aiohttp爬取表情包

aiohttp爬取表情包

import aiohttp,asyncio,requests,re,time
import uuid,os

url = "https://www.doutula.com/photo/list/?page=%s"

headers = {
   "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36"

}

async def run():
   async with aiohttp.ClientSession() as session:
      for i in range(1):
         print("请求第%s页" %str(i+1))
         async with session.get("https://www.doutula.com/photo/list/?page=%s"%str(i), headers=headers) as res:
            json = await res.text()
            s = re.findall(r'data-original="(.*?)"', json)
            for i in s:
               async with session.get(i, headers=headers) as res1:
                  image = await res1.read()
                  file_name = str(i).split(".")[3]
                  with open(os.path.join(r"C:\file",
                                         str(uuid.uuid4())) + "." + file_name, "wb") as f:
                     f.write(image)




loop = asyncio.get_event_loop()
tasks = [run(), ]
loop.run_until_complete(asyncio.wait(tasks))