运行一段时间显示Eventloop is closed

一只魈咸鱼

代码如下：（这里提前创建了‘彼岸桌面壁纸下载’这个文件夹用来放图片）
import asyncio
import aiohttp
from lxml import etree
import requests
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
}
#/html/body/div[13]/div[1]/div[2]/dl/dd/a/img
async def download(url):
    name = url.rsplit('/',1)[1]
    async with aiohttp.ClientSession() as session:
        async with session.get(url) as res:
            with open(f'彼岸桌面壁纸下载/{name}','wb') as f:
                f.write(await res.content.read())

if __name__ == '__main__':
    url0 = f'https://www.enterdesk.com/zhuomianbizhi/{0}.html'
    urls = []
    for i in range(10):
        text = requests.get(url0.format(i)).text
        tree = etree.HTML(text)
        url = tree.xpath('/html/body/div[13]/div[1]/div/dl/dd/a/img/@src')
        urls.extend(url)
    print(urls)
    loop = asyncio.get_event_loop()
    tasks = [loop.create_task(download(url)) for url in urls]
    loop.run_until_complete(asyncio.wait(tasks))
    loop.close()

报错如下：（我有尝试去掉loop.close，这次没报错，但是爬取图片数量和报错的一样多）
D:\MyPcharmProject\venv\Scripts\python.exe D:/MyPcharmProject/爬虫/Umei.py
['https://up.enterdesk.com/edpic_360_360/7c/b3/21/7cb32180d0c74bd6f9a3ec6e32a8474b.jpg', 'https://up.enterdesk.com/edpic_360_360/0f/e3/73/0fe373591a738375bb25a949cc993d17.jpg', 'https://up.enterdesk.com/edpic_360_360/ed/64/b3/ed64b3faff775c57a3fe7c3000c4f61f.jpg', 'https://up.enterdesk.com/edpic_360_360/1b/e1/7f/1be17fbc8443df8b46d91b420be75e69.jpg'
................................................................................
................................................................................（都是和上下文一样的图片网址）
'https://up.enterdesk.com/edpic_360_360/d0/48/ac/d048ac0930025d5bda22a8c80f21db68.jpg', 'https://up.enterdesk.com/edpic_360_360/f7/f1/25/f7f12509b55471d79718ea80e2678c49.jpg', 'https://up.enterdesk.com/edpic_360_360/38/52/91/385291c55d44b6c47edfa52767e6f687.jpg', 'https://up.enterdesk.com/edpic_360_360/89/2a/1f/892a1fdb1e0b3433b08ee9312c6b8f57.jpg']
Exception ignored in: <function _ProactorBasePipeTransport.__del__ at 0x000001DF9942B5E0>
Traceback (most recent call last):
  File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\asyncio\proactor_events.py", line 116, in __del__
    self.close()
  File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\asyncio\proactor_events.py", line 108, in close
    self._loop.call_soon(self._call_connection_lost, None)
  File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\asyncio\base_events.py", line 711, in call_soon
    self._check_closed()
  File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\asyncio\base_events.py", line 504, in _check_closed
    raise RuntimeError('Event loop is closed')
RuntimeError: Event loop is closed
Exception ignored in: <function _ProactorBasePipeTransport.__del__ at 0x000001DF9942B5E0>
Traceback (most recent call last):
  File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\asyncio\proactor_events.py", line 116, in __del__
    self.close()
  File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\asyncio\proactor_events.py", line 108, in close
    self._loop.call_soon(self._call_connection_lost, None)
  File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\asyncio\base_events.py", line 711, in call_soon
    self._check_closed()
  File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\asyncio\base_events.py", line 504, in _check_closed
    raise RuntimeError('Event loop is closed')
RuntimeError: Event loop is closed

Process finished with exit code 0

qaoapp

1. import asyncio
   
2. import aiohttp
   
3. from lxml import etree
   
4. import requests
   
5. headers = {
   
6.     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
   
7. }
   
8. #/html/body/div[13]/div[1]/div[2]/dl/dd/a/img
   
9. async def download(url):
   
10.     name = url.rsplit('/',1)[1]
    
11.     async with aiohttp.ClientSession() as session:
    
12.         async with session.get(url) as res:
    
13.             with open(f'彼岸桌面壁纸下载/{name}','wb') as f:
    
14.                 f.write(await res.content.read())
    
15. 
    
16. async def main():
    
17.     url0 = f'https://www.enterdesk.com/zhuomianbizhi/{0}.html'
    
18.     urls = []
    
19.     for i in range(10):
    
20.         text = requests.get(url0.format(i)).text
    
21.         tree = etree.HTML(text)
    
22.         url = tree.xpath('/html/body/div[13]/div[1]/div/dl/dd/a/img/@src')
    
23.         urls.extend(url)
    
24.     print(urls)
    
25. 
    
26.     tasks = [asyncio.create_task(download(url)) for url in urls]
    
27.     await asyncio.wait(tasks)
    
28. 
    
29. if __name__ == '__main__':
    
30.     asyncio.get_event_loop().run_until_complete(main())

复制代码

一只魈咸鱼

qaoapp 发表于 2021-10-2 15:38

不行呀，虽然没报错，但图片就下载了几张

qaoapp

一只魈咸鱼 发表于 2021-10-3 17:52
不行呀，虽然没报错，但图片就下载了几张

1. import asyncio
   
2. import aiohttp
   
3. from lxml import etree
   
4. import requests
   
5. from bs4 import BeautifulSoup
   
6. 
   
7. headers = {
   
8.     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
   
9. }
   
10. #/html/body/div[13]/div[1]/div[2]/dl/dd/a/img
    
11. async def download(url):
    
12.     name = url.rsplit('/',1)[1]
    
13.     async with aiohttp.ClientSession() as session:
    
14.         async with session.get(url) as res:
    
15.             with open(f'/彼岸桌面壁纸下载/{name}','wb') as f:
    
16.                 f.write(await res.content.read())
    
17. 
    
18. 
    
19. def get_pic_url(url):
    
20.     soup = BeautifulSoup(requests.get(url).text, 'lxml')
    
21.     egeli_pic_li_list = soup.find_all('div', class_='egeli_pic_li')
    
22.     return  [
    
23.         egeli_pic_li.find('dl', class_='egeli_pic_dl').find('dd').find('a').find('img').get('src')
    
24.         for egeli_pic_li in egeli_pic_li_list
    
25.         if egeli_pic_li.find('dl', class_='egeli_pic_dl')
    
26.     ]
    
27. 
    
28. async def main():
    
29.     # url0 = f'https://www.enterdesk.com/zhuomianbizhi/{0}.html'
    
30.     urls = []
    
31.     # for i in range(10):
    
32.     #     text = requests.get(url0.format(i)).text
    
33.     #     tree = etree.HTML(text)
    
34.     #     url = tree.xpath('/html/body/div[13]/div[1]/div/dl/dd/a/img/@src')
    
35.     #     urls.extend(url)
    
36.     for i in range(1, 10):
    
37.         url = f'https://www.enterdesk.com/zhuomianbizhi/{i}.html'
    
38.         urls.extend(get_pic_url(url))
    
39. 
    
40.     tasks = [asyncio.create_task(download(url)) for url in urls]
    
41.     await asyncio.wait(tasks)
    
42. 
    
43. 
    
44. if __name__ == '__main__':
    
45.     asyncio.get_event_loop().run_until_complete(main())

复制代码

问题在lxml这个库构造的url, 协程是正常的