【Ruby爬虫03】获取王者荣耀皮肤图片

require 'json'  
require 'http'  
require 'nokogiri'  
require 'fileutils'  
  
# 伪装自己  
headers = {  
  'User-Agent' => 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36'  
}  
  
hero_list_url = 'https://pvp.qq.com/web201605/js/herolist.json'  
resp = HTTP.get(hero_list_url,:headers => headers)  
hero_list_json = JSON.parse(resp.body.to_s)  
# puts hero_list_json  
  
hero_list_json.each do |h|  
  ename = h['ename']  
  cname = h['cname']  
  
  FileUtils.mkdir_p(cname) unless File.directory?(cname)  
  
  # 访问英雄主页  
  hero_info_url = "https://pvp.qq.com/web201605/herodetail/#{ename}.shtml"  
  hero_info_html =  HTTP.get(hero_info_url,:headers => headers).body.to_s  
  
  doc = Nokogiri::HTML(hero_info_html,nil,'GBK')  
  
  names = doc.xpath('//ul[@class="pic-pf-list pic-pf-list3"]/@data-imgname')[0].content  
  
  names = names.split('|').map { |name| name[0..name.index('&') - 1] }  
  
  # 发送请求  
  names.each_with_index do |n, i|  
    skin_url = "http://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/#{ename}/#{ename}-bigskin-#{i + 1}.jpg"  
    skin_content = HTTP.get(skin_url, :headers=> headers).body.to_s  
  
    # 保存图片(皮肤)  
    File.open("#{cname}/#{n}.jpg", 'wb') do |f|  
      f.write(skin_content)  
    end  
  
    puts "已下载: #{n} 的皮肤"  
    sleep(1)  
  end  
end

本文由【产品经理不是经理】gzh 同步发布，欢迎关注