"""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 of libcurl is 7.22.0, and the minimum version of pycurl is 7.18.2. It is highly recommended that your ``libcurl`` installation is built with asynchronous DNS resolver (threaded or c-ares), otherwise you may encounter various problems with request timeouts (for more information, see http://curl.haxx.se/libcurl/c/curl_easy_setopt.html#CURLOPTCONNECTTIMEOUTMS and comments in curl_httpclient.py). To select ``curl_httpclient``, call `AsyncHTTPClient.configure` at startup:: AsyncHTTPClient.configure("tornado.curl_httpclient.CurlAsyncHTTPClient") """ from __future__ import absolute_import, division, print_function import functools import time import warnings import weakref from tornado.concurrent import Future, future_set_result_unless_cancelled from tornado.escape import utf8, native_str from tornado import gen, httputil, stack_context from tornado.ioloop import IOLoop from tornado.util import Configurable class HTTPClient(object): """A blocking HTTP client. This interface is provided to make it easier to share code between synchronous and asynchronous applications. Applications that are running an `.IOLoop` must 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: # HTTPError is raised for non-200 responses; the response # can be found in e.response. print("Error: " + str(e)) except Exception as e: # Other errors are possible, such as IOError. print("Error: " + str(e)) http_client.close() .. versionchanged:: 5.0 Due to limitations in `asyncio`, it is no longer possible to use the synchronous ``HTTPClient`` while an `.IOLoop` is running. Use `AsyncHTTPClient` instead. """ def __init__(self, async_client_class=None, **kwargs): # Initialize self._closed at the beginning of the constructor # so that an exception raised here doesn't lead to confusing # failures in __del__. self._closed = True self._io_loop = IOLoop(make_current=False) if async_client_class is None: async_client_class = AsyncHTTPClient # Create the client while our IOLoop is "current", without # clobbering the thread's real current IOLoop (if any). self._async_client = self._io_loop.run_sync( gen.coroutine(lambda: async_client_class(**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` unless the ``raise_error`` keyword argument is set to False. """ response = self._io_loop.run_sync(functools.partial( self._async_client.fetch, request, **kwargs)) return response class AsyncHTTPClient(Configurable): """An non-blocking HTTP client. Example usage:: async def f(): http_client = AsyncHTTPClient() try: response = await http_client.fetch("http://www.google.com") except Exception as e: print("Error: %s" % e) else: print(response.body) 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. Unless ``force_instance=True`` is used, no arguments should be passed to the `AsyncHTTPClient` constructor. The implementation subclass as well as arguments to its constructor can be set with the static method `configure()` All `AsyncHTTPClient` implementations support a ``defaults`` keyword argument, which can be used to set default values for `HTTPRequest` attributes. For example:: AsyncHTTPClient.configure( None, defaults=dict(user_agent="MyUserAgent")) # or with force_instance: client = AsyncHTTPClient(force_instance=True, defaults=dict(user_agent="MyUserAgent")) .. versionchanged:: 5.0 The ``io_loop`` argument (deprecated since version 4.1) has been removed. """ @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, force_instance=False, **kwargs): io_loop = IOLoop.current() if force_instance: instance_cache = None else: instance_cache = cls._async_clients() if instance_cache is not None and io_loop in instance_cache: return instance_cache[io_loop] instance = super(AsyncHTTPClient, cls).__new__(cls, **kwargs) # Make sure the instance knows which cache to remove itself from. # It can't simply call _async_clients() because we may be in # __new__(AsyncHTTPClient) but instance.__class__ may be # SimpleAsyncHTTPClient. instance._instance_cache = instance_cache if instance_cache is not None: instance_cache[instance.io_loop] = instance return instance def initialize(self, defaults=None): self.io_loop = IOLoop.current() self.defaults = dict(HTTPRequest._DEFAULTS) if defaults is not None: self.defaults.update(defaults) self._closed = False def close(self): """Destroys this HTTP client, freeing any file descriptors used. This method is **not needed in normal use** due to the way that `AsyncHTTPClient` objects are transparently reused. ``close()`` is generally only necessary when either the `.IOLoop` is also being closed, or the ``force_instance=True`` argument was used when creating the `AsyncHTTPClient`. No other methods may be called on the `AsyncHTTPClient` after ``close()``. """ if self._closed: return self._closed = True if self._instance_cache is not None: if self._instance_cache.get(self.io_loop) is not self: raise RuntimeError("inconsistent AsyncHTTPClient cache") del self._instance_cache[self.io_loop] def fetch(self, request, callback=None, raise_error=True, **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`. By default, the ``Future`` will raise an `HTTPError` if the request returned a non-200 response code (other errors may also be raised if the server could not be contacted). Instead, if ``raise_error`` is set to False, the response will always be returned regardless of the 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. .. deprecated:: 5.1 The ``callback`` argument is deprecated and will be removed in 6.0. Use the returned `.Future` instead. The ``raise_error=False`` argument currently suppresses *all* errors, encapsulating them in `HTTPResponse` objects with a 599 response code. This will change in Tornado 6.0: ``raise_error=False`` will only affect the `HTTPError` raised when a non-200 response code is used. """ if self._closed: raise RuntimeError("fetch() called on closed AsyncHTTPClient") if not isinstance(request, HTTPRequest): request = HTTPRequest(url=request, **kwargs) else: if kwargs: raise ValueError("kwargs can't be used if request is an HTTPRequest object") # 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: warnings.warn("callback arguments are deprecated, use the returned Future instead", DeprecationWarning) 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 raise_error and response.error: if isinstance(response.error, HTTPError): response.error.response = response future.set_exception(response.error) else: if response.error and not response._error_is_response_code: warnings.warn("raise_error=False will allow '%s' to be raised in the future" % response.error, DeprecationWarning) future_set_result_unless_cancelled(future, 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, decompress_response=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, proxy_auth_mode=None, allow_nonstandard_methods=None, validate_cert=None, ca_certs=None, allow_ipv6=None, client_key=None, client_cert=None, body_producer=None, expect_100_continue=False, decompress_response=None, ssl_options=None): r"""All parameters except ``url`` are optional. :arg str url: URL to fetch :arg str method: HTTP method, e.g. "GET" or "POST" :arg headers: Additional HTTP headers to pass on the request :type headers: `~tornado.httputil.HTTPHeaders` or `dict` :arg body: HTTP request body as a string (byte or unicode; if unicode the utf-8 encoding will be used) :arg body_producer: Callable used for lazy/asynchronous request bodies. It is called with one argument, a ``write`` function, and should return a `.Future`. It should call the write function with new data as it becomes available. The write function returns a `.Future` which can be used for flow control. Only one of ``body`` and ``body_producer`` may be specified. ``body_producer`` is not supported on ``curl_httpclient``. When using ``body_producer`` it is recommended to pass a ``Content-Length`` in the headers as otherwise chunked encoding will be used, and many servers do not support chunked encoding on requests. New in Tornado 4.0 :arg str auth_username: Username for HTTP authentication :arg str auth_password: Password for HTTP authentication :arg str 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, default 20 seconds :arg float request_timeout: Timeout for entire request in seconds, default 20 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? Default True. :arg int max_redirects: Limit for ``follow_redirects``, default 5. :arg str user_agent: String to send as ``User-Agent`` header :arg bool decompress_response: Request a compressed response from the server and decompress it after downloading. Default is True. New in Tornado 4.0. :arg bool use_gzip: Deprecated alias for ``decompress_response`` since Tornado 4.0. :arg str network_interface: Network interface to use for request. ``curl_httpclient`` only; see note below. :arg collections.abc.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 collections.abc.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 collections.abc.Callable prepare_curl_callback: If set, will be called with a ``pycurl.Curl`` object to allow the application to make additional ``setopt`` calls. :arg str proxy_host: HTTP proxy hostname. To use proxies, ``proxy_host`` and ``proxy_port`` must be set; ``proxy_username``, ``proxy_pass`` and ``proxy_auth_mode`` are optional. Proxies are currently only supported with ``curl_httpclient``. :arg int proxy_port: HTTP proxy port :arg str proxy_username: HTTP proxy username :arg str proxy_password: HTTP proxy password :arg str proxy_auth_mode: HTTP proxy Authentication mode; default is "basic". supports "basic" and "digest" :arg bool allow_nonstandard_methods: Allow unknown values for ``method`` argument? Default is False. :arg bool validate_cert: For HTTPS requests, validate the server's certificate? Default is True. :arg str ca_certs: filename of CA certificates in PEM format, or None to use defaults. See note below when used with ``curl_httpclient``. :arg str client_key: Filename for client SSL key, if any. See note below when used with ``curl_httpclient``. :arg str client_cert: Filename for client SSL certificate, if any. See note below when used with ``curl_httpclient``. :arg ssl.SSLContext ssl_options: `ssl.SSLContext` object for use in ``simple_httpclient`` (unsupported by ``curl_httpclient``). Overrides ``validate_cert``, ``ca_certs``, ``client_key``, and ``client_cert``. :arg bool allow_ipv6: Use IPv6 when available? Default is true. :arg bool expect_100_continue: If true, send the ``Expect: 100-continue`` header and wait for a continue response before sending the request body. Only supported with simple_httpclient. .. note:: When using ``curl_httpclient`` certain options may be inherited by subsequent fetches because ``pycurl`` does not allow them to be cleanly reset. This applies to the ``ca_certs``, ``client_key``, ``client_cert``, and ``network_interface`` arguments. If you use these options, you should pass them on every request (you don't have to always use the same values, but it's not possible to mix requests that specify these options with ones that use the defaults). .. versionadded:: 3.1 The ``auth_mode`` argument. .. versionadded:: 4.0 The ``body_producer`` and ``expect_100_continue`` arguments. .. versionadded:: 4.2 The ``ssl_options`` argument. .. versionadded:: 4.5 The ``proxy_auth_mode`` argument. """ # Note that some of these attributes go through property setters # defined below. self.headers = headers if if_modified_since: self.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.proxy_auth_mode = proxy_auth_mode self.url = url self.method = method self.body = body self.body_producer = body_producer 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 if decompress_response is not None: self.decompress_response = decompress_response else: self.decompress_response = use_gzip self.network_interface = network_interface self.streaming_callback = streaming_callback self.header_callback = header_callback self.prepare_curl_callback = 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.ssl_options = ssl_options self.expect_100_continue = expect_100_continue self.start_time = time.time() @property def headers(self): return self._headers @headers.setter def headers(self, value): if value is None: self._headers = httputil.HTTPHeaders() else: self._headers = value @property def body(self): return self._body @body.setter def body(self, value): self._body = utf8(value) @property def body_producer(self): return self._body_producer @body_producer.setter def body_producer(self, value): self._body_producer = stack_context.wrap(value) @property def streaming_callback(self): return self._streaming_callback @streaming_callback.setter def streaming_callback(self, value): self._streaming_callback = stack_context.wrap(value) @property def header_callback(self): return self._header_callback @header_callback.setter def header_callback(self, value): self._header_callback = stack_context.wrap(value) @property def prepare_curl_callback(self): return self._prepare_curl_callback @prepare_curl_callback.setter def prepare_curl_callback(self, value): self._prepare_curl_callback = stack_context.wrap(value) 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 * headers: `tornado.httputil.HTTPHeaders` object * effective_url: final location of the resource after following any redirects * buffer: ``cStringIO`` object for response body * body: response body as bytes (created on demand from ``self.buffer``) * error: Exception object, if any * request_time: seconds from request start to finish. Includes all network operations from DNS resolution to receiving the last byte of data. Does not include time spent in the queue (due to the ``max_clients`` option). If redirects were followed, only includes the final request. * start_time: Time at which the HTTP operation started, based on `time.time` (not the monotonic clock used by `.IOLoop.time`). May be ``None`` if the request timed out while in the queue. * 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. .. versionadded:: 5.1 Added the ``start_time`` attribute. .. versionchanged:: 5.1 The ``request_time`` attribute previously included time spent in the queue for ``simple_httpclient``, but not in ``curl_httpclient``. Now queueing time is excluded in both implementations. ``request_time`` is now more accurate for ``curl_httpclient`` because it uses a monotonic clock when available. """ def __init__(self, request, code, headers=None, buffer=None, effective_url=None, error=None, request_time=None, time_info=None, reason=None, start_time=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 self._error_is_response_code = False if error is None: if self.code < 200 or self.code >= 300: self._error_is_response_code = True self.error = HTTPError(self.code, message=self.reason, response=self) else: self.error = None else: self.error = error self.start_time = start_time self.request_time = request_time self.time_info = time_info or {} @property def body(self): if self.buffer is None: return None elif self._body is None: self._body = self.buffer.getvalue() return self._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 HTTPClientError(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. .. versionchanged:: 5.1 Renamed from ``HTTPError`` to ``HTTPClientError`` to avoid collisions with `tornado.web.HTTPError`. The name ``tornado.httpclient.HTTPError`` remains as an alias. """ def __init__(self, code, message=None, response=None): self.code = code self.message = message or httputil.responses.get(code, "Unknown") self.response = response super(HTTPClientError, self).__init__(code, message, response) def __str__(self): return "HTTP %d: %s" % (self.code, self.message) # There is a cyclic reference between self and self.response, # which breaks the default __repr__ implementation. # (especially on pypy, which doesn't have the same recursion # detection as cpython). __repr__ = __str__ HTTPError = HTTPClientError 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) define("proxy_host", type=str) define("proxy_port", type=int) 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, proxy_host=options.proxy_host, proxy_port=options.proxy_port, ) 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(native_str(response.body)) client.close() if __name__ == "__main__": main()