【发布时间】:2020-12-30 23:30:17
【问题描述】:
我正在使用 Python 向smashgg API 请求内容(查询在 GraphQL 中),并且在运行以下代码时遇到了以前从未遇到过的错误:
headers = {"Authorization": "Bearer my token"}
def run_query(query, variables): # A simple function to use requests.post to make the API call. Note the json= section.
request = requests.post('https://api.smash.gg/gql/alpha', json={'query': query, 'variables': variables}, headers=headers)
if request.status_code == 200:
return request.json()
else:
raise Exception("Query failed to run by returning code of {}. {}".format(request.status_code, query))
nbRequestsPerMinute = 75
dataFrameAllSets = pd.read_csv('dataFrameAllSets.csv') #sets of players I already fetched
countryByPlayer = pd.DataFrame(columns = [
"playerId",
"playerCountry"
])
uniqueValues1 = dataFrameAllSets["setWinnerId"].unique()
uniqueValues2 = dataFrameAllSets["setLoserId"].unique()
concate = np.concatenate((uniqueValues1, uniqueValues2))
countryByPlayer["playerId"] = concate
countryByPlayer.drop_duplicates(subset = "playerId", inplace = True)
#countryByPlayer has more than 200 000 rows
def queryCountry(playerId) :
query = """
query player ($playerId: ID!){
player(id: $playerId){
user{
location {
country
}
}
}
}
"""
variables = {
"playerId": playerId
}
return query, variables
for index, x in countryByPlayer.iterrows() :
t0 = time.time()
query, variables = queryCountry(int(x['playerId']))
result = run_query(query, variables) # Execute the query
if result["data"]["player"] != None :
if result["data"]["player"]["user"] != None :
if result["data"]["player"]["user"]["location"] != None :
countryByPlayer.at[index, "playerCountry"] = result["data"]["player"]["user"]["location"]["country"]
else :
countryByPlayer.at[index, "playerCountry"] = "noneLocation"
else :
countryByPlayer.at[index, "playerCountry"] = "nonePlayer"
t1 = time.time()
if t1 - t0 < 60/nbRequestsPerMinute :
time.sleep(60/nbRequestsPerMinute - t1 + t0)
错误信息如下:
RemoteDisconnected Traceback (most recent call last)
~\Anaconda3\lib\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\lib\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\lib\site-packages\urllib3\packages\six.py in raise_from(value, from_value)
~\Anaconda3\lib\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\lib\http\client.py in getresponse(self)
1320 try:
-> 1321 response.begin()
1322 except ConnectionError:
~\Anaconda3\lib\http\client.py in begin(self)
295 while True:
--> 296 version, status, reason = self._read_status()
297 if status != CONTINUE:
~\Anaconda3\lib\http\client.py in _read_status(self)
264 # sending a valid response.
--> 265 raise RemoteDisconnected("Remote end closed connection without"
266 " response")
RemoteDisconnected: Remote end closed connection without response
During handling of the above exception, another exception occurred:
ProtocolError Traceback (most recent call last)
~\Anaconda3\lib\site-packages\requests\adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
448 retries=self.max_retries,
--> 449 timeout=timeout
450 )
~\Anaconda3\lib\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\lib\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\lib\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\lib\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\lib\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\lib\site-packages\urllib3\packages\six.py in raise_from(value, from_value)
~\Anaconda3\lib\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\lib\http\client.py in getresponse(self)
1320 try:
-> 1321 response.begin()
1322 except ConnectionError:
~\Anaconda3\lib\http\client.py in begin(self)
295 while True:
--> 296 version, status, reason = self._read_status()
297 if status != CONTINUE:
~\Anaconda3\lib\http\client.py in _read_status(self)
264 # sending a valid response.
--> 265 raise RemoteDisconnected("Remote end closed connection without"
266 " 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-5-f3b194f946df> in <module>
4 compteurPlayers += 1
5 query, variables = queryCountry(int(x['playerId']))
----> 6 result = run_query(query, variables) # Execute the query
7 if result["data"]["player"] != None :
8 if result["data"]["player"]["user"] != None :
<ipython-input-2-2a5c0920ef76> in run_query(query, variables)
3
4 def run_query(query, variables): # A simple function to use requests.post to make the API call. Note the json= section.
----> 5 request = requests.post('https://api.smash.gg/gql/alpha', json={'query': query, 'variables': variables}, headers=headers)
6 if request.status_code == 200:
7 return request.json()
~\Anaconda3\lib\site-packages\requests\api.py in post(url, data, json, **kwargs)
114 """
115
--> 116 return request('post', url, data=data, json=json, **kwargs)
117
118
~\Anaconda3\lib\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\lib\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\lib\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\lib\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'))
我最初认为这与 API 的速率限制有关,该限制设置为每分钟 80 个请求,但是,我将循环延迟到始终低于此速率限制。 而且,我多次重新测试我的代码时,错误是在循环过程中随机出现的。
所以我来找你们是因为我真的需要你们的帮助。
提前致谢。
【问题讨论】: