gem 'httparty'

gem 'nokogiri'

 ENV['RAILS_ENV'] = ARGV.first || ENV['RAILS_ENV'] || 'production'
   require File.expand_path(File.dirname(__FILE__) + '/../config/environment')
   require 'rails'
   require 'rubygems'
   require 'json'
     
   def get_single_page_urls page
     puts "=== in page: #{page}"
     url = ""
     response = HTTParty.get(url)
     #puts response.body, response.code, response.message, response.headers.inspect
    
     my_body = JSON.parse response.body
     puts my_body['data']['list'][0]['url']
     my_body['data']['list'].each do |element|
       puts element['url']
     end
   end
   
   (1..12).each do |page|
     get_single_page_urls page
   end

 ENV['RAILS_ENV'] = ARGV.first || ENV['RAILS_ENV'] || 'production'
   require File.expand_path(File.dirname(__FILE__) + '/../config/environment')
   require 'rails'
   require 'rubygems'
   require 'json'
   
  urls = %w{
……把第三步运行的结果复制在这里（记得删除'=== in page: #{page}'打印出来的东，它只是方便你查看url是否拉取完整）……
}

def get_post_body(url)
   request = HTTParty.get(url)
   parsed_body = Nokogiri::HTML(request.body)
 
   title = parsed_body.css('#articleContentId').first.content
   puts "== title: #{title}"
   created_at = parsed_body.css('.time').first.content.gsub('已于', '').gsub('修改', '').strip
   puts "== 时间: #{created_at}"
   article_body = parsed_body.css('#content_views')
   puts "== 内容: #{article_body}"
 
   # 检查数据库中是否已存在具有相同标题的文章
   if Article.exists?(title: title)
     puts "文章已存在，跳过保存"
   else
     # 这一行的内容替换为你真实文章表的列（我文章列的标题，内容，时间分别是title, content, created_at)
     Article.create!(title: title, content: article_body, created_at: created_at)
     puts "保存文章成功"
   end
 end
 
 urls.each do |url|
   get_post_body(url)
 end