如何解决'连接中止'。使用BeautifulSoup在Python中出错

Posted 2021-05-03

我每天都运行这个代码几周没有错误。今天早上，它适当地运行了for循环超过100次，然后给出了连接问题。每次我试图运行它，它将运行5到130次，但总是在完成之前给出连接错误。

我仍然获得200的状态代码。我在Python中看到一些引用“内存泄漏”问题的帖子，但我不知道如何弄清楚这是否是问题。这也很奇怪，因为它一直运作良好，直到今天。

我在同一站点上的其他页面的代码类似，但仍然可以正常运行。

这是代码：

import requests
from bs4 import BeautifulSoup

updates = []

print(f'Getting {total_timebanks} timebank details... ')
for timebank in range(len(timebanks)):
    url = f"http://community.timebanks.org/{timebanks['slug'][timebank]}"
    res = requests.get(url, headers=headers)
    soup = BeautifulSoup(res.content, 'lxml')

    update = {}
    update['members'] = soup.find('div', {'class': 'views-field-field-num-users-value'}).span.text.strip().replace(',', '')

    updates.append(update)

    time.sleep(1)

这是完整的错误消息：

---------------------------------------------------------------------------
RemoteDisconnected                        Traceback (most recent call last)
/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
    599                                                   body=body, headers=headers,
--> 600                                                   chunked=chunked)
    601 

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
    383                     # otherwise it looks like a programming error was the cause.
--> 384                     six.raise_from(e, None)
    385         except (SocketTimeout, BaseSSLError, SocketError) as e:

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/packages/six.py in raise_from(value, from_value)

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
    379                 try:
--> 380                     httplib_response = conn.getresponse()
    381                 except Exception as e:

/anaconda3/envs/DSI-6/lib/python3.6/http/client.py in getresponse(self)
   1330             try:
-> 1331                 response.begin()
   1332             except ConnectionError:

/anaconda3/envs/DSI-6/lib/python3.6/http/client.py in begin(self)
    296         while True:
--> 297             version, status, reason = self._read_status()
    298             if status != CONTINUE:

/anaconda3/envs/DSI-6/lib/python3.6/http/client.py in _read_status(self)
    265             # sending a valid response.
--> 266             raise RemoteDisconnected("Remote end closed connection without"
    267                                      " response")

RemoteDisconnected: Remote end closed connection without response

During handling of the above exception, another exception occurred:

ProtocolError                             Traceback (most recent call last)
/anaconda3/envs/DSI-6/lib/python3.6/site-packages/requests/adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
    448                     retries=self.max_retries,
--> 449                     timeout=timeout
    450                 )

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
    637             retries = retries.increment(method, url, error=e, _pool=self,
--> 638                                         _stacktrace=sys.exc_info()[2])
    639             retries.sleep()

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/util/retry.py in increment(self, method, url, response, error, _pool, _stacktrace)
    366             if read is False or not self._is_method_retryable(method):
--> 367                 raise six.reraise(type(error), error, _stacktrace)
    368             elif read is not None:

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/packages/six.py in reraise(tp, value, tb)
    684         if value.__traceback__ is not tb:
--> 685             raise value.with_traceback(tb)
    686         raise value

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
    599                                                   body=body, headers=headers,
--> 600                                                   chunked=chunked)
    601 

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
    383                     # otherwise it looks like a programming error was the cause.
--> 384                     six.raise_from(e, None)
    385         except (SocketTimeout, BaseSSLError, SocketError) as e:

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/packages/six.py in raise_from(value, from_value)

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/urllib3/connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
    379                 try:
--> 380                     httplib_response = conn.getresponse()
    381                 except Exception as e:

/anaconda3/envs/DSI-6/lib/python3.6/http/client.py in getresponse(self)
   1330             try:
-> 1331                 response.begin()
   1332             except ConnectionError:

/anaconda3/envs/DSI-6/lib/python3.6/http/client.py in begin(self)
    296         while True:
--> 297             version, status, reason = self._read_status()
    298             if status != CONTINUE:

/anaconda3/envs/DSI-6/lib/python3.6/http/client.py in _read_status(self)
    265             # sending a valid response.
--> 266             raise RemoteDisconnected("Remote end closed connection without"
    267                                      " response")

ProtocolError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response',))

During handling of the above exception, another exception occurred:

ConnectionError                           Traceback (most recent call last)
<ipython-input-17-31257fee2c23> in <module>
      5 for timebank in range(len(timebanks)):
      6     url = f"http://community.timebanks.org/{timebanks['slug'][timebank]}"
----> 7     res = requests.get(url, headers=headers)
      8     soup = BeautifulSoup(res.content, 'lxml')
      9 

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/requests/api.py in get(url, params, **kwargs)
     73 
     74     kwargs.setdefault('allow_redirects', True)
---> 75     return request('get', url, params=params, **kwargs)
     76 
     77 

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/requests/api.py in request(method, url, **kwargs)
     58     # cases, and look like a memory leak in others.
     59     with sessions.Session() as session:
---> 60         return session.request(method=method, url=url, **kwargs)
     61 
     62 

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/requests/sessions.py in request(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)
    531         }
    532         send_kwargs.update(settings)
--> 533         resp = self.send(prep, **send_kwargs)
    534 
    535         return resp

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/requests/sessions.py in send(self, request, **kwargs)
    644 
    645         # Send the request
--> 646         r = adapter.send(request, **kwargs)
    647 
    648         # Total elapsed time of the request (approximately)

/anaconda3/envs/DSI-6/lib/python3.6/site-packages/requests/adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
    496 
    497         except (ProtocolError, socket.error) as err:
--> 498             raise ConnectionError(err, request=request)
    499 
    500         except MaxRetryError as e:

ConnectionError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response',))

答案

问题似乎已经解决了。如果没有对代码进行任何更改，它将在今天早上恢复运行。

我对昨天为什么会出现连接错误没有太多的了解，但它似乎确实是网站的问题，而不是代码。

谢谢你的回复！作为参考，我也尝试将睡眠定时器增加到30，但这并没有解决昨天的问题。