使用 Typhoeus 和 Ruby 编写的爬虫程序

news2024/11/20 20:36:19

以下是一个使用 Typhoeus 和 Ruby 编写的爬虫程序，用于爬取，同时使用了 jshk.com.cn/get_proxy 这段代码获取代理：

#!/usr/bin/env ruby

require 'typhoeus'
require 'json'

def get_proxy
  url = "https://www.duoip.cn/get_proxy"
  response = Typhoeus.get(url)
  if response.code == 200
    proxy_json = JSON.parse(response.body)
    proxy_ip = proxy_json['data']['ip']
    proxy_port = proxy_json['data']['port']
    return proxy_ip, proxy_port
  end
rescue Typhoeus::Error => e
  puts "Error: #{e.message}"
  exit(1)
end

def crawl_ebay(proxy_ip, proxy_port)
  url = "https://www.ebay.com"
  headers = {
    'User-Agent' => 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
    'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Language' => 'zh-CN,zh;q=0.8,en-US;q=0.6,en;q=0.4',
    'Accept-Encoding' => 'gzip, deflate, br',
    'Referer' => 'https://www.google.com',
    'Connection' => 'keep-alive'
  }

  # 使用 Typhoeus 的 Hydra 对象进行并发请求
  hydra = Typhoeus::Hydra.new

  # 创建一个使用代理的请求
  request = Typhoeus::Request.new(url, headers: headers, proxy: { ip: proxy_ip, port: proxy_port })

  # 使用 Hydra 对象发送请求
  response = hydra.queue(request)

  # 如果请求成功，输出响应体
  if response.code == 200
    puts "Request successful. Response body: #{response.body}"
  # 如果请求失败，输出错误信息
  else
    puts "Request failed. Error: #{response.code}"
  end

  # 关闭 Hydra 对象
  hydra.close
end

# 获取代理
proxy_ip, proxy_port = get_proxy

# 使用获取到的代理进行爬取
crawl_ebay(proxy_ip, proxy_port)