GeocoderUnavailable:使用 python 的最大尝试次数超出错误

问题描述

我是网络抓取和网络抓取的新手。我正在尝试使用以下 Python 代码连接到这个特定站点提取一些数据。但是我收到以下错误作为 GeocoderUnavailable: 下面的详细错误。我试图通过增加睡眠时间来更新我的代码,但它仍然不起作用,当我尝试将 .非常感谢任何帮助,并提前感谢您。

代码如下:

from geopy.geocoders import Nominatim
import requests
import pandas as pd
import json
import time

location = "32052 Herford,Deutschland"
Fachgebiet = '12001_SID' 
https://www.kvwl.de/DocSearchService/DocSearchService/getExpertiseAreaStructure 

geolocator = Nominatim(user_agent="KVWL_retrieval")
location = geolocator.geocode(location)

headers = {"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/70.0.3538.77 Safari/537.36",'content-type': 'application/json; charset=UTF-8'}
data = '{"Latitude":' + str(location.latitude) + ',"Longitude":' + str(location.longitude) + ',"Docgender":"","DocNamePattern":"","ExpertiseAreaStructureId":"' + Fachgebiet + '","ApplicableQualificationId":"","SpecialServiceId":"","LanguageId":"","BarrierFreeAttributeFilter":{"ids":[]},"PageId":0,"PageSize":100}'
response = requests.post('https://www.kvwl.de/DocSearchService/DocSearchService/searchDocs',headers=headers,data=data)
r = json.loads(response.content)

df = pd.json_normalize(r['DoctorAbstracts']['DoctorAbstract'])

def get_doctor(id_nr):
    data = '{"Id":"' + id_nr + '"}'
    response = requests.post('https://www.kvwl.de/DocSearchService/DocSearchService/getDoctor',data=data)
    r = json.loads(response.content)
    time.sleep(6) 
    return pd.json_normalize(r)

Final = df.join(df.apply(lambda x: pd.Series(get_doctor(x.Id).to_dict()),1),rsuffix='_right')

错误

---------------------------------------------------------------------------
timeout                                   Traceback (most recent call last)
~\Anaconda3\lib\site-packages\urllib3\connectionpool.py in _make_request(self,conn,method,url,timeout,chunked,**httplib_request_kw)
    425                     # Otherwise it looks like a bug in the code.
--> 426                     six.raise_from(e,None)
    427         except (SocketTimeout,BaseSSLError,SocketError) as e:

~\Anaconda3\lib\ssl.py in recv_into(self,buffer,nbytes,flags)
   1240                   self.__class__)
-> 1241             return self.read(nbytes,buffer)
   1242         else:

~\Anaconda3\lib\ssl.py in read(self,len,buffer)
   1098             if buffer is not None:
-> 1099                 return self._sslobj.read(len,buffer)
   1100             else:

timeout: The read operation timed out

During handling of the above exception,another exception occurred:

ReadTimeoutError                          Traceback (most recent call last)
~\Anaconda3\lib\site-packages\urllib3\connectionpool.py in urlopen(self,body,headers,retries,redirect,assert_same_host,pool_timeout,release_conn,body_pos,**response_kw)
    669             # Make the request on the httplib connection object.
--> 670             httplib_response = self._make_request(
    671                 conn,~\Anaconda3\lib\site-packages\urllib3\connectionpool.py in _make_request(self,**httplib_request_kw)
    427         except (SocketTimeout,SocketError) as e:
--> 428             self._raise_timeout(err=e,url=url,timeout_value=read_timeout)
    429             raise

~\Anaconda3\lib\site-packages\urllib3\connectionpool.py in _raise_timeout(self,err,timeout_value)
    334         if isinstance(err,SocketTimeout):
--> 335             raise ReadTimeoutError(
    336                 self,"Read timed out. (read timeout=%s)" % timeout_value

ReadTimeoutError: HTTPSConnectionPool(host='nominatim.openstreetmap.org',port=443): Read timed out. (read timeout=1)

During handling of the above exception,another exception occurred:

MaxRetryError                             Traceback (most recent call last)
~\Anaconda3\lib\site-packages\requests\adapters.py in send(self,request,stream,verify,cert,proxies)
    438             if not chunked:
--> 439                 resp = conn.urlopen(
    440                     method=request.method,~\Anaconda3\lib\site-packages\urllib3\connectionpool.py in urlopen(self,**response_kw)
    753             )
--> 754             return self.urlopen(
    755                 method,**response_kw)
    725 
--> 726             retries = retries.increment(
    727                 method,error=e,_pool=self,_stacktrace=sys.exc_info()[2]

~\Anaconda3\lib\site-packages\urllib3\util\retry.py in increment(self,response,error,_pool,_stacktrace)
    445         if new_retry.is_exhausted():
--> 446             raise MaxRetryError(_pool,error or ResponseError(cause))
    447 

MaxRetryError: HTTPSConnectionPool(host='nominatim.openstreetmap.org',port=443): Max retries exceeded with url: /search?q=32052+Herford%2C+Deutschland&format=json&limit=1 (Caused by ReadTimeoutError("HTTPSConnectionPool(host='nominatim.openstreetmap.org',port=443): Read timed out. (read timeout=1)"))

During handling of the above exception,another exception occurred:

ConnectionError                           Traceback (most recent call last)
~\Anaconda3\lib\site-packages\geopy\adapters.py in _request(self,headers)
    386         try:
--> 387             resp = self.session.get(url,timeout=timeout,headers=headers)
    388         except Exception as error:

~\Anaconda3\lib\site-packages\requests\sessions.py in get(self,**kwargs)
    542         kwargs.setdefault('allow_redirects',True)
--> 543         return self.request('GET',**kwargs)
    544 

~\Anaconda3\lib\site-packages\requests\sessions.py in request(self,params,data,cookies,files,auth,allow_redirects,proxies,hooks,json)
    529         send_kwargs.update(settings)
--> 530         resp = self.send(prep,**send_kwargs)
    531 

~\Anaconda3\lib\site-packages\requests\sessions.py in send(self,**kwargs)
    642         # Send the request
--> 643         r = adapter.send(request,**kwargs)
    644 

~\Anaconda3\lib\site-packages\requests\adapters.py in send(self,proxies)
    515 
--> 516             raise ConnectionError(e,request=request)
    517 

ConnectionError: HTTPSConnectionPool(host='nominatim.openstreetmap.org',another exception occurred:

GeocoderUnavailable                       Traceback (most recent call last)
<ipython-input-5-bf04616147f9> in <module>
      9 
     10 geolocator = Nominatim(user_agent="KVWL_retrieval")
---> 11 location = geolocator.geocode(location)
     12 
     13 headers = {"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,'content-type': 'application/json; charset=UTF-8'}

~\Anaconda3\lib\site-packages\geopy\geocoders\nominatim.py in geocode(self,query,exactly_one,limit,addressdetails,language,geometry,extratags,country_codes,viewBox,bounded,featuretype,namedetails)
    295         logger.debug("%s.geocode: %s",self.__class__.__name__,url)
    296         callback = partial(self._parse_json,exactly_one=exactly_one)
--> 297         return self._call_geocoder(url,callback,timeout=timeout)
    298 
    299     def reverse(

~\Anaconda3\lib\site-packages\geopy\geocoders\base.py in _call_geocoder(self,is_json,headers)
    358         try:
    359             if is_json:
--> 360                 result = self.adapter.get_json(url,headers=req_headers)
    361             else:
    362                 result = self.adapter.get_text(url,headers=req_headers)

~\Anaconda3\lib\site-packages\geopy\adapters.py in get_json(self,headers)
    375 
    376     def get_json(self,*,headers):
--> 377         resp = self._request(url,headers=headers)
    378         try:
    379             return resp.json()

~\Anaconda3\lib\site-packages\geopy\adapters.py in _request(self,headers)
    397                     raise GeocoderServiceError(message)
    398                 else:
--> 399                     raise GeocoderUnavailable(message)
    400             elif isinstance(error,requests.Timeout):
    401                 raise GeocoderTimedOut("Service timed out")

GeocoderUnavailable: HTTPSConnectionPool(host='nominatim.openstreetmap.org',port=443): Read timed out. (read timeout=1)"))

解决方法

暂无找到可以解决该程序问题的有效方法,小编努力寻找整理中!

如果你已经找到好的解决方法,欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@)

相关问答

Selenium Web驱动程序和Java。元素在(x,y)点处不可单击。其...
Python-如何使用点“。” 访问字典成员?
Java 字符串是不可变的。到底是什么意思?
Java中的“ final”关键字如何工作?(我仍然可以修改对象。...
“loop:”在Java代码中。这是什么,为什么要编译?
java.lang.ClassNotFoundException:sun.jdbc.odbc.JdbcOdbc...