/usr/share/pyshared/atom/http_core.py is in python-gdata 2.0.14-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 | #!/usr/bin/env python
#
# Copyright (C) 2009 Google Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# This module is used for version 2 of the Google Data APIs.
# TODO: add proxy handling.
__author__ = 'j.s@google.com (Jeff Scudder)'
import os
import StringIO
import urlparse
import urllib
import httplib
ssl = None
try:
import ssl
except ImportError:
pass
class Error(Exception):
pass
class UnknownSize(Error):
pass
class ProxyError(Error):
pass
MIME_BOUNDARY = 'END_OF_PART'
def get_headers(http_response):
"""Retrieves all HTTP headers from an HTTP response from the server.
This method is provided for backwards compatibility for Python2.2 and 2.3.
The httplib.HTTPResponse object in 2.2 and 2.3 does not have a getheaders
method so this function will use getheaders if available, but if not it
will retrieve a few using getheader.
"""
if hasattr(http_response, 'getheaders'):
return http_response.getheaders()
else:
headers = []
for header in (
'location', 'content-type', 'content-length', 'age', 'allow',
'cache-control', 'content-location', 'content-encoding', 'date',
'etag', 'expires', 'last-modified', 'pragma', 'server',
'set-cookie', 'transfer-encoding', 'vary', 'via', 'warning',
'www-authenticate', 'gdata-version'):
value = http_response.getheader(header, None)
if value is not None:
headers.append((header, value))
return headers
class HttpRequest(object):
"""Contains all of the parameters for an HTTP 1.1 request.
The HTTP headers are represented by a dictionary, and it is the
responsibility of the user to ensure that duplicate field names are combined
into one header value according to the rules in section 4.2 of RFC 2616.
"""
method = None
uri = None
def __init__(self, uri=None, method=None, headers=None):
"""Construct an HTTP request.
Args:
uri: The full path or partial path as a Uri object or a string.
method: The HTTP method for the request, examples include 'GET', 'POST',
etc.
headers: dict of strings The HTTP headers to include in the request.
"""
self.headers = headers or {}
self._body_parts = []
if method is not None:
self.method = method
if isinstance(uri, (str, unicode)):
uri = Uri.parse_uri(uri)
self.uri = uri or Uri()
def add_body_part(self, data, mime_type, size=None):
"""Adds data to the HTTP request body.
If more than one part is added, this is assumed to be a mime-multipart
request. This method is designed to create MIME 1.0 requests as specified
in RFC 1341.
Args:
data: str or a file-like object containing a part of the request body.
mime_type: str The MIME type describing the data
size: int Required if the data is a file like object. If the data is a
string, the size is calculated so this parameter is ignored.
"""
if isinstance(data, str):
size = len(data)
if size is None:
# TODO: support chunked transfer if some of the body is of unknown size.
raise UnknownSize('Each part of the body must have a known size.')
if 'Content-Length' in self.headers:
content_length = int(self.headers['Content-Length'])
else:
content_length = 0
# If this is the first part added to the body, then this is not a multipart
# request.
if len(self._body_parts) == 0:
self.headers['Content-Type'] = mime_type
content_length = size
self._body_parts.append(data)
elif len(self._body_parts) == 1:
# This is the first member in a mime-multipart request, so change the
# _body_parts list to indicate a multipart payload.
self._body_parts.insert(0, 'Media multipart posting')
boundary_string = '\r\n--%s\r\n' % (MIME_BOUNDARY,)
content_length += len(boundary_string) + size
self._body_parts.insert(1, boundary_string)
content_length += len('Media multipart posting')
# Put the content type of the first part of the body into the multipart
# payload.
original_type_string = 'Content-Type: %s\r\n\r\n' % (
self.headers['Content-Type'],)
self._body_parts.insert(2, original_type_string)
content_length += len(original_type_string)
boundary_string = '\r\n--%s\r\n' % (MIME_BOUNDARY,)
self._body_parts.append(boundary_string)
content_length += len(boundary_string)
# Change the headers to indicate this is now a mime multipart request.
self.headers['Content-Type'] = 'multipart/related; boundary="%s"' % (
MIME_BOUNDARY,)
self.headers['MIME-version'] = '1.0'
# Include the mime type of this part.
type_string = 'Content-Type: %s\r\n\r\n' % (mime_type)
self._body_parts.append(type_string)
content_length += len(type_string)
self._body_parts.append(data)
ending_boundary_string = '\r\n--%s--' % (MIME_BOUNDARY,)
self._body_parts.append(ending_boundary_string)
content_length += len(ending_boundary_string)
else:
# This is a mime multipart request.
boundary_string = '\r\n--%s\r\n' % (MIME_BOUNDARY,)
self._body_parts.insert(-1, boundary_string)
content_length += len(boundary_string) + size
# Include the mime type of this part.
type_string = 'Content-Type: %s\r\n\r\n' % (mime_type)
self._body_parts.insert(-1, type_string)
content_length += len(type_string)
self._body_parts.insert(-1, data)
self.headers['Content-Length'] = str(content_length)
# I could add an "append_to_body_part" method as well.
AddBodyPart = add_body_part
def add_form_inputs(self, form_data,
mime_type='application/x-www-form-urlencoded'):
"""Form-encodes and adds data to the request body.
Args:
form_data: dict or sequnce or two member tuples which contains the
form keys and values.
mime_type: str The MIME type of the form data being sent. Defaults
to 'application/x-www-form-urlencoded'.
"""
body = urllib.urlencode(form_data)
self.add_body_part(body, mime_type)
AddFormInputs = add_form_inputs
def _copy(self):
"""Creates a deep copy of this request."""
copied_uri = Uri(self.uri.scheme, self.uri.host, self.uri.port,
self.uri.path, self.uri.query.copy())
new_request = HttpRequest(uri=copied_uri, method=self.method,
headers=self.headers.copy())
new_request._body_parts = self._body_parts[:]
return new_request
def _dump(self):
"""Converts to a printable string for debugging purposes.
In order to preserve the request, it does not read from file-like objects
in the body.
"""
output = 'HTTP Request\n method: %s\n url: %s\n headers:\n' % (
self.method, str(self.uri))
for header, value in self.headers.iteritems():
output += ' %s: %s\n' % (header, value)
output += ' body sections:\n'
i = 0
for part in self._body_parts:
if isinstance(part, (str, unicode)):
output += ' %s: %s\n' % (i, part)
else:
output += ' %s: <file like object>\n' % i
i += 1
return output
def _apply_defaults(http_request):
if http_request.uri.scheme is None:
if http_request.uri.port == 443:
http_request.uri.scheme = 'https'
else:
http_request.uri.scheme = 'http'
class Uri(object):
"""A URI as used in HTTP 1.1"""
scheme = None
host = None
port = None
path = None
def __init__(self, scheme=None, host=None, port=None, path=None, query=None):
"""Constructor for a URI.
Args:
scheme: str This is usually 'http' or 'https'.
host: str The host name or IP address of the desired server.
post: int The server's port number.
path: str The path of the resource following the host. This begins with
a /, example: '/calendar/feeds/default/allcalendars/full'
query: dict of strings The URL query parameters. The keys and values are
both escaped so this dict should contain the unescaped values.
For example {'my key': 'val', 'second': '!!!'} will become
'?my+key=val&second=%21%21%21' which is appended to the path.
"""
self.query = query or {}
if scheme is not None:
self.scheme = scheme
if host is not None:
self.host = host
if port is not None:
self.port = port
if path:
self.path = path
def _get_query_string(self):
param_pairs = []
for key, value in self.query.iteritems():
param_pairs.append('='.join((urllib.quote_plus(key),
urllib.quote_plus(str(value)))))
return '&'.join(param_pairs)
def _get_relative_path(self):
"""Returns the path with the query parameters escaped and appended."""
param_string = self._get_query_string()
if self.path is None:
path = '/'
else:
path = self.path
if param_string:
return '?'.join([path, param_string])
else:
return path
def _to_string(self):
if self.scheme is None and self.port == 443:
scheme = 'https'
elif self.scheme is None:
scheme = 'http'
else:
scheme = self.scheme
if self.path is None:
path = '/'
else:
path = self.path
if self.port is None:
return '%s://%s%s' % (scheme, self.host, self._get_relative_path())
else:
return '%s://%s:%s%s' % (scheme, self.host, str(self.port),
self._get_relative_path())
def __str__(self):
return self._to_string()
def modify_request(self, http_request=None):
"""Sets HTTP request components based on the URI."""
if http_request is None:
http_request = HttpRequest()
if http_request.uri is None:
http_request.uri = Uri()
# Determine the correct scheme.
if self.scheme:
http_request.uri.scheme = self.scheme
if self.port:
http_request.uri.port = self.port
if self.host:
http_request.uri.host = self.host
# Set the relative uri path
if self.path:
http_request.uri.path = self.path
if self.query:
http_request.uri.query = self.query.copy()
return http_request
ModifyRequest = modify_request
def parse_uri(uri_string):
"""Creates a Uri object which corresponds to the URI string.
This method can accept partial URIs, but it will leave missing
members of the Uri unset.
"""
parts = urlparse.urlparse(uri_string)
uri = Uri()
if parts[0]:
uri.scheme = parts[0]
if parts[1]:
host_parts = parts[1].split(':')
if host_parts[0]:
uri.host = host_parts[0]
if len(host_parts) > 1:
uri.port = int(host_parts[1])
if parts[2]:
uri.path = parts[2]
if parts[4]:
param_pairs = parts[4].split('&')
for pair in param_pairs:
pair_parts = pair.split('=')
if len(pair_parts) > 1:
uri.query[urllib.unquote_plus(pair_parts[0])] = (
urllib.unquote_plus(pair_parts[1]))
elif len(pair_parts) == 1:
uri.query[urllib.unquote_plus(pair_parts[0])] = None
return uri
parse_uri = staticmethod(parse_uri)
ParseUri = parse_uri
parse_uri = Uri.parse_uri
ParseUri = Uri.parse_uri
class HttpResponse(object):
status = None
reason = None
_body = None
def __init__(self, status=None, reason=None, headers=None, body=None):
self._headers = headers or {}
if status is not None:
self.status = status
if reason is not None:
self.reason = reason
if body is not None:
if hasattr(body, 'read'):
self._body = body
else:
self._body = StringIO.StringIO(body)
def getheader(self, name, default=None):
if name in self._headers:
return self._headers[name]
else:
return default
def getheaders(self):
return self._headers
def read(self, amt=None):
if self._body is None:
return None
if not amt:
return self._body.read()
else:
return self._body.read(amt)
def _dump_response(http_response):
"""Converts to a string for printing debug messages.
Does not read the body since that may consume the content.
"""
output = 'HttpResponse\n status: %s\n reason: %s\n headers:' % (
http_response.status, http_response.reason)
headers = get_headers(http_response)
if isinstance(headers, dict):
for header, value in headers.iteritems():
output += ' %s: %s\n' % (header, value)
else:
for pair in headers:
output += ' %s: %s\n' % (pair[0], pair[1])
return output
class HttpClient(object):
"""Performs HTTP requests using httplib."""
debug = None
def request(self, http_request):
return self._http_request(http_request.method, http_request.uri,
http_request.headers, http_request._body_parts)
Request = request
def _get_connection(self, uri, headers=None):
"""Opens a socket connection to the server to set up an HTTP request.
Args:
uri: The full URL for the request as a Uri object.
headers: A dict of string pairs containing the HTTP headers for the
request.
"""
connection = None
if uri.scheme == 'https':
if not uri.port:
connection = httplib.HTTPSConnection(uri.host)
else:
connection = httplib.HTTPSConnection(uri.host, int(uri.port))
else:
if not uri.port:
connection = httplib.HTTPConnection(uri.host)
else:
connection = httplib.HTTPConnection(uri.host, int(uri.port))
return connection
def _http_request(self, method, uri, headers=None, body_parts=None):
"""Makes an HTTP request using httplib.
Args:
method: str example: 'GET', 'POST', 'PUT', 'DELETE', etc.
uri: str or atom.http_core.Uri
headers: dict of strings mapping to strings which will be sent as HTTP
headers in the request.
body_parts: list of strings, objects with a read method, or objects
which can be converted to strings using str. Each of these
will be sent in order as the body of the HTTP request.
"""
if isinstance(uri, (str, unicode)):
uri = Uri.parse_uri(uri)
connection = self._get_connection(uri, headers=headers)
if self.debug:
connection.debuglevel = 1
if connection.host != uri.host:
connection.putrequest(method, str(uri))
else:
connection.putrequest(method, uri._get_relative_path())
# Overcome a bug in Python 2.4 and 2.5
# httplib.HTTPConnection.putrequest adding
# HTTP request header 'Host: www.google.com:443' instead of
# 'Host: www.google.com', and thus resulting the error message
# 'Token invalid - AuthSub token has wrong scope' in the HTTP response.
if (uri.scheme == 'https' and int(uri.port or 443) == 443 and
hasattr(connection, '_buffer') and
isinstance(connection._buffer, list)):
header_line = 'Host: %s:443' % uri.host
replacement_header_line = 'Host: %s' % uri.host
try:
connection._buffer[connection._buffer.index(header_line)] = (
replacement_header_line)
except ValueError: # header_line missing from connection._buffer
pass
# Send the HTTP headers.
for header_name, value in headers.iteritems():
connection.putheader(header_name, value)
connection.endheaders()
# If there is data, send it in the request.
if body_parts:
for part in body_parts:
_send_data_part(part, connection)
# Return the HTTP Response from the server.
return connection.getresponse()
def _send_data_part(data, connection):
if isinstance(data, (str, unicode)):
# I might want to just allow str, not unicode.
connection.send(data)
return
# Check to see if data is a file-like object that has a read method.
elif hasattr(data, 'read'):
# Read the file and send it a chunk at a time.
while 1:
binarydata = data.read(100000)
if binarydata == '': break
connection.send(binarydata)
return
else:
# The data object was not a file.
# Try to convert to a string and send the data.
connection.send(str(data))
return
class ProxiedHttpClient(HttpClient):
def _get_connection(self, uri, headers=None):
# Check to see if there are proxy settings required for this request.
proxy = None
if uri.scheme == 'https':
proxy = os.environ.get('https_proxy')
elif uri.scheme == 'http':
proxy = os.environ.get('http_proxy')
if not proxy:
return HttpClient._get_connection(self, uri, headers=headers)
# Now we have the URL of the appropriate proxy server.
# Get a username and password for the proxy if required.
proxy_auth = _get_proxy_auth()
if uri.scheme == 'https':
import socket
if proxy_auth:
proxy_auth = 'Proxy-authorization: %s' % proxy_auth
# Construct the proxy connect command.
port = uri.port
if not port:
port = 443
proxy_connect = 'CONNECT %s:%s HTTP/1.0\r\n' % (uri.host, port)
# Set the user agent to send to the proxy
user_agent = ''
if headers and 'User-Agent' in headers:
user_agent = 'User-Agent: %s\r\n' % (headers['User-Agent'])
proxy_pieces = '%s%s%s\r\n' % (proxy_connect, proxy_auth, user_agent)
# Find the proxy host and port.
proxy_uri = Uri.parse_uri(proxy)
if not proxy_uri.port:
proxy_uri.port = '80'
# Connect to the proxy server, very simple recv and error checking
p_sock = socket.socket(socket.AF_INET,socket.SOCK_STREAM)
p_sock.connect((proxy_uri.host, int(proxy_uri.port)))
p_sock.sendall(proxy_pieces)
response = ''
# Wait for the full response.
while response.find("\r\n\r\n") == -1:
response += p_sock.recv(8192)
p_status = response.split()[1]
if p_status != str(200):
raise ProxyError('Error status=%s' % str(p_status))
# Trivial setup for ssl socket.
sslobj = None
if ssl is not None:
sslobj = ssl.wrap_socket(p_sock, None, None)
else:
sock_ssl = socket.ssl(p_sock, None, Nonesock_)
sslobj = httplib.FakeSocket(p_sock, sock_ssl)
# Initalize httplib and replace with the proxy socket.
connection = httplib.HTTPConnection(proxy_uri.host)
connection.sock = sslobj
return connection
elif uri.scheme == 'http':
proxy_uri = Uri.parse_uri(proxy)
if not proxy_uri.port:
proxy_uri.port = '80'
if proxy_auth:
headers['Proxy-Authorization'] = proxy_auth.strip()
return httplib.HTTPConnection(proxy_uri.host, int(proxy_uri.port))
return None
def _get_proxy_auth():
import base64
proxy_username = os.environ.get('proxy-username')
if not proxy_username:
proxy_username = os.environ.get('proxy_username')
proxy_password = os.environ.get('proxy-password')
if not proxy_password:
proxy_password = os.environ.get('proxy_password')
if proxy_username:
user_auth = base64.b64encode('%s:%s' % (proxy_username,
proxy_password))
return 'Basic %s\r\n' % (user_auth.strip())
else:
return ''
|