cpython/Lib/urllib/parse.py at 3.15 · 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

"""Parse (absolute and relative) URLs.

urllib.parse module is based upon the following RFC specifications.

RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding

and L. Masinter, January 2005.

RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter

and L.Masinter, December 1999.

RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.

Berners-Lee, R. Fielding, and L. Masinter, August 1998.

RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zawinski, July 1998.

RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June

1995.

RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.

McCahill, December 1994

RFC 3986 is considered the current standard and any future changes to

urllib.parse module should conform with it. The urllib.parse module is

currently not entirely compliant with this RFC due to defacto

scenarios for parsing, and for backward compatibility purposes, some

parsing quirks from older RFCs are retained. The testcases in

test_urlparse.py provides a good indicator of parsing behavior.

The WHATWG URL Parser spec should also be considered. We are not compliant with

it either due to existing user code API behavior expectations (Hyrum's Law).

It serves as a useful guide when making changes.

"""

from collections import namedtuple

import functools

import math

import re

import types

import warnings

import ipaddress

__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",

"urlsplit", "urlunsplit", "urlencode", "parse_qs",

"parse_qsl", "quote", "quote_plus", "quote_from_bytes",

"unquote", "unquote_plus", "unquote_to_bytes",

"DefragResult", "ParseResult", "SplitResult",

"DefragResultBytes", "ParseResultBytes", "SplitResultBytes"]

# A classification of schemes.

# The empty string classifies URLs with no scheme specified,

# being the default value returned by “urlsplit” and “urlparse”.

uses_relative = ['', 'ftp', 'http', 'gopher', 'nntp', 'imap',

'wais', 'file', 'https', 'shttp', 'mms',

'prospero', 'rtsp', 'rtsps', 'rtspu', 'sftp',

'svn', 'svn+ssh', 'ws', 'wss']

uses_netloc = ['', 'ftp', 'http', 'gopher', 'nntp', 'telnet',

'imap', 'wais', 'file', 'mms', 'https', 'shttp',

'snews', 'prospero', 'rtsp', 'rtsps', 'rtspu', 'rsync',

'svn', 'svn+ssh', 'sftp', 'nfs', 'git', 'git+ssh',

'ws', 'wss', 'itms-services']

uses_params = ['', 'ftp', 'hdl', 'prospero', 'http', 'imap',

'https', 'shttp', 'rtsp', 'rtsps', 'rtspu', 'sip',

'sips', 'mms', 'sftp', 'tel']

# These are not actually used anymore, but should stay for backwards

# compatibility. (They are undocumented, but have a public-looking name.)

non_hierarchical = ['gopher', 'hdl', 'mailto', 'news',

'telnet', 'wais', 'imap', 'snews', 'sip', 'sips']

uses_query = ['', 'http', 'wais', 'imap', 'https', 'shttp', 'mms',

'gopher', 'rtsp', 'rtsps', 'rtspu', 'sip', 'sips']

uses_fragment = ['', 'ftp', 'hdl', 'http', 'gopher', 'news',

'nntp', 'wais', 'https', 'shttp', 'snews',

'file', 'prospero']

# Characters valid in scheme names

scheme_chars = ('abcdefghijklmnopqrstuvwxyz'

'ABCDEFGHIJKLMNOPQRSTUVWXYZ'

'0123456789'

'+-.')

# Leading and trailing C0 control and space to be stripped per WHATWG spec.

# == "".join([chr(i) for i in range(0, 0x20 + 1)])

_WHATWG_C0_CONTROL_OR_SPACE = '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f '

# Unsafe bytes to be removed per WHATWG spec

_UNSAFE_URL_BYTES_TO_REMOVE = ['\t', '\r', '\n']

def clear_cache():

"""Clear internal performance caches. Undocumented; some tests want it."""

urlsplit.cache_clear()

_byte_quoter_factory.cache_clear()

# Helpers for bytes handling

# We deliberately require applications that

# handle improperly quoted URLs to do their

# own decoding and encoding.

_implicit_encoding = 'ascii'

_implicit_errors = 'strict'

def _noop(obj):

return obj

def _encode_result(obj, encoding=_implicit_encoding,

errors=_implicit_errors):

return obj.encode(encoding, errors)

def _decode_args(args, encoding=_implicit_encoding,

errors=_implicit_errors):

return tuple(x.decode(encoding, errors) if x

else '' if x is not None

else None

for x in args)

def _coerce_args(*args):

# Invokes decode if necessary to create str args

# and returns the coerced inputs along with

# an appropriate result coercion function

# - noop for str inputs

# - encoding function otherwise

str_input = None

for arg in args:

if arg:

if str_input is None:

str_input = isinstance(arg, str)

else:

if isinstance(arg, str) != str_input:

raise TypeError("Cannot mix str and non-str arguments")

if str_input is None:

for arg in args:

if arg is not None:

str_input = isinstance(arg, str)

break

if str_input is not False:

return args + (_noop,)

return _decode_args(args) + (_encode_result,)

# Result objects are more helpful than simple tuples

class _ResultMixinStr(object):

"""Standard approach to encoding parsed results from str to bytes"""

__slots__ = ()

def encode(self, encoding='ascii', errors='strict'):

result = self._encoded_counterpart(*(x.encode(encoding, errors)

if x is not None else None

for x in self))

try:

result._keep_empty = self._keep_empty

except AttributeError:

pass

return result

class _ResultMixinBytes(object):

"""Standard approach to decoding parsed results from bytes to str"""

__slots__ = ()

def decode(self, encoding='ascii', errors='strict'):

result = self._decoded_counterpart(*(x.decode(encoding, errors)

if x is not None else None

for x in self))

try:

result._keep_empty = self._keep_empty

except AttributeError:

pass

return result

class _NetlocResultMixinBase(object):

"""Shared methods for the parsed result objects containing a netloc element"""

__slots__ = ()

@property

def username(self):

return self._userinfo[0]

@property

def password(self):

return self._userinfo[1]

@property

def hostname(self):

hostname = self._hostinfo[0]

if not hostname:

return None

# Scoped IPv6 address may have zone info, which must not be lowercased

# like http://[fe80::822a:a8ff:fe49:470c%tESt]:1234/keys

separator = '%' if isinstance(hostname, str) else b'%'

hostname, percent, zone = hostname.partition(separator)

return hostname.lower() + percent + zone

@property

def port(self):

port = self._hostinfo[1]

if port is not None:

if port.isdigit() and port.isascii():

port = int(port)

else:

raise ValueError(f"Port could not be cast to integer value as {port!r}")

if not (0 <= port <= 65535):

raise ValueError("Port out of range 0-65535")

return port

__class_getitem__ = classmethod(types.GenericAlias)

class _NetlocResultMixinStr(_NetlocResultMixinBase, _ResultMixinStr):

__slots__ = ()

@property

def _userinfo(self):

netloc = self.netloc

if netloc is None:

return None, None

userinfo, have_info, hostinfo = netloc.rpartition('@')

if have_info:

username, have_password, password = userinfo.partition(':')

if not have_password:

password = None

else:

username = password = None

return username, password

@property

def _hostinfo(self):

netloc = self.netloc

if netloc is None:

return None, None

_, _, hostinfo = netloc.rpartition('@')

_, have_open_br, bracketed = hostinfo.partition('[')

if have_open_br:

hostname, _, port = bracketed.partition(']')

_, _, port = port.partition(':')

else:

hostname, _, port = hostinfo.partition(':')

if not port:

port = None

return hostname, port

class _NetlocResultMixinBytes(_NetlocResultMixinBase, _ResultMixinBytes):

__slots__ = ()

@property

def _userinfo(self):

netloc = self.netloc

if netloc is None:

return None, None

userinfo, have_info, hostinfo = netloc.rpartition(b'@')

if have_info:

username, have_password, password = userinfo.partition(b':')

if not have_password:

password = None

else:

username = password = None

return username, password

@property

def _hostinfo(self):

netloc = self.netloc

if netloc is None:

return None, None

_, _, hostinfo = netloc.rpartition(b'@')

_, have_open_br, bracketed = hostinfo.partition(b'[')

if have_open_br:

hostname, _, port = bracketed.partition(b']')

_, _, port = port.partition(b':')

else:

hostname, _, port = hostinfo.partition(b':')

if not port:

port = None

return hostname, port

_UNSPECIFIED = sentinel("_UNSPECIFIED", repr="<not specified>")

_MISSING_AS_NONE_DEFAULT = False

class _ResultBase:

__slots__ = ()

def __replace__(self, /, **kwargs):

result = super().__replace__(**kwargs)

try:

result._keep_empty = self._keep_empty

except AttributeError:

pass

return result

def _replace(self, /, **kwargs):

result = super()._replace(**kwargs)

try:

result._keep_empty = self._keep_empty

except AttributeError:

pass

return result

def __copy__(self):

return self

def __deepcopy__(self, memo):

return self

def __getstate__(self):

state = super().__getstate__()

try:

if state[1]['_keep_empty'] == _MISSING_AS_NONE_DEFAULT:

del state[1]['_keep_empty']

if state == (None, {}):

state = None

except LookupError:

pass

return state

class _DefragResultBase(_ResultBase, namedtuple('_DefragResultBase', 'url fragment')):

__slots__ = ('_keep_empty',)

def geturl(self):

if self.fragment or (self.fragment is not None and

getattr(self, '_keep_empty', _MISSING_AS_NONE_DEFAULT)):

return self.url + self._HASH + self.fragment

else:

return self.url

class _SplitResultBase(_ResultBase, namedtuple(

'_SplitResultBase', 'scheme netloc path query fragment')):

__slots__ = ('_keep_empty',)

def geturl(self):

return urlunsplit(self)

class _ParseResultBase(_ResultBase, namedtuple(

'_ParseResultBase', 'scheme netloc path params query fragment')):

__slots__ = ('_keep_empty',)

def geturl(self):

return urlunparse(self)

_DefragResultBase.__doc__ = """

DefragResult(url, fragment)

A 2-tuple that contains the url without fragment identifier and the fragment

identifier as a separate argument.

"""

_DefragResultBase.url.__doc__ = """The URL with no fragment identifier."""

_DefragResultBase.fragment.__doc__ = """

Fragment identifier separated from URL, that allows indirect identification of a

secondary resource by reference to a primary resource and additional identifying

information.

"""

_SplitResultBase.__doc__ = """

SplitResult(scheme, netloc, path, query, fragment)

A 5-tuple that contains the different components of a URL. Similar to

ParseResult, but does not split params.

"""

_SplitResultBase.scheme.__doc__ = """Specifies URL scheme for the request."""

_SplitResultBase.netloc.__doc__ = """

Network location where the request is made to.

"""

_SplitResultBase.path.__doc__ = """

The hierarchical path, such as the path to a file to download.

"""

_SplitResultBase.query.__doc__ = """

The query component, that contains non-hierarchical data, that along with data

in path component, identifies a resource in the scope of URI's scheme and

network location.

"""

_SplitResultBase.fragment.__doc__ = """

Fragment identifier, that allows indirect identification of a secondary resource

by reference to a primary resource and additional identifying information.

"""

_ParseResultBase.__doc__ = """

ParseResult(scheme, netloc, path, params, query, fragment)

A 6-tuple that contains components of a parsed URL.

"""

_ParseResultBase.scheme.__doc__ = _SplitResultBase.scheme.__doc__

_ParseResultBase.netloc.__doc__ = _SplitResultBase.netloc.__doc__

_ParseResultBase.path.__doc__ = _SplitResultBase.path.__doc__

_ParseResultBase.params.__doc__ = """

Parameters for last path element used to dereference the URI in order to provide

access to perform some operation on the resource.

"""

_ParseResultBase.query.__doc__ = _SplitResultBase.query.__doc__

_ParseResultBase.fragment.__doc__ = _SplitResultBase.fragment.__doc__

# For backwards compatibility, alias _NetlocResultMixinStr

# ResultBase is no longer part of the documented API, but it is

# retained since deprecating it isn't worth the hassle

ResultBase = _NetlocResultMixinStr

# Structured result objects for string data

class DefragResult(_DefragResultBase, _ResultMixinStr):

__slots__ = ()

_HASH = '#'

class SplitResult(_SplitResultBase, _NetlocResultMixinStr):

__slots__ = ()

class ParseResult(_ParseResultBase, _NetlocResultMixinStr):

__slots__ = ()

# Structured result objects for bytes data

class DefragResultBytes(_DefragResultBase, _ResultMixinBytes):

__slots__ = ()

_HASH = b'#'

class SplitResultBytes(_SplitResultBase, _NetlocResultMixinBytes):

__slots__ = ()

class ParseResultBytes(_ParseResultBase, _NetlocResultMixinBytes):

__slots__ = ()

# Set up the encode/decode result pairs

def _fix_result_transcoding():

_result_pairs = (

(DefragResult, DefragResultBytes),

(SplitResult, SplitResultBytes),

(ParseResult, ParseResultBytes),

)

for _decoded, _encoded in _result_pairs:

_decoded._encoded_counterpart = _encoded

_encoded._decoded_counterpart = _decoded

_fix_result_transcoding()

del _fix_result_transcoding

def urlparse(url, scheme=None, allow_fragments=True, *, missing_as_none=_MISSING_AS_NONE_DEFAULT):

"""Parse a URL into 6 components:

The result is a named 6-tuple with fields corresponding to the

above. It is either a ParseResult or ParseResultBytes object,

depending on the type of the url parameter.

The username, password, hostname, and port sub-components of netloc

can also be accessed as attributes of the returned object.

The scheme argument provides the default value of the scheme

component when no scheme is found in url.

If allow_fragments is False, no attempt is made to separate the

fragment component from the previous component, which can be either

path or query.

Note that % escapes are not expanded.

urlsplit() should generally be used instead of urlparse().

"""

url, scheme, _coerce_result = _coerce_args(url, scheme)

if url is None:

url = ''

scheme, netloc, url, params, query, fragment = _urlparse(url, scheme, allow_fragments)

if not missing_as_none:

if scheme is None: scheme = ''

if netloc is None: netloc = ''

if params is None: params = ''

if query is None: query = ''

if fragment is None: fragment = ''

result = ParseResult(scheme, netloc, url, params, query, fragment)

result = _coerce_result(result)

result._keep_empty = missing_as_none

return result

def _urlparse(url, scheme=None, allow_fragments=True):

scheme, netloc, url, query, fragment = _urlsplit(url, scheme, allow_fragments)

if (scheme or '') in uses_params and ';' in url:

url, params = _splitparams(url, missing_as_none=True)

else:

params = None

return (scheme, netloc, url, params, query, fragment)

def _splitparams(url, missing_as_none=False):

if '/' in url:

i = url.find(';', url.rfind('/'))

if i < 0:

return url, None if missing_as_none else ''

else:

i = url.find(';')

return url[:i], url[i+1:]

def _splitnetloc(url, start=0):

delim = len(url) # position of end of domain part of url, default is end

for c in '/?#': # look for delimiters; the order is NOT important

wdelim = url.find(c, start) # find first of this delim

if wdelim >= 0: # if found

delim = min(delim, wdelim) # use earliest delim position

return url[start:delim], url[delim:] # return (domain, rest)

def _checknetloc(netloc):

if not netloc or netloc.isascii():

return

# looking for characters like \u2100 that expand to 'a/c'

# IDNA uses NFKC equivalence, so normalize for this check

import unicodedata

n = netloc.replace('@', '') # ignore characters already included

n = n.replace(':', '') # but not the surrounding text

n = n.replace('#', '')

n = n.replace('?', '')

netloc2 = unicodedata.normalize('NFKC', n)

if n == netloc2:

return

for c in '/?#@:':

if c in netloc2:

raise ValueError("netloc '" + netloc + "' contains invalid " +

"characters under NFKC normalization")

def _check_bracketed_netloc(netloc):

# Note that this function must mirror the splitting

# done in NetlocResultMixins._hostinfo().

hostname_and_port = netloc.rpartition('@')[2]

before_bracket, have_open_br, bracketed = hostname_and_port.partition('[')

if have_open_br:

# No data is allowed before a bracket.

if before_bracket:

raise ValueError("Invalid IPv6 URL")

hostname, _, port = bracketed.partition(']')

# No data is allowed after the bracket but before the port delimiter.

if port and not port.startswith(":"):

raise ValueError("Invalid IPv6 URL")

else:

hostname, _, port = hostname_and_port.partition(':')

_check_bracketed_host(hostname)

# Valid bracketed hosts are defined in

# https://www.rfc-editor.org/rfc/rfc3986#page-49 and https://url.spec.whatwg.org/

def _check_bracketed_host(hostname):

if hostname.startswith(('v', 'V')):

if not re.match(r"\A[vV][a-fA-F0-9]+\..+\z", hostname):

raise ValueError(f"IPvFuture address is invalid")

else:

ip = ipaddress.ip_address(hostname) # Throws Value Error if not IPv6 or IPv4

if isinstance(ip, ipaddress.IPv4Address):

raise ValueError(f"An IPv4 address cannot be in brackets")

# typed=True avoids BytesWarnings being emitted during cache key

# comparison since this API supports both bytes and str input.

@functools.lru_cache(typed=True)

def urlsplit(url, scheme=None, allow_fragments=True, *, missing_as_none=_MISSING_AS_NONE_DEFAULT):

"""Parse a URL into 5 components:

The result is a named 5-tuple with fields corresponding to the

above. It is either a SplitResult or SplitResultBytes object,

depending on the type of the url parameter.

The username, password, hostname, and port sub-components of netloc

can also be accessed as attributes of the returned object.

The scheme argument provides the default value of the scheme

component when no scheme is found in url.

If allow_fragments is False, no attempt is made to separate the

fragment component from the previous component, which can be either

path or query.

Note that % escapes are not expanded.

"""

url, scheme, _coerce_result = _coerce_args(url, scheme)

if url is None:

url = ''

scheme, netloc, url, query, fragment = _urlsplit(url, scheme, allow_fragments)

if not missing_as_none:

if scheme is None: scheme = ''

if netloc is None: netloc = ''

if query is None: query = ''

if fragment is None: fragment = ''

result = SplitResult(scheme, netloc, url, query, fragment)

result = _coerce_result(result)

result._keep_empty = missing_as_none

return result

def _urlsplit(url, scheme=None, allow_fragments=True):

# Only lstrip url as some applications rely on preserving trailing space.

# (https://url.spec.whatwg.org/#concept-basic-url-parser would strip both)

url = url.lstrip(_WHATWG_C0_CONTROL_OR_SPACE)

for b in _UNSAFE_URL_BYTES_TO_REMOVE:

url = url.replace(b, "")

if scheme is not None:

scheme = scheme.strip(_WHATWG_C0_CONTROL_OR_SPACE)

for b in _UNSAFE_URL_BYTES_TO_REMOVE:

scheme = scheme.replace(b, "")

allow_fragments = bool(allow_fragments)

netloc = query = fragment = None

i = url.find(':')

if i > 0 and url[0].isascii() and url[0].isalpha():

for c in url[:i]:

if c not in scheme_chars:

break

else:

scheme, url = url[:i].lower(), url[i+1:]

if url[:2] == '//':

netloc, url = _splitnetloc(url, 2)

if (('[' in netloc and ']' not in netloc) or

(']' in netloc and '[' not in netloc)):

raise ValueError("Invalid IPv6 URL")

if '[' in netloc and ']' in netloc:

_check_bracketed_netloc(netloc)

if allow_fragments and '#' in url:

url, fragment = url.split('#', 1)

if '?' in url:

url, query = url.split('?', 1)

_checknetloc(netloc)

return (scheme, netloc, url, query, fragment)

def urlunparse(components, *, keep_empty=_UNSPECIFIED):

"""Put a parsed URL back together again. This may result in a

slightly different, but equivalent URL, if the URL that was parsed

originally had redundant delimiters, e.g. a ? with an empty query

(the draft states that these are equivalent) and keep_empty is false

or components is the result of the urlparse() call with

missing_as_none=False."""

scheme, netloc, url, params, query, fragment, _coerce_result = (

_coerce_args(*components))

if keep_empty is _UNSPECIFIED:

keep_empty = getattr(components, '_keep_empty', _MISSING_AS_NONE_DEFAULT)

elif keep_empty and not getattr(components, '_keep_empty', True):

raise ValueError('Cannot distinguish between empty and not defined '

'URI components in the result of parsing URL with '

'missing_as_none=False')

if not keep_empty:

if not netloc:

if scheme and scheme in uses_netloc and (not url or url[:1] == '/'):

netloc = ''

else:

netloc = None

if not scheme: scheme = None

if not params: params = None

if not query: query = None

if not fragment: fragment = None

if params is not None:

url = "%s;%s" % (url, params)

return _coerce_result(_urlunsplit(scheme, netloc, url, query, fragment))

def urlunsplit(components, *, keep_empty=_UNSPECIFIED):

"""Combine the elements of a tuple as returned by urlsplit() into a

complete URL as a string. The data argument can be any five-item iterable.

This may result in a slightly different, but equivalent URL, if the URL that

was parsed originally had unnecessary delimiters (for example, a ? with an

empty query; the RFC states that these are equivalent) and keep_empty

is false or components is the result of the urlsplit() call with

missing_as_none=False."""

scheme, netloc, url, query, fragment, _coerce_result = (

_coerce_args(*components))

if keep_empty is _UNSPECIFIED:

keep_empty = getattr(components, '_keep_empty', _MISSING_AS_NONE_DEFAULT)

elif keep_empty and not getattr(components, '_keep_empty', True):

raise ValueError('Cannot distinguish between empty and not defined '

'URI components in the result of parsing URL with '

'missing_as_none=False')

if not keep_empty:

if not netloc:

if scheme and scheme in uses_netloc and (not url or url[:1] == '/'):

netloc = ''

else:

netloc = None

if not scheme: scheme = None

if not query: query = None

if not fragment: fragment = None

return _coerce_result(_urlunsplit(scheme, netloc, url, query, fragment))

def _urlunsplit(scheme, netloc, url, query, fragment):

if netloc is not None:

if url and url[:1] != '/': url = '/' + url

url = '//' + netloc + url

elif url[:2] == '//':

url = '//' + url

if scheme:

url = scheme + ':' + url

if query is not None:

url = url + '?' + query

if fragment is not None:

url = url + '#' + fragment

return url

def urljoin(base, url, allow_fragments=True):

"""Join a base URL and a possibly relative URL to form an absolute

interpretation of the latter."""

if not base:

return url

if not url:

return base

base, url, _coerce_result = _coerce_args(base, url)

bscheme, bnetloc, bpath, bquery, bfragment = \

_urlsplit(base, None, allow_fragments)

scheme, netloc, path, query, fragment = \

_urlsplit(url, None, allow_fragments)

if scheme is None:

scheme = bscheme

if scheme != bscheme or (scheme and scheme not in uses_relative):

return _coerce_result(url)

if not scheme or scheme in uses_netloc:

if netloc:

return _coerce_result(_urlunsplit(scheme, netloc, path,

query, fragment))

netloc = bnetloc

if not path:

path = bpath

if query is None:

query = bquery

if fragment is None:

fragment = bfragment

return _coerce_result(_urlunsplit(scheme, netloc, path,

query, fragment))

base_parts = bpath.split('/')

if base_parts[-1] != '':

# the last item is not a directory, so will not be taken into account

# in resolving the relative path

del base_parts[-1]

# for rfc3986, ignore all base path should the first character be root.

if path[:1] == '/':

segments = path.split('/')

else:

segments = base_parts + path.split('/')

# filter out elements that would cause redundant slashes on re-joining

# the resolved_path

segments[1:-1] = filter(None, segments[1:-1])

resolved_path = []

for seg in segments:

if seg == '..':

try:

resolved_path.pop()

except IndexError:

# ignore any .. segments that would otherwise cause an IndexError

# when popped from resolved_path if resolving for rfc3986

pass

elif seg == '.':

continue

else:

resolved_path.append(seg)

if segments[-1] in ('.', '..'):

# do some post-processing here. if the last segment was a relative dir,

# then we need to append the trailing '/'

resolved_path.append('')

return _coerce_result(_urlunsplit(scheme, netloc, '/'.join(

resolved_path) or '/', query, fragment))

def urldefrag(url, *, missing_as_none=_MISSING_AS_NONE_DEFAULT):

"""Removes any existing fragment from URL.

Returns a tuple of the defragmented URL and the fragment. If

the URL contained no fragments, the second element is the

empty string or None if missing_as_none is True.

"""

url, _coerce_result = _coerce_args(url)

if '#' in url:

s, n, p, q, frag = _urlsplit(url)

defrag = _urlunsplit(s, n, p, q, None)

else:

frag = None

defrag = url

if not missing_as_none and frag is None: frag = ''

result = _coerce_result(DefragResult(defrag, frag))

result._keep_empty = missing_as_none

return result

_hexdig = '0123456789ABCDEFabcdef'

_hextobyte = None

def unquote_to_bytes(string):

"""unquote_to_bytes('abc%20def') -> b'abc def'."""

return bytes(_unquote_impl(string))

def _unquote_impl(string: bytes | bytearray | str) -> bytes | bytearray:

# Note: strings are encoded as UTF-8. This is only an issue if it contains

# unescaped non-ASCII characters, which URIs should not.

if not string:

# Is it a string-like object?

string.split

return b''

if isinstance(string, str):

string = string.encode('utf-8')

bits = string.split(b'%')

if len(bits) == 1:

return string

res = bytearray(bits[0])

append = res.extend

# Delay the initialization of the table to not waste memory

# if the function is never called

global _hextobyte

if _hextobyte is None:

_hextobyte = {(a + b).encode(): bytes.fromhex(a + b)

for a in _hexdig for b in _hexdig}

for item in bits[1:]:

try:

append(_hextobyte[item[:2]])

append(item[2:])

except KeyError:

append(b'%')

append(item)

return res

_asciire = re.compile('([\x00-\x7f]+)')

def _generate_unquoted_parts(string, encoding, errors):

previous_match_end = 0

for ascii_match in _asciire.finditer(string):

start, end = ascii_match.span()

yield string[previous_match_end:start] # Non-ASCII

# The ascii_match[1] group == string[start:end].

yield _unquote_impl(ascii_match[1]).decode(encoding, errors)

previous_match_end = end

yield string[previous_match_end:] # Non-ASCII tail

def unquote(string, encoding='utf-8', errors='replace'):

"""Replace %xx escapes by their single-character equivalent. The optional

encoding and errors parameters specify how to decode percent-encoded

sequences into Unicode characters, as accepted by the bytes.decode()

method.

By default, percent-encoded sequences are decoded with UTF-8, and invalid

sequences are replaced by a placeholder character.

unquote('abc%20def') -> 'abc def'.

"""

if isinstance(string, bytes):

return _unquote_impl(string).decode(encoding, errors)

if '%' not in string:

# Is it a string-like object?

string.split

return string

if encoding is None:

encoding = 'utf-8'

if errors is None:

errors = 'replace'

return ''.join(_generate_unquoted_parts(string, encoding, errors))

def parse_qs(qs, keep_blank_values=False, strict_parsing=False,

encoding='utf-8', errors='replace', max_num_fields=None, separator='&'):

"""Parse a query given as a string argument.

Arguments:

qs: percent-encoded query string to be parsed

keep_blank_values: flag indicating whether blank values in

percent-encoded queries should be treated as blank strings.

A true value indicates that blanks should be retained as

blank strings. The default false value indicates that

blank values are to be ignored and treated as if they were

not included.

strict_parsing: flag indicating what to do with parsing errors.

If false (the default), errors are silently ignored.

If true, errors raise a ValueError exception.

encoding and errors: specify how to decode percent-encoded sequences

into Unicode characters, as accepted by the bytes.decode() method.

max_num_fields: int. If set, then throws a ValueError if there

are more than n fields read by parse_qsl().

separator: str. The symbol to use for separating the query arguments.

Defaults to &.

Returns a dictionary.

"""

parsed_result = {}

pairs = parse_qsl(qs, keep_blank_values, strict_parsing,

encoding=encoding, errors=errors,

max_num_fields=max_num_fields, separator=separator,

_stacklevel=2)

for name, value in pairs:

if name in parsed_result:

parsed_result[name].append(value)

else:

parsed_result[name] = [value]

return parsed_result

def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,

encoding='utf-8', errors='replace', max_num_fields=None, separator='&', *, _stacklevel=1):

"""Parse a query given as a string argument.

Arguments:

qs: percent-encoded query string to be parsed

keep_blank_values: flag indicating whether blank values in

percent-encoded queries should be treated as blank strings.

A true value indicates that blanks should be retained as blank

strings. The default false value indicates that blank values

are to be ignored and treated as if they were not included.

strict_parsing: flag indicating what to do with parsing errors. If

false (the default), errors are silently ignored. If true,

errors raise a ValueError exception.

encoding and errors: specify how to decode percent-encoded sequences

into Unicode characters, as accepted by the bytes.decode() method.

max_num_fields: int. If set, then throws a ValueError

if there are more than n fields read by parse_qsl().

separator: str. The symbol to use for separating the query arguments.

Defaults to &.

Returns a list, as G-d intended.

"""

if not separator or not isinstance(separator, (str, bytes)):

raise ValueError("Separator must be of type string or bytes.")

if isinstance(qs, str):

if not isinstance(separator, str):

separator = str(separator, 'ascii')

eq = '='

def _unquote(s):

return unquote_plus(s, encoding=encoding, errors=errors)

elif qs is None:

return []

else:

try:

# Use memoryview() to reject integers and iterables,

# acceptable by the bytes constructor.

qs = bytes(memoryview(qs))

except TypeError:

if not qs:

warnings.warn(f"Accepting {type(qs).__name__} objects with "

f"false value in urllib.parse.parse_qsl() is "

f"deprecated as of 3.14",

DeprecationWarning, stacklevel=_stacklevel + 1)

return []

raise

if isinstance(separator, str):

separator = bytes(separator, 'ascii')

eq = b'='

def _unquote(s):

return unquote_to_bytes(s.replace(b'+', b' '))

if not qs:

return []

# If max_num_fields is defined then check that the number of fields

# is less than max_num_fields. This prevents a memory exhaustion DOS

# attack via post bodies with many fields.

if max_num_fields is not None:

num_fields = 1 + qs.count(separator)

if max_num_fields < num_fields:

raise ValueError('Max number of fields exceeded')

r = []

for name_value in qs.split(separator):

if name_value or strict_parsing:

name, has_eq, value = name_value.partition(eq)

if not has_eq and strict_parsing:

raise ValueError("bad query field: %r" % (name_value,))

if value or keep_blank_values:

name = _unquote(name)

value = _unquote(value)

r.append((name, value))

return r

def unquote_plus(string, encoding='utf-8', errors='replace'):

"""Like unquote(), but also replace plus signs by spaces, as required for

unquoting HTML form values.

unquote_plus('%7e/abc+def') -> '~/abc def'

"""

string = string.replace('+', ' ')

return unquote(string, encoding, errors)

_ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ'

b'abcdefghijklmnopqrstuvwxyz'

b'0123456789'

b'_.-~')

_ALWAYS_SAFE_BYTES = bytes(_ALWAYS_SAFE)

class _Quoter(dict):

"""A mapping from bytes numbers (in range(0,256)) to strings.

View remainder of file in raw view

cpython/Lib/urllib/parse.py at 3.15 · python/cpython · GitHub

Repository navigation

Expand file tree

Breadcrumbs

parse.py

Latest commit

History

Breadcrumbs

parse.py

File metadata and controls