Splash API 调用

• render.html

  render.html 接口用于获取 JavaScript 渲染的页面的 HTML 代码，接口地址就是 Splash 的运行地址加此接口名称，例如http://localhost:8050/render.html。
  http://0.0.0.0:8050/render.html?url=https://www.baidu.com&wait=5
  http://0.0.0.0:8050      +       render.html      +        url=https://www.baidu.com       +       wait=5

  import requests
  
  url = 'http://0.0.0.0:8050/render.html?url=https://www.baidu.com&wait=5'
  response = requests.get(url)
  print(response.text)
  
  # 运行
  给此接口传递了一个url参数来指定渲染的URL，等待5秒钟，返回结果即页面渲染后的源代码。

• render.png

  render.png 接口可以获取网页截图，通过 width 和 height 来控制宽高，它返回的是PNG 格式的图片二进制数据。

  http://localhost:8050/render.png?url=https://www.jd.com&wait=5&width=1000&height=700

  http://localhost:8050/render.png?url=https://www.jd.com&wait=5&width=1000&height=700

  import requests
  
  url = 'http://localhost:8050/render.png?url=https://www.jd.com&wait=5&width=1000&height=700'
  response = requests.get(url)
  with open('taobao.png', 'wb') as f:
      f.write(response.content)

• render.jpng

  render.jpng 接口和 render.png 接口类似，只是多了个 quality 参数来设置图片的质量
  

• render.har

  render.har 接口用于获取页面加载的HAR数据，它的返回结果非常多，是一个 JSON 格式的数据，其中包含页面加载过程中的 HAR 数据。

  import requests
  
  url = 'http://localhost:8050/render.har?url=https://www.jd.com&wait=5'
  response = requests.get(url)
  with open('jd1.json', 'wb') as f:
      f.write(response.content)
  
  # 运行生成一个名为jd.json的文件

• execute

  最强大的接口

  import requests
  from urllib.parse import quote
  
  # lua脚本
  lua = '''
  function main(splash)
      return 'hello'
  end
  '''
  
  # quote()方法将lua脚本进行URL转码。lua_source作为参数传递
  url = 'http://localhost:8050/execute?lua_source=' + quote(lua)
  
  response = requests.get(url)
  print(response.text)
  print(quote(lua))
  
  # 输出：
  hello
  %0Afunction%20main%28splash%29%0A%20%20%20%20return%20%27hello%27%0Aend%0A

  import requests
  from urllib.parse import quote
  
  lua = '''
  function main(splash, args)
    local treat = require("treat")
    local response = splash:http_get("http://httpbin.org/get")
      return {
      html=treat.as_string(response.body),
      url=response.url,
      status=response.status
      }
  end
  '''
  
  url = 'http://localhost:8050/execute?lua_source=' + quote(lua)
  response = requests.get(url)
  print(response.text)
  print(quote(lua))
  
  # 输出：
  {"html": "{\n  \"args\": {}, \n  \"headers\": {\n    \"Accept-Encoding\": \"gzip, deflate\", \n    \"Accept-Language\": \"en,*\", \n    \"Host\": \"httpbin.org\", \n    \"User-Agent\": \"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/602.1 (KHTML, like Gecko) splash Version/9.0 Safari/602.1\"\n  }, \n  \"origin\": \"120.239.195.171, 120.239.195.171\", \n  \"url\": \"https://httpbin.org/get\"\n}\n", "status": 200, "url": "http://httpbin.org/get"}
  %0Afunction%20main%28splash%2C%20args%29%0A%20%20local%20treat%20%3D%20require%28%22treat%22%29%0A%20%20local%20response%20%3D%20splash%3Ahttp_get%28%22http%3A//httpbin.org/get%22%29%0A%20%20%20%20return%20%7B%0A%20%20%20%20html%3Dtreat.as_string%28response.body%29%2C%0A%20%20%20%20url%3Dresponse.url%2C%0A%20%20%20%20status%3Dresponse.status%0A%20%20%20%20%7D%0Aend%0A

  function main(splash, args)
    local treat = require("treat")
    local response = splash:http_get("http://httpbin.org/get")
      return {
      html=treat.as_string(response.body),
      url=response.url,
      status=response.status
      }
  end
  
  // 输出：
  Object
  html: String (length )
  {
    "args": {},
    "headers": {
      "Accept-Encoding": "gzip, deflate",
      "Accept-Language": "en,*",
      "Host": "httpbin.org",
      "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/602.1 (KHTML, like Gecko) splash Version/9.0 Safari/602.1"
    },
    "origin": "120.239.195.171, 120.239.195.171",
    "url": "https://httpbin.org/get"
  }
  status:
  url: "http://httpbin.org/get"

  Lua脚本