Splash无法正常渲染galaxus.ch站点搜索页内容问题求助

开发者阿泽

2026-10-5

问题根因

galaxus.ch近期更新了反爬检测规则，可识别Splash默认的无头浏览器特征、旧版本请求标识，之前的脚本配置特征和真实浏览器差异过大，因此被拦截无内容返回。

修复后脚本

function main(splash, args)
  -- 替换为较新版本Chrome UA，规避旧版本浏览器特征拦截
  splash:set_user_agent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36")
  splash.private_mode_enabled = false
  splash.js_enabled = true

  -- 补全真实浏览器常规请求头，消除请求特征差异
  splash:set_custom_headers({
    ["Accept"] = "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
    ["Accept-Language"] = "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
    ["Accept-Encoding"] = "gzip, deflate, br",
    ["Connection"] = "keep-alive",
    ["Upgrade-Insecure-Requests"] = "1"
  })

  -- 清除历史Cookie，避免之前的异常访问被站点标记
  splash:clear_cookies()
  assert(splash:go(args.url))
  -- 随机等待时长，同时等待站点反爬前置校验逻辑执行完成
  assert(splash:wait(math.random(3,7)))
  -- 模拟真实用户滚动操作，规避无交互爬虫检测
  splash:scroll_position = {y=math.random(100,300)}
  assert(splash:wait(1))

  splash:set_viewport_full()
  return {
    png = splash:png(),
    html = splash:html()
  }
end