appked_api.rb

require 'open-uri'
require 'nokogiri'

class AppkedApi
  def initialize
    require 'open-uri'
    require 'nokogiri'
  end

  def content(url, entry=true)
    site = open(url)
    doc = Nokogiri::HTML(site)
    download_url = doc.css('.article.clearfix .text .appdl a').first['href']
    all_entries = []
    entries = doc.css('.post.clearfix .entry')
    entries.each do |entry|
      title_link = entry.css('h2 a').first
      site_url = title_link['href']
      title = title_link.text
      desc = entry.css('.desc')
      category_tags = desc.css('a[rel="category tag"]').collect{|s| [s.text, s['href']]}.to_h
      date = Time.parse(desc.text.split('/').collect{|s| s.strip}.last)
      tags = entry.css('.tag a').collect{|a| [a.text, a['href']]}.to_h
      views = entry.css('.view a').text
      if entry
        data = {
          title: title,
          url: site_url,
          categories: category_tags,
          date: date,
          tags: tags,
          views: views,
          download_url: download_url
        }
      else
        data = {
          title: title,
          url: site_url,
          categories: category_tags,
          date: date,
          tags: tags,
          views: views
        }
      end

      if entry
        return data
      end
      all_entries << data
    end
    all_entries
  end
  
  def topics
    site = open('http://www.macneed.com/topics/')
    doc = Nokogiri::HTML(site)
    raw_tags = doc.xpath('//div[@id="page"]/p[3]/a')
    raw_tags.collect {|a| [a.text, a['href']] }.to_h
  end

  def apps
    doc = Nokogiri::HTML(open('http://www.macneed.com/articles/'))
    doc.css('ul.car-monthlisting li a').collect{ |a| [a.text, a['href']]}.group_by{|x| get_name(x.first)}
  end

  def download(url)
    doc = Nokogiri::HTML(open(url))
    content = doc.css('#content')
    date = Time.parse(content.css('span.appked_date').text)
    title_link = content.css('p.appked_title a').first
    download_links = content.css('.downloadlink a').collect{|x| [x.text, x['href']]}.to_h

    a = {
      url: title_link['href'],
      title: title_link['title'],
      download_links: download_links,
      date: date
    }

    a
  end

  private
  def get_name(text)
    m = /(.*?)(?:(?:(?:\d+[.])+\d+)|$)/.match(text.split('–').first)[1]
    /(\[.*?\])?[ ]?([^\[]*?)(?:\d+|$)/.match(m.strip)[2]
  end
end