diff options
Diffstat (limited to 'requests')
29 files changed, 4817 insertions, 0 deletions
diff --git a/requests/__init__.py b/requests/__init__.py new file mode 100644 index 0000000..e3300cf --- /dev/null +++ b/requests/__init__.py @@ -0,0 +1,34 @@ +# -*- coding: utf-8 -*- + +# __ +# /__) _ _ _ _ _/ _ +# / ( (- (/ (/ (- _) / _) +# / + +""" +requests +~~~~~~~~ + +:copyright: (c) 2012 by Kenneth Reitz. +:license: ISC, see LICENSE for more details. + +""" + +__title__ = 'requests' +__version__ = '0.10.0' +__build__ = 0x001000 +__author__ = 'Kenneth Reitz' +__license__ = 'ISC' +__copyright__ = 'Copyright 2012 Kenneth Reitz' + + + +from . import utils +from .models import Request, Response +from .api import request, get, head, post, patch, put, delete, options +from .sessions import session, Session +from .status_codes import codes +from .exceptions import ( + RequestException, Timeout, URLRequired, + TooManyRedirects, HTTPError, ConnectionError +) diff --git a/requests/api.py b/requests/api.py new file mode 100644 index 0000000..b7d4158 --- /dev/null +++ b/requests/api.py @@ -0,0 +1,116 @@ +# -*- coding: utf-8 -*- + +""" +requests.api +~~~~~~~~~~~~ + +This module implements the Requests API. + +:copyright: (c) 2012 by Kenneth Reitz. +:license: ISC, see LICENSE for more details. + +""" + +from . import sessions + +def request(method, url, **kwargs): + """Constructs and sends a :class:`Request <Request>`. + Returns :class:`Response <Response>` object. + + :param method: method for the new :class:`Request` object. + :param url: URL for the new :class:`Request` object. + :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`. + :param data: (optional) Dictionary or bytes to send in the body of the :class:`Request`. + :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`. + :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. + :param files: (optional) Dictionary of 'name': file-like-objects (or {'name': ('filename', fileobj)}) for multipart encoding upload. + :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. + :param timeout: (optional) Float describing the timeout of the request. + :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed. + :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy. + :param return_response: (optional) If False, an un-sent Request object will returned. + :param session: (optional) A :class:`Session` object to be used for the request. + :param config: (optional) A configuration dictionary. + :param verify: (optional) if ``True``, the SSL cert will be verified. A CA_BUNDLE path can also be provided. + :param prefetch: (optional) if ``True``, the response content will be immediately downloaded. + """ + + s = kwargs.pop('session') if 'session' in kwargs else sessions.session() + return s.request(method=method, url=url, **kwargs) + + + +def get(url, **kwargs): + """Sends a GET request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + kwargs.setdefault('allow_redirects', True) + return request('get', url, **kwargs) + + +def options(url, **kwargs): + """Sends a OPTIONS request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + kwargs.setdefault('allow_redirects', True) + return request('options', url, **kwargs) + + +def head(url, **kwargs): + """Sends a HEAD request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + kwargs.setdefault('allow_redirects', True) + return request('head', url, **kwargs) + + +def post(url, data=None, **kwargs): + """Sends a POST request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param data: (optional) Dictionary or bytes to send in the body of the :class:`Request`. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + return request('post', url, data=data, **kwargs) + + +def put(url, data=None, **kwargs): + """Sends a PUT request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param data: (optional) Dictionary or bytes to send in the body of the :class:`Request`. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + return request('put', url, data=data, **kwargs) + + +def patch(url, data=None, **kwargs): + """Sends a PATCH request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param data: (optional) Dictionary or bytes to send in the body of the :class:`Request`. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + return request('patch', url, data=data, **kwargs) + + +def delete(url, **kwargs): + """Sends a DELETE request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + return request('delete', url, **kwargs) diff --git a/requests/async.py b/requests/async.py new file mode 100644 index 0000000..9488447 --- /dev/null +++ b/requests/async.py @@ -0,0 +1,88 @@ +# -*- coding: utf-8 -*- + +""" +requests.async +~~~~~~~~~~~~~~ + +This module contains an asynchronous replica of ``requests.api``, powered +by gevent. All API methods return a ``Request`` instance (as opposed to +``Response``). A list of requests can be sent with ``map()``. +""" + +try: + import gevent + from gevent import monkey as curious_george + from gevent.pool import Pool +except ImportError: + raise RuntimeError('Gevent is required for requests.async.') + +# Monkey-patch. +curious_george.patch_all(thread=False) + +from . import api + + +__all__ = ( + 'map', + 'get', 'options', 'head', 'post', 'put', 'patch', 'delete', 'request' +) + + +def patched(f): + """Patches a given API function to not send.""" + + def wrapped(*args, **kwargs): + + kwargs['return_response'] = False + kwargs['prefetch'] = True + + config = kwargs.get('config', {}) + config.update(safe_mode=True) + + kwargs['config'] = config + + return f(*args, **kwargs) + + return wrapped + + +def send(r, pool=None): + """Sends the request object using the specified pool. If a pool isn't + specified this method blocks. Pools are useful because you can specify size + and can hence limit concurrency.""" + + if pool != None: + return pool.spawn(r.send) + + return gevent.spawn(r.send) + + +# Patched requests.api functions. +get = patched(api.get) +options = patched(api.options) +head = patched(api.head) +post = patched(api.post) +put = patched(api.put) +patch = patched(api.patch) +delete = patched(api.delete) +request = patched(api.request) + + +def map(requests, prefetch=True, size=None): + """Concurrently converts a list of Requests to Responses. + + :param requests: a collection of Request objects. + :param prefetch: If False, the content will not be downloaded immediately. + :param size: Specifies the number of requests to make at a time. If None, no throttling occurs. + """ + + requests = list(requests) + + pool = Pool(size) if size else None + jobs = [send(r, pool) for r in requests] + gevent.joinall(jobs) + + if prefetch: + [r.response.content for r in requests] + + return [r.response for r in requests]
\ No newline at end of file diff --git a/requests/auth.py b/requests/auth.py new file mode 100644 index 0000000..d1da4ee --- /dev/null +++ b/requests/auth.py @@ -0,0 +1,138 @@ +# -*- coding: utf-8 -*- + +""" +requests.auth +~~~~~~~~~~~~~ + +This module contains the authentication handlers for Requests. +""" + +import time +import hashlib + +from base64 import b64encode +from urlparse import urlparse + +from .utils import randombytes, parse_dict_header + + + +def _basic_auth_str(username, password): + """Returns a Basic Auth string.""" + return 'Basic %s' % b64encode('%s:%s' % (username, password)) + + +class AuthBase(object): + """Base class that all auth implementations derive from""" + + def __call__(self, r): + raise NotImplementedError('Auth hooks must be callable.') + + +class HTTPBasicAuth(AuthBase): + """Attaches HTTP Basic Authentication to the given Request object.""" + def __init__(self, username, password): + self.username = str(username) + self.password = str(password) + + def __call__(self, r): + r.headers['Authorization'] = _basic_auth_str(self.username, self.password) + return r + + +class HTTPProxyAuth(HTTPBasicAuth): + """Attaches HTTP Proxy Authenetication to a given Request object.""" + def __call__(self, r): + r.headers['Proxy-Authorization'] = _basic_auth_str(self.username, self.password) + return r + + +class HTTPDigestAuth(AuthBase): + """Attaches HTTP Digest Authentication to the given Request object.""" + def __init__(self, username, password): + self.username = username + self.password = password + + def handle_401(self, r): + """Takes the given response and tries digest-auth, if needed.""" + + s_auth = r.headers.get('www-authenticate', '') + + if 'digest' in s_auth.lower(): + + last_nonce = '' + nonce_count = 0 + + chal = parse_dict_header(s_auth.replace('Digest ', '')) + + realm = chal['realm'] + nonce = chal['nonce'] + qop = chal.get('qop') + algorithm = chal.get('algorithm', 'MD5') + opaque = chal.get('opaque', None) + + algorithm = algorithm.upper() + # lambdas assume digest modules are imported at the top level + if algorithm == 'MD5': + H = lambda x: hashlib.md5(x).hexdigest() + elif algorithm == 'SHA': + H = lambda x: hashlib.sha1(x).hexdigest() + # XXX MD5-sess + KD = lambda s, d: H("%s:%s" % (s, d)) + + if H is None: + return None + + # XXX not implemented yet + entdig = None + p_parsed = urlparse(r.request.url) + path = p_parsed.path + if p_parsed.query: + path += '?' + p_parsed.query + + A1 = '%s:%s:%s' % (self.username, realm, self.password) + A2 = '%s:%s' % (r.request.method, path) + + if qop == 'auth': + if nonce == last_nonce: + nonce_count += 1 + else: + nonce_count = 1 + last_nonce = nonce + + ncvalue = '%08x' % nonce_count + cnonce = (hashlib.sha1("%s:%s:%s:%s" % ( + nonce_count, nonce, time.ctime(), randombytes(8))) + .hexdigest()[:16] + ) + noncebit = "%s:%s:%s:%s:%s" % (nonce, ncvalue, cnonce, qop, H(A2)) + respdig = KD(H(A1), noncebit) + elif qop is None: + respdig = KD(H(A1), "%s:%s" % (nonce, H(A2))) + else: + # XXX handle auth-int. + return None + + # XXX should the partial digests be encoded too? + base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \ + 'response="%s"' % (self.username, realm, nonce, path, respdig) + if opaque: + base += ', opaque="%s"' % opaque + if entdig: + base += ', digest="%s"' % entdig + base += ', algorithm="%s"' % algorithm + if qop: + base += ', qop=auth, nc=%s, cnonce="%s"' % (ncvalue, cnonce) + + r.request.headers['Authorization'] = 'Digest %s' % (base) + r.request.send(anyway=True) + _r = r.request.response + _r.history.append(r) + + return _r + + return r + + def __call__(self, r): + r.register_hook('response', self.handle_401) + return r diff --git a/requests/defaults.py b/requests/defaults.py new file mode 100644 index 0000000..424d373 --- /dev/null +++ b/requests/defaults.py @@ -0,0 +1,40 @@ +# -*- coding: utf-8 -*- + +""" +requests.defaults +~~~~~~~~~~~~~~~~~ + +This module provides the Requests configuration defaults. + +Configurations: + +:base_headers: Default HTTP headers. +:verbose: Stream to write request logging to. +:max_redirects: Maximum number of redirects allowed within a request.s +:keep_alive: Reuse HTTP Connections? +:max_retries: The number of times a request should be retried in the event of a connection failure. +:danger_mode: If true, Requests will raise errors immediately. +:safe_mode: If true, Requests will catch all errors. +:pool_maxsize: The maximium size of an HTTP connection pool. +:pool_connections: The number of active HTTP connection pools to use. +""" + +from . import __version__ + +defaults = dict() + + +defaults['base_headers'] = { + 'User-Agent': 'python-requests/%s' % __version__, + 'Accept-Encoding': ', '.join(('identity', 'deflate', 'compress', 'gzip')), + 'Accept': '*/*' +} + +defaults['verbose'] = None +defaults['max_redirects'] = 30 +defaults['pool_connections'] = 10 +defaults['pool_maxsize'] = 10 +defaults['max_retries'] = 0 +defaults['danger_mode'] = False +defaults['safe_mode'] = False +defaults['keep_alive'] = True diff --git a/requests/exceptions.py b/requests/exceptions.py new file mode 100644 index 0000000..c7b98e6 --- /dev/null +++ b/requests/exceptions.py @@ -0,0 +1,31 @@ +# -*- coding: utf-8 -*- + +""" +requests.exceptions +~~~~~~~~~~~~~~~~~~~ + +This module contains the set of Requests' exceptions. + +""" + +class RequestException(Exception): + """There was an ambiguous exception that occurred while handling your + request.""" + +class HTTPError(RequestException): + """An HTTP error occurred.""" + +class ConnectionError(RequestException): + """A Connection error occurred.""" + +class SSLError(ConnectionError): + """An SSL error occurred.""" + +class Timeout(RequestException): + """The request timed out.""" + +class URLRequired(RequestException): + """A valid URL is required to make a request.""" + +class TooManyRedirects(RequestException): + """Too many redirects.""" diff --git a/requests/hooks.py b/requests/hooks.py new file mode 100644 index 0000000..3560b89 --- /dev/null +++ b/requests/hooks.py @@ -0,0 +1,48 @@ +# -*- coding: utf-8 -*- + +""" +requests.hooks +~~~~~~~~~~~~~~ + +This module provides the capabilities for the Requests hooks system. + +Available hooks: + +``args``: + A dictionary of the arguments being sent to Request(). + +``pre_request``: + The Request object, directly before being sent. + +``post_request``: + The Request object, directly after being sent. + +``response``: + The response generated from a Request. + +""" + +import traceback + + +HOOKS = ('args', 'pre_request', 'post_request', 'response') + + +def dispatch_hook(key, hooks, hook_data): + """Dispatches a hook dictionary on a given piece of data.""" + + hooks = hooks or dict() + + if key in hooks: + hooks = hooks.get(key) + + if hasattr(hooks, '__call__'): + hooks = [hooks] + + for hook in hooks: + try: + hook_data = hook(hook_data) or hook_data + except Exception: + traceback.print_exc() + + return hook_data diff --git a/requests/models.py b/requests/models.py new file mode 100644 index 0000000..84a2ec6 --- /dev/null +++ b/requests/models.py @@ -0,0 +1,784 @@ +# -*- coding: utf-8 -*- + +""" +requests.models +~~~~~~~~~~~~~~~ + +This module contains the primary objects that power Requests. +""" + +import os +import urllib + +from urlparse import urlparse, urlunparse, urljoin, urlsplit +from datetime import datetime + +from .hooks import dispatch_hook, HOOKS +from .structures import CaseInsensitiveDict +from .status_codes import codes +from .packages import oreos +from .auth import HTTPBasicAuth, HTTPProxyAuth +from .packages.urllib3.response import HTTPResponse +from .packages.urllib3.exceptions import MaxRetryError +from .packages.urllib3.exceptions import SSLError as _SSLError +from .packages.urllib3.exceptions import HTTPError as _HTTPError +from .packages.urllib3 import connectionpool, poolmanager +from .packages.urllib3.filepost import encode_multipart_formdata +from .exceptions import ( + ConnectionError, HTTPError, RequestException, Timeout, TooManyRedirects, + URLRequired, SSLError) +from .utils import ( + get_encoding_from_headers, stream_decode_response_unicode, + stream_decompress, guess_filename, requote_path) + +# Import chardet if it is available. +try: + import chardet +except ImportError: + pass + +REDIRECT_STATI = (codes.moved, codes.found, codes.other, codes.temporary_moved) + + + +class Request(object): + """The :class:`Request <Request>` object. It carries out all functionality of + Requests. Recommended interface is with the Requests functions. + """ + + def __init__(self, + url=None, + headers=dict(), + files=None, + method=None, + data=dict(), + params=dict(), + auth=None, + cookies=None, + timeout=None, + redirect=False, + allow_redirects=False, + proxies=None, + hooks=None, + config=None, + _poolmanager=None, + verify=None, + session=None): + + #: Float describes the timeout of the request. + # (Use socket.setdefaulttimeout() as fallback) + self.timeout = timeout + + #: Request URL. + self.url = url + + #: Dictionary of HTTP Headers to attach to the :class:`Request <Request>`. + self.headers = dict(headers or []) + + #: Dictionary of files to multipart upload (``{filename: content}``). + self.files = files + + #: HTTP Method to use. + self.method = method + + #: Dictionary or byte of request body data to attach to the + #: :class:`Request <Request>`. + self.data = None + + #: Dictionary or byte of querystring data to attach to the + #: :class:`Request <Request>`. + self.params = None + + #: True if :class:`Request <Request>` is part of a redirect chain (disables history + #: and HTTPError storage). + self.redirect = redirect + + #: Set to True if full redirects are allowed (e.g. re-POST-ing of data at new ``Location``) + self.allow_redirects = allow_redirects + + # Dictionary mapping protocol to the URL of the proxy (e.g. {'http': 'foo.bar:3128'}) + self.proxies = dict(proxies or []) + + self.data, self._enc_data = self._encode_params(data) + self.params, self._enc_params = self._encode_params(params) + + #: :class:`Response <Response>` instance, containing + #: content and metadata of HTTP Response, once :attr:`sent <send>`. + self.response = Response() + + #: Authentication tuple or object to attach to :class:`Request <Request>`. + self.auth = auth + + #: CookieJar to attach to :class:`Request <Request>`. + self.cookies = dict(cookies or []) + + #: Dictionary of configurations for this request. + self.config = dict(config or []) + + #: True if Request has been sent. + self.sent = False + + #: Event-handling hooks. + self.hooks = {} + + for event in HOOKS: + self.hooks[event] = [] + + hooks = hooks or {} + + for (k, v) in hooks.items(): + self.register_hook(event=k, hook=v) + + #: Session. + self.session = session + + #: SSL Verification. + self.verify = verify + + if headers: + headers = CaseInsensitiveDict(self.headers) + else: + headers = CaseInsensitiveDict() + + # Add configured base headers. + for (k, v) in self.config.get('base_headers', {}).items(): + if k not in headers: + headers[k] = v + + self.headers = headers + self._poolmanager = _poolmanager + + # Pre-request hook. + r = dispatch_hook('pre_request', hooks, self) + self.__dict__.update(r.__dict__) + + + def __repr__(self): + return '<Request [%s]>' % (self.method) + + + def _build_response(self, resp): + """Build internal :class:`Response <Response>` object + from given response. + """ + + def build(resp): + + response = Response() + + # Pass settings over. + response.config = self.config + + if resp: + + # Fallback to None if there's no status_code, for whatever reason. + response.status_code = getattr(resp, 'status', None) + + # Make headers case-insensitive. + response.headers = CaseInsensitiveDict(getattr(resp, 'headers', None)) + + # Set encoding. + response.encoding = get_encoding_from_headers(response.headers) + + # Start off with our local cookies. + cookies = self.cookies or dict() + + # Add new cookies from the server. + if 'set-cookie' in response.headers: + cookie_header = response.headers['set-cookie'] + cookies = oreos.dict_from_string(cookie_header) + + # Save cookies in Response. + response.cookies = cookies + + # No exceptions were harmed in the making of this request. + response.error = getattr(resp, 'error', None) + + # Save original response for later. + response.raw = resp + response.url = self.full_url.decode('utf-8') + + return response + + history = [] + + r = build(resp) + cookies = self.cookies + self.cookies.update(r.cookies) + + if r.status_code in REDIRECT_STATI and not self.redirect: + + while ( + ('location' in r.headers) and + ((r.status_code is codes.see_other) or (self.allow_redirects)) + ): + + if not len(history) < self.config.get('max_redirects'): + raise TooManyRedirects() + + history.append(r) + + url = r.headers['location'] + + # Handle redirection without scheme (see: RFC 1808 Section 4) + if url.startswith('//'): + parsed_rurl = urlparse(r.url) + url = '%s:%s' % (parsed_rurl.scheme, url) + + # Facilitate non-RFC2616-compliant 'location' headers + # (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource') + if not urlparse(url).netloc: + url = urljoin(r.url, url) + + # http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.4 + if r.status_code is codes.see_other: + method = 'GET' + else: + method = self.method + + # Remove the cookie headers that were sent. + headers = self.headers + try: + del headers['Cookie'] + except KeyError: + pass + + request = Request( + url=url, + headers=headers, + files=self.files, + method=method, + params=self.session.params, + auth=self.auth, + cookies=cookies, + redirect=True, + config=self.config, + timeout=self.timeout, + _poolmanager=self._poolmanager, + proxies = self.proxies, + verify = self.verify, + session = self.session + ) + + request.send() + cookies.update(request.response.cookies) + r = request.response + self.cookies.update(r.cookies) + + r.history = history + + self.response = r + self.response.request = self + self.response.cookies.update(self.cookies) + + + @staticmethod + def _encode_params(data): + """Encode parameters in a piece of data. + + If the data supplied is a dictionary, encodes each parameter in it, and + returns a list of tuples containing the encoded parameters, and a urlencoded + version of that. + + Otherwise, assumes the data is already encoded appropriately, and + returns it twice. + """ + + if hasattr(data, '__iter__'): + data = dict(data) + + if hasattr(data, 'items'): + result = [] + for k, vs in data.items(): + for v in isinstance(vs, list) and vs or [vs]: + result.append((k.encode('utf-8') if isinstance(k, unicode) else k, + v.encode('utf-8') if isinstance(v, unicode) else v)) + return result, urllib.urlencode(result, doseq=True) + else: + return data, data + + @property + def full_url(self): + """Build the actual URL to use.""" + + if not self.url: + raise URLRequired() + + # Support for unicode domain names and paths. + scheme, netloc, path, params, query, fragment = urlparse(self.url) + + if not scheme: + raise ValueError("Invalid URL %r: No schema supplied" %self.url) + + netloc = netloc.encode('idna') + + if isinstance(path, unicode): + path = path.encode('utf-8') + + path = requote_path(path) + + url = str(urlunparse([ scheme, netloc, path, params, query, fragment ])) + + if self._enc_params: + if urlparse(url).query: + return '%s&%s' % (url, self._enc_params) + else: + return '%s?%s' % (url, self._enc_params) + else: + return url + + @property + def path_url(self): + """Build the path URL to use.""" + + url = [] + + p = urlsplit(self.full_url) + + # Proxies use full URLs. + if p.scheme in self.proxies: + return self.full_url + + path = p.path + if not path: + path = '/' + url.append(path) + + query = p.query + if query: + url.append('?') + url.append(query) + + return ''.join(url) + + + def register_hook(self, event, hook): + """Properly register a hook.""" + + return self.hooks[event].append(hook) + + + def send(self, anyway=False, prefetch=False): + """Sends the request. Returns True of successful, false if not. + If there was an HTTPError during transmission, + self.response.status_code will contain the HTTPError code. + + Once a request is successfully sent, `sent` will equal True. + + :param anyway: If True, request will be sent, even if it has + already been sent. + """ + + # Build the URL + url = self.full_url + + # Logging + if self.config.get('verbose'): + self.config.get('verbose').write('%s %s %s\n' % ( + datetime.now().isoformat(), self.method, url + )) + + # Nottin' on you. + body = None + content_type = None + + # Multi-part file uploads. + if self.files: + if not isinstance(self.data, basestring): + + try: + fields = self.data.copy() + except AttributeError: + fields = dict(self.data) + + for (k, v) in self.files.items(): + # support for explicit filename + if isinstance(v, (tuple, list)): + fn, fp = v + else: + fn = guess_filename(v) or k + fp = v + fields.update({k: (fn, fp.read())}) + + (body, content_type) = encode_multipart_formdata(fields) + else: + pass + # TODO: Conflict? + else: + if self.data: + + body = self._enc_data + if isinstance(self.data, basestring): + content_type = None + else: + content_type = 'application/x-www-form-urlencoded' + + # Add content-type if it wasn't explicitly provided. + if (content_type) and (not 'content-type' in self.headers): + self.headers['Content-Type'] = content_type + + if self.auth: + if isinstance(self.auth, tuple) and len(self.auth) == 2: + # special-case basic HTTP auth + self.auth = HTTPBasicAuth(*self.auth) + + # Allow auth to make its changes. + r = self.auth(self) + + # Update self to reflect the auth changes. + self.__dict__.update(r.__dict__) + + _p = urlparse(url) + proxy = self.proxies.get(_p.scheme) + + if proxy: + conn = poolmanager.proxy_from_url(proxy) + _proxy = urlparse(proxy) + if '@' in _proxy.netloc: + auth, url = _proxy.netloc.split('@', 1) + self.proxy_auth = HTTPProxyAuth(*auth.split(':', 1)) + r = self.proxy_auth(self) + self.__dict__.update(r.__dict__) + else: + # Check to see if keep_alive is allowed. + if self.config.get('keep_alive'): + conn = self._poolmanager.connection_from_url(url) + else: + conn = connectionpool.connection_from_url(url) + + if url.startswith('https') and self.verify: + + cert_loc = None + + # Allow self-specified cert location. + if self.verify is not True: + cert_loc = self.verify + + + # Look for configuration. + if not cert_loc: + cert_loc = os.environ.get('REQUESTS_CA_BUNDLE') + + # Curl compatiblity. + if not cert_loc: + cert_loc = os.environ.get('CURL_CA_BUNDLE') + + # Use the awesome certifi list. + if not cert_loc: + cert_loc = __import__('certifi').where() + + conn.cert_reqs = 'CERT_REQUIRED' + conn.ca_certs = cert_loc + else: + conn.cert_reqs = 'CERT_NONE' + conn.ca_certs = None + + if not self.sent or anyway: + + if self.cookies: + + # Skip if 'cookie' header is explicitly set. + if 'cookie' not in self.headers: + + # Simple cookie with our dict. + c = oreos.monkeys.SimpleCookie() + for (k, v) in self.cookies.items(): + c[k] = v + + # Turn it into a header. + cookie_header = c.output(header='', sep='; ').strip() + + # Attach Cookie header to request. + self.headers['Cookie'] = cookie_header + + try: + # The inner try .. except re-raises certain exceptions as + # internal exception types; the outer suppresses exceptions + # when safe mode is set. + try: + # Send the request. + r = conn.urlopen( + method=self.method, + url=self.path_url, + body=body, + headers=self.headers, + redirect=False, + assert_same_host=False, + preload_content=False, + decode_content=True, + retries=self.config.get('max_retries', 0), + timeout=self.timeout, + ) + self.sent = True + + except MaxRetryError, e: + raise ConnectionError(e) + + except (_SSLError, _HTTPError), e: + if self.verify and isinstance(e, _SSLError): + raise SSLError(e) + + raise Timeout('Request timed out.') + + except RequestException, e: + if self.config.get('safe_mode', False): + # In safe mode, catch the exception and attach it to + # a blank urllib3.HTTPResponse object. + r = HTTPResponse() + r.error = e + else: + raise + + self._build_response(r) + + # Response manipulation hook. + self.response = dispatch_hook('response', self.hooks, self.response) + + # Post-request hook. + r = dispatch_hook('post_request', self.hooks, self) + self.__dict__.update(r.__dict__) + + # If prefetch is True, mark content as consumed. + if prefetch: + # Save the response. + self.response.content + + if self.config.get('danger_mode'): + self.response.raise_for_status() + + return self.sent + + +class Response(object): + """The core :class:`Response <Response>` object. All + :class:`Request <Request>` objects contain a + :class:`response <Response>` attribute, which is an instance + of this class. + """ + + def __init__(self): + + self._content = None + self._content_consumed = False + + #: Integer Code of responded HTTP Status. + self.status_code = None + + #: Case-insensitive Dictionary of Response Headers. + #: For example, ``headers['content-encoding']`` will return the + #: value of a ``'Content-Encoding'`` response header. + self.headers = CaseInsensitiveDict() + + #: File-like object representation of response (for advanced usage). + self.raw = None + + #: Final URL location of Response. + self.url = None + + #: Resulting :class:`HTTPError` of request, if one occurred. + self.error = None + + #: Encoding to decode with when accessing r.content. + self.encoding = None + + #: A list of :class:`Response <Response>` objects from + #: the history of the Request. Any redirect responses will end + #: up here. + self.history = [] + + #: The :class:`Request <Request>` that created the Response. + self.request = None + + #: A dictionary of Cookies the server sent back. + self.cookies = {} + + #: Dictionary of configurations for this request. + self.config = {} + + + def __repr__(self): + return '<Response [%s]>' % (self.status_code) + + def __nonzero__(self): + """Returns true if :attr:`status_code` is 'OK'.""" + return self.ok + + @property + def ok(self): + try: + self.raise_for_status() + except HTTPError: + return False + return True + + + def iter_content(self, chunk_size=10 * 1024, decode_unicode=False): + """Iterates over the response data. This avoids reading the content + at once into memory for large responses. The chunk size is the number + of bytes it should read into memory. This is not necessarily the + length of each item returned as decoding can take place. + """ + if self._content_consumed: + raise RuntimeError( + 'The content for this response was already consumed' + ) + + def generate(): + while 1: + chunk = self.raw.read(chunk_size) + if not chunk: + break + yield chunk + self._content_consumed = True + + def generate_chunked(): + resp = self.raw._original_response + fp = resp.fp + if resp.chunk_left is not None: + pending_bytes = resp.chunk_left + while pending_bytes: + chunk = fp.read(min(chunk_size, pending_bytes)) + pending_bytes-=len(chunk) + yield chunk + fp.read(2) # throw away crlf + while 1: + #XXX correct line size? (httplib has 64kb, seems insane) + pending_bytes = fp.readline(40).strip() + pending_bytes = int(pending_bytes, 16) + if pending_bytes == 0: + break + while pending_bytes: + chunk = fp.read(min(chunk_size, pending_bytes)) + pending_bytes-=len(chunk) + yield chunk + fp.read(2) # throw away crlf + self._content_consumed = True + fp.close() + + + if getattr(getattr(self.raw, '_original_response', None), 'chunked', False): + gen = generate_chunked() + else: + gen = generate() + + if 'gzip' in self.headers.get('content-encoding', ''): + gen = stream_decompress(gen, mode='gzip') + elif 'deflate' in self.headers.get('content-encoding', ''): + gen = stream_decompress(gen, mode='deflate') + + if decode_unicode: + gen = stream_decode_response_unicode(gen, self) + + return gen + + + def iter_lines(self, chunk_size=10 * 1024, decode_unicode=None): + """Iterates over the response data, one line at a time. This + avoids reading the content at once into memory for large + responses. + """ + + #TODO: why rstrip by default + pending = None + + for chunk in self.iter_content(chunk_size, decode_unicode=decode_unicode): + + if pending is not None: + chunk = pending + chunk + lines = chunk.splitlines(True) + + for line in lines[:-1]: + yield line.rstrip() + + # Save the last part of the chunk for next iteration, to keep full line together + # lines may be empty for the last chunk of a chunked response + + if lines: + pending = lines[-1] + #if pending is a complete line, give it baack + if pending[-1] == '\n': + yield pending.rstrip() + pending = None + else: + pending = None + + # Yield the last line + if pending is not None: + yield pending.rstrip() + + + @property + def content(self): + """Content of the response, in bytes.""" + + if self._content is None: + # Read the contents. + try: + if self._content_consumed: + raise RuntimeError( + 'The content for this response was already consumed') + + self._content = self.raw.read() + except AttributeError: + self._content = None + + self._content_consumed = True + return self._content + + + @property + def text(self): + """Content of the response, in unicode. + + if Response.encoding is None and chardet module is available, encoding + will be guessed. + """ + + # Try charset from content-type + content = None + encoding = self.encoding + + # Fallback to auto-detected encoding if chardet is available. + if self.encoding is None: + try: + detected = chardet.detect(self.content) or {} + encoding = detected.get('encoding') + + # Trust that chardet isn't available or something went terribly wrong. + except Exception: + pass + + # Decode unicode from given encoding. + try: + content = unicode(self.content, encoding) + except UnicodeError, TypeError: + pass + + # Try to fall back: + if not content: + try: + content = unicode(content, encoding, errors='replace') + except UnicodeError, TypeError: + pass + + + + return content + + + def raise_for_status(self): + """Raises stored :class:`HTTPError` or :class:`URLError`, if one occurred.""" + + if self.error: + raise self.error + + if (self.status_code >= 300) and (self.status_code < 400): + raise HTTPError('%s Redirection' % self.status_code) + + elif (self.status_code >= 400) and (self.status_code < 500): + raise HTTPError('%s Client Error' % self.status_code) + + elif (self.status_code >= 500) and (self.status_code < 600): + raise HTTPError('%s Server Error' % self.status_code) + + diff --git a/requests/packages/__init__.py b/requests/packages/__init__.py new file mode 100644 index 0000000..d62c4b7 --- /dev/null +++ b/requests/packages/__init__.py @@ -0,0 +1,3 @@ +from __future__ import absolute_import + +from . import urllib3 diff --git a/requests/packages/oreos/__init__.py b/requests/packages/oreos/__init__.py new file mode 100644 index 0000000..d01340f --- /dev/null +++ b/requests/packages/oreos/__init__.py @@ -0,0 +1,3 @@ +# -*- coding: utf-8 -*- + +from .core import dict_from_string
\ No newline at end of file diff --git a/requests/packages/oreos/core.py b/requests/packages/oreos/core.py new file mode 100644 index 0000000..359d744 --- /dev/null +++ b/requests/packages/oreos/core.py @@ -0,0 +1,24 @@ +# -*- coding: utf-8 -*- + +""" +oreos.core +~~~~~~~~~~ + +The creamy white center. +""" + +from .monkeys import SimpleCookie + + +def dict_from_string(s): + """Returns a MultiDict with Cookies.""" + + cookies = dict() + + c = SimpleCookie() + c.load(s) + + for k,v in c.items(): + cookies.update({k: v.value}) + + return cookies
\ No newline at end of file diff --git a/requests/packages/oreos/monkeys.py b/requests/packages/oreos/monkeys.py new file mode 100644 index 0000000..6be3074 --- /dev/null +++ b/requests/packages/oreos/monkeys.py @@ -0,0 +1,770 @@ +# -*- coding: utf-8 -*- + +""" +oreos.monkeys +~~~~~~~~~~~~~ + +Monkeypatches. +""" +#!/usr/bin/env python +# + +#### +# Copyright 2000 by Timothy O'Malley <timo@alum.mit.edu> +# +# All Rights Reserved +# +# Permission to use, copy, modify, and distribute this software +# and its documentation for any purpose and without fee is hereby +# granted, provided that the above copyright notice appear in all +# copies and that both that copyright notice and this permission +# notice appear in supporting documentation, and that the name of +# Timothy O'Malley not be used in advertising or publicity +# pertaining to distribution of the software without specific, written +# prior permission. +# +# Timothy O'Malley DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS +# SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY +# AND FITNESS, IN NO EVENT SHALL Timothy O'Malley BE LIABLE FOR +# ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES +# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, +# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS +# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR +# PERFORMANCE OF THIS SOFTWARE. +# +#### +# +# Id: Cookie.py,v 2.29 2000/08/23 05:28:49 timo Exp +# by Timothy O'Malley <timo@alum.mit.edu> +# +# Cookie.py is a Python module for the handling of HTTP +# cookies as a Python dictionary. See RFC 2109 for more +# information on cookies. +# +# The original idea to treat Cookies as a dictionary came from +# Dave Mitchell (davem@magnet.com) in 1995, when he released the +# first version of nscookie.py. +# +#### + +r""" +Here's a sample session to show how to use this module. +At the moment, this is the only documentation. + +The Basics +---------- + +Importing is easy.. + + >>> import Cookie + +Most of the time you start by creating a cookie. Cookies come in +three flavors, each with slightly different encoding semantics, but +more on that later. + + >>> C = Cookie.SimpleCookie() + >>> C = Cookie.SerialCookie() + >>> C = Cookie.SmartCookie() + +[Note: Long-time users of Cookie.py will remember using +Cookie.Cookie() to create an Cookie object. Although deprecated, it +is still supported by the code. See the Backward Compatibility notes +for more information.] + +Once you've created your Cookie, you can add values just as if it were +a dictionary. + + >>> C = Cookie.SmartCookie() + >>> C["fig"] = "newton" + >>> C["sugar"] = "wafer" + >>> C.output() + 'Set-Cookie: fig=newton\r\nSet-Cookie: sugar=wafer' + +Notice that the printable representation of a Cookie is the +appropriate format for a Set-Cookie: header. This is the +default behavior. You can change the header and printed +attributes by using the .output() function + + >>> C = Cookie.SmartCookie() + >>> C["rocky"] = "road" + >>> C["rocky"]["path"] = "/cookie" + >>> print C.output(header="Cookie:") + Cookie: rocky=road; Path=/cookie + >>> print C.output(attrs=[], header="Cookie:") + Cookie: rocky=road + +The load() method of a Cookie extracts cookies from a string. In a +CGI script, you would use this method to extract the cookies from the +HTTP_COOKIE environment variable. + + >>> C = Cookie.SmartCookie() + >>> C.load("chips=ahoy; vienna=finger") + >>> C.output() + 'Set-Cookie: chips=ahoy\r\nSet-Cookie: vienna=finger' + +The load() method is darn-tootin smart about identifying cookies +within a string. Escaped quotation marks, nested semicolons, and other +such trickeries do not confuse it. + + >>> C = Cookie.SmartCookie() + >>> C.load('keebler="E=everybody; L=\\"Loves\\"; fudge=\\012;";') + >>> print C + Set-Cookie: keebler="E=everybody; L=\"Loves\"; fudge=\012;" + +Each element of the Cookie also supports all of the RFC 2109 +Cookie attributes. Here's an example which sets the Path +attribute. + + >>> C = Cookie.SmartCookie() + >>> C["oreo"] = "doublestuff" + >>> C["oreo"]["path"] = "/" + >>> print C + Set-Cookie: oreo=doublestuff; Path=/ + +Each dictionary element has a 'value' attribute, which gives you +back the value associated with the key. + + >>> C = Cookie.SmartCookie() + >>> C["twix"] = "none for you" + >>> C["twix"].value + 'none for you' + + +A Bit More Advanced +------------------- + +As mentioned before, there are three different flavors of Cookie +objects, each with different encoding/decoding semantics. This +section briefly discusses the differences. + +SimpleCookie + +The SimpleCookie expects that all values should be standard strings. +Just to be sure, SimpleCookie invokes the str() builtin to convert +the value to a string, when the values are set dictionary-style. + + >>> C = Cookie.SimpleCookie() + >>> C["number"] = 7 + >>> C["string"] = "seven" + >>> C["number"].value + '7' + >>> C["string"].value + 'seven' + >>> C.output() + 'Set-Cookie: number=7\r\nSet-Cookie: string=seven' + + +SerialCookie + +The SerialCookie expects that all values should be serialized using +cPickle (or pickle, if cPickle isn't available). As a result of +serializing, SerialCookie can save almost any Python object to a +value, and recover the exact same object when the cookie has been +returned. (SerialCookie can yield some strange-looking cookie +values, however.) + + >>> C = Cookie.SerialCookie() + >>> C["number"] = 7 + >>> C["string"] = "seven" + >>> C["number"].value + 7 + >>> C["string"].value + 'seven' + >>> C.output() + 'Set-Cookie: number="I7\\012."\r\nSet-Cookie: string="S\'seven\'\\012p1\\012."' + +Be warned, however, if SerialCookie cannot de-serialize a value (because +it isn't a valid pickle'd object), IT WILL RAISE AN EXCEPTION. + + +SmartCookie + +The SmartCookie combines aspects of each of the other two flavors. +When setting a value in a dictionary-fashion, the SmartCookie will +serialize (ala cPickle) the value *if and only if* it isn't a +Python string. String objects are *not* serialized. Similarly, +when the load() method parses out values, it attempts to de-serialize +the value. If it fails, then it fallsback to treating the value +as a string. + + >>> C = Cookie.SmartCookie() + >>> C["number"] = 7 + >>> C["string"] = "seven" + >>> C["number"].value + 7 + >>> C["string"].value + 'seven' + >>> C.output() + 'Set-Cookie: number="I7\\012."\r\nSet-Cookie: string=seven' + + +Backwards Compatibility +----------------------- + +In order to keep compatibilty with earlier versions of Cookie.py, +it is still possible to use Cookie.Cookie() to create a Cookie. In +fact, this simply returns a SmartCookie. + + >>> C = Cookie.Cookie() + >>> print C.__class__.__name__ + SmartCookie + + +Finis. +""" #" +# ^ +# |----helps out font-lock + +# +# Import our required modules +# +import string + +try: + from cPickle import dumps, loads +except ImportError: + from pickle import dumps, loads + +import re, warnings + +__all__ = ["CookieError","BaseCookie","SimpleCookie","SerialCookie", + "SmartCookie","Cookie"] + +_nulljoin = ''.join +_semispacejoin = '; '.join +_spacejoin = ' '.join + +# +# Define an exception visible to External modules +# +class CookieError(Exception): + pass + + +# These quoting routines conform to the RFC2109 specification, which in +# turn references the character definitions from RFC2068. They provide +# a two-way quoting algorithm. Any non-text character is translated +# into a 4 character sequence: a forward-slash followed by the +# three-digit octal equivalent of the character. Any '\' or '"' is +# quoted with a preceeding '\' slash. +# +# These are taken from RFC2068 and RFC2109. +# _LegalChars is the list of chars which don't require "'s +# _Translator hash-table for fast quoting +# +_LegalChars = string.ascii_letters + string.digits + "!#$%&'*+-.^_`|~[]_" +_Translator = { + '\000' : '\\000', '\001' : '\\001', '\002' : '\\002', + '\003' : '\\003', '\004' : '\\004', '\005' : '\\005', + '\006' : '\\006', '\007' : '\\007', '\010' : '\\010', + '\011' : '\\011', '\012' : '\\012', '\013' : '\\013', + '\014' : '\\014', '\015' : '\\015', '\016' : '\\016', + '\017' : '\\017', '\020' : '\\020', '\021' : '\\021', + '\022' : '\\022', '\023' : '\\023', '\024' : '\\024', + '\025' : '\\025', '\026' : '\\026', '\027' : '\\027', + '\030' : '\\030', '\031' : '\\031', '\032' : '\\032', + '\033' : '\\033', '\034' : '\\034', '\035' : '\\035', + '\036' : '\\036', '\037' : '\\037', + + # Because of the way browsers really handle cookies (as opposed + # to what the RFC says) we also encode , and ; + + ',' : '\\054', ';' : '\\073', + + '"' : '\\"', '\\' : '\\\\', + + '\177' : '\\177', '\200' : '\\200', '\201' : '\\201', + '\202' : '\\202', '\203' : '\\203', '\204' : '\\204', + '\205' : '\\205', '\206' : '\\206', '\207' : '\\207', + '\210' : '\\210', '\211' : '\\211', '\212' : '\\212', + '\213' : '\\213', '\214' : '\\214', '\215' : '\\215', + '\216' : '\\216', '\217' : '\\217', '\220' : '\\220', + '\221' : '\\221', '\222' : '\\222', '\223' : '\\223', + '\224' : '\\224', '\225' : '\\225', '\226' : '\\226', + '\227' : '\\227', '\230' : '\\230', '\231' : '\\231', + '\232' : '\\232', '\233' : '\\233', '\234' : '\\234', + '\235' : '\\235', '\236' : '\\236', '\237' : '\\237', + '\240' : '\\240', '\241' : '\\241', '\242' : '\\242', + '\243' : '\\243', '\244' : '\\244', '\245' : '\\245', + '\246' : '\\246', '\247' : '\\247', '\250' : '\\250', + '\251' : '\\251', '\252' : '\\252', '\253' : '\\253', + '\254' : '\\254', '\255' : '\\255', '\256' : '\\256', + '\257' : '\\257', '\260' : '\\260', '\261' : '\\261', + '\262' : '\\262', '\263' : '\\263', '\264' : '\\264', + '\265' : '\\265', '\266' : '\\266', '\267' : '\\267', + '\270' : '\\270', '\271' : '\\271', '\272' : '\\272', + '\273' : '\\273', '\274' : '\\274', '\275' : '\\275', + '\276' : '\\276', '\277' : '\\277', '\300' : '\\300', + '\301' : '\\301', '\302' : '\\302', '\303' : '\\303', + '\304' : '\\304', '\305' : '\\305', '\306' : '\\306', + '\307' : '\\307', '\310' : '\\310', '\311' : '\\311', + '\312' : '\\312', '\313' : '\\313', '\314' : '\\314', + '\315' : '\\315', '\316' : '\\316', '\317' : '\\317', + '\320' : '\\320', '\321' : '\\321', '\322' : '\\322', + '\323' : '\\323', '\324' : '\\324', '\325' : '\\325', + '\326' : '\\326', '\327' : '\\327', '\330' : '\\330', + '\331' : '\\331', '\332' : '\\332', '\333' : '\\333', + '\334' : '\\334', '\335' : '\\335', '\336' : '\\336', + '\337' : '\\337', '\340' : '\\340', '\341' : '\\341', + '\342' : '\\342', '\343' : '\\343', '\344' : '\\344', + '\345' : '\\345', '\346' : '\\346', '\347' : '\\347', + '\350' : '\\350', '\351' : '\\351', '\352' : '\\352', + '\353' : '\\353', '\354' : '\\354', '\355' : '\\355', + '\356' : '\\356', '\357' : '\\357', '\360' : '\\360', + '\361' : '\\361', '\362' : '\\362', '\363' : '\\363', + '\364' : '\\364', '\365' : '\\365', '\366' : '\\366', + '\367' : '\\367', '\370' : '\\370', '\371' : '\\371', + '\372' : '\\372', '\373' : '\\373', '\374' : '\\374', + '\375' : '\\375', '\376' : '\\376', '\377' : '\\377' + } + +_idmap = ''.join(chr(x) for x in xrange(256)) + +def _quote(str, LegalChars=_LegalChars, + idmap=_idmap, translate=string.translate): + # + # If the string does not need to be double-quoted, + # then just return the string. Otherwise, surround + # the string in doublequotes and precede quote (with a \) + # special characters. + # + if "" == translate(str, idmap, LegalChars): + return str + else: + return '"' + _nulljoin( map(_Translator.get, str, str) ) + '"' +# end _quote + + +_OctalPatt = re.compile(r"\\[0-3][0-7][0-7]") +_QuotePatt = re.compile(r"[\\].") + +def _unquote(str): + # If there aren't any doublequotes, + # then there can't be any special characters. See RFC 2109. + if len(str) < 2: + return str + if str[0] != '"' or str[-1] != '"': + return str + + # We have to assume that we must decode this string. + # Down to work. + + # Remove the "s + str = str[1:-1] + + # Check for special sequences. Examples: + # \012 --> \n + # \" --> " + # + i = 0 + n = len(str) + res = [] + while 0 <= i < n: + Omatch = _OctalPatt.search(str, i) + Qmatch = _QuotePatt.search(str, i) + if not Omatch and not Qmatch: # Neither matched + res.append(str[i:]) + break + # else: + j = k = -1 + if Omatch: j = Omatch.start(0) + if Qmatch: k = Qmatch.start(0) + if Qmatch and ( not Omatch or k < j ): # QuotePatt matched + res.append(str[i:k]) + res.append(str[k+1]) + i = k+2 + else: # OctalPatt matched + res.append(str[i:j]) + res.append( chr( int(str[j+1:j+4], 8) ) ) + i = j+4 + return _nulljoin(res) +# end _unquote + +# The _getdate() routine is used to set the expiration time in +# the cookie's HTTP header. By default, _getdate() returns the +# current time in the appropriate "expires" format for a +# Set-Cookie header. The one optional argument is an offset from +# now, in seconds. For example, an offset of -3600 means "one hour ago". +# The offset may be a floating point number. +# + +_weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] + +_monthname = [None, + 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', + 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] + +def _getdate(future=0, weekdayname=_weekdayname, monthname=_monthname): + from time import gmtime, time + now = time() + year, month, day, hh, mm, ss, wd, y, z = gmtime(now + future) + return "%s, %02d-%3s-%4d %02d:%02d:%02d GMT" % \ + (weekdayname[wd], day, monthname[month], year, hh, mm, ss) + + +# +# A class to hold ONE key,value pair. +# In a cookie, each such pair may have several attributes. +# so this class is used to keep the attributes associated +# with the appropriate key,value pair. +# This class also includes a coded_value attribute, which +# is used to hold the network representation of the +# value. This is most useful when Python objects are +# pickled for network transit. +# + +class Morsel(dict): + # RFC 2109 lists these attributes as reserved: + # path comment domain + # max-age secure version + # + # For historical reasons, these attributes are also reserved: + # expires + # + # This is an extension from Microsoft: + # httponly + # + # This dictionary provides a mapping from the lowercase + # variant on the left to the appropriate traditional + # formatting on the right. + _reserved = { "expires" : "expires", + "path" : "Path", + "comment" : "Comment", + "domain" : "Domain", + "max-age" : "Max-Age", + "secure" : "secure", + "httponly" : "httponly", + "version" : "Version", + } + + def __init__(self): + # Set defaults + self.key = self.value = self.coded_value = None + + # Set default attributes + for K in self._reserved: + dict.__setitem__(self, K, "") + # end __init__ + + def __setitem__(self, K, V): + K = K.lower() + if not K in self._reserved: + raise CookieError("Invalid Attribute %s" % K) + dict.__setitem__(self, K, V) + # end __setitem__ + + def isReservedKey(self, K): + return K.lower() in self._reserved + # end isReservedKey + + def set(self, key, val, coded_val, + LegalChars=_LegalChars, + idmap=_idmap, translate=string.translate): + # First we verify that the key isn't a reserved word + # Second we make sure it only contains legal characters + if key.lower() in self._reserved: + raise CookieError("Attempt to set a reserved key: %s" % key) + if "" != translate(key, idmap, LegalChars): + raise CookieError("Illegal key value: %s" % key) + + # It's a good key, so save it. + self.key = key + self.value = val + self.coded_value = coded_val + # end set + + def output(self, attrs=None, header = "Set-Cookie:"): + return "%s %s" % ( header, self.OutputString(attrs) ) + + __str__ = output + + def __repr__(self): + return '<%s: %s=%s>' % (self.__class__.__name__, + self.key, repr(self.value) ) + + def js_output(self, attrs=None): + # Print javascript + return """ + <script type="text/javascript"> + <!-- begin hiding + document.cookie = \"%s\"; + // end hiding --> + </script> + """ % ( self.OutputString(attrs).replace('"',r'\"'), ) + # end js_output() + + def OutputString(self, attrs=None): + # Build up our result + # + result = [] + RA = result.append + + # First, the key=value pair + RA("%s=%s" % (self.key, self.coded_value)) + + # Now add any defined attributes + if attrs is None: + attrs = self._reserved + items = self.items() + items.sort() + for K,V in items: + if V == "": continue + if K not in attrs: continue + if K == "expires" and type(V) == type(1): + RA("%s=%s" % (self._reserved[K], _getdate(V))) + elif K == "max-age" and type(V) == type(1): + RA("%s=%d" % (self._reserved[K], V)) + elif K == "secure": + RA(str(self._reserved[K])) + elif K == "httponly": + RA(str(self._reserved[K])) + else: + RA("%s=%s" % (self._reserved[K], V)) + + # Return the result + return _semispacejoin(result) + # end OutputString +# end Morsel class + + + +# +# Pattern for finding cookie +# +# This used to be strict parsing based on the RFC2109 and RFC2068 +# specifications. I have since discovered that MSIE 3.0x doesn't +# follow the character rules outlined in those specs. As a +# result, the parsing rules here are less strict. +# + +_LegalCharsPatt = r"[\w\d!#%&'~_`><@,:/\$\*\+\-\.\^\|\)\(\?\}\{\=\[\]\_]" + +_CookiePattern = re.compile( + r"(?x)" # This is a Verbose pattern + r"(?P<key>" # Start of group 'key' + ""+ _LegalCharsPatt +"+?" # Any word of at least one letter, nongreedy + r")" # End of group 'key' + r"\s*=\s*" # Equal Sign + r"(?P<val>" # Start of group 'val' + r'"(?:[^\\"]|\\.)*"' # Any doublequoted string + r"|" # or + r"\w{3},\s[\w\d-]{9,11}\s[\d:]{8}\sGMT" # Special case for "expires" attr + r"|" # or + ""+ _LegalCharsPatt +"*" # Any word or empty string + r")" # End of group 'val' + r"\s*;?" # Probably ending in a semi-colon + ) + + +# At long last, here is the cookie class. +# Using this class is almost just like using a dictionary. +# See this module's docstring for example usage. +# +class BaseCookie(dict): + # A container class for a set of Morsels + # + + def value_decode(self, val): + """real_value, coded_value = value_decode(STRING) + Called prior to setting a cookie's value from the network + representation. The VALUE is the value read from HTTP + header. + Override this function to modify the behavior of cookies. + """ + return val, val + # end value_encode + + def value_encode(self, val): + """real_value, coded_value = value_encode(VALUE) + Called prior to setting a cookie's value from the dictionary + representation. The VALUE is the value being assigned. + Override this function to modify the behavior of cookies. + """ + strval = str(val) + return strval, strval + # end value_encode + + def __init__(self, input=None): + if input: self.load(input) + # end __init__ + + def __set(self, key, real_value, coded_value): + """Private method for setting a cookie's value""" + M = self.get(key, Morsel()) + M.set(key, real_value, coded_value) + dict.__setitem__(self, key, M) + # end __set + + def __setitem__(self, key, value): + """Dictionary style assignment.""" + rval, cval = self.value_encode(value) + self.__set(key, rval, cval) + # end __setitem__ + + def output(self, attrs=None, header="Set-Cookie:", sep="\015\012"): + """Return a string suitable for HTTP.""" + result = [] + items = self.items() + items.sort() + for K,V in items: + result.append( V.output(attrs, header) ) + return sep.join(result) + # end output + + __str__ = output + + def __repr__(self): + L = [] + items = self.items() + items.sort() + for K,V in items: + L.append( '%s=%s' % (K,repr(V.value) ) ) + return '<%s: %s>' % (self.__class__.__name__, _spacejoin(L)) + + def js_output(self, attrs=None): + """Return a string suitable for JavaScript.""" + result = [] + items = self.items() + items.sort() + for K,V in items: + result.append( V.js_output(attrs) ) + return _nulljoin(result) + # end js_output + + def load(self, rawdata): + """Load cookies from a string (presumably HTTP_COOKIE) or + from a dictionary. Loading cookies from a dictionary 'd' + is equivalent to calling: + map(Cookie.__setitem__, d.keys(), d.values()) + """ + if type(rawdata) == type(""): + self.__ParseString(rawdata) + else: + # self.update() wouldn't call our custom __setitem__ + for k, v in rawdata.items(): + self[k] = v + return + # end load() + + def __ParseString(self, str, patt=_CookiePattern): + i = 0 # Our starting point + n = len(str) # Length of string + M = None # current morsel + + while 0 <= i < n: + # Start looking for a cookie + match = patt.search(str, i) + if not match: break # No more cookies + + K,V = match.group("key"), match.group("val") + i = match.end(0) + + # Parse the key, value in case it's metainfo + if K[0] == "$": + # We ignore attributes which pertain to the cookie + # mechanism as a whole. See RFC 2109. + # (Does anyone care?) + if M: + M[ K[1:] ] = V + elif K.lower() in Morsel._reserved: + if M: + M[ K ] = _unquote(V) + else: + rval, cval = self.value_decode(V) + self.__set(K, rval, cval) + M = self[K] + # end __ParseString +# end BaseCookie class + +class SimpleCookie(BaseCookie): + """SimpleCookie + SimpleCookie supports strings as cookie values. When setting + the value using the dictionary assignment notation, SimpleCookie + calls the builtin str() to convert the value to a string. Values + received from HTTP are kept as strings. + """ + def value_decode(self, val): + return _unquote( val ), val + def value_encode(self, val): + strval = str(val) + return strval, _quote( strval ) +# end SimpleCookie + +class SerialCookie(BaseCookie): + """SerialCookie + SerialCookie supports arbitrary objects as cookie values. All + values are serialized (using cPickle) before being sent to the + client. All incoming values are assumed to be valid Pickle + representations. IF AN INCOMING VALUE IS NOT IN A VALID PICKLE + FORMAT, THEN AN EXCEPTION WILL BE RAISED. + + Note: Large cookie values add overhead because they must be + retransmitted on every HTTP transaction. + + Note: HTTP has a 2k limit on the size of a cookie. This class + does not check for this limit, so be careful!!! + """ + def __init__(self, input=None): + warnings.warn("SerialCookie class is insecure; do not use it", + DeprecationWarning) + BaseCookie.__init__(self, input) + # end __init__ + def value_decode(self, val): + # This could raise an exception! + return loads( _unquote(val) ), val + def value_encode(self, val): + return val, _quote( dumps(val) ) +# end SerialCookie + +class SmartCookie(BaseCookie): + """SmartCookie + SmartCookie supports arbitrary objects as cookie values. If the + object is a string, then it is quoted. If the object is not a + string, however, then SmartCookie will use cPickle to serialize + the object into a string representation. + + Note: Large cookie values add overhead because they must be + retransmitted on every HTTP transaction. + + Note: HTTP has a 2k limit on the size of a cookie. This class + does not check for this limit, so be careful!!! + """ + def __init__(self, input=None): + warnings.warn("Cookie/SmartCookie class is insecure; do not use it", + DeprecationWarning) + BaseCookie.__init__(self, input) + # end __init__ + def value_decode(self, val): + strval = _unquote(val) + try: + return loads(strval), val + except: + return strval, val + def value_encode(self, val): + if type(val) == type(""): + return val, _quote(val) + else: + return val, _quote( dumps(val) ) +# end SmartCookie + + +########################################################### +# Backwards Compatibility: Don't break any existing code! + +# We provide Cookie() as an alias for SmartCookie() +Cookie = SmartCookie + +# +########################################################### + +def _test(): + import doctest, Cookie + return doctest.testmod(Cookie) + +if __name__ == "__main__": + _test() + + +#Local Variables: +#tab-width: 4 +#end: diff --git a/requests/packages/oreos/structures.py b/requests/packages/oreos/structures.py new file mode 100644 index 0000000..063d5f9 --- /dev/null +++ b/requests/packages/oreos/structures.py @@ -0,0 +1,399 @@ +# -*- coding: utf-8 -*- + +""" +oreos.sructures +~~~~~~~~~~~~~~~ + +The plastic blue packaging. + +This is mostly directly stolen from mitsuhiko/werkzeug. +""" + +__all__ = ('MultiDict',) + +class _Missing(object): + + def __repr__(self): + return 'no value' + + def __reduce__(self): + return '_missing' + +_missing = _Missing() + + + +def iter_multi_items(mapping): + """Iterates over the items of a mapping yielding keys and values + without dropping any from more complex structures. + """ + if isinstance(mapping, MultiDict): + for item in mapping.iteritems(multi=True): + yield item + elif isinstance(mapping, dict): + for key, value in mapping.iteritems(): + if isinstance(value, (tuple, list)): + for value in value: + yield key, value + else: + yield key, value + else: + for item in mapping: + yield item + + + +class TypeConversionDict(dict): + """Works like a regular dict but the :meth:`get` method can perform + type conversions. :class:`MultiDict` and :class:`CombinedMultiDict` + are subclasses of this class and provide the same feature. + + .. versionadded:: 0.5 + """ + + def get(self, key, default=None, type=None): + """Return the default value if the requested data doesn't exist. + If `type` is provided and is a callable it should convert the value, + return it or raise a :exc:`ValueError` if that is not possible. In + this case the function will return the default as if the value was not + found: + + >>> d = TypeConversionDict(foo='42', bar='blub') + >>> d.get('foo', type=int) + 42 + >>> d.get('bar', -1, type=int) + -1 + + :param key: The key to be looked up. + :param default: The default value to be returned if the key can't + be looked up. If not further specified `None` is + returned. + :param type: A callable that is used to cast the value in the + :class:`MultiDict`. If a :exc:`ValueError` is raised + by this callable the default value is returned. + """ + try: + rv = self[key] + if type is not None: + rv = type(rv) + except (KeyError, ValueError): + rv = default + return rv + + +class MultiDict(TypeConversionDict): + """A :class:`MultiDict` is a dictionary subclass customized to deal with + multiple values for the same key which is for example used by the parsing + functions in the wrappers. This is necessary because some HTML form + elements pass multiple values for the same key. + + :class:`MultiDict` implements all standard dictionary methods. + Internally, it saves all values for a key as a list, but the standard dict + access methods will only return the first value for a key. If you want to + gain access to the other values, too, you have to use the `list` methods as + explained below. + + Basic Usage: + + >>> d = MultiDict([('a', 'b'), ('a', 'c')]) + >>> d + MultiDict([('a', 'b'), ('a', 'c')]) + >>> d['a'] + 'b' + >>> d.getlist('a') + ['b', 'c'] + >>> 'a' in d + True + + It behaves like a normal dict thus all dict functions will only return the + first value when multiple values for one key are found. + + From Werkzeug 0.3 onwards, the `KeyError` raised by this class is also a + subclass of the :exc:`~exceptions.BadRequest` HTTP exception and will + render a page for a ``400 BAD REQUEST`` if caught in a catch-all for HTTP + exceptions. + + A :class:`MultiDict` can be constructed from an iterable of + ``(key, value)`` tuples, a dict, a :class:`MultiDict` or from Werkzeug 0.2 + onwards some keyword parameters. + + :param mapping: the initial value for the :class:`MultiDict`. Either a + regular dict, an iterable of ``(key, value)`` tuples + or `None`. + """ + + def __init__(self, mapping=None): + if isinstance(mapping, MultiDict): + dict.__init__(self, ((k, l[:]) for k, l in mapping.iterlists())) + elif isinstance(mapping, dict): + tmp = {} + for key, value in mapping.iteritems(): + if isinstance(value, (tuple, list)): + value = list(value) + else: + value = [value] + tmp[key] = value + dict.__init__(self, tmp) + else: + tmp = {} + for key, value in mapping or (): + tmp.setdefault(key, []).append(value) + dict.__init__(self, tmp) + + def __getstate__(self): + return dict(self.lists()) + + def __setstate__(self, value): + dict.clear(self) + dict.update(self, value) + + def __iter__(self): + return self.iterkeys() + + def __getitem__(self, key): + """Return the first data value for this key; + raises KeyError if not found. + + :param key: The key to be looked up. + :raise KeyError: if the key does not exist. + """ + if key in self: + return dict.__getitem__(self, key)[0] + raise KeyError(key) + + def __setitem__(self, key, value): + """Like :meth:`add` but removes an existing key first. + + :param key: the key for the value. + :param value: the value to set. + """ + dict.__setitem__(self, key, [value]) + + def add(self, key, value): + """Adds a new value for the key. + + .. versionadded:: 0.6 + + :param key: the key for the value. + :param value: the value to add. + """ + dict.setdefault(self, key, []).append(value) + + def getlist(self, key, type=None): + """Return the list of items for a given key. If that key is not in the + `MultiDict`, the return value will be an empty list. Just as `get` + `getlist` accepts a `type` parameter. All items will be converted + with the callable defined there. + + :param key: The key to be looked up. + :param type: A callable that is used to cast the value in the + :class:`MultiDict`. If a :exc:`ValueError` is raised + by this callable the value will be removed from the list. + :return: a :class:`list` of all the values for the key. + """ + try: + rv = dict.__getitem__(self, key) + except KeyError: + return [] + if type is None: + return list(rv) + result = [] + for item in rv: + try: + result.append(type(item)) + except ValueError: + pass + return result + + def setlist(self, key, new_list): + """Remove the old values for a key and add new ones. Note that the list + you pass the values in will be shallow-copied before it is inserted in + the dictionary. + + >>> d = MultiDict() + >>> d.setlist('foo', ['1', '2']) + >>> d['foo'] + '1' + >>> d.getlist('foo') + ['1', '2'] + + :param key: The key for which the values are set. + :param new_list: An iterable with the new values for the key. Old values + are removed first. + """ + dict.__setitem__(self, key, list(new_list)) + + def setdefault(self, key, default=None): + """Returns the value for the key if it is in the dict, otherwise it + returns `default` and sets that value for `key`. + + :param key: The key to be looked up. + :param default: The default value to be returned if the key is not + in the dict. If not further specified it's `None`. + """ + if key not in self: + self[key] = default + else: + default = self[key] + return default + + def setlistdefault(self, key, default_list=None): + """Like `setdefault` but sets multiple values. The list returned + is not a copy, but the list that is actually used internally. This + means that you can put new values into the dict by appending items + to the list: + + >>> d = MultiDict({"foo": 1}) + >>> d.setlistdefault("foo").extend([2, 3]) + >>> d.getlist("foo") + [1, 2, 3] + + :param key: The key to be looked up. + :param default: An iterable of default values. It is either copied + (in case it was a list) or converted into a list + before returned. + :return: a :class:`list` + """ + if key not in self: + default_list = list(default_list or ()) + dict.__setitem__(self, key, default_list) + else: + default_list = dict.__getitem__(self, key) + return default_list + + def items(self, multi=False): + """Return a list of ``(key, value)`` pairs. + + :param multi: If set to `True` the list returned will have a + pair for each value of each key. Otherwise it + will only contain pairs for the first value of + each key. + + :return: a :class:`list` + """ + return list(self.iteritems(multi)) + + def lists(self): + """Return a list of ``(key, values)`` pairs, where values is the list of + all values associated with the key. + + :return: a :class:`list` + """ + return list(self.iterlists()) + + def values(self): + """Returns a list of the first value on every key's value list. + + :return: a :class:`list`. + """ + return [self[key] for key in self.iterkeys()] + + def listvalues(self): + """Return a list of all values associated with a key. Zipping + :meth:`keys` and this is the same as calling :meth:`lists`: + + >>> d = MultiDict({"foo": [1, 2, 3]}) + >>> zip(d.keys(), d.listvalues()) == d.lists() + True + + :return: a :class:`list` + """ + return list(self.iterlistvalues()) + + def iteritems(self, multi=False): + """Like :meth:`items` but returns an iterator.""" + for key, values in dict.iteritems(self): + if multi: + for value in values: + yield key, value + else: + yield key, values[0] + + def iterlists(self): + """Like :meth:`items` but returns an iterator.""" + for key, values in dict.iteritems(self): + yield key, list(values) + + def itervalues(self): + """Like :meth:`values` but returns an iterator.""" + for values in dict.itervalues(self): + yield values[0] + + def iterlistvalues(self): + """Like :meth:`listvalues` but returns an iterator.""" + return dict.itervalues(self) + + def copy(self): + """Return a shallow copy of this object.""" + return self.__class__(self) + + def to_dict(self, flat=True): + """Return the contents as regular dict. If `flat` is `True` the + returned dict will only have the first item present, if `flat` is + `False` all values will be returned as lists. + + :param flat: If set to `False` the dict returned will have lists + with all the values in it. Otherwise it will only + contain the first value for each key. + :return: a :class:`dict` + """ + if flat: + return dict(self.iteritems()) + return dict(self.lists()) + + def update(self, other_dict): + """update() extends rather than replaces existing key lists.""" + for key, value in iter_multi_items(other_dict): + MultiDict.add(self, key, value) + + def pop(self, key, default=_missing): + """Pop the first item for a list on the dict. Afterwards the + key is removed from the dict, so additional values are discarded: + + >>> d = MultiDict({"foo": [1, 2, 3]}) + >>> d.pop("foo") + 1 + >>> "foo" in d + False + + :param key: the key to pop. + :param default: if provided the value to return if the key was + not in the dictionary. + """ + try: + return dict.pop(self, key)[0] + except KeyError, e: + if default is not _missing: + return default + raise KeyError(str(e)) + + def popitem(self): + """Pop an item from the dict.""" + try: + item = dict.popitem(self) + return (item[0], item[1][0]) + except KeyError, e: + raise KeyError(str(e)) + + def poplist(self, key): + """Pop the list for a key from the dict. If the key is not in the dict + an empty list is returned. + + .. versionchanged:: 0.5 + If the key does no longer exist a list is returned instead of + raising an error. + """ + return dict.pop(self, key, []) + + def popitemlist(self): + """Pop a ``(key, list)`` tuple from the dict.""" + try: + return dict.popitem(self) + except KeyError, e: + raise KeyError(str(e)) + + def __copy__(self): + return self.copy() + + def __repr__(self): + return '%s(%r)' % (self.__class__.__name__, self.items(multi=True)) diff --git a/requests/packages/urllib3/__init__.py b/requests/packages/urllib3/__init__.py new file mode 100644 index 0000000..20b1fb4 --- /dev/null +++ b/requests/packages/urllib3/__init__.py @@ -0,0 +1,48 @@ +# urllib3/__init__.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + +""" +urllib3 - Thread-safe connection pooling and re-using. +""" + +__author__ = 'Andrey Petrov (andrey.petrov@shazow.net)' +__license__ = 'MIT' +__version__ = '1.0.2' + + +from .connectionpool import ( + HTTPConnectionPool, + HTTPSConnectionPool, + connection_from_url, + get_host, + make_headers) + + +from .exceptions import ( + HTTPError, + MaxRetryError, + SSLError, + TimeoutError) + +from .poolmanager import PoolManager, ProxyManager, proxy_from_url +from .response import HTTPResponse +from .filepost import encode_multipart_formdata + + +# Set default logging handler to avoid "No handler found" warnings. +import logging +try: + from logging import NullHandler +except ImportError: + class NullHandler(logging.Handler): + def emit(self, record): + pass + +logging.getLogger(__name__).addHandler(NullHandler()) + +# ... Clean up. +del logging +del NullHandler diff --git a/requests/packages/urllib3/_collections.py b/requests/packages/urllib3/_collections.py new file mode 100644 index 0000000..00b2cd5 --- /dev/null +++ b/requests/packages/urllib3/_collections.py @@ -0,0 +1,131 @@ +# urllib3/_collections.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + +from collections import deque + +from threading import RLock + +__all__ = ['RecentlyUsedContainer'] + + +class AccessEntry(object): + __slots__ = ('key', 'is_valid') + + def __init__(self, key, is_valid=True): + self.key = key + self.is_valid = is_valid + + +class RecentlyUsedContainer(dict): + """ + Provides a dict-like that maintains up to ``maxsize`` keys while throwing + away the least-recently-used keys beyond ``maxsize``. + """ + + # If len(self.access_log) exceeds self._maxsize * CLEANUP_FACTOR, then we + # will attempt to cleanup the invalidated entries in the access_log + # datastructure during the next 'get' operation. + CLEANUP_FACTOR = 10 + + def __init__(self, maxsize=10): + self._maxsize = maxsize + + self._container = {} + + # We use a deque to to store our keys ordered by the last access. + self.access_log = deque() + self.access_log_lock = RLock() + + # We look up the access log entry by the key to invalidate it so we can + # insert a new authorative entry at the head without having to dig and + # find the old entry for removal immediately. + self.access_lookup = {} + + # Trigger a heap cleanup when we get past this size + self.access_log_limit = maxsize * self.CLEANUP_FACTOR + + def _invalidate_entry(self, key): + "If exists: Invalidate old entry and return it." + old_entry = self.access_lookup.get(key) + if old_entry: + old_entry.is_valid = False + + return old_entry + + def _push_entry(self, key): + "Push entry onto our access log, invalidate the old entry if exists." + self._invalidate_entry(key) + + new_entry = AccessEntry(key) + self.access_lookup[key] = new_entry + + self.access_log_lock.acquire() + self.access_log.appendleft(new_entry) + self.access_log_lock.release() + + def _prune_entries(self, num): + "Pop entries from our access log until we popped ``num`` valid ones." + while num > 0: + self.access_log_lock.acquire() + p = self.access_log.pop() + self.access_log_lock.release() + + if not p.is_valid: + continue # Invalidated entry, skip + + dict.pop(self, p.key, None) + self.access_lookup.pop(p.key, None) + num -= 1 + + def _prune_invalidated_entries(self): + "Rebuild our access_log without the invalidated entries." + self.access_log_lock.acquire() + self.access_log = deque(e for e in self.access_log if e.is_valid) + self.access_log_lock.release() + + def _get_ordered_access_keys(self): + "Return ordered access keys for inspection. Used for testing." + self.access_log_lock.acquire() + r = [e.key for e in self.access_log if e.is_valid] + self.access_log_lock.release() + + return r + + def __getitem__(self, key): + item = dict.get(self, key) + + if not item: + raise KeyError(key) + + # Insert new entry with new high priority, also implicitly invalidates + # the old entry. + self._push_entry(key) + + if len(self.access_log) > self.access_log_limit: + # Heap is getting too big, try to clean up any tailing invalidated + # entries. + self._prune_invalidated_entries() + + return item + + def __setitem__(self, key, item): + # Add item to our container and access log + dict.__setitem__(self, key, item) + self._push_entry(key) + + # Discard invalid and excess entries + self._prune_entries(len(self) - self._maxsize) + + def __delitem__(self, key): + self._invalidate_entry(key) + self.access_lookup.pop(key, None) + dict.__delitem__(self, key) + + def get(self, key, default=None): + try: + return self[key] + except KeyError: + return default diff --git a/requests/packages/urllib3/connectionpool.py b/requests/packages/urllib3/connectionpool.py new file mode 100644 index 0000000..17f2f84 --- /dev/null +++ b/requests/packages/urllib3/connectionpool.py @@ -0,0 +1,548 @@ +# urllib3/connectionpool.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + +import logging +import socket + + +from httplib import HTTPConnection, HTTPSConnection, HTTPException +from Queue import Queue, Empty, Full +from select import select +from socket import error as SocketError, timeout as SocketTimeout + +from .packages.ssl_match_hostname import match_hostname, CertificateError + +try: + import ssl + BaseSSLError = ssl.SSLError +except ImportError: + ssl = None + BaseSSLError = None + + +from .request import RequestMethods +from .response import HTTPResponse +from .exceptions import ( + SSLError, + MaxRetryError, + TimeoutError, + HostChangedError, + EmptyPoolError, +) + + +log = logging.getLogger(__name__) + +_Default = object() + + +## Connection objects (extension of httplib) + +class VerifiedHTTPSConnection(HTTPSConnection): + """ + Based on httplib.HTTPSConnection but wraps the socket with + SSL certification. + """ + cert_reqs = None + ca_certs = None + + def set_cert(self, key_file=None, cert_file=None, + cert_reqs='CERT_NONE', ca_certs=None): + ssl_req_scheme = { + 'CERT_NONE': ssl.CERT_NONE, + 'CERT_OPTIONAL': ssl.CERT_OPTIONAL, + 'CERT_REQUIRED': ssl.CERT_REQUIRED + } + + self.key_file = key_file + self.cert_file = cert_file + self.cert_reqs = ssl_req_scheme.get(cert_reqs) or ssl.CERT_NONE + self.ca_certs = ca_certs + + def connect(self): + # Add certificate verification + sock = socket.create_connection((self.host, self.port), self.timeout) + + # Wrap socket using verification with the root certs in + # trusted_root_certs + self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, + cert_reqs=self.cert_reqs, + ca_certs=self.ca_certs) + if self.ca_certs: + match_hostname(self.sock.getpeercert(), self.host) + +## Pool objects + +class ConnectionPool(object): + """ + Base class for all connection pools, such as + :class:`.HTTPConnectionPool` and :class:`.HTTPSConnectionPool`. + """ + pass + + +class HTTPConnectionPool(ConnectionPool, RequestMethods): + """ + 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`. + + :param timeout: + Socket timeout for each individual connection, can be a float. None + disables timeout. + + :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. + """ + + scheme = 'http' + + def __init__(self, host, port=None, strict=False, timeout=None, maxsize=1, + block=False, headers=None): + self.host = host + self.port = port + self.strict = strict + self.timeout = timeout + self.pool = Queue(maxsize) + self.block = block + self.headers = headers or {} + + # Fill the queue up so that doing get() on it will block properly + for _ in xrange(maxsize): + self.pool.put(None) + + # These are mostly for testing and debugging purposes. + self.num_connections = 0 + self.num_requests = 0 + + def _new_conn(self): + """ + Return a fresh :class:`httplib.HTTPConnection`. + """ + self.num_connections += 1 + log.info("Starting new HTTP connection (%d): %s" % + (self.num_connections, self.host)) + return HTTPConnection(host=self.host, port=self.port) + + def _get_conn(self, timeout=None): + """ + 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``. + """ + conn = None + try: + conn = self.pool.get(block=self.block, timeout=timeout) + + # If this is a persistent connection, check if it got disconnected + if conn and conn.sock and select([conn.sock], [], [], 0.0)[0]: + # Either data is buffered (bad), or the connection is dropped. + log.info("Resetting dropped connection: %s" % self.host) + conn.close() + + except Empty: + if self.block: + raise EmptyPoolError("Pool reached maximum size and no more " + "connections are allowed.") + pass # Oh well, we'll create a new connection then + + return conn or self._new_conn() + + def _put_conn(self, conn): + """ + 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 discarded because we + exceeded maxsize. If connections are discarded frequently, then maxsize + should be increased. + """ + try: + self.pool.put(conn, block=False) + except Full: + # This should never happen if self.block == True + log.warning("HttpConnectionPool is full, discarding connection: %s" + % self.host) + + def _make_request(self, conn, method, url, timeout=_Default, + **httplib_request_kw): + """ + Perform a request on a given httplib connection object taken from our + pool. + """ + self.num_requests += 1 + + if timeout is _Default: + timeout = self.timeout + + conn.timeout = timeout # This only does anything in Py26+ + + conn.request(method, url, **httplib_request_kw) + conn.sock.settimeout(timeout) + httplib_response = conn.getresponse() + + log.debug("\"%s %s %s\" %s %s" % + (method, url, + conn._http_vsn_str, # pylint: disable-msg=W0212 + httplib_response.status, httplib_response.length)) + + return httplib_response + + + def is_same_host(self, url): + """ + Check if the given ``url`` is a member of the same host as this + conncetion pool. + """ + # TODO: Add optional support for socket.gethostbyname checking. + return (url.startswith('/') or + get_host(url) == (self.scheme, self.host, self.port)) + + def urlopen(self, method, url, body=None, headers=None, retries=3, + redirect=True, assert_same_host=True, timeout=_Default, + pool_timeout=None, release_conn=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: + Number of retries to allow before raising a MaxRetryError exception. + + :param redirect: + Automatically handle redirects (status codes 301, 302, 303, 307), + each redirect counts as a retry. + + :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. + + :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 \**response_kw: + Additional parameters are passed to + :meth:`urllib3.response.HTTPResponse.from_httplib` + """ + if headers is None: + headers = self.headers + + if retries < 0: + raise MaxRetryError(url) + + if timeout is _Default: + timeout = self.timeout + + if release_conn is None: + release_conn = response_kw.get('preload_content', True) + + # Check host + if assert_same_host and not self.is_same_host(url): + host = "%s://%s" % (self.scheme, self.host) + if self.port: + host = "%s:%d" % (host, self.port) + + raise HostChangedError(host, url, retries - 1) + + conn = None + + try: + # Request a connection from the queue + # (Could raise SocketError: Bad file descriptor) + conn = self._get_conn(timeout=pool_timeout) + + # Make the request on the httplib connection object + httplib_response = self._make_request(conn, method, url, + timeout=timeout, + body=body, headers=headers) + + # If we're going to release the connection in ``finally:``, then + # the request doesn't need to know about the connection. Otherwise + # it will also try to release it and we'll have a double-release + # mess. + response_conn = not release_conn and conn + + # Import httplib's response into our own wrapper object + response = HTTPResponse.from_httplib(httplib_response, + pool=self, + connection=response_conn, + **response_kw) + + # else: + # The connection will be put back into the pool when + # ``response.release_conn()`` is called (implicitly by + # ``response.read()``) + + except (Empty), e: + # Timed out by queue + raise TimeoutError("Request timed out. (pool_timeout=%s)" % + pool_timeout) + + except (SocketTimeout), e: + # Timed out by socket + raise TimeoutError("Request timed out. (timeout=%s)" % + timeout) + + except (BaseSSLError), e: + # SSL certificate error + raise SSLError(e) + + except (CertificateError), e: + # Name mismatch + raise SSLError(e) + + except (HTTPException, SocketError), e: + # Connection broken, discard. It will be replaced next _get_conn(). + conn = None + + finally: + if conn and release_conn: + # Put the connection back to be reused + self._put_conn(conn) + + if not conn: + log.warn("Retrying (%d attempts remain) after connection " + "broken by '%r': %s" % (retries, e, url)) + return self.urlopen(method, url, body, headers, retries - 1, + redirect, assert_same_host) # Try again + + # Handle redirect? + redirect_location = redirect and response.get_redirect_location() + if redirect_location: + log.info("Redirecting %s -> %s" % (url, redirect_location)) + return self.urlopen(method, redirect_location, body, headers, + retries - 1, redirect, assert_same_host) + + return response + + +class HTTPSConnectionPool(HTTPConnectionPool): + """ + 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:httplib.HTTPSConnection`. + + The ``key_file``, ``cert_file``, ``cert_reqs``, and ``ca_certs`` parameters + are only used if :mod:`ssl` is available and are fed into + :meth:`ssl.wrap_socket` to upgrade the connection socket into an SSL socket. + """ + + scheme = 'https' + + def __init__(self, host, port=None, + strict=False, timeout=None, maxsize=1, + block=False, headers=None, + key_file=None, cert_file=None, + cert_reqs='CERT_NONE', ca_certs=None): + + super(HTTPSConnectionPool, self).__init__(host, port, + strict, timeout, maxsize, + block, headers) + self.key_file = key_file + self.cert_file = cert_file + self.cert_reqs = cert_reqs + self.ca_certs = ca_certs + + def _new_conn(self): + """ + Return a fresh :class:`httplib.HTTPSConnection`. + """ + self.num_connections += 1 + log.info("Starting new HTTPS connection (%d): %s" + % (self.num_connections, self.host)) + + if not ssl: + return HTTPSConnection(host=self.host, port=self.port) + + connection = VerifiedHTTPSConnection(host=self.host, port=self.port) + connection.set_cert(key_file=self.key_file, cert_file=self.cert_file, + cert_reqs=self.cert_reqs, ca_certs=self.ca_certs) + return connection + + +## Helpers + +def make_headers(keep_alive=None, accept_encoding=None, user_agent=None, + basic_auth=None): + """ + Shortcuts for generating request headers. + + :param keep_alive: + If ``True``, adds 'connection: keep-alive' header. + + :param accept_encoding: + Can be a boolean, list, or string. + ``True`` translates to 'gzip,deflate'. + List will get joined by comma. + String will be used as provided. + + :param user_agent: + String representing the user-agent you want, such as + "python-urllib3/0.6" + + :param basic_auth: + Colon-separated username:password string for 'authorization: basic ...' + auth header. + + Example: :: + + >>> make_headers(keep_alive=True, user_agent="Batman/1.0") + {'connection': 'keep-alive', 'user-agent': 'Batman/1.0'} + >>> make_headers(accept_encoding=True) + {'accept-encoding': 'gzip,deflate'} + """ + headers = {} + if accept_encoding: + if isinstance(accept_encoding, str): + pass + elif isinstance(accept_encoding, list): + accept_encoding = ','.join(accept_encoding) + else: + accept_encoding = 'gzip,deflate' + headers['accept-encoding'] = accept_encoding + + if user_agent: + headers['user-agent'] = user_agent + + if keep_alive: + headers['connection'] = 'keep-alive' + + if basic_auth: + headers['authorization'] = 'Basic ' + \ + basic_auth.encode('base64').strip() + + return headers + + +def get_host(url): + """ + Given a url, return its scheme, host and port (None if it's not there). + + For example: :: + + >>> get_host('http://google.com/mail/') + ('http', 'google.com', None) + >>> get_host('google.com:80') + ('http', 'google.com', 80) + """ + # This code is actually similar to urlparse.urlsplit, but much + # simplified for our needs. + port = None + scheme = 'http' + if '://' in url: + scheme, url = url.split('://', 1) + if '/' in url: + url, _path = url.split('/', 1) + if '@' in url: + _auth, url = url.split('@', 1) + if ':' in url: + url, port = url.split(':', 1) + port = int(port) + return scheme, url, port + + +def connection_from_url(url, **kw): + """ + 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) + if scheme == 'https': + return HTTPSConnectionPool(host, port=port, **kw) + else: + return HTTPConnectionPool(host, port=port, **kw) diff --git a/requests/packages/urllib3/contrib/__init__.py b/requests/packages/urllib3/contrib/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/requests/packages/urllib3/contrib/__init__.py diff --git a/requests/packages/urllib3/contrib/ntlmpool.py b/requests/packages/urllib3/contrib/ntlmpool.py new file mode 100644 index 0000000..c5f010e --- /dev/null +++ b/requests/packages/urllib3/contrib/ntlmpool.py @@ -0,0 +1,117 @@ +# urllib3/contrib/ntlmpool.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + +""" +NTLM authenticating pool, contributed by erikcederstran + +Issue #10, see: http://code.google.com/p/urllib3/issues/detail?id=10 +""" + +import httplib +from logging import getLogger +from ntlm import ntlm + +from urllib3 import HTTPSConnectionPool + + +log = getLogger(__name__) + + +class NTLMConnectionPool(HTTPSConnectionPool): + """ + Implements an NTLM authentication version of an urllib3 connection pool + """ + + scheme = 'https' + + def __init__(self, user, pw, authurl, *args, **kwargs): + """ + authurl is a random URL on the server that is protected by NTLM. + user is the Windows user, probably in the DOMAIN\username format. + pw is the password for the user. + """ + super(NTLMConnectionPool, self).__init__(*args, **kwargs) + self.authurl = authurl + self.rawuser = user + user_parts = user.split('\\', 1) + self.domain = user_parts[0].upper() + self.user = user_parts[1] + self.pw = pw + + def _new_conn(self): + # Performs the NTLM handshake that secures the connection. The socket + # must be kept open while requests are performed. + self.num_connections += 1 + log.debug('Starting NTLM HTTPS connection no. %d: https://%s%s' % + (self.num_connections, self.host, self.authurl)) + + headers = {} + headers['Connection'] = 'Keep-Alive' + req_header = 'Authorization' + resp_header = 'www-authenticate' + + conn = httplib.HTTPSConnection(host=self.host, port=self.port) + + # Send negotiation message + headers[req_header] = ( + 'NTLM %s' % ntlm.create_NTLM_NEGOTIATE_MESSAGE(self.rawuser)) + log.debug('Request headers: %s' % headers) + conn.request('GET', self.authurl, None, headers) + res = conn.getresponse() + reshdr = dict(res.getheaders()) + log.debug('Response status: %s %s' % (res.status, res.reason)) + log.debug('Response headers: %s' % reshdr) + log.debug('Response data: %s [...]' % res.read(100)) + + # Remove the reference to the socket, so that it can not be closed by + # the response object (we want to keep the socket open) + res.fp = None + + # Server should respond with a challenge message + auth_header_values = reshdr[resp_header].split(', ') + auth_header_value = None + for s in auth_header_values: + if s[:5] == 'NTLM ': + auth_header_value = s[5:] + if auth_header_value is None: + raise Exception('Unexpected %s response header: %s' % + (resp_header, reshdr[resp_header])) + + # Send authentication message + ServerChallenge, NegotiateFlags = \ + ntlm.parse_NTLM_CHALLENGE_MESSAGE(auth_header_value) + auth_msg = ntlm.create_NTLM_AUTHENTICATE_MESSAGE(ServerChallenge, + self.user, + self.domain, + self.pw, + NegotiateFlags) + headers[req_header] = 'NTLM %s' % auth_msg + log.debug('Request headers: %s' % headers) + conn.request('GET', self.authurl, None, headers) + res = conn.getresponse() + log.debug('Response status: %s %s' % (res.status, res.reason)) + log.debug('Response headers: %s' % dict(res.getheaders())) + log.debug('Response data: %s [...]' % res.read()[:100]) + if res.status != 200: + if res.status == 401: + raise Exception('Server rejected request: wrong ' + 'username or password') + raise Exception('Wrong server response: %s %s' % + (res.status, res.reason)) + + res.fp = None + log.debug('Connection established') + return conn + + def urlopen(self, method, url, body=None, headers=None, retries=3, + redirect=True, assert_same_host=True): + if headers is None: + headers = {} + headers['Connection'] = 'Keep-Alive' + return super(NTLMConnectionPool, self).urlopen(method, url, body, + headers, retries, + redirect, + assert_same_host) diff --git a/requests/packages/urllib3/exceptions.py b/requests/packages/urllib3/exceptions.py new file mode 100644 index 0000000..47937f7 --- /dev/null +++ b/requests/packages/urllib3/exceptions.py @@ -0,0 +1,45 @@ +# urllib3/exceptions.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + +## Exceptions + +class HTTPError(Exception): + "Base exception used by this module." + pass + + +class SSLError(Exception): + "Raised when SSL certificate fails in an HTTPS connection." + pass + + +class MaxRetryError(HTTPError): + "Raised when the maximum number of retries is exceeded." + def __init__(self, url): + HTTPError.__init__(self, "Max retries exceeded for url: %s" % url) + self.url = url + + +class TimeoutError(HTTPError): + "Raised when a socket timeout occurs." + pass + + +class HostChangedError(HTTPError): + "Raised when an existing pool gets a request for a foreign host." + def __init__(self, original_host, new_url, retries=3): + HTTPError.__init__(self, + "Connection pool with host '%s' tried to open a foreign host: %s" % + (original_host, new_url)) + + self.original_host = original_host + self.new_url = new_url + self.retries = retries + + +class EmptyPoolError(HTTPError): + "Raised when a pool runs out of connections and no more are allowed." + pass diff --git a/requests/packages/urllib3/filepost.py b/requests/packages/urllib3/filepost.py new file mode 100644 index 0000000..2ffea8b --- /dev/null +++ b/requests/packages/urllib3/filepost.py @@ -0,0 +1,71 @@ +# urllib3/filepost.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + +import codecs +import mimetools +import mimetypes + +try: + from cStringIO import StringIO +except ImportError: + from StringIO import StringIO # pylint: disable-msg=W0404 + + +writer = codecs.lookup('utf-8')[3] + + +def get_content_type(filename): + return mimetypes.guess_type(filename)[0] or 'application/octet-stream' + + +def encode_multipart_formdata(fields, boundary=None): + """ + Encode a dictionary of ``fields`` using the multipart/form-data mime format. + + :param fields: + Dictionary of fields. The key is treated as the field name, and the + value as the body of the form-data. If the value is a tuple of two + elements, then the first element is treated as the filename of the + form-data section. + + :param boundary: + If not specified, then a random boundary will be generated using + :func:`mimetools.choose_boundary`. + """ + body = StringIO() + if boundary is None: + boundary = mimetools.choose_boundary() + + for fieldname, value in fields.iteritems(): + body.write('--%s\r\n' % (boundary)) + + if isinstance(value, tuple): + filename, data = value + writer(body).write('Content-Disposition: form-data; name="%s"; ' + 'filename="%s"\r\n' % (fieldname, filename)) + body.write('Content-Type: %s\r\n\r\n' % + (get_content_type(filename))) + else: + data = value + writer(body).write('Content-Disposition: form-data; name="%s"\r\n' + % (fieldname)) + body.write('Content-Type: text/plain\r\n\r\n') + + if isinstance(data, int): + data = str(data) # Backwards compatibility + + if isinstance(data, unicode): + writer(body).write(data) + else: + body.write(data) + + body.write('\r\n') + + body.write('--%s--\r\n' % (boundary)) + + content_type = 'multipart/form-data; boundary=%s' % boundary + + return body.getvalue(), content_type diff --git a/requests/packages/urllib3/packages/__init__.py b/requests/packages/urllib3/packages/__init__.py new file mode 100644 index 0000000..37e8351 --- /dev/null +++ b/requests/packages/urllib3/packages/__init__.py @@ -0,0 +1,4 @@ +from __future__ import absolute_import + +from . import ssl_match_hostname + diff --git a/requests/packages/urllib3/packages/ssl_match_hostname/__init__.py b/requests/packages/urllib3/packages/ssl_match_hostname/__init__.py new file mode 100644 index 0000000..9560b04 --- /dev/null +++ b/requests/packages/urllib3/packages/ssl_match_hostname/__init__.py @@ -0,0 +1,61 @@ +"""The match_hostname() function from Python 3.2, essential when using SSL.""" + +import re + +__version__ = '3.2.2' + +class CertificateError(ValueError): + pass + +def _dnsname_to_pat(dn): + pats = [] + for frag in dn.split(r'.'): + if frag == '*': + # When '*' is a fragment by itself, it matches a non-empty dotless + # fragment. + pats.append('[^.]+') + else: + # Otherwise, '*' matches any dotless fragment. + frag = re.escape(frag) + pats.append(frag.replace(r'\*', '[^.]*')) + return re.compile(r'\A' + r'\.'.join(pats) + r'\Z', re.IGNORECASE) + +def match_hostname(cert, hostname): + """Verify that *cert* (in decoded format as returned by + SSLSocket.getpeercert()) matches the *hostname*. RFC 2818 rules + are mostly followed, but IP addresses are not accepted for *hostname*. + + CertificateError is raised on failure. On success, the function + returns nothing. + """ + if not cert: + raise ValueError("empty or no certificate") + dnsnames = [] + san = cert.get('subjectAltName', ()) + for key, value in san: + if key == 'DNS': + if _dnsname_to_pat(value).match(hostname): + return + dnsnames.append(value) + if not dnsnames: + # The subject is only checked when there is no dNSName entry + # in subjectAltName + for sub in cert.get('subject', ()): + for key, value in sub: + # XXX according to RFC 2818, the most specific Common Name + # must be used. + if key == 'commonName': + if _dnsname_to_pat(value).match(hostname): + return + dnsnames.append(value) + if len(dnsnames) > 1: + raise CertificateError("hostname %r " + "doesn't match either of %s" + % (hostname, ', '.join(map(repr, dnsnames)))) + elif len(dnsnames) == 1: + raise CertificateError("hostname %r " + "doesn't match %r" + % (hostname, dnsnames[0])) + else: + raise CertificateError("no appropriate commonName or " + "subjectAltName fields were found") diff --git a/requests/packages/urllib3/poolmanager.py b/requests/packages/urllib3/poolmanager.py new file mode 100644 index 0000000..482ee4a --- /dev/null +++ b/requests/packages/urllib3/poolmanager.py @@ -0,0 +1,133 @@ +# urllib3/poolmanager.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + +import logging + +from ._collections import RecentlyUsedContainer +from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool +from .connectionpool import get_host, connection_from_url +from .exceptions import HostChangedError +from .request import RequestMethods + + +__all__ = ['PoolManager', 'ProxyManager', 'proxy_from_url'] + + +pool_classes_by_scheme = { + 'http': HTTPConnectionPool, + 'https': HTTPSConnectionPool, +} + +port_by_scheme = { + 'http': 80, + 'https': 443, +} + +log = logging.getLogger(__name__) + + +class PoolManager(RequestMethods): + """ + Allows for arbitrary requests while transparently keeping track of + necessary connection pools for you. + + :param num_pools: + Number of connection pools to cache before discarding the least recently + used pool. + + :param \**connection_pool_kw: + Additional parameters are used to create fresh + :class:`urllib3.connectionpool.ConnectionPool` instances. + + Example: :: + + >>> manager = PoolManager() + >>> r = manager.urlopen("http://google.com/") + >>> r = manager.urlopen("http://google.com/mail") + >>> r = manager.urlopen("http://yahoo.com/") + >>> len(r.pools) + 2 + + """ + + # TODO: Make sure there are no memory leaks here. + + def __init__(self, num_pools=10, **connection_pool_kw): + self.connection_pool_kw = connection_pool_kw + self.pools = RecentlyUsedContainer(num_pools) + + def connection_from_host(self, host, port=80, scheme='http'): + """ + Get a :class:`ConnectionPool` based on the host, port, and scheme. + + Note that an appropriate ``port`` value is required here to normalize + connection pools in our container most effectively. + """ + pool_key = (scheme, host, port) + + # If the scheme, host, or port doesn't match existing open connections, + # open a new ConnectionPool. + pool = self.pools.get(pool_key) + if pool: + return pool + + # Make a fresh ConnectionPool of the desired type + pool_cls = pool_classes_by_scheme[scheme] + pool = pool_cls(host, port, **self.connection_pool_kw) + + self.pools[pool_key] = pool + + return pool + + def connection_from_url(self, url): + """ + Similar to :func:`urllib3.connectionpool.connection_from_url` but + doesn't pass any additional parameters to the + :class:`urllib3.connectionpool.ConnectionPool` constructor. + + Additional parameters are taken from the :class:`.PoolManager` + constructor. + """ + scheme, host, port = get_host(url) + + port = port or port_by_scheme.get(scheme, 80) + + return self.connection_from_host(host, port=port, scheme=scheme) + + def urlopen(self, method, url, **kw): + """ + Same as :meth:`urllib3.connectionpool.HTTPConnectionPool.urlopen`. + + ``url`` must be absolute, such that an appropriate + :class:`urllib3.connectionpool.ConnectionPool` can be chosen for it. + """ + conn = self.connection_from_url(url) + try: + return conn.urlopen(method, url, **kw) + + except HostChangedError, e: + kw['retries'] = e.retries # Persist retries countdown + return self.urlopen(method, e.new_url, **kw) + + +class ProxyManager(RequestMethods): + """ + Given a ConnectionPool to a proxy, the ProxyManager's ``urlopen`` method + will make requests to any url through the defined proxy. + """ + + def __init__(self, proxy_pool): + self.proxy_pool = proxy_pool + + def urlopen(self, method, url, **kw): + "Same as HTTP(S)ConnectionPool.urlopen, ``url`` must be absolute." + kw['assert_same_host'] = False + return self.proxy_pool.urlopen(method, url, **kw) + + +def proxy_from_url(url, **pool_kw): + proxy_pool = connection_from_url(url, **pool_kw) + return ProxyManager(proxy_pool) diff --git a/requests/packages/urllib3/request.py b/requests/packages/urllib3/request.py new file mode 100644 index 0000000..a7e0b5d --- /dev/null +++ b/requests/packages/urllib3/request.py @@ -0,0 +1,145 @@ +# urllib3/request.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + + +from urllib import urlencode + +from .filepost import encode_multipart_formdata + + +__all__ = ['RequestMethods'] + + +class RequestMethods(object): + """ + Convenience mixin for classes who implement a :meth:`urlopen` method, such + as :class:`~urllib3.connectionpool.HTTPConnectionPool` and + :class:`~urllib3.poolmanager.PoolManager`. + + Provides behavior for making common types of HTTP request methods and + decides which type of request field encoding to use. + + Specifically, + + :meth:`.request_encode_url` is for sending requests whose fields are encoded + in the URL (such as GET, HEAD, DELETE). + + :meth:`.request_encode_body` is for sending requests whose fields are + encoded in the *body* of the request using multipart or www-orm-urlencoded + (such as for POST, PUT, PATCH). + + :meth:`.request` is for making any kind of request, it will look up the + appropriate encoding format and use one of the above two methods to make + the request. + """ + + _encode_url_methods = set(['DELETE', 'GET', 'HEAD', 'OPTIONS']) + + _encode_body_methods = set(['PATCH', 'POST', 'PUT', 'TRACE']) + + def urlopen(self, method, url, body=None, headers=None, + encode_multipart=True, multipart_boundary=None, + **kw): + raise NotImplemented("Classes extending RequestMethods must implement " + "their own ``urlopen`` method.") + + def request(self, method, url, fields=None, headers=None, **urlopen_kw): + """ + Make a request using :meth:`urlopen` with the appropriate encoding of + ``fields`` based on the ``method`` used. + + This is a convenience method that requires the least amount of manual + effort. It can be used in most situations, while still having the option + to drop down to more specific methods when necessary, such as + :meth:`request_encode_url`, :meth:`request_encode_body`, + or even the lowest level :meth:`urlopen`. + """ + method = method.upper() + + if method in self._encode_url_methods: + return self.request_encode_url(method, url, fields=fields, + headers=headers, + **urlopen_kw) + else: + return self.request_encode_body(method, url, fields=fields, + headers=headers, + **urlopen_kw) + + def request_encode_url(self, method, url, fields=None, **urlopen_kw): + """ + Make a request using :meth:`urlopen` with the ``fields`` encoded in + the url. This is useful for request methods like GET, HEAD, DELETE, etc. + """ + if fields: + url += '?' + urlencode(fields) + return self.urlopen(method, url, **urlopen_kw) + + def request_encode_body(self, method, url, fields=None, headers=None, + encode_multipart=True, multipart_boundary=None, + **urlopen_kw): + """ + Make a request using :meth:`urlopen` with the ``fields`` encoded in + the body. This is useful for request methods like POST, PUT, PATCH, etc. + + When ``encode_multipart=True`` (default), then + :meth:`urllib3.filepost.encode_multipart_formdata` is used to encode the + payload with the appropriate content type. Otherwise + :meth:`urllib.urlencode` is used with the + 'application/x-www-form-urlencoded' content type. + + Multipart encoding must be used when posting files, and it's reasonably + safe to use it in other times too. However, it may break request signing, + such as with OAuth. + + Supports an optional ``fields`` parameter of key/value strings AND + key/filetuple. A filetuple is a (filename, data) tuple. For example: :: + + fields = { + 'foo': 'bar', + 'fakefile': ('foofile.txt', 'contents of foofile'), + 'realfile': ('barfile.txt', open('realfile').read()), + 'nonamefile': ('contents of nonamefile field'), + } + + When uploading a file, providing a filename (the first parameter of the + tuple) is optional but recommended to best mimick behavior of browsers. + + Note that if ``headers`` are supplied, the 'Content-Type' header will be + overwritten because it depends on the dynamic random boundary string + which is used to compose the body of the request. The random boundary + string can be explicitly set with the ``multipart_boundary`` parameter. + """ + if encode_multipart: + body, content_type = encode_multipart_formdata(fields or {}, + boundary=multipart_boundary) + else: + body, content_type = (urlencode(fields or {}), + 'application/x-www-form-urlencoded') + + headers = headers or {} + headers.update({'Content-Type': content_type}) + + return self.urlopen(method, url, body=body, headers=headers, + **urlopen_kw) + + # Deprecated: + + def get_url(self, url, fields=None, **urlopen_kw): + """ + .. deprecated:: 1.0 + Use :meth:`request` instead. + """ + return self.request_encode_url('GET', url, fields=fields, + **urlopen_kw) + + def post_url(self, url, fields=None, headers=None, **urlopen_kw): + """ + .. deprecated:: 1.0 + Use :meth:`request` instead. + """ + return self.request_encode_body('POST', url, fields=fields, + headers=headers, + **urlopen_kw) diff --git a/requests/packages/urllib3/response.py b/requests/packages/urllib3/response.py new file mode 100644 index 0000000..ee2ff66 --- /dev/null +++ b/requests/packages/urllib3/response.py @@ -0,0 +1,195 @@ +# urllib3/response.py +# Copyright 2008-2011 Andrey Petrov and contributors (see CONTRIBUTORS.txt) +# +# This module is part of urllib3 and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php + +import gzip +import logging +import zlib + + +try: + from cStringIO import StringIO +except ImportError: + from StringIO import StringIO # pylint: disable-msg=W0404 + + +from .exceptions import HTTPError + + +log = logging.getLogger(__name__) + + +def decode_gzip(data): + gzipper = gzip.GzipFile(fileobj=StringIO(data)) + return gzipper.read() + + +def decode_deflate(data): + try: + return zlib.decompress(data) + except zlib.error: + return zlib.decompress(data, -zlib.MAX_WBITS) + + +class HTTPResponse(object): + """ + HTTP Response container. + + Backwards-compatible to httplib's HTTPResponse but the response ``body`` is + loaded and decoded on-demand when the ``data`` property is accessed. + + Extra parameters for behaviour not present in httplib.HTTPResponse: + + :param preload_content: + If True, the response's body will be preloaded during construction. + + :param decode_content: + If True, attempts to decode specific content-encoding's based on headers + (like 'gzip' and 'deflate') will be skipped and raw data will be used + instead. + + :param original_response: + When this HTTPResponse wrapper is generated from an httplib.HTTPResponse + object, it's convenient to include the original for debug purposes. It's + otherwise unused. + """ + + CONTENT_DECODERS = { + 'gzip': decode_gzip, + 'deflate': decode_deflate, + } + + def __init__(self, body='', headers=None, status=0, version=0, reason=None, + strict=0, preload_content=True, decode_content=True, + original_response=None, pool=None, connection=None): + self.headers = headers or {} + self.status = status + self.version = version + self.reason = reason + self.strict = strict + + self._decode_content = decode_content + self._body = None + self._fp = None + self._original_response = original_response + + self._pool = pool + self._connection = connection + + if hasattr(body, 'read'): + self._fp = body + + if preload_content: + self._body = self.read(decode_content=decode_content) + + def get_redirect_location(self): + """ + Should we redirect and where to? + + :returns: Truthy redirect location string if we got a redirect status + code and valid location. ``None`` if redirect status and no + location. ``False`` if not a redirect status code. + """ + if self.status in [301, 302, 303, 307]: + return self.headers.get('location') + + return False + + def release_conn(self): + if not self._pool or not self._connection: + return + + self._pool._put_conn(self._connection) + self._connection = None + + @property + def data(self): + # For backwords-compat with earlier urllib3 0.4 and earlier. + if self._body: + return self._body + + if self._fp: + return self.read(cache_content=True) + + def read(self, amt=None, decode_content=None, cache_content=False): + """ + Similar to :meth:`httplib.HTTPResponse.read`, but with two additional + parameters: ``decode_content`` and ``cache_content``. + + :param amt: + How much of the content to read. If specified, decoding and caching + is skipped because we can't decode partial content nor does it make + sense to cache partial content as the full response. + + :param decode_content: + If True, will attempt to decode the body based on the + 'content-encoding' header. (Overridden if ``amt`` is set.) + + :param cache_content: + If True, will save the returned data such that the same result is + returned despite of the state of the underlying file object. This + is useful if you want the ``.data`` property to continue working + after having ``.read()`` the file object. (Overridden if ``amt`` is + set.) + """ + content_encoding = self.headers.get('content-encoding') + decoder = self.CONTENT_DECODERS.get(content_encoding) + if decode_content is None: + decode_content = self._decode_content + + data = self._fp and self._fp.read(amt) + + try: + + if amt: + return data + + if not decode_content or not decoder: + if cache_content: + self._body = data + + return data + + try: + data = decoder(data) + except IOError: + raise HTTPError("Received response with content-encoding: %s, but " + "failed to decode it." % content_encoding) + + if cache_content: + self._body = data + + return data + + finally: + + if self._original_response and self._original_response.isclosed(): + self.release_conn() + + @classmethod + def from_httplib(ResponseCls, r, **response_kw): + """ + Given an :class:`httplib.HTTPResponse` instance ``r``, return a + corresponding :class:`urllib3.response.HTTPResponse` object. + + Remaining parameters are passed to the HTTPResponse constructor, along + with ``original_response=r``. + """ + + return ResponseCls(body=r, + headers=dict(r.getheaders()), + status=r.status, + version=r.version, + reason=r.reason, + strict=r.strict, + original_response=r, + **response_kw) + + # Backwards-compatibility methods for httplib.HTTPResponse + def getheaders(self): + return self.headers + + def getheader(self, name, default=None): + return self.headers.get(name, default) diff --git a/requests/sessions.py b/requests/sessions.py new file mode 100644 index 0000000..af9f9c7 --- /dev/null +++ b/requests/sessions.py @@ -0,0 +1,288 @@ +# -*- coding: utf-8 -*- + +""" +requests.session +~~~~~~~~~~~~~~~~ + +This module provides a Session object to manage and persist settings across +requests (cookies, auth, proxies). + +""" + +from .defaults import defaults +from .models import Request +from .hooks import dispatch_hook +from .utils import header_expand +from .packages.urllib3.poolmanager import PoolManager + + +def merge_kwargs(local_kwarg, default_kwarg): + """Merges kwarg dictionaries. + + If a local key in the dictionary is set to None, it will be removed. + """ + + if default_kwarg is None: + return local_kwarg + + if isinstance(local_kwarg, basestring): + return local_kwarg + + if local_kwarg is None: + return default_kwarg + + # Bypass if not a dictionary (e.g. timeout) + if not hasattr(default_kwarg, 'items'): + return local_kwarg + + # Update new values. + kwargs = default_kwarg.copy() + kwargs.update(local_kwarg) + + # Remove keys that are set to None. + for (k,v) in local_kwarg.items(): + if v is None: + del kwargs[k] + + return kwargs + + +class Session(object): + """A Requests session.""" + + __attrs__ = [ + 'headers', 'cookies', 'auth', 'timeout', 'proxies', 'hooks', + 'params', 'config'] + + + def __init__(self, + headers=None, + cookies=None, + auth=None, + timeout=None, + proxies=None, + hooks=None, + params=None, + config=None, + verify=True): + + self.headers = headers or {} + self.cookies = cookies or {} + self.auth = auth + self.timeout = timeout + self.proxies = proxies or {} + self.hooks = hooks or {} + self.params = params or {} + self.config = config or {} + self.verify = verify + + for (k, v) in defaults.items(): + self.config.setdefault(k, v) + + self.poolmanager = PoolManager( + num_pools=self.config.get('pool_connections'), + maxsize=self.config.get('pool_maxsize') + ) + + # Set up a CookieJar to be used by default + self.cookies = {} + + # Add passed cookies in. + if cookies is not None: + self.cookies.update(cookies) + + def __repr__(self): + return '<requests-client at 0x%x>' % (id(self)) + + def __enter__(self): + return self + + def __exit__(self, *args): + pass + + def request(self, method, url, + params=None, + data=None, + headers=None, + cookies=None, + files=None, + auth=None, + timeout=None, + allow_redirects=False, + proxies=None, + hooks=None, + return_response=True, + config=None, + prefetch=False, + verify=None): + + """Constructs and sends a :class:`Request <Request>`. + Returns :class:`Response <Response>` object. + + :param method: method for the new :class:`Request` object. + :param url: URL for the new :class:`Request` object. + :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`. + :param data: (optional) Dictionary or bytes to send in the body of the :class:`Request`. + :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`. + :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. + :param files: (optional) Dictionary of 'filename': file-like-objects for multipart encoding upload. + :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. + :param timeout: (optional) Float describing the timeout of the request. + :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed. + :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy. + :param return_response: (optional) If False, an un-sent Request object will returned. + :param config: (optional) A configuration dictionary. + :param prefetch: (optional) if ``True``, the response content will be immediately downloaded. + :param verify: (optional) if ``True``, the SSL cert will be verified. A CA_BUNDLE path can also be provided. + """ + + method = str(method).upper() + + # Default empty dicts for dict params. + cookies = {} if cookies is None else cookies + data = {} if data is None else data + files = {} if files is None else files + headers = {} if headers is None else headers + params = {} if params is None else params + hooks = {} if hooks is None else hooks + + if verify is None: + verify = self.verify + + # use session's hooks as defaults + for key, cb in self.hooks.iteritems(): + hooks.setdefault(key, cb) + + # Expand header values. + if headers: + for k, v in headers.items() or {}: + headers[k] = header_expand(v) + + args = dict( + method=method, + url=url, + data=data, + params=params, + headers=headers, + cookies=cookies, + files=files, + auth=auth, + hooks=hooks, + timeout=timeout, + allow_redirects=allow_redirects, + proxies=proxies, + config=config, + verify=verify, + _poolmanager=self.poolmanager + ) + + # Merge local kwargs with session kwargs. + for attr in self.__attrs__: + session_val = getattr(self, attr, None) + local_val = args.get(attr) + + args[attr] = merge_kwargs(local_val, session_val) + + # Arguments manipulation hook. + args = dispatch_hook('args', args['hooks'], args) + + # Create the (empty) response. + r = Request(**args) + + # Give the response some context. + r.session = self + + # Don't send if asked nicely. + if not return_response: + return r + + # Send the HTTP Request. + r.send(prefetch=prefetch) + + # Send any cookies back up the to the session. + self.cookies.update(r.response.cookies) + + # Return the response. + return r.response + + + def get(self, url, **kwargs): + """Sends a GET request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + kwargs.setdefault('allow_redirects', True) + return self.request('get', url, **kwargs) + + + def options(self, url, **kwargs): + """Sends a OPTIONS request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + kwargs.setdefault('allow_redirects', True) + return self.request('options', url, **kwargs) + + + def head(self, url, **kwargs): + """Sends a HEAD request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + kwargs.setdefault('allow_redirects', True) + return self.request('head', url, **kwargs) + + + def post(self, url, data=None, **kwargs): + """Sends a POST request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param data: (optional) Dictionary or bytes to send in the body of the :class:`Request`. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + return self.request('post', url, data=data, **kwargs) + + + def put(self, url, data=None, **kwargs): + """Sends a PUT request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param data: (optional) Dictionary or bytes to send in the body of the :class:`Request`. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + return self.request('put', url, data=data, **kwargs) + + + def patch(self, url, data=None, **kwargs): + """Sends a PATCH request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param data: (optional) Dictionary or bytes to send in the body of the :class:`Request`. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + return self.request('patch', url, data=data, **kwargs) + + + def delete(self, url, **kwargs): + """Sends a DELETE request. Returns :class:`Response` object. + + :param url: URL for the new :class:`Request` object. + :param **kwargs: Optional arguments that ``request`` takes. + """ + + return self.request('delete', url, **kwargs) + + +def session(**kwargs): + """Returns a :class:`Session` for context-management.""" + + return Session(**kwargs) diff --git a/requests/status_codes.py b/requests/status_codes.py new file mode 100644 index 0000000..fab8e95 --- /dev/null +++ b/requests/status_codes.py @@ -0,0 +1,86 @@ +# -*- coding: utf-8 -*- + +from .structures import LookupDict + +_codes = { + + # Informational. + 100: ('continue',), + 101: ('switching_protocols',), + 102: ('processing',), + 103: ('checkpoint',), + 122: ('uri_too_long', 'request_uri_too_long'), + 200: ('ok', 'okay', 'all_ok', 'all_okay', 'all_good', '\\o/'), + 201: ('created',), + 202: ('accepted',), + 203: ('non_authoritative_info', 'non_authoritative_information'), + 204: ('no_content',), + 205: ('reset_content', 'reset'), + 206: ('partial_content', 'partial'), + 207: ('multi_status', 'multiple_status', 'multi_stati', 'multiple_stati'), + 208: ('im_used',), + + # Redirection. + 300: ('multiple_choices',), + 301: ('moved_permanently', 'moved', '\\o-'), + 302: ('found',), + 303: ('see_other', 'other'), + 304: ('not_modified',), + 305: ('use_proxy',), + 306: ('switch_proxy',), + 307: ('temporary_redirect', 'temporary_moved', 'temporary'), + 308: ('resume_incomplete', 'resume'), + + # Client Error. + 400: ('bad_request', 'bad'), + 401: ('unauthorized',), + 402: ('payment_required', 'payment'), + 403: ('forbidden',), + 404: ('not_found', '-o-'), + 405: ('method_not_allowed', 'not_allowed'), + 406: ('not_acceptable',), + 407: ('proxy_authentication_required', 'proxy_auth', 'proxy_authentication'), + 408: ('request_timeout', 'timeout'), + 409: ('conflict',), + 410: ('gone',), + 411: ('length_required',), + 412: ('precondition_failed', 'precondition'), + 413: ('request_entity_too_large',), + 414: ('request_uri_too_large',), + 415: ('unsupported_media_type', 'unsupported_media', 'media_type'), + 416: ('requested_range_not_satisfiable', 'requested_range', 'range_not_satisfiable'), + 417: ('expectation_failed',), + 418: ('im_a_teapot', 'teapot', 'i_am_a_teapot'), + 422: ('unprocessable_entity', 'unprocessable'), + 423: ('locked',), + 424: ('failed_dependency', 'dependency'), + 425: ('unordered_collection', 'unordered'), + 426: ('upgrade_required', 'upgrade'), + 428: ('precondition_required', 'precondition'), + 429: ('too_many_requests', 'too_many'), + 431: ('header_fields_too_large', 'fields_too_large'), + 444: ('no_response', 'none'), + 449: ('retry_with', 'retry'), + 450: ('blocked_by_windows_parental_controls', 'parental_controls'), + 499: ('client_closed_request',), + + # Server Error. + 500: ('internal_server_error', 'server_error', '/o\\'), + 501: ('not_implemented',), + 502: ('bad_gateway',), + 503: ('service_unavailable', 'unavailable'), + 504: ('gateway_timeout',), + 505: ('http_version_not_supported', 'http_version'), + 506: ('variant_also_negotiates',), + 507: ('insufficient_storage',), + 509: ('bandwidth_limit_exceeded', 'bandwidth'), + 510: ('not_extended',), +} + +codes = LookupDict(name='status_codes') + +for (code, titles) in _codes.items(): + for title in titles: + setattr(codes, title, code) + if not title.startswith('\\'): + setattr(codes, title.upper(), code)
\ No newline at end of file diff --git a/requests/structures.py b/requests/structures.py new file mode 100644 index 0000000..35a903f --- /dev/null +++ b/requests/structures.py @@ -0,0 +1,66 @@ +# -*- coding: utf-8 -*- + +""" +requests.structures +~~~~~~~~~~~~~~~~~~~ + +Data structures that power Requests. + +""" + + +class CaseInsensitiveDict(dict): + """Case-insensitive Dictionary + + For example, ``headers['content-encoding']`` will return the + value of a ``'Content-Encoding'`` response header.""" + + @property + def lower_keys(self): + if not hasattr(self, '_lower_keys') or not self._lower_keys: + self._lower_keys = dict((k.lower(), k) for k in self.iterkeys()) + return self._lower_keys + + def _clear_lower_keys(self): + if hasattr(self, '_lower_keys'): + self._lower_keys.clear() + + def __setitem__(self, key, value): + dict.__setitem__(self, key, value) + self._clear_lower_keys() + + def __delitem__(self, key): + dict.__delitem__(self, key) + self._lower_keys.clear() + + def __contains__(self, key): + return key.lower() in self.lower_keys + + def __getitem__(self, key): + # We allow fall-through here, so values default to None + if key in self: + return dict.__getitem__(self, self.lower_keys[key.lower()]) + + def get(self, key, default=None): + if key in self: + return self[key] + else: + return default + +class LookupDict(dict): + """Dictionary lookup object.""" + + def __init__(self, name=None): + self.name = name + super(LookupDict, self).__init__() + + def __repr__(self): + return '<lookup \'%s\'>' % (self.name) + + def __getitem__(self, key): + # We allow fall-through here, so values default to None + + return self.__dict__.get(key, None) + + def get(self, key, default=None): + return self.__dict__.get(key, default)
\ No newline at end of file diff --git a/requests/utils.py b/requests/utils.py new file mode 100644 index 0000000..95dea4b --- /dev/null +++ b/requests/utils.py @@ -0,0 +1,401 @@ +# -*- coding: utf-8 -*- + +""" +requests.utils +~~~~~~~~~~~~~~ + +This module provides utility functions that are used within Requests +that are also useful for external consumption. + +""" + +import cgi +import codecs +import cookielib +import os +import random +import re +import zlib +import urllib + +from urllib2 import parse_http_list as _parse_list_header + + +def guess_filename(obj): + """Tries to guess the filename of the given object.""" + name = getattr(obj, 'name', None) + if name and name[0] != '<' and name[-1] != '>': + return name + +# From mitsuhiko/werkzeug (used with permission). +def parse_list_header(value): + """Parse lists as described by RFC 2068 Section 2. + + In particular, parse comma-separated lists where the elements of + the list may include quoted-strings. A quoted-string could + contain a comma. A non-quoted string could have quotes in the + middle. Quotes are removed automatically after parsing. + + It basically works like :func:`parse_set_header` just that items + may appear multiple times and case sensitivity is preserved. + + The return value is a standard :class:`list`: + + >>> parse_list_header('token, "quoted value"') + ['token', 'quoted value'] + + To create a header from the :class:`list` again, use the + :func:`dump_header` function. + + :param value: a string with a list header. + :return: :class:`list` + """ + result = [] + for item in _parse_list_header(value): + if item[:1] == item[-1:] == '"': + item = unquote_header_value(item[1:-1]) + result.append(item) + return result + + +# From mitsuhiko/werkzeug (used with permission). +def parse_dict_header(value): + """Parse lists of key, value pairs as described by RFC 2068 Section 2 and + convert them into a python dict: + + >>> d = parse_dict_header('foo="is a fish", bar="as well"') + >>> type(d) is dict + True + >>> sorted(d.items()) + [('bar', 'as well'), ('foo', 'is a fish')] + + If there is no value for a key it will be `None`: + + >>> parse_dict_header('key_without_value') + {'key_without_value': None} + + To create a header from the :class:`dict` again, use the + :func:`dump_header` function. + + :param value: a string with a dict header. + :return: :class:`dict` + """ + result = {} + for item in _parse_list_header(value): + if '=' not in item: + result[item] = None + continue + name, value = item.split('=', 1) + if value[:1] == value[-1:] == '"': + value = unquote_header_value(value[1:-1]) + result[name] = value + return result + + +# From mitsuhiko/werkzeug (used with permission). +def unquote_header_value(value, is_filename=False): + r"""Unquotes a header value. (Reversal of :func:`quote_header_value`). + This does not use the real unquoting but what browsers are actually + using for quoting. + + :param value: the header value to unquote. + """ + if value and value[0] == value[-1] == '"': + # this is not the real unquoting, but fixing this so that the + # RFC is met will result in bugs with internet explorer and + # probably some other browsers as well. IE for example is + # uploading files with "C:\foo\bar.txt" as filename + value = value[1:-1] + + # if this is a filename and the starting characters look like + # a UNC path, then just return the value without quotes. Using the + # replace sequence below on a UNC path has the effect of turning + # the leading double slash into a single slash and then + # _fix_ie_filename() doesn't work correctly. See #458. + if not is_filename or value[:2] != '\\\\': + return value.replace('\\\\', '\\').replace('\\"', '"') + return value + + +def header_expand(headers): + """Returns an HTTP Header value string from a dictionary. + + Example expansion:: + + {'text/x-dvi': {'q': '.8', 'mxb': '100000', 'mxt': '5.0'}, 'text/x-c': {}} + # Accept: text/x-dvi; q=.8; mxb=100000; mxt=5.0, text/x-c + + (('text/x-dvi', {'q': '.8', 'mxb': '100000', 'mxt': '5.0'}), ('text/x-c', {})) + # Accept: text/x-dvi; q=.8; mxb=100000; mxt=5.0, text/x-c + """ + + collector = [] + + if isinstance(headers, dict): + headers = headers.items() + + elif isinstance(headers, basestring): + return headers + + for i, (value, params) in enumerate(headers): + + _params = [] + + for (p_k, p_v) in params.items(): + + _params.append('%s=%s' % (p_k, p_v)) + + collector.append(value) + collector.append('; ') + + if len(params): + + collector.append('; '.join(_params)) + + if not len(headers) == i+1: + collector.append(', ') + + + # Remove trailing separators. + if collector[-1] in (', ', '; '): + del collector[-1] + + return ''.join(collector) + + + +def randombytes(n): + """Return n random bytes.""" + # Use /dev/urandom if it is available. Fall back to random module + # if not. It might be worthwhile to extend this function to use + # other platform-specific mechanisms for getting random bytes. + if os.path.exists("/dev/urandom"): + f = open("/dev/urandom") + s = f.read(n) + f.close() + return s + else: + L = [chr(random.randrange(0, 256)) for i in range(n)] + return "".join(L) + + +def dict_from_cookiejar(cj): + """Returns a key/value dictionary from a CookieJar. + + :param cj: CookieJar object to extract cookies from. + """ + + cookie_dict = {} + + for _, cookies in cj._cookies.items(): + for _, cookies in cookies.items(): + for cookie in cookies.values(): + # print cookie + cookie_dict[cookie.name] = cookie.value + + return cookie_dict + + +def cookiejar_from_dict(cookie_dict): + """Returns a CookieJar from a key/value dictionary. + + :param cookie_dict: Dict of key/values to insert into CookieJar. + """ + + # return cookiejar if one was passed in + if isinstance(cookie_dict, cookielib.CookieJar): + return cookie_dict + + # create cookiejar + cj = cookielib.CookieJar() + + cj = add_dict_to_cookiejar(cj, cookie_dict) + + return cj + + +def add_dict_to_cookiejar(cj, cookie_dict): + """Returns a CookieJar from a key/value dictionary. + + :param cj: CookieJar to insert cookies into. + :param cookie_dict: Dict of key/values to insert into CookieJar. + """ + + for k, v in cookie_dict.items(): + + cookie = cookielib.Cookie( + version=0, + name=k, + value=v, + port=None, + port_specified=False, + domain='', + domain_specified=False, + domain_initial_dot=False, + path='/', + path_specified=True, + secure=False, + expires=None, + discard=True, + comment=None, + comment_url=None, + rest={'HttpOnly': None}, + rfc2109=False + ) + + # add cookie to cookiejar + cj.set_cookie(cookie) + + return cj + + +def get_encodings_from_content(content): + """Returns encodings from given content string. + + :param content: bytestring to extract encodings from. + """ + + charset_re = re.compile(r'<meta.*?charset=["\']*(.+?)["\'>]', flags=re.I) + + return charset_re.findall(content) + + +def get_encoding_from_headers(headers): + """Returns encodings from given HTTP Header Dict. + + :param headers: dictionary to extract encoding from. + """ + + content_type = headers.get('content-type') + + if not content_type: + return None + + content_type, params = cgi.parse_header(content_type) + + if 'charset' in params: + return params['charset'].strip("'\"") + + if 'text' in content_type: + return 'ISO-8859-1' + + +def unicode_from_html(content): + """Attempts to decode an HTML string into unicode. + If unsuccessful, the original content is returned. + """ + + encodings = get_encodings_from_content(content) + + for encoding in encodings: + + try: + return unicode(content, encoding) + except (UnicodeError, TypeError): + pass + + return content + + +def stream_decode_response_unicode(iterator, r): + """Stream decodes a iterator.""" + + if r.encoding is None: + for item in iterator: + yield item + return + + decoder = codecs.getincrementaldecoder(r.encoding)(errors='replace') + for chunk in iterator: + rv = decoder.decode(chunk) + if rv: + yield rv + rv = decoder.decode('', final=True) + if rv: + yield rv + + +def get_unicode_from_response(r): + """Returns the requested content back in unicode. + + :param r: Response object to get unicode content from. + + Tried: + + 1. charset from content-type + + 2. every encodings from ``<meta ... charset=XXX>`` + + 3. fall back and replace all unicode characters + + """ + + tried_encodings = [] + + # Try charset from content-type + encoding = get_encoding_from_headers(r.headers) + + if encoding: + try: + return unicode(r.content, encoding) + except UnicodeError: + tried_encodings.append(encoding) + + # Fall back: + try: + return unicode(r.content, encoding, errors='replace') + except TypeError: + return r.content + + +def decode_gzip(content): + """Return gzip-decoded string. + + :param content: bytestring to gzip-decode. + """ + + return zlib.decompress(content, 16 + zlib.MAX_WBITS) + + +def stream_decompress(iterator, mode='gzip'): + """ + Stream decodes an iterator over compressed data + + :param iterator: An iterator over compressed data + :param mode: 'gzip' or 'deflate' + :return: An iterator over decompressed data + """ + + if mode not in ['gzip', 'deflate']: + raise ValueError('stream_decompress mode must be gzip or deflate') + + zlib_mode = 16 + zlib.MAX_WBITS if mode == 'gzip' else -zlib.MAX_WBITS + dec = zlib.decompressobj(zlib_mode) + try: + for chunk in iterator: + rv = dec.decompress(chunk) + if rv: + yield rv + except zlib.error: + # If there was an error decompressing, just return the raw chunk + yield chunk + # Continue to return the rest of the raw data + for chunk in iterator: + yield chunk + else: + # Make sure everything has been returned from the decompression object + buf = dec.decompress('') + rv = buf + dec.flush() + if rv: + yield rv + + +def requote_path(path): + """Re-quote the given URL path component. + + This function passes the given path through an unquote/quote cycle to + ensure that it is fully and consistently quoted. + """ + parts = path.split("/") + parts = (urllib.quote(urllib.unquote(part), safe="") for part in parts) + return "/".join(parts) |