python 爬取数据intraday_利用Python进行数据分析(11)：金融和经济数据应用
---------------------------------------------------------------------------
gaierror Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\requests\packages\urllib3\connection.py in _new_conn(self)
137 conn = connection.create_connection(
--> 138(self.host, self.port), self.timeout, **extra_kw)139
C:\ProgramData\Anaconda3\lib\site-packages\requests\packages\urllib3\util\connection.py in create_connection(address, timeout, source_address, socket_options)
74
---> 75for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
76 af, socktype, proto, canonname, sa = res
C:\ProgramData\Anaconda3\lib\socket.py in getaddrinfo(host, port, family, type, proto, flags)
742 addrlist = []
--> 743for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
744 af, socktype, proto, canonname, sa = res
gaierror: [Errno 11004] getaddrinfo failed
During handling of the above exception, another exception occurred:
NewConnectionError Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\requests\packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, **response_kw)
593 body=body, headers=headers,
--> 594chunked=chunked)595
C:\ProgramData\Anaconda3\lib\site-packages\requests\packages\urllib3\connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
360 else:
--> 361conn.request(method, url, **httplib_request_kw)
362
C:\ProgramData\Anaconda3\lib\http\client.py in request(self, method, url, body, headers, encode_chunked)
1238 """Send a complete request to the server."""
-> 1239self._send_request(method, url, body, headers, encode_chunked)
1240
C:\ProgramData\Anaconda3\lib\http\client.py in _send_request(self, method, url, body, headers, encode_chunked)
1284 body = _encode(body, 'body')
-> 1285self.endheaders(body, encode_chunked=encode_chunked)
1286
C:\ProgramData\Anaconda3\lib\http\client.py in endheaders(self, message_body, encode_chunked)
1233 raise CannotSendHeader()
-> 1234self._send_output(message_body, encode_chunked=encode_chunked)
1235
C:\ProgramData\Anaconda3\lib\http\client.py in _send_output(self, message_body, encode_chunked)
1025 del self._buffer[:]
-> 1026self.send(msg)
1027
C:\ProgramData\Anaconda3\lib\http\client.py in send(self, data)
963 if self.auto_open:
--> 964self.connect()
965 else:
C:\ProgramData\Anaconda3\lib\site-packages\requests\packages\urllib3\connection.py in connect(self)
162 def connect(self):
--> 163conn = self._new_conn()
164 self._prepare_conn(conn)
C:\ProgramData\Anaconda3\lib\site-packages\requests\packages\urllib3\connection.py in _new_conn(self)
146 raise NewConnectionError(
--> 147self, "Failed to establish a new connection: %s" % e)148
NewConnectionError: : Failed to establish a new connection: [Errno 11004] getaddrinfo failed
During handling of the above exception, another exception occurred:
MaxRetryError Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\requests\adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
422 retries=self.max_retries,
--> 423timeout=timeout
424 )
C:\ProgramData\Anaconda3\lib\site-packages\requests\packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, **response_kw)
642 retries = retries.increment(method, url, error=e, _pool=self,
--> 643_stacktrace=sys.exc_info()[2])644 retries.sleep()
C:\ProgramData\Anaconda3\lib\site-packages\requests\packages\urllib3\util\retry.py in increment(self, method, url, response, error, _pool, _stacktrace)
362 if new_retry.is_exhausted():
--> 363raise MaxRetryError(_pool, url, error or ResponseError(cause))
364
MaxRetryError: HTTPConnectionPool(host='ichart.finance.yahoo.com', port=80): Max retries exceeded with url: /table.csv?s=AAPL&a=0&b=1&c=2010&d=6&e=24&f=2017&g=d&ignore=.csv (Caused by NewConnectionError(': Failed to establish a new connection: [Errno 11004] getaddrinfo failed',))
During handling of the above exception, another exception occurred:
ConnectionError Traceback (most recent call last)
in ()
5 def get_px(stock, start, end):
6 return web.DataReader(stock, 'yahoo',start, end)['Adj Close']
----> 7px = DataFrame({n: get_px(n, None, None) for n in names})
8
9 #px = pd.read_csv('data/ch11/stock_px.csv')
in (.0)
5 def get_px(stock, start, end):
6 return web.DataReader(stock, 'yahoo',start, end)['Adj Close']
----> 7px = DataFrame({n: get_px(n, None, None) for n in names})
8
9 #px = pd.read_csv('data/ch11/stock_px.csv')
in get_px(stock, start, end)
4 names = ['AAPL', 'GOOG', 'MSFT', 'DELL', 'GS', 'MS', 'BAC', 'C']
5 def get_px(stock, start, end):
----> 6return web.DataReader(stock, 'yahoo',start, end)['Adj Close']
7 px = DataFrame({n: get_px(n, None, None) for n in names})
8
C:\ProgramData\Anaconda3\lib\site-packages\pandas_datareader\data.py in DataReader(name, data_source, start, end, retry_count, pause, session, access_key)
115 adjust_price=False, chunksize=25,
116 retry_count=retry_count, pause=pause,
--> 117session=session).read()118
119 elif data_source == "yahoo-actions":
C:\ProgramData\Anaconda3\lib\site-packages\pandas_datareader\yahoo\daily.py in read(self)
75 def read(self):
76 """ read one data from specified URL """
---> 77df = super(YahooDailyReader, self).read()
78 if self.ret_index:
79 df['Ret_Index'] = _calc_return_index(df['Adj Close'])
C:\ProgramData\Anaconda3\lib\site-packages\pandas_datareader\base.py in read(self)
155 if isinstance(self.symbols, (compat.string_types, int)):
156 df = self._read_one_data(self.url,
--> 157params=self._get_params(self.symbols))158 # Or multiple symbols, (e.g., ['GOOG', 'AAPL', 'MSFT'])
159 elif isinstance(self.symbols, DataFrame):
C:\ProgramData\Anaconda3\lib\site-packages\pandas_datareader\base.py in _read_one_data(self, url, params)
72 """ read one data from specified URL """
73 if self._format == 'string':
---> 74out = self._read_url_as_StringIO(url, params=params)
75 elif self._format == 'json':
76 out = self._get_response(url, params=params).json()
C:\ProgramData\Anaconda3\lib\site-packages\pandas_datareader\base.py in _read_url_as_StringIO(self, url, params)
83 Open url (and retry)
84 """
---> 85response = self._get_response(url, params=params)
86 text = self._sanitize_response(response)
87 out = StringIO()
C:\ProgramData\Anaconda3\lib\site-packages\pandas_datareader\base.py in _get_response(self, url, params)
112 # initial attempt + retry
113 for i in range(self.retry_count + 1):
--> 114response = self.session.get(url, params=params)
115 if response.status_code == requests.codes.ok:
116 return response
C:\ProgramData\Anaconda3\lib\site-packages\requests\sessions.py in get(self, url, **kwargs)
499
500 kwargs.setdefault('allow_redirects', True)
--> 501return self.request('GET', url, **kwargs)
502
503 def options(self, url, **kwargs):
C:\ProgramData\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)
486 }
487 send_kwargs.update(settings)
--> 488resp = self.send(prep, **send_kwargs)
489
490 return resp
C:\ProgramData\Anaconda3\lib\site-packages\requests\sessions.py in send(self, request, **kwargs)
607
608 # Send the request
--> 609r = adapter.send(request, **kwargs)
610
611 # Total elapsed time of the request (approximately)
C:\ProgramData\Anaconda3\lib\site-packages\requests\adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
485 raise ProxyError(e, request=request)
486
--> 487raise ConnectionError(e, request=request)
488
489 except ClosedPoolError as e:
ConnectionError: HTTPConnectionPool(host='ichart.finance.yahoo.com', port=80): Max retries exceeded with url: /table.csv?s=AAPL&a=0&b=1&c=2010&d=6&e=24&f=2017&g=d&ignore=.csv (Caused by NewConnectionError(': Failed to establish a new connection: [Errno 11004] getaddrinfo failed',))