cpython/Lib/urllib/request.py at main · python/cpython · GitHub

Repository navigation

History

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

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

656

657

658

659

660

661

662

663

664

665

666

667

668

669

670

671

672

673

674

675

676

677

678

679

680

681

682

683

684

685

686

687

688

689

690

691

692

693

694

695

696

697

698

699

700

701

702

703

704

705

706

707

708

709

710

711

712

713

714

715

716

717

718

719

720

721

722

723

724

725

726

727

728

729

730

731

732

733

734

735

736

737

738

739

740

741

742

743

744

745

746

747

748

749

750

751

752

753

754

755

756

757

758

759

760

761

762

763

764

765

766

767

768

769

770

771

772

773

774

775

776

777

778

779

780

781

782

783

784

785

786

787

788

789

790

791

792

793

794

795

796

797

798

799

800

801

802

803

804

805

806

807

808

809

810

811

812

813

814

815

816

817

818

819

820

821

822

823

824

825

826

827

828

829

830

831

832

833

834

835

836

837

838

839

840

841

842

843

844

845

846

847

848

849

850

851

852

853

854

855

856

857

858

859

860

861

862

863

864

865

866

867

868

869

870

871

872

873

874

875

876

877

878

879

880

881

882

883

884

885

886

887

888

889

890

891

892

893

894

895

896

897

898

899

900

901

902

903

904

905

906

907

908

909

910

911

912

913

914

915

916

917

918

919

920

921

922

923

924

925

926

927

928

929

930

931

932

933

934

935

936

937

938

939

940

941

942

943

944

945

946

947

948

949

950

951

952

953

954

955

956

957

958

959

960

961

962

963

964

965

966

967

968

969

970

971

972

973

974

975

976

977

978

979

980

981

982

983

984

985

986

987

988

989

990

991

992

993

994

995

996

997

998

999

1000

"""An extensible library for opening URLs using a variety of protocols

The simplest way to use this module is to call the urlopen function,

which accepts a string containing a URL or a Request object (described

below). It opens the URL and returns the results as file-like

object; the returned object has some extra methods described below.

The OpenerDirector manages a collection of Handler objects that do

all the actual work. Each Handler implements a particular protocol or

option. The OpenerDirector is a composite object that invokes the

Handlers needed to open the requested URL. For example, the

HTTPHandler performs HTTP GET and POST requests and deals with

non-error returns. The HTTPRedirectHandler automatically deals with

HTTP 301, 302, 303, 307, and 308 redirect errors, and the

HTTPDigestAuthHandler deals with digest authentication.

urlopen(url, data=None) -- Basic usage is the same as original

urllib. pass the url and optionally data to post to an HTTP URL, and

get a file-like object back. One difference is that you can also pass

a Request instance instead of URL. Raises a URLError (subclass of

OSError); for HTTP errors, raises an HTTPError, which can also be

treated as a valid response.

build_opener -- Function that creates a new OpenerDirector instance.

Will install the default handlers. Accepts one or more Handlers as

arguments, either instances or Handler classes that it will

instantiate. If one of the argument is a subclass of the default

handler, the argument will be installed instead of the default.

install_opener -- Installs a new opener as the default opener.

objects of interest:

OpenerDirector -- Sets up the User Agent as the Python-urllib client and manages

the Handler classes, while dealing with requests and responses.

Request -- An object that encapsulates the state of a request. The

state can be as simple as the URL. It can also include extra HTTP

headers, e.g. a User-Agent.

BaseHandler --

internals:

BaseHandler and parent

_call_chain conventions

Example usage:

import urllib.request

# set up authentication info

authinfo = urllib.request.HTTPBasicAuthHandler()

authinfo.add_password(realm='PDQ Application',

uri='https://mahler:8092/site-updates.py',

user='klem',

passwd='geheim$parole')

proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})

# build a new opener that adds authentication and caching FTP handlers

opener = urllib.request.build_opener(proxy_support, authinfo,

urllib.request.CacheFTPHandler)

# install it

urllib.request.install_opener(opener)

f = urllib.request.urlopen('https://www.python.org/')

"""

# XXX issues:

# If an authentication error handler that tries to perform

# authentication for some reason but fails, how should the error be

# signalled? The client needs to know the HTTP error code. But if

# the handler knows that the problem was, e.g., that it didn't know

# that hash algo that requested in the challenge, it would be good to

# pass that information along to the client, too.

# ftp errors aren't handled cleanly

# check digest against correct (i.e. non-apache) implementation

# Possible extensions:

# complex proxies XXX not sure what exactly was meant by this

# abstract factory for opener

import base64

import bisect

import contextlib

import email

import hashlib

import http.client

import io

import os

import re

import socket

import string

import sys

import time

import tempfile

from urllib.error import URLError, HTTPError, ContentTooShortError

from urllib.parse import (

urlparse, urlsplit, urljoin, unwrap, quote, unquote,

_splittype, _splithost, _splitport, _splituser, _splitpasswd,

_splitattr, _splitvalue, _splittag,

unquote_to_bytes, urlunparse)

from urllib.response import addinfourl, addclosehook

# check for SSL

try:

import ssl # noqa: F401

except ImportError:

_have_ssl = False

else:

_have_ssl = True

__all__ = [

# Classes

'Request', 'OpenerDirector', 'BaseHandler', 'HTTPDefaultErrorHandler',

'HTTPRedirectHandler', 'HTTPCookieProcessor', 'ProxyHandler',

'HTTPPasswordMgr', 'HTTPPasswordMgrWithDefaultRealm',

'HTTPPasswordMgrWithPriorAuth', 'AbstractBasicAuthHandler',

'HTTPBasicAuthHandler', 'ProxyBasicAuthHandler', 'AbstractDigestAuthHandler',

'HTTPDigestAuthHandler', 'ProxyDigestAuthHandler', 'HTTPHandler',

'FileHandler', 'FTPHandler', 'CacheFTPHandler', 'DataHandler',

'UnknownHandler', 'HTTPErrorProcessor',

# Functions

'urlopen', 'install_opener', 'build_opener',

'pathname2url', 'url2pathname', 'getproxies',

# Legacy interface

'urlretrieve', 'urlcleanup',

]

# used in User-Agent header sent

__version__ = '%d.%d' % sys.version_info[:2]

_opener = None

def urlopen(url, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,

*, context=None):

'''Open the URL url, which can be either a string or a Request object.

*data* must be an object specifying additional data to be sent to

the server, or None if no such data is needed. See Request for

details.

urllib.request module uses HTTP/1.1 and includes a "Connection:close"

header in its HTTP requests.

The optional *timeout* parameter specifies a timeout in seconds for

blocking operations like the connection attempt (if not specified, the

global default timeout setting will be used). This only works for HTTP,

HTTPS and FTP connections.

If *context* is specified, it must be a ssl.SSLContext instance describing

the various SSL options. See HTTPSConnection for more details.

This function always returns an object which can work as a

context manager and has the properties url, headers, and status.

See urllib.response.addinfourl for more detail on these properties.

For HTTP and HTTPS URLs, this function returns a http.client.HTTPResponse

object slightly modified. In addition to the three new methods above, the

msg attribute contains the same information as the reason attribute ---

the reason phrase returned by the server --- instead of the response

headers as it is specified in the documentation for HTTPResponse.

For FTP, file, and data URLs, this function returns a

urllib.response.addinfourl object.

Note that None may be returned if no handler handles the request (though

the default installed global OpenerDirector uses UnknownHandler to ensure

this never happens).

In addition, if proxy settings are detected (for example, when a *_proxy

environment variable like http_proxy is set), ProxyHandler is default

installed and makes sure the requests are handled through the proxy.

'''

global _opener

if context:

https_handler = HTTPSHandler(context=context)

opener = build_opener(https_handler)

elif _opener is None:

_opener = opener = build_opener()

else:

opener = _opener

return opener.open(url, data, timeout)

def install_opener(opener):

global _opener

_opener = opener

_url_tempfiles = []

def urlretrieve(url, filename=None, reporthook=None, data=None):

"""

Retrieve a URL into a temporary location on disk.

Requires a URL argument. If a filename is passed, it is used as

the temporary file location. The reporthook argument should be

a callable that accepts a block number, a read size, and the

total file size of the URL target. The data argument should be

valid URL encoded data.

If a filename is passed and the URL points to a local resource,

the result is a copy from local file to new file.

Returns a tuple containing the path to the newly created

data file as well as the resulting HTTPMessage object.

"""

url_type, path = _splittype(url)

with contextlib.closing(urlopen(url, data)) as fp:

headers = fp.info()

# Just return the local path and the "headers" for file://

# URLs. No sense in performing a copy unless requested.

if url_type == "file" and not filename:

return os.path.normpath(path), headers

# Handle temporary file setup.

if filename:

tfp = open(filename, 'wb')

else:

tfp = tempfile.NamedTemporaryFile(delete=False)

filename = tfp.name

_url_tempfiles.append(filename)

with tfp:

result = filename, headers

bs = 1024*8

size = -1

read = 0

blocknum = 0

if "content-length" in headers:

size = int(headers["Content-Length"])

if reporthook:

reporthook(blocknum, bs, size)

while block := fp.read(bs):

read += len(block)

tfp.write(block)

blocknum += 1

if reporthook:

reporthook(blocknum, bs, size)

if size >= 0 and read < size:

raise ContentTooShortError(

"retrieval incomplete: got only %i out of %i bytes"

% (read, size), result)

return result

def urlcleanup():

"""Clean up temporary files from urlretrieve calls."""

for temp_file in _url_tempfiles:

try:

os.unlink(temp_file)

except OSError:

pass

del _url_tempfiles[:]

global _opener

if _opener:

_opener = None

# copied from cookielib.py

_cut_port_re = re.compile(r":\d+$", re.ASCII)

def request_host(request):

"""Return request-host, as defined by RFC 2965.

Variation from RFC: returned value is lowercased, for convenient

comparison.

"""

url = request.full_url

host = urlparse(url).netloc

if host == "":

host = request.get_header("Host", "")

# remove port, if present

host = _cut_port_re.sub("", host, 1)

return host.lower()

class Request:

def __init__(self, url, data=None, headers={},

origin_req_host=None, unverifiable=False,

method=None):

self.full_url = url

self.headers = {}

self.unredirected_hdrs = {}

self._data = None

self.data = data

self._tunnel_host = None

for key, value in headers.items():

self.add_header(key, value)

if origin_req_host is None:

origin_req_host = request_host(self)

self.origin_req_host = origin_req_host

self.unverifiable = unverifiable

if method:

self.method = method

@property

def full_url(self):

if self.fragment:

return '{}#{}'.format(self._full_url, self.fragment)

return self._full_url

@full_url.setter

def full_url(self, url):

# unwrap('<URL:type://host/path>') --> 'type://host/path'

self._full_url = unwrap(url)

self._full_url, self.fragment = _splittag(self._full_url)

self._parse()

@full_url.deleter

def full_url(self):

self._full_url = None

self.fragment = None

self.selector = ''

@property

def data(self):

return self._data

@data.setter

def data(self, data):

if data != self._data:

self._data = data

# issue 16464

# if we change data we need to remove content-length header

# (cause it's most probably calculated for previous value)

if self.has_header("Content-length"):

self.remove_header("Content-length")

@data.deleter

def data(self):

self.data = None

def _parse(self):

self.type, rest = _splittype(self._full_url)

if self.type is None:

raise ValueError("unknown url type: %r" % self.full_url)

self.host, self.selector = _splithost(rest)

if self.host:

self.host = unquote(self.host)

def get_method(self):

"""Return a string indicating the HTTP request method."""

default_method = "POST" if self.data is not None else "GET"

return getattr(self, 'method', default_method)

def get_full_url(self):

return self.full_url

def set_proxy(self, host, type):

if self.type == 'https' and not self._tunnel_host:

self._tunnel_host = self.host

else:

self.type= type

self.selector = self.full_url

self.host = host

def has_proxy(self):

return self.selector == self.full_url

def add_header(self, key, val):

# useful for something like authentication

self.headers[key.capitalize()] = val

def add_unredirected_header(self, key, val):

# will not be added to a redirected request

self.unredirected_hdrs[key.capitalize()] = val

def has_header(self, header_name):

return (header_name in self.headers or

header_name in self.unredirected_hdrs)

def get_header(self, header_name, default=None):

return self.headers.get(

header_name,

self.unredirected_hdrs.get(header_name, default))

def remove_header(self, header_name):

self.headers.pop(header_name, None)

self.unredirected_hdrs.pop(header_name, None)

def header_items(self):

hdrs = {**self.unredirected_hdrs, **self.headers}

return list(hdrs.items())

class OpenerDirector:

def __init__(self):

client_version = "Python-urllib/%s" % __version__

self.addheaders = [('User-agent', client_version)]

# self.handlers is retained only for backward compatibility

self.handlers = []

# manage the individual handlers

self.handle_open = {}

self.handle_error = {}

self.process_response = {}

self.process_request = {}

def add_handler(self, handler):

if not hasattr(handler, "add_parent"):

raise TypeError("expected BaseHandler instance, got %r" %

type(handler))

added = False

for meth in dir(handler):

if meth in ["redirect_request", "do_open", "proxy_open"]:

# oops, coincidental match

continue

i = meth.find("_")

if i < 1:

continue

protocol = meth[:i]

condition = meth[i+1:]

if condition.startswith("error"):

j = condition.find("_") + i + 1

kind = meth[j+1:]

try:

kind = int(kind)

except ValueError:

pass

lookup = self.handle_error.get(protocol, {})

self.handle_error[protocol] = lookup

elif condition == "open":

kind = protocol

lookup = self.handle_open

elif condition == "response":

kind = protocol

lookup = self.process_response

elif condition == "request":

kind = protocol

lookup = self.process_request

else:

continue

handlers = lookup.setdefault(kind, [])

if handlers:

bisect.insort(handlers, handler)

else:

handlers.append(handler)

added = True

if added:

bisect.insort(self.handlers, handler)

handler.add_parent(self)

def close(self):

# Only exists for backwards compatibility.

pass

def _call_chain(self, chain, kind, meth_name, *args):

# Handlers raise an exception if no one else should try to handle

# the request, or return None if they can't but another handler

# could. Otherwise, they return the response.

handlers = chain.get(kind, ())

for handler in handlers:

func = getattr(handler, meth_name)

result = func(*args)

if result is not None:

return result

def open(self, fullurl, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT):

# accept a URL or a Request object

if isinstance(fullurl, str):

req = Request(fullurl, data)

else:

req = fullurl

if data is not None:

req.data = data

req.timeout = timeout

protocol = req.type

# pre-process request

meth_name = protocol+"_request"

for processor in self.process_request.get(protocol, []):

meth = getattr(processor, meth_name)

req = meth(req)

sys.audit('urllib.Request', req.full_url, req.data, req.headers, req.get_method())

response = self._open(req, data)

# post-process response

meth_name = protocol+"_response"

for processor in self.process_response.get(protocol, []):

meth = getattr(processor, meth_name)

response = meth(req, response)

return response

def _open(self, req, data=None):

result = self._call_chain(self.handle_open, 'default',

'default_open', req)

if result:

return result

protocol = req.type

result = self._call_chain(self.handle_open, protocol, protocol +

'_open', req)

if result:

return result

return self._call_chain(self.handle_open, 'unknown',

'unknown_open', req)

def error(self, proto, *args):

if proto in ('http', 'https'):

# XXX http[s] protocols are special-cased

dict = self.handle_error['http'] # https is not different than http

proto = args[2] # YUCK!

meth_name = 'http_error_%s' % proto

http_err = 1

orig_args = args

else:

dict = self.handle_error

meth_name = proto + '_error'

http_err = 0

args = (dict, proto, meth_name) + args

result = self._call_chain(*args)

if result:

return result

if http_err:

args = (dict, 'default', 'http_error_default') + orig_args

return self._call_chain(*args)

# XXX probably also want an abstract factory that knows when it makes

# sense to skip a superclass in favor of a subclass and when it might

# make sense to include both

def build_opener(*handlers):

"""Create an opener object from a list of handlers.

The opener will use several default handlers, including support

for HTTP, FTP and when applicable HTTPS.

If any of the handlers passed as arguments are subclasses of the

default handlers, the default handlers will not be used.

"""

opener = OpenerDirector()

default_classes = [ProxyHandler, UnknownHandler, HTTPHandler,

HTTPDefaultErrorHandler, HTTPRedirectHandler,

FTPHandler, FileHandler, HTTPErrorProcessor,

DataHandler]

if hasattr(http.client, "HTTPSConnection"):

default_classes.append(HTTPSHandler)

skip = set()

for klass in default_classes:

for check in handlers:

if isinstance(check, type):

if issubclass(check, klass):

skip.add(klass)

elif isinstance(check, klass):

skip.add(klass)

for klass in skip:

default_classes.remove(klass)

for klass in default_classes:

opener.add_handler(klass())

for h in handlers:

if isinstance(h, type):

h = h()

opener.add_handler(h)

return opener

class BaseHandler:

handler_order = 500

def add_parent(self, parent):

self.parent = parent

def close(self):

# Only exists for backwards compatibility

pass

def __lt__(self, other):

if not hasattr(other, "handler_order"):

# Try to preserve the old behavior of having custom classes

# inserted after default ones (works only for custom user

# classes which are not aware of handler_order).

return True

return self.handler_order < other.handler_order

class HTTPErrorProcessor(BaseHandler):

"""Process HTTP error responses."""

handler_order = 1000 # after all other processing

def http_response(self, request, response):

code, msg, hdrs = response.code, response.msg, response.info()

# According to RFC 2616, "2xx" code indicates that the client's

# request was successfully received, understood, and accepted.

if not (200 <= code < 300):

response = self.parent.error(

'http', request, response, code, msg, hdrs)

return response

https_response = http_response

class HTTPDefaultErrorHandler(BaseHandler):

def http_error_default(self, req, fp, code, msg, hdrs):

raise HTTPError(req.full_url, code, msg, hdrs, fp)

class HTTPRedirectHandler(BaseHandler):

# maximum number of redirections to any single URL

# this is needed because of the state that cookies introduce

max_repeats = 4

# maximum total number of redirections (regardless of URL) before

# assuming we're in a loop

max_redirections = 10

def redirect_request(self, req, fp, code, msg, headers, newurl):

"""Return a Request or None in response to a redirect.

This is called by the http_error_30x methods when a

redirection response is received. If a redirection should

take place, return a new Request to allow http_error_30x to

perform the redirect. Otherwise, raise HTTPError if no-one

else should try to handle this url. Return None if you can't

but another Handler might.

"""

m = req.get_method()

if (not (code in (301, 302, 303, 307, 308) and m in ("GET", "HEAD")

or code in (301, 302, 303) and m == "POST")):

raise HTTPError(req.full_url, code, msg, headers, fp)

# Strictly (according to RFC 2616), 301 or 302 in response to

# a POST MUST NOT cause a redirection without confirmation

# from the user (of urllib.request, in this case). In practice,

# essentially all clients do redirect in this case, so we do

# the same.

# Be conciliant with URIs containing a space. This is mainly

# redundant with the more complete encoding done in http_error_302(),

# but it is kept for compatibility with other callers.

newurl = newurl.replace(' ', '%20')

CONTENT_HEADERS = ("content-length", "content-type")

newheaders = {k: v for k, v in req.headers.items()

if k.lower() not in CONTENT_HEADERS}

return Request(newurl,

method="HEAD" if m == "HEAD" else "GET",

headers=newheaders,

origin_req_host=req.origin_req_host,

unverifiable=True)

# Implementation note: To avoid the server sending us into an

# infinite loop, the request object needs to track what URLs we

# have already seen. Do this by adding a handler-specific

# attribute to the Request object.

def http_error_302(self, req, fp, code, msg, headers):

# Some servers (incorrectly) return multiple Location headers

# (so probably same goes for URI). Use first header.

if "location" in headers:

newurl = headers["location"]

elif "uri" in headers:

newurl = headers["uri"]

else:

return

# fix a possible malformed URL

urlparts = urlparse(newurl)

# For security reasons we don't allow redirection to anything other

# than http, https or ftp.

if urlparts.scheme not in ('http', 'https', 'ftp', ''):

raise HTTPError(

newurl, code,

"%s - Redirection to url '%s' is not allowed" % (msg, newurl),

headers, fp)

if not urlparts.path and urlparts.netloc:

urlparts = list(urlparts)

urlparts[2] = "/"

newurl = urlunparse(urlparts)

# http.client.parse_headers() decodes as ISO-8859-1. Recover the

# original bytes and percent-encode non-ASCII bytes, and any special

# characters such as the space.

newurl = quote(

newurl, encoding="iso-8859-1", safe=string.punctuation)

newurl = urljoin(req.full_url, newurl)

# XXX Probably want to forget about the state of the current

# request, although that might interact poorly with other

# handlers that also use handler-specific request attributes

new = self.redirect_request(req, fp, code, msg, headers, newurl)

if new is None:

return

# loop detection

# .redirect_dict has a key url if url was previously visited.

if hasattr(req, 'redirect_dict'):

visited = new.redirect_dict = req.redirect_dict

if (visited.get(newurl, 0) >= self.max_repeats or

len(visited) >= self.max_redirections):

raise HTTPError(req.full_url, code,

self.inf_msg + msg, headers, fp)

else:

visited = new.redirect_dict = req.redirect_dict = {}

visited[newurl] = visited.get(newurl, 0) + 1

# Don't close the fp until we are sure that we won't use it

# with HTTPError.

fp.read()

fp.close()

return self.parent.open(new, timeout=req.timeout)

http_error_301 = http_error_303 = http_error_307 = http_error_308 = http_error_302

inf_msg = "The HTTP server returned a redirect error that would " \

"lead to an infinite loop.\n" \

"The last 30x error message was:\n"

def _parse_proxy(proxy):

"""Return (scheme, user, password, host/port) given a URL or an authority.

If a URL is supplied, it must have an authority (host:port) component.

According to RFC 3986, having an authority component means the URL must

have two slashes after the scheme.

"""

scheme, r_scheme = _splittype(proxy)

if not r_scheme.startswith("/"):

# authority

scheme = None

authority = proxy

else:

# URL

if not r_scheme.startswith("//"):

raise ValueError("proxy URL with no authority: %r" % proxy)

# We have an authority, so for RFC 3986-compliant URLs (by ss 3.

# and 3.3.), path is empty or starts with '/'

if '@' in r_scheme:

host_separator = r_scheme.find('@')

end = r_scheme.find("/", host_separator)

else:

end = r_scheme.find("/", 2)

if end == -1:

end = None

authority = r_scheme[2:end]

userinfo, hostport = _splituser(authority)

if userinfo is not None:

user, password = _splitpasswd(userinfo)

else:

user = password = None

return scheme, user, password, hostport

class ProxyHandler(BaseHandler):

# Proxies must be in front

handler_order = 100

def __init__(self, proxies=None):

if proxies is None:

proxies = getproxies()

assert hasattr(proxies, 'keys'), "proxies must be a mapping"

self.proxies = proxies

for type, url in proxies.items():

type = type.lower()

setattr(self, '%s_open' % type,

lambda r, proxy=url, type=type, meth=self.proxy_open:

meth(r, proxy, type))

def proxy_open(self, req, proxy, type):

orig_type = req.type

proxy_type, user, password, hostport = _parse_proxy(proxy)

if proxy_type is None:

proxy_type = orig_type

if req.host and proxy_bypass(req.host):

return None

if user and password:

user_pass = '%s:%s' % (unquote(user),

unquote(password))

creds = base64.b64encode(user_pass.encode()).decode("ascii")

req.add_header('Proxy-authorization', 'Basic ' + creds)

hostport = unquote(hostport)

req.set_proxy(hostport, proxy_type)

if orig_type == proxy_type or orig_type == 'https':

# let other handlers take care of it

return None

else:

# need to start over, because the other handlers don't

# grok the proxy's URL type

# e.g. if we have a constructor arg proxies like so:

# {'http': 'ftp://proxy.example.com'}, we may end up turning

# a request for http://acme.example.com/a into one for

# ftp://proxy.example.com/a

return self.parent.open(req, timeout=req.timeout)

class HTTPPasswordMgr:

def __init__(self):

self.passwd = {}

def add_password(self, realm, uri, user, passwd):

# uri could be a single URI or a sequence

if isinstance(uri, str):

uri = [uri]

if realm not in self.passwd:

self.passwd[realm] = {}

for default_port in True, False:

reduced_uri = tuple(

self._reduce_uri_with_scheme(u, default_port) for u in uri)

self.passwd[realm][reduced_uri] = (user, passwd)

def find_user_password(self, realm, authuri):

domains = self.passwd.get(realm, {})

for default_port in True, False:

reduced_authuri = self._reduce_uri_with_scheme(

authuri, default_port)

for uris, authinfo in domains.items():

for uri in uris:

if self._is_suburi_with_scheme(uri, reduced_authuri):

return authinfo

return None, None

def reduce_uri(self, uri, default_port=True):

"""Accept authority or URI and extract only the authority and path."""

# note HTTP URLs do not have a userinfo component

parts = urlsplit(uri)

if parts.netloc:

# URI

scheme = parts.scheme

authority = parts.netloc

path = parts.path or '/'

else:

# host or host:port

scheme = None

authority = uri

path = '/'

host, port = _splitport(authority)

if default_port and port is None and scheme is not None:

dport = {"http": 80,

"https": 443,

}.get(scheme)

if dport is not None:

authority = "%s:%d" % (host, dport)

return authority, path

def _reduce_uri_with_scheme(self, uri, default_port=True):

parts = urlsplit(uri)

scheme = parts[0] if parts[1] else None

return (scheme or None, *self.reduce_uri(uri, default_port))

def _is_suburi_with_scheme(self, base, test):

if (base[0] is not None and test[0] is not None and

base[0] != test[0]):

return False

return self.is_suburi(base[1:], test[1:])

def is_suburi(self, base, test):

"""Check if test is below base in a URI tree

Both args must be URIs in reduced form.

"""

if base == test:

return True

if base[0] != test[0]:

return False

prefix = base[1]

if prefix[-1:] != '/':

prefix += '/'

return test[1].startswith(prefix)

class HTTPPasswordMgrWithDefaultRealm(HTTPPasswordMgr):

def find_user_password(self, realm, authuri):

user, password = HTTPPasswordMgr.find_user_password(self, realm,

authuri)

if user is not None:

return user, password

return HTTPPasswordMgr.find_user_password(self, None, authuri)

class HTTPPasswordMgrWithPriorAuth(HTTPPasswordMgrWithDefaultRealm):

def __init__(self):

self.authenticated = {}

super().__init__()

def add_password(self, realm, uri, user, passwd, is_authenticated=False):

self.update_authenticated(uri, is_authenticated)

# Add a default for prior auth requests

if realm is not None:

super().add_password(None, uri, user, passwd)

super().add_password(realm, uri, user, passwd)

def update_authenticated(self, uri, is_authenticated=False):

# uri could be a single URI or a sequence

if isinstance(uri, str):

uri = [uri]

for default_port in True, False:

for u in uri:

reduced_uri = self._reduce_uri_with_scheme(u, default_port)

self.authenticated[reduced_uri] = is_authenticated

def is_authenticated(self, authuri):

for default_port in True, False:

reduced_authuri = self._reduce_uri_with_scheme(

authuri, default_port)

for uri in self.authenticated:

if self._is_suburi_with_scheme(uri, reduced_authuri):

return self.authenticated[uri]

class AbstractBasicAuthHandler:

# XXX this allows for multiple auth-schemes, but will stupidly pick

# the last one with a realm specified.

# allow for double- and single-quoted realm values

# (single quotes are a violation of the RFC, but appear in the wild)

rx = re.compile('(?:^|,)' # start of the string or ','

'[ \t]*' # optional whitespaces

'([^ \t,]+)' # scheme like "Basic"

'[ \t]+' # mandatory whitespaces

# realm=xxx

# realm='xxx'

# realm="xxx"

'realm=(["\']?)([^"\']*)\\2',

re.I)

# XXX could pre-emptively send auth info already accepted (RFC 2617,

# end of section 2, and section 1.2 immediately after "credentials"

# production).

def __init__(self, password_mgr=None):

if password_mgr is None:

password_mgr = HTTPPasswordMgr()

self.passwd = password_mgr

self.add_password = self.passwd.add_password

def _parse_realm(self, header):

# parse WWW-Authenticate header: accept multiple challenges per header

found_challenge = False

for mo in AbstractBasicAuthHandler.rx.finditer(header):

scheme, quote, realm = mo.groups()

if quote not in ['"', "'"]:

import warnings

warnings.warn("Basic Auth Realm was unquoted",

UserWarning, 3)

yield (scheme, realm)

found_challenge = True

if not found_challenge:

if header:

scheme = header.split()[0]

else:

scheme = ''

yield (scheme, None)

def http_error_auth_reqed(self, authreq, host, req, headers):

# host may be an authority (without userinfo) or a URL with an

# authority

headers = headers.get_all(authreq)

if not headers:

# no header found

return

unsupported = None

for header in headers:

for scheme, realm in self._parse_realm(header):

if scheme.lower() != 'basic':

unsupported = scheme

continue

if realm is not None:

# Use the first matching Basic challenge.

# Ignore following challenges even if they use the Basic

# scheme.

return self.retry_http_basic_auth(host, req, realm)

if unsupported is not None:

raise ValueError("AbstractBasicAuthHandler does not "

"support the following scheme: %r"

% (scheme,))

def retry_http_basic_auth(self, host, req, realm):

user, pw = self.passwd.find_user_password(realm, host)

if pw is not None:

raw = "%s:%s" % (user, pw)

View remainder of file in raw view

cpython/Lib/urllib/request.py at main · python/cpython · GitHub

Repository navigation

Expand file tree

Breadcrumbs

request.py

Latest commit

History

Breadcrumbs

request.py

File metadata and controls