/usr/lib/python2.7/dist-packages/tornado/httpclient.py is in python-tornado 3.1.1-1ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 | """Blocking and non-blocking HTTP client interfaces.
This module defines a common interface shared by two implementations,
``simple_httpclient`` and ``curl_httpclient``. Applications may either
instantiate their chosen implementation class directly or use the
`AsyncHTTPClient` class from this module, which selects an implementation
that can be overridden with the `AsyncHTTPClient.configure` method.
The default implementation is ``simple_httpclient``, and this is expected
to be suitable for most users' needs. However, some applications may wish
to switch to ``curl_httpclient`` for reasons such as the following:
* ``curl_httpclient`` has some features not found in ``simple_httpclient``,
including support for HTTP proxies and the ability to use a specified
network interface.
* ``curl_httpclient`` is more likely to be compatible with sites that are
not-quite-compliant with the HTTP spec, or sites that use little-exercised
features of HTTP.
* ``curl_httpclient`` is faster.
* ``curl_httpclient`` was the default prior to Tornado 2.0.
Note that if you are using ``curl_httpclient``, it is highly recommended that
you use a recent version of ``libcurl`` and ``pycurl``. Currently the minimum
supported version is 7.18.2, and the recommended version is 7.21.1 or newer.
"""
from __future__ import absolute_import, division, print_function, with_statement
import functools
import time
import weakref
from tornado.concurrent import Future
from tornado.escape import utf8
from tornado import httputil, stack_context
from tornado.ioloop import IOLoop
from tornado.util import Configurable
class HTTPClient(object):
"""A blocking HTTP client.
This interface is provided for convenience and testing; most applications
that are running an IOLoop will want to use `AsyncHTTPClient` instead.
Typical usage looks like this::
http_client = httpclient.HTTPClient()
try:
response = http_client.fetch("http://www.google.com/")
print response.body
except httpclient.HTTPError as e:
print "Error:", e
http_client.close()
"""
def __init__(self, async_client_class=None, **kwargs):
self._io_loop = IOLoop()
if async_client_class is None:
async_client_class = AsyncHTTPClient
self._async_client = async_client_class(self._io_loop, **kwargs)
self._closed = False
def __del__(self):
self.close()
def close(self):
"""Closes the HTTPClient, freeing any resources used."""
if not self._closed:
self._async_client.close()
self._io_loop.close()
self._closed = True
def fetch(self, request, **kwargs):
"""Executes a request, returning an `HTTPResponse`.
The request may be either a string URL or an `HTTPRequest` object.
If it is a string, we construct an `HTTPRequest` using any additional
kwargs: ``HTTPRequest(request, **kwargs)``
If an error occurs during the fetch, we raise an `HTTPError`.
"""
response = self._io_loop.run_sync(functools.partial(
self._async_client.fetch, request, **kwargs))
response.rethrow()
return response
class AsyncHTTPClient(Configurable):
"""An non-blocking HTTP client.
Example usage::
def handle_request(response):
if response.error:
print "Error:", response.error
else:
print response.body
http_client = AsyncHTTPClient()
http_client.fetch("http://www.google.com/", handle_request)
The constructor for this class is magic in several respects: It
actually creates an instance of an implementation-specific
subclass, and instances are reused as a kind of pseudo-singleton
(one per `.IOLoop`). The keyword argument ``force_instance=True``
can be used to suppress this singleton behavior. Constructor
arguments other than ``io_loop`` and ``force_instance`` are
deprecated. The implementation subclass as well as arguments to
its constructor can be set with the static method `configure()`
"""
@classmethod
def configurable_base(cls):
return AsyncHTTPClient
@classmethod
def configurable_default(cls):
from tornado.simple_httpclient import SimpleAsyncHTTPClient
return SimpleAsyncHTTPClient
@classmethod
def _async_clients(cls):
attr_name = '_async_client_dict_' + cls.__name__
if not hasattr(cls, attr_name):
setattr(cls, attr_name, weakref.WeakKeyDictionary())
return getattr(cls, attr_name)
def __new__(cls, io_loop=None, force_instance=False, **kwargs):
io_loop = io_loop or IOLoop.current()
if io_loop in cls._async_clients() and not force_instance:
return cls._async_clients()[io_loop]
instance = super(AsyncHTTPClient, cls).__new__(cls, io_loop=io_loop,
**kwargs)
if not force_instance:
cls._async_clients()[io_loop] = instance
return instance
def initialize(self, io_loop, defaults=None):
self.io_loop = io_loop
self.defaults = dict(HTTPRequest._DEFAULTS)
if defaults is not None:
self.defaults.update(defaults)
def close(self):
"""Destroys this HTTP client, freeing any file descriptors used.
Not needed in normal use, but may be helpful in unittests that
create and destroy http clients. No other methods may be called
on the `AsyncHTTPClient` after ``close()``.
"""
if self._async_clients().get(self.io_loop) is self:
del self._async_clients()[self.io_loop]
def fetch(self, request, callback=None, **kwargs):
"""Executes a request, asynchronously returning an `HTTPResponse`.
The request may be either a string URL or an `HTTPRequest` object.
If it is a string, we construct an `HTTPRequest` using any additional
kwargs: ``HTTPRequest(request, **kwargs)``
This method returns a `.Future` whose result is an
`HTTPResponse`. The ``Future`` wil raise an `HTTPError` if
the request returned a non-200 response code.
If a ``callback`` is given, it will be invoked with the `HTTPResponse`.
In the callback interface, `HTTPError` is not automatically raised.
Instead, you must check the response's ``error`` attribute or
call its `~HTTPResponse.rethrow` method.
"""
if not isinstance(request, HTTPRequest):
request = HTTPRequest(url=request, **kwargs)
# We may modify this (to add Host, Accept-Encoding, etc),
# so make sure we don't modify the caller's object. This is also
# where normal dicts get converted to HTTPHeaders objects.
request.headers = httputil.HTTPHeaders(request.headers)
request = _RequestProxy(request, self.defaults)
future = Future()
if callback is not None:
callback = stack_context.wrap(callback)
def handle_future(future):
exc = future.exception()
if isinstance(exc, HTTPError) and exc.response is not None:
response = exc.response
elif exc is not None:
response = HTTPResponse(
request, 599, error=exc,
request_time=time.time() - request.start_time)
else:
response = future.result()
self.io_loop.add_callback(callback, response)
future.add_done_callback(handle_future)
def handle_response(response):
if response.error:
future.set_exception(response.error)
else:
future.set_result(response)
self.fetch_impl(request, handle_response)
return future
def fetch_impl(self, request, callback):
raise NotImplementedError()
@classmethod
def configure(cls, impl, **kwargs):
"""Configures the `AsyncHTTPClient` subclass to use.
``AsyncHTTPClient()`` actually creates an instance of a subclass.
This method may be called with either a class object or the
fully-qualified name of such a class (or ``None`` to use the default,
``SimpleAsyncHTTPClient``)
If additional keyword arguments are given, they will be passed
to the constructor of each subclass instance created. The
keyword argument ``max_clients`` determines the maximum number
of simultaneous `~AsyncHTTPClient.fetch()` operations that can
execute in parallel on each `.IOLoop`. Additional arguments
may be supported depending on the implementation class in use.
Example::
AsyncHTTPClient.configure("tornado.curl_httpclient.CurlAsyncHTTPClient")
"""
super(AsyncHTTPClient, cls).configure(impl, **kwargs)
class HTTPRequest(object):
"""HTTP client request object."""
# Default values for HTTPRequest parameters.
# Merged with the values on the request object by AsyncHTTPClient
# implementations.
_DEFAULTS = dict(
connect_timeout=20.0,
request_timeout=20.0,
follow_redirects=True,
max_redirects=5,
use_gzip=True,
proxy_password='',
allow_nonstandard_methods=False,
validate_cert=True)
def __init__(self, url, method="GET", headers=None, body=None,
auth_username=None, auth_password=None, auth_mode=None,
connect_timeout=None, request_timeout=None,
if_modified_since=None, follow_redirects=None,
max_redirects=None, user_agent=None, use_gzip=None,
network_interface=None, streaming_callback=None,
header_callback=None, prepare_curl_callback=None,
proxy_host=None, proxy_port=None, proxy_username=None,
proxy_password=None, allow_nonstandard_methods=None,
validate_cert=None, ca_certs=None,
allow_ipv6=None,
client_key=None, client_cert=None):
r"""All parameters except ``url`` are optional.
:arg string url: URL to fetch
:arg string method: HTTP method, e.g. "GET" or "POST"
:arg headers: Additional HTTP headers to pass on the request
:arg body: HTTP body to pass on the request
:type headers: `~tornado.httputil.HTTPHeaders` or `dict`
:arg string auth_username: Username for HTTP authentication
:arg string auth_password: Password for HTTP authentication
:arg string auth_mode: Authentication mode; default is "basic".
Allowed values are implementation-defined; ``curl_httpclient``
supports "basic" and "digest"; ``simple_httpclient`` only supports
"basic"
:arg float connect_timeout: Timeout for initial connection in seconds
:arg float request_timeout: Timeout for entire request in seconds
:arg if_modified_since: Timestamp for ``If-Modified-Since`` header
:type if_modified_since: `datetime` or `float`
:arg bool follow_redirects: Should redirects be followed automatically
or return the 3xx response?
:arg int max_redirects: Limit for ``follow_redirects``
:arg string user_agent: String to send as ``User-Agent`` header
:arg bool use_gzip: Request gzip encoding from the server
:arg string network_interface: Network interface to use for request
:arg callable streaming_callback: If set, ``streaming_callback`` will
be run with each chunk of data as it is received, and
``HTTPResponse.body`` and ``HTTPResponse.buffer`` will be empty in
the final response.
:arg callable header_callback: If set, ``header_callback`` will
be run with each header line as it is received (including the
first line, e.g. ``HTTP/1.0 200 OK\r\n``, and a final line
containing only ``\r\n``. All lines include the trailing newline
characters). ``HTTPResponse.headers`` will be empty in the final
response. This is most useful in conjunction with
``streaming_callback``, because it's the only way to get access to
header data while the request is in progress.
:arg callable prepare_curl_callback: If set, will be called with
a ``pycurl.Curl`` object to allow the application to make additional
``setopt`` calls.
:arg string proxy_host: HTTP proxy hostname. To use proxies,
``proxy_host`` and ``proxy_port`` must be set; ``proxy_username`` and
``proxy_pass`` are optional. Proxies are currently only supported
with ``curl_httpclient``.
:arg int proxy_port: HTTP proxy port
:arg string proxy_username: HTTP proxy username
:arg string proxy_password: HTTP proxy password
:arg bool allow_nonstandard_methods: Allow unknown values for ``method``
argument?
:arg bool validate_cert: For HTTPS requests, validate the server's
certificate?
:arg string ca_certs: filename of CA certificates in PEM format,
or None to use defaults. Note that in ``curl_httpclient``, if
any request uses a custom ``ca_certs`` file, they all must (they
don't have to all use the same ``ca_certs``, but it's not possible
to mix requests with ``ca_certs`` and requests that use the defaults.
:arg bool allow_ipv6: Use IPv6 when available? Default is false in
``simple_httpclient`` and true in ``curl_httpclient``
:arg string client_key: Filename for client SSL key, if any
:arg string client_cert: Filename for client SSL certificate, if any
.. versionadded:: 3.1
The ``auth_mode`` argument.
"""
if headers is None:
headers = httputil.HTTPHeaders()
if if_modified_since:
headers["If-Modified-Since"] = httputil.format_timestamp(
if_modified_since)
self.proxy_host = proxy_host
self.proxy_port = proxy_port
self.proxy_username = proxy_username
self.proxy_password = proxy_password
self.url = url
self.method = method
self.headers = headers
self.body = utf8(body)
self.auth_username = auth_username
self.auth_password = auth_password
self.auth_mode = auth_mode
self.connect_timeout = connect_timeout
self.request_timeout = request_timeout
self.follow_redirects = follow_redirects
self.max_redirects = max_redirects
self.user_agent = user_agent
self.use_gzip = use_gzip
self.network_interface = network_interface
self.streaming_callback = stack_context.wrap(streaming_callback)
self.header_callback = stack_context.wrap(header_callback)
self.prepare_curl_callback = stack_context.wrap(prepare_curl_callback)
self.allow_nonstandard_methods = allow_nonstandard_methods
self.validate_cert = validate_cert
self.ca_certs = ca_certs
self.allow_ipv6 = allow_ipv6
self.client_key = client_key
self.client_cert = client_cert
self.start_time = time.time()
class HTTPResponse(object):
"""HTTP Response object.
Attributes:
* request: HTTPRequest object
* code: numeric HTTP status code, e.g. 200 or 404
* reason: human-readable reason phrase describing the status code
(with curl_httpclient, this is a default value rather than the
server's actual response)
* headers: `tornado.httputil.HTTPHeaders` object
* buffer: ``cStringIO`` object for response body
* body: response body as string (created on demand from ``self.buffer``)
* error: Exception object, if any
* request_time: seconds from request start to finish
* time_info: dictionary of diagnostic timing information from the request.
Available data are subject to change, but currently uses timings
available from http://curl.haxx.se/libcurl/c/curl_easy_getinfo.html,
plus ``queue``, which is the delay (if any) introduced by waiting for
a slot under `AsyncHTTPClient`'s ``max_clients`` setting.
"""
def __init__(self, request, code, headers=None, buffer=None,
effective_url=None, error=None, request_time=None,
time_info=None, reason=None):
if isinstance(request, _RequestProxy):
self.request = request.request
else:
self.request = request
self.code = code
self.reason = reason or httputil.responses.get(code, "Unknown")
if headers is not None:
self.headers = headers
else:
self.headers = httputil.HTTPHeaders()
self.buffer = buffer
self._body = None
if effective_url is None:
self.effective_url = request.url
else:
self.effective_url = effective_url
if error is None:
if self.code < 200 or self.code >= 300:
self.error = HTTPError(self.code, response=self)
else:
self.error = None
else:
self.error = error
self.request_time = request_time
self.time_info = time_info or {}
def _get_body(self):
if self.buffer is None:
return None
elif self._body is None:
self._body = self.buffer.getvalue()
return self._body
body = property(_get_body)
def rethrow(self):
"""If there was an error on the request, raise an `HTTPError`."""
if self.error:
raise self.error
def __repr__(self):
args = ",".join("%s=%r" % i for i in sorted(self.__dict__.items()))
return "%s(%s)" % (self.__class__.__name__, args)
class HTTPError(Exception):
"""Exception thrown for an unsuccessful HTTP request.
Attributes:
* ``code`` - HTTP error integer error code, e.g. 404. Error code 599 is
used when no HTTP response was received, e.g. for a timeout.
* ``response`` - `HTTPResponse` object, if any.
Note that if ``follow_redirects`` is False, redirects become HTTPErrors,
and you can look at ``error.response.headers['Location']`` to see the
destination of the redirect.
"""
def __init__(self, code, message=None, response=None):
self.code = code
message = message or httputil.responses.get(code, "Unknown")
self.response = response
Exception.__init__(self, "HTTP %d: %s" % (self.code, message))
class _RequestProxy(object):
"""Combines an object with a dictionary of defaults.
Used internally by AsyncHTTPClient implementations.
"""
def __init__(self, request, defaults):
self.request = request
self.defaults = defaults
def __getattr__(self, name):
request_attr = getattr(self.request, name)
if request_attr is not None:
return request_attr
elif self.defaults is not None:
return self.defaults.get(name, None)
else:
return None
def main():
from tornado.options import define, options, parse_command_line
define("print_headers", type=bool, default=False)
define("print_body", type=bool, default=True)
define("follow_redirects", type=bool, default=True)
define("validate_cert", type=bool, default=True)
args = parse_command_line()
client = HTTPClient()
for arg in args:
try:
response = client.fetch(arg,
follow_redirects=options.follow_redirects,
validate_cert=options.validate_cert,
)
except HTTPError as e:
if e.response is not None:
response = e.response
else:
raise
if options.print_headers:
print(response.headers)
if options.print_body:
print(response.body)
client.close()
if __name__ == "__main__":
main()
|