|
ClosedPoolError, ProtocolError, EmptyPoolError, HeaderParsingError, HostChangedError, LocationValueError, MaxRetryError, ProxyError, ReadTimeoutError, SSLError, TimeoutError, InsecureRequestWarning, NewConnectionError, ) port_by_scheme, DummyConnection, HTTPConnection, HTTPSConnection, VerifiedHTTPSConnection, HTTPException, BaseSSLError, )
get_host, parse_url, Url, _normalize_host as normalize_host, _encode_target, )
# Pool objects """ Base class for all connection pools, such as :class:`.HTTPConnectionPool` and :class:`.HTTPSConnectionPool`.
.. note:: ConnectionPool.urlopen() does not normalize or percent-encode target URIs which is useful if your target server doesn't support percent-encoded target URIs. """
raise LocationValueError("No host specified.")
def __str__(self): return "%s(host=%r, port=%r)" % (type(self).__name__, self.host, self.port)
return self
self.close() # Return False to re-raise any potential exceptions return False
""" Close all pooled connections and disable the pool. """ pass
# This is taken from http://hg.python.org/cpython/file/7aaba721ebc0/Lib/socket.py#l252
""" Thread-safe connection pool for one host.
:param host: Host used for this HTTP Connection (e.g. "localhost"), passed into :class:`httplib.HTTPConnection`.
:param port: Port used for this HTTP Connection (None is equivalent to 80), passed into :class:`httplib.HTTPConnection`.
:param strict: Causes BadStatusLine to be raised if the status line can't be parsed as a valid HTTP/1.0 or 1.1 status line, passed into :class:`httplib.HTTPConnection`.
.. note:: Only works in Python 2. This parameter is ignored in Python 3.
:param timeout: Socket timeout in seconds for each individual connection. This can be a float or integer, which sets the timeout for the HTTP request, or an instance of :class:`urllib3.util.Timeout` which gives you more fine-grained control over request timeouts. After the constructor has been parsed, this is always a `urllib3.util.Timeout` object.
:param maxsize: Number of connections to save that can be reused. More than 1 is useful in multithreaded situations. If ``block`` is set to False, more connections will be created but they will not be saved once they've been used.
:param block: If set to True, no more than ``maxsize`` connections will be used at a time. When no free connections are available, the call will block until a connection has been released. This is a useful side effect for particular multithreaded situations where one does not want to use more than maxsize connections per host to prevent flooding.
:param headers: Headers to include with all requests, unless other headers are given explicitly.
:param retries: Retry configuration to use by default with requests in this pool.
:param _proxy: Parsed proxy URL, should not be used directly, instead, see :class:`urllib3.connectionpool.ProxyManager`"
:param _proxy_headers: A dictionary with proxy headers, should not be used directly, instead, see :class:`urllib3.connectionpool.ProxyManager`"
:param \\**conn_kw: Additional parameters are used to create fresh :class:`urllib3.connection.HTTPConnection`, :class:`urllib3.connection.HTTPSConnection` instances. """
self, host, port=None, strict=False, timeout=Timeout.DEFAULT_TIMEOUT, maxsize=1, block=False, headers=None, retries=None, _proxy=None, _proxy_headers=None, **conn_kw ):
# Fill the queue up so that doing get() on it will block properly
# These are mostly for testing and debugging purposes.
# Enable Nagle's algorithm for proxies, to avoid packet fragmentation. # We cannot know if the user has added default socket options, so we cannot replace the # list. self.conn_kw.setdefault("socket_options", [])
""" Return a fresh :class:`HTTPConnection`. """ "Starting new HTTP connection (%d): %s:%s", self.num_connections, self.host, self.port or "80", )
host=self.host, port=self.port, timeout=self.timeout.connect_timeout, strict=self.strict, **self.conn_kw )
""" Get a connection. Will return a pooled connection if one is available.
If no connections are available and :prop:`.block` is ``False``, then a fresh connection is returned.
:param timeout: Seconds to wait before giving up and raising :class:`urllib3.exceptions.EmptyPoolError` if the pool is empty and :prop:`.block` is ``True``. """
except AttributeError: # self.pool is None raise ClosedPoolError(self, "Pool is closed.")
except queue.Empty: if self.block: raise EmptyPoolError( self, "Pool reached maximum size and no more connections are allowed.", ) pass # Oh well, we'll create a new connection then
# If this is a persistent connection, check if it got disconnected # This is a proxied connection that has been mutated by # httplib._tunnel() and cannot be reused (since it would # attempt to bypass the proxy) conn = None
""" Put a connection back into the pool.
:param conn: Connection object for the current host and port as returned by :meth:`._new_conn` or :meth:`._get_conn`.
If the pool is already full, the connection is closed and discarded because we exceeded maxsize. If connections are discarded frequently, then maxsize should be increased.
If the pool is closed, then the connection will be closed and discarded. """ except AttributeError: # self.pool is None. pass except queue.Full: # This should never happen if self.block == True log.warning("Connection pool is full, discarding connection: %s", self.host)
# Connection never got put back into the pool, close it. if conn: conn.close()
""" Called right before a request is made, after the socket is created. """
# Nothing to do for HTTP connections. pass
""" Helper that always returns a :class:`urllib3.util.Timeout` """ return self.timeout.clone()
else: # User passed us an int/float. This is for backwards compatibility, # can be removed later return Timeout.from_float(timeout)
def _raise_timeout(self, err, url, timeout_value): """Is the error actually a timeout? Will raise a ReadTimeout or pass"""
if isinstance(err, SocketTimeout): raise ReadTimeoutError( self, url, "Read timed out. (read timeout=%s)" % timeout_value )
# See the above comment about EAGAIN in Python 3. In Python 2 we have # to specifically catch it and throw the timeout error if hasattr(err, "errno") and err.errno in _blocking_errnos: raise ReadTimeoutError( self, url, "Read timed out. (read timeout=%s)" % timeout_value )
# Catch possible read timeouts thrown as SSL errors. If not the # case, rethrow the original. We need to do this because of: # http://bugs.python.org/issue10272 if "timed out" in str(err) or "did not complete (read)" in str( err ): # Python < 2.7.4 raise ReadTimeoutError( self, url, "Read timed out. (read timeout=%s)" % timeout_value )
self, conn, method, url, timeout=_Default, chunked=False, **httplib_request_kw ): """ Perform a request on a given urllib connection object taken from our pool.
:param conn: a connection from one of our connection pools
:param timeout: Socket timeout in seconds for the request. This can be a float or integer, which will set the same timeout value for the socket connect and the socket read, or an instance of :class:`urllib3.util.Timeout`, which gives you more fine-grained control over your timeouts. """
# Trigger any extra validation we need to do. except (SocketTimeout, BaseSSLError) as e: # Py2 raises this as a BaseSSLError, Py3 raises it as socket timeout. self._raise_timeout(err=e, url=url, timeout_value=conn.timeout) raise
# conn.request() calls httplib.*.request, not the method in # urllib3.request. It also calls makefile (recv) on the socket. conn.request_chunked(method, url, **httplib_request_kw) else:
# Reset the timeout for the recv() on the socket
# App Engine doesn't have a sock attr # In Python 3 socket.py will catch EAGAIN and return None when you # try and read into the file pointer created by http.client, which # instead raises a BadStatusLine exception. Instead of catching # the exception and assuming all BadStatusLine exceptions are read # timeouts, check for a zero timeout before making the request. raise ReadTimeoutError( self, url, "Read timed out. (read timeout=%s)" % read_timeout ) conn.sock.settimeout(socket.getdefaulttimeout()) else: # None or a value
# Receive the response from the server # Python 2.7, use buffering of HTTP responses # Python 3 except BaseException as e: # Remove the TypeError from the exception chain in # Python 3 (including for exceptions like SystemExit). # Otherwise it looks like a bug in the code. six.raise_from(e, None) except (SocketTimeout, BaseSSLError, SocketError) as e: self._raise_timeout(err=e, url=url, timeout_value=read_timeout) raise
# AppEngine doesn't have a version attr. '%s://%s:%s "%s %s %s" %s %s', self.scheme, self.host, self.port, method, url, http_version, httplib_response.status, httplib_response.length, )
except (HeaderParsingError, TypeError) as hpe: # Platform-specific: Python 3 log.warning( "Failed to parse headers (url=%s): %s", self._absolute_url(url), hpe, exc_info=True, )
return Url(scheme=self.scheme, host=self.host, port=self.port, path=path).url
""" Close all pooled connections and disable the pool. """ return # Disable access to the pool
""" Check if the given ``url`` is a member of the same host as this connection pool. """ if url.startswith("/"): return True
# TODO: Add optional support for socket.gethostbyname checking. scheme, host, port = get_host(url) if host is not None: host = _normalize_host(host, scheme=scheme)
# Use explicit default port for comparison when none is given if self.port and not port: port = port_by_scheme.get(scheme) elif not self.port and port == port_by_scheme.get(scheme): port = None
return (scheme, host, port) == (self.scheme, self.host, self.port)
self, method, url, body=None, headers=None, retries=None, redirect=True, assert_same_host=True, timeout=_Default, pool_timeout=None, release_conn=None, chunked=False, body_pos=None, **response_kw ): """ Get a connection from the pool and perform an HTTP request. This is the lowest level call for making a request, so you'll need to specify all the raw details.
.. note::
More commonly, it's appropriate to use a convenience method provided by :class:`.RequestMethods`, such as :meth:`request`.
.. note::
`release_conn` will only behave as expected if `preload_content=False` because we want to make `preload_content=False` the default behaviour someday soon without breaking backwards compatibility.
:param method: HTTP request method (such as GET, POST, PUT, etc.)
:param body: Data to send in the request body (useful for creating POST requests, see HTTPConnectionPool.post_url for more convenience).
:param headers: Dictionary of custom headers to send, such as User-Agent, If-None-Match, etc. If None, pool headers are used. If provided, these headers completely replace any pool-specific headers.
:param retries: Configure the number of retries to allow before raising a :class:`~urllib3.exceptions.MaxRetryError` exception.
Pass ``None`` to retry until you receive a response. Pass a :class:`~urllib3.util.retry.Retry` object for fine-grained control over different types of retries. Pass an integer number to retry connection errors that many times, but no other types of errors. Pass zero to never retry.
If ``False``, then retries are disabled and any exception is raised immediately. Also, instead of raising a MaxRetryError on redirects, the redirect response will be returned.
:type retries: :class:`~urllib3.util.retry.Retry`, False, or an int.
:param redirect: If True, automatically handle redirects (status codes 301, 302, 303, 307, 308). Each redirect counts as a retry. Disabling retries will disable redirect, too.
:param assert_same_host: If ``True``, will make sure that the host of the pool requests is consistent else will raise HostChangedError. When False, you can use the pool on an HTTP proxy and request foreign hosts.
:param timeout: If specified, overrides the default timeout for this one request. It may be a float (in seconds) or an instance of :class:`urllib3.util.Timeout`.
:param pool_timeout: If set and the pool is set to block=True, then this method will block for ``pool_timeout`` seconds and raise EmptyPoolError if no connection is available within the time period.
:param release_conn: If False, then the urlopen call will not release the connection back into the pool once a response is received (but will release if you read the entire contents of the response such as when `preload_content=True`). This is useful if you're not preloading the response's content immediately. You will need to call ``r.release_conn()`` on the response ``r`` to return the connection back into the pool. If None, it takes the value of ``response_kw.get('preload_content', True)``.
:param chunked: If True, urllib3 will send the body using chunked transfer encoding. Otherwise, urllib3 will send the body using the standard content-length form. Defaults to False.
:param int body_pos: Position to seek to in file-like body in the event of a retry or redirect. Typically this won't need to be set because urllib3 will auto-populate the value when needed.
:param \\**response_kw: Additional parameters are passed to :meth:`urllib3.response.HTTPResponse.from_httplib` """ headers = self.headers
retries = Retry.from_int(retries, redirect=redirect, default=self.retries)
# Check host raise HostChangedError(self, url, retries)
# Ensure that the URL we're connecting to is properly encoded else: url = six.ensure_str(parse_url(url).url)
# Track whether `conn` needs to be released before # returning/raising/recursing. Update this variable if necessary, and # leave `release_conn` constant throughout the function. That way, if # the function recurses, the original value of `release_conn` will be # passed down into the recursive call, and its value will be respected. # # See issue #651 [1] for details. # # [1] <https://github.com/urllib3/urllib3/issues/651>
# Merge the proxy headers. Only do this in HTTP. We have to copy the # headers dict so we can safely change it without those changes being # reflected in anyone else's copy.
# Must keep the exception bound to a separate variable or else Python 3 # complains about UnboundLocalError.
# Keep track of whether we cleanly exited the except block. This # ensures we do proper cleanup in finally.
# Rewind body position, if needed. Record current position # for future rewinds in the event of a redirect/retry.
# Request a connection from the queue.
conn, "sock", None ) self._prepare_proxy(conn)
# Make the request on the httplib connection object. conn, method, url, timeout=timeout_obj, body=body, headers=headers, chunked=chunked, )
# If we're going to release the connection in ``finally:``, then # the response doesn't need to know about the connection. Otherwise # it will also try to release it and we'll have a double-release # mess.
# Pass method to Response for length checking
# Import httplib's response into our own wrapper object httplib_response, pool=self, connection=response_conn, retries=retries, **response_kw )
# Everything went great!
except EmptyPoolError: # Didn't get a connection from the pool, no need to clean up clean_exit = True release_this_conn = False raise
except ( TimeoutError, HTTPException, SocketError, ProtocolError, BaseSSLError, SSLError, CertificateError, ) as e: # Discard the connection for these exceptions. It will be # replaced during the next _get_conn() call. clean_exit = False if isinstance(e, (BaseSSLError, CertificateError)): e = SSLError(e) elif isinstance(e, (SocketError, NewConnectionError)) and self.proxy: e = ProxyError("Cannot connect to proxy.", e) elif isinstance(e, (SocketError, HTTPException)): e = ProtocolError("Connection aborted.", e)
retries = retries.increment( method, url, error=e, _pool=self, _stacktrace=sys.exc_info()[2] ) retries.sleep()
# Keep track of the error for the retry warning. err = e
finally: # We hit some kind of exception, handled or otherwise. We need # to throw the connection away unless explicitly told not to. # Close the connection, set the variable to None, and make sure # we put the None back in the pool to avoid leaking it. conn = conn and conn.close() release_this_conn = True
# Put the connection back to be reused. If the connection is # expired then it will be None, which will get replaced with a # fresh connection during _get_conn. self._put_conn(conn)
# Try again log.warning( "Retrying (%r) after connection broken by '%r': %s", retries, err, url ) return self.urlopen( method, url, body, headers, retries, redirect, assert_same_host, timeout=timeout, pool_timeout=pool_timeout, release_conn=release_conn, chunked=chunked, body_pos=body_pos, **response_kw )
# Handle redirect? if response.status == 303: method = "GET"
try: retries = retries.increment(method, url, response=response, _pool=self) except MaxRetryError: if retries.raise_on_redirect: response.drain_conn() raise return response
response.drain_conn() retries.sleep_for_retry(response) log.debug("Redirecting %s -> %s", url, redirect_location) return self.urlopen( method, redirect_location, body, headers, retries=retries, redirect=redirect, assert_same_host=assert_same_host, timeout=timeout, pool_timeout=pool_timeout, release_conn=release_conn, chunked=chunked, body_pos=body_pos, **response_kw )
# Check if we should retry the HTTP response. try: retries = retries.increment(method, url, response=response, _pool=self) except MaxRetryError: if retries.raise_on_status: response.drain_conn() raise return response
response.drain_conn() retries.sleep(response) log.debug("Retry: %s", url) return self.urlopen( method, url, body, headers, retries=retries, redirect=redirect, assert_same_host=assert_same_host, timeout=timeout, pool_timeout=pool_timeout, release_conn=release_conn, chunked=chunked, body_pos=body_pos, **response_kw )
""" Same as :class:`.HTTPConnectionPool`, but HTTPS.
When Python is compiled with the :mod:`ssl` module, then :class:`.VerifiedHTTPSConnection` is used, which *can* verify certificates, instead of :class:`.HTTPSConnection`.
:class:`.VerifiedHTTPSConnection` uses one of ``assert_fingerprint``, ``assert_hostname`` and ``host`` in this order to verify connections. If ``assert_hostname`` is False, no verification is done.
The ``key_file``, ``cert_file``, ``cert_reqs``, ``ca_certs``, ``ca_cert_dir``, ``ssl_version``, ``key_password`` are only used if :mod:`ssl` is available and are fed into :meth:`urllib3.util.ssl_wrap_socket` to upgrade the connection socket into an SSL socket. """
self, host, port=None, strict=False, timeout=Timeout.DEFAULT_TIMEOUT, maxsize=1, block=False, headers=None, retries=None, _proxy=None, _proxy_headers=None, key_file=None, cert_file=None, cert_reqs=None, key_password=None, ca_certs=None, ssl_version=None, assert_hostname=None, assert_fingerprint=None, ca_cert_dir=None, **conn_kw ):
self, host, port, strict, timeout, maxsize, block, headers, retries, _proxy, _proxy_headers, **conn_kw )
""" Prepare the ``connection`` for :meth:`urllib3.util.ssl_wrap_socket` and establish the tunnel if proxy is used. """
key_file=self.key_file, key_password=self.key_password, cert_file=self.cert_file, cert_reqs=self.cert_reqs, ca_certs=self.ca_certs, ca_cert_dir=self.ca_cert_dir, assert_hostname=self.assert_hostname, assert_fingerprint=self.assert_fingerprint, )
""" Establish tunnel connection early, because otherwise httplib would improperly set Host: header to proxy's IP:port. """ conn.set_tunnel(self._proxy_host, self.port, self.proxy_headers) conn.connect()
""" Return a fresh :class:`httplib.HTTPSConnection`. """ "Starting new HTTPS connection (%d): %s:%s", self.num_connections, self.host, self.port or "443", )
raise SSLError( "Can't connect to HTTPS URL because the SSL module is not available." )
actual_host = self.proxy.host actual_port = self.proxy.port
host=actual_host, port=actual_port, timeout=self.timeout.connect_timeout, strict=self.strict, cert_file=self.cert_file, key_file=self.key_file, key_password=self.key_password, **self.conn_kw )
""" Called right before a request is made, after the socket is created. """
# Force connect early to allow us to validate the connection.
warnings.warn( ( "Unverified HTTPS request is being made to host '%s'. " "Adding certificate verification is strongly advised. See: " "https://urllib3.readthedocs.io/en/latest/advanced-usage.html" "#ssl-warnings" % conn.host ), InsecureRequestWarning, )
""" Given a url, return an :class:`.ConnectionPool` instance of its host.
This is a shortcut for not having to parse out the scheme, host, and port of the url before creating an :class:`.ConnectionPool` instance.
:param url: Absolute URL string that must include the scheme. Port is optional.
:param \\**kw: Passes additional parameters to the constructor of the appropriate :class:`.ConnectionPool`. Useful for specifying things like timeout, maxsize, headers, etc.
Example::
>>> conn = connection_from_url('http://google.com/') >>> r = conn.request('GET', '/') """ scheme, host, port = get_host(url) port = port or port_by_scheme.get(scheme, 80) if scheme == "https": return HTTPSConnectionPool(host, port=port, **kw) else: return HTTPConnectionPool(host, port=port, **kw)
""" Normalize hosts for comparisons and use with sockets. """
# httplib doesn't like it when we include brackets in IPv6 addresses # Specifically, if we include brackets but also pass the port then # httplib crazily doubles up the square brackets on the Host header. # Instead, we need to make sure we never pass ``None`` as the port. # However, for backward compatibility reasons we can't actually # *assert* that. See http://bugs.python.org/issue28539 host = host[1:-1] |