Question

当我尝试使用pandas从维基百科下载数据时出现错误。

pd.read_html('http://simple.wikipedia.org/wiki/List_of_U.S._states')

错误消息显示，

SSLError                                  Traceback (most recent call 

last)
/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
   1239             try:
-> 1240                 h.request(req.get_method(), req.selector, req.data, headers)
   1241             except OSError as err: # timeout error

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/http/client.py in request(self, method, url, body, headers)
   1082         """Send a complete request to the server."""
-> 1083         self._send_request(method, url, body, headers)
   1084 

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/http/client.py in _send_request(self, method, url, body, headers)
   1127             body = body.encode('iso-8859-1')
-> 1128         self.endheaders(body)
   1129 

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/http/client.py in endheaders(self, message_body)
   1078             raise CannotSendHeader()
-> 1079         self._send_output(message_body)
   1080 

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/http/client.py in _send_output(self, message_body)
    910 
--> 911         self.send(msg)
    912         if message_body is not None:

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/http/client.py in send(self, data)
    853             if self.auto_open:
--> 854                 self.connect()
    855             else:

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/http/client.py in connect(self)
   1236             self.sock = self._context.wrap_socket(self.sock,
-> 1237                                                   server_hostname=server_hostname)
   1238             if not self._context.check_hostname and self._check_hostname:

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/ssl.py in wrap_socket(self, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname)
    375                          server_hostname=server_hostname,
--> 376                          _context=self)
    377 

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/ssl.py in __init__(self, sock, keyfile, certfile, server_side, cert_reqs, ssl_version, ca_certs, do_handshake_on_connect, family, type, proto, fileno, suppress_ragged_eofs, npn_protocols, ciphers, server_hostname, _context)
    746                         raise ValueError("do_handshake_on_connect should not be specified for non-blocking sockets")
--> 747                     self.do_handshake()
    748 

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/ssl.py in do_handshake(self, block)
    982                 self.settimeout(None)
--> 983             self._sslobj.do_handshake()
    984         finally:

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/ssl.py in do_handshake(self)
    627         """Start the SSL/TLS handshake."""
--> 628         self._sslobj.do_handshake()
    629         if self.context.check_hostname:

SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:646)

During handling of the above exception, another exception occurred:

URLError                                  Traceback (most recent call last)
<ipython-input-51-330bd889a78f> in <module>()
----> 1 fiddy_states = pd.read_html('http://simple.wikipedia.org/wiki/List_of_U.S._states')
      2 print(fiddy_states)

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/site-packages/pandas/io/html.py in read_html(io, match, flavor, header, index_col, skiprows, attrs, parse_dates, tupleize_cols, thousands, encoding)
    864     _validate_header_arg(header)
    865     return _parse(flavor, io, match, header, index_col, skiprows,
--> 866                   parse_dates, tupleize_cols, thousands, attrs, encoding)

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/site-packages/pandas/io/html.py in _parse(flavor, io, match, header, index_col, skiprows, parse_dates, tupleize_cols, thousands, attrs, encoding)
    726             break
    727     else:
--> 728         raise_with_traceback(retained)
    729 
    730     ret = []

/Users/Soma/.pyenv/versions/3.5.0/lib/python3.5/site-packages/pandas/compat/__init__.py in raise_with_traceback(exc, traceback)
    746         if traceback == Ellipsis:
    747             _, _, traceback = sys.exc_info()
--> 748         raise exc.with_traceback(traceback)
    749 else:
    750     # this version of raise is a syntax error in Python 3

URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:646)>

我不知道为什么会这样。

Answer 1

我在Linux上遇到的问题与Linux网站上的问题相同 - 在Windows上，相同的代码解析了网站上的表格。花了一些时间在Linux上比较和更新库版本没有结果，我在使用read_html之前添加了一些额外的代码来处理SSL证书：

> import urllib3,certifi
> 
> #Force certificate check and use certifi to handle the certificate. 
> https = urllib3.PoolManager( cert_reqs='CERT_REQUIRED',
> ca_certs=certifi.where(),)  
> 
> url = https.urlopen('GET','https://yoursecureproblematicwebsite.com') 
> 
> #Then you parse the html as usual 
> foo = pd.read_html(url.data)

还要确保您拥有最新版本的certifi：

>python -m pip install certifi --update

这很可能不是最有效的方式，但我希望有所帮助。

丰齐

验证SSL证书时出错

1 个答案: