_extractor"

# create full text RSS feed from Yahoo! News HK
feed = Fullfeed::Feed.new("http://hk.news.yahoo.com/rss/hongkong/rss.xml")
puts feed.fetch