aboutsummaryrefslogtreecommitdiff
path: root/requests/utils.py
blob: 68e50cf0a9646d1d941b3d5d453ff0cb0280e509 (plain)
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
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
# -*- 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 collections
import io
import os
import platform
import re
import sys
import socket
import struct

from . import __version__
from . import certs
from .compat import parse_http_list as _parse_list_header
from .compat import (quote, urlparse, bytes, str, OrderedDict, unquote, is_py2,
                     builtin_str, getproxies, proxy_bypass, urlunparse)
from .cookies import RequestsCookieJar, cookiejar_from_dict
from .structures import CaseInsensitiveDict
from .exceptions import InvalidURL

_hush_pyflakes = (RequestsCookieJar,)

NETRC_FILES = ('.netrc', '_netrc')

DEFAULT_CA_BUNDLE_PATH = certs.where()


def dict_to_sequence(d):
    """Returns an internal sequence dictionary update."""

    if hasattr(d, 'items'):
        d = d.items()

    return d


def super_len(o):
    if hasattr(o, '__len__'):
        return len(o)

    if hasattr(o, 'len'):
        return o.len

    if hasattr(o, 'fileno'):
        try:
            fileno = o.fileno()
        except io.UnsupportedOperation:
            pass
        else:
            return os.fstat(fileno).st_size

    if hasattr(o, 'getvalue'):
        # e.g. BytesIO, cStringIO.StringIO
        return len(o.getvalue())


def get_netrc_auth(url):
    """Returns the Requests tuple auth for a given url from netrc."""

    try:
        from netrc import netrc, NetrcParseError

        netrc_path = None

        for f in NETRC_FILES:
            try:
                loc = os.path.expanduser('~/{0}'.format(f))
            except KeyError:
                # os.path.expanduser can fail when $HOME is undefined and
                # getpwuid fails. See http://bugs.python.org/issue20164 &
                # https://github.com/kennethreitz/requests/issues/1846
                return

            if os.path.exists(loc):
                netrc_path = loc
                break

        # Abort early if there isn't one.
        if netrc_path is None:
            return

        ri = urlparse(url)

        # Strip port numbers from netloc
        host = ri.netloc.split(':')[0]

        try:
            _netrc = netrc(netrc_path).authenticators(host)
            if _netrc:
                # Return with login / password
                login_i = (0 if _netrc[0] else 1)
                return (_netrc[login_i], _netrc[2])
        except (NetrcParseError, IOError):
            # If there was a parsing error or a permissions issue reading the file,
            # we'll just skip netrc auth
            pass

    # AppEngine hackiness.
    except (ImportError, AttributeError):
        pass


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 os.path.basename(name)


def from_key_val_list(value):
    """Take an object and test to see if it can be represented as a
    dictionary. Unless it can not be represented as such, return an
    OrderedDict, e.g.,

    ::

        >>> from_key_val_list([('key', 'val')])
        OrderedDict([('key', 'val')])
        >>> from_key_val_list('string')
        ValueError: need more than 1 value to unpack
        >>> from_key_val_list({'key': 'val'})
        OrderedDict([('key', 'val')])
    """
    if value is None:
        return None

    if isinstance(value, (str, bytes, bool, int)):
        raise ValueError('cannot encode objects that are not 2-tuples')

    return OrderedDict(value)


def to_key_val_list(value):
    """Take an object and test to see if it can be represented as a
    dictionary. If it can be, return a list of tuples, e.g.,

    ::

        >>> to_key_val_list([('key', 'val')])
        [('key', 'val')]
        >>> to_key_val_list({'key': 'val'})
        [('key', 'val')]
        >>> to_key_val_list('string')
        ValueError: cannot encode objects that are not 2-tuples.
    """
    if value is None:
        return None

    if isinstance(value, (str, bytes, bool, int)):
        raise ValueError('cannot encode objects that are not 2-tuples')

    if isinstance(value, collections.Mapping):
        value = value.items()

    return list(value)


# 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 dict_from_cookiejar(cj):
    """Returns a key/value dictionary from a CookieJar.

    :param cj: CookieJar object to extract cookies from.
    """

    cookie_dict = {}

    for cookie in cj:
        cookie_dict[cookie.name] = cookie.value

    return cookie_dict


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.
    """

    cj2 = cookiejar_from_dict(cookie_dict)
    cj.update(cj2)
    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)
    pragma_re = re.compile(r'<meta.*?content=["\']*;?charset=(.+?)["\'>]', flags=re.I)
    xml_re = re.compile(r'^<\?xml.*?encoding=["\']*(.+?)["\'>]')

    return (charset_re.findall(content) +
            pragma_re.findall(content) +
            xml_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 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(b'', final=True)
    if rv:
        yield rv


def iter_slices(string, slice_length):
    """Iterate over slices of a string."""
    pos = 0
    while pos < len(string):
        yield string[pos:pos + slice_length]
        pos += slice_length


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 str(r.content, encoding)
        except UnicodeError:
            tried_encodings.append(encoding)

    # Fall back:
    try:
        return str(r.content, encoding, errors='replace')
    except TypeError:
        return r.content


# The unreserved URI characters (RFC 3986)
UNRESERVED_SET = frozenset(
    "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
    + "0123456789-._~")


def unquote_unreserved(uri):
    """Un-escape any percent-escape sequences in a URI that are unreserved
    characters. This leaves all reserved, illegal and non-ASCII bytes encoded.
    """
    parts = uri.split('%')
    for i in range(1, len(parts)):
        h = parts[i][0:2]
        if len(h) == 2 and h.isalnum():
            try:
                c = chr(int(h, 16))
            except ValueError:
                raise InvalidURL("Invalid percent-escape sequence: '%s'" % h)

            if c in UNRESERVED_SET:
                parts[i] = c + parts[i][2:]
            else:
                parts[i] = '%' + parts[i]
        else:
            parts[i] = '%' + parts[i]
    return ''.join(parts)


def requote_uri(uri):
    """Re-quote the given URI.

    This function passes the given URI through an unquote/quote cycle to
    ensure that it is fully and consistently quoted.
    """
    # Unquote only the unreserved characters
    # Then quote only illegal characters (do not quote reserved, unreserved,
    # or '%')
    return quote(unquote_unreserved(uri), safe="!#$%&'()*+,/:;=?@[]~")


def address_in_network(ip, net):
    """
    This function allows you to check if on IP belongs to a network subnet
    Example: returns True if ip = 192.168.1.1 and net = 192.168.1.0/24
             returns False if ip = 192.168.1.1 and net = 192.168.100.0/24
    """
    ipaddr = struct.unpack('=L', socket.inet_aton(ip))[0]
    netaddr, bits = net.split('/')
    netmask = struct.unpack('=L', socket.inet_aton(dotted_netmask(int(bits))))[0]
    network = struct.unpack('=L', socket.inet_aton(netaddr))[0] & netmask
    return (ipaddr & netmask) == (network & netmask)


def dotted_netmask(mask):
    """
    Converts mask from /xx format to xxx.xxx.xxx.xxx
    Example: if mask is 24 function returns 255.255.255.0
    """
    bits = 0xffffffff ^ (1 << 32 - mask) - 1
    return socket.inet_ntoa(struct.pack('>I', bits))


def is_ipv4_address(string_ip):
    try:
        socket.inet_aton(string_ip)
    except socket.error:
        return False
    return True


def is_valid_cidr(string_network):
    """Very simple check of the cidr format in no_proxy variable"""
    if string_network.count('/') == 1:
        try:
            mask = int(string_network.split('/')[1])
        except ValueError:
            return False

        if mask < 1 or mask > 32:
            return False

        try:
            socket.inet_aton(string_network.split('/')[0])
        except socket.error:
            return False
    else:
        return False
    return True


def should_bypass_proxies(url):
    """
    Returns whether we should bypass proxies or not.
    """
    get_proxy = lambda k: os.environ.get(k) or os.environ.get(k.upper())

    # First check whether no_proxy is defined. If it is, check that the URL
    # we're getting isn't in the no_proxy list.
    no_proxy = get_proxy('no_proxy')
    netloc = urlparse(url).netloc

    if no_proxy:
        # We need to check whether we match here. We need to see if we match
        # the end of the netloc, both with and without the port.
        no_proxy = no_proxy.replace(' ', '').split(',')

        ip = netloc.split(':')[0]
        if is_ipv4_address(ip):
            for proxy_ip in no_proxy:
                if is_valid_cidr(proxy_ip):
                    if address_in_network(ip, proxy_ip):
                        return True
        else:
            for host in no_proxy:
                if netloc.endswith(host) or netloc.split(':')[0].endswith(host):
                    # The URL does match something in no_proxy, so we don't want
                    # to apply the proxies on this URL.
                    return True

    # If the system proxy settings indicate that this URL should be bypassed,
    # don't proxy.
    # The proxy_bypass function is incredibly buggy on OS X in early versions
    # of Python 2.6, so allow this call to fail. Only catch the specific
    # exceptions we've seen, though: this call failing in other ways can reveal
    # legitimate problems.
    try:
        bypass = proxy_bypass(netloc)
    except (TypeError, socket.gaierror):
        bypass = False

    if bypass:
        return True

    return False

def get_environ_proxies(url):
    """Return a dict of environment proxies."""
    if should_bypass_proxies(url):
        return {}
    else:
        return getproxies()


def default_user_agent(name="python-requests"):
    """Return a string representing the default user agent."""
    _implementation = platform.python_implementation()

    if _implementation == 'CPython':
        _implementation_version = platform.python_version()
    elif _implementation == 'PyPy':
        _implementation_version = '%s.%s.%s' % (sys.pypy_version_info.major,
                                                sys.pypy_version_info.minor,
                                                sys.pypy_version_info.micro)
        if sys.pypy_version_info.releaselevel != 'final':
            _implementation_version = ''.join([_implementation_version, sys.pypy_version_info.releaselevel])
    elif _implementation == 'Jython':
        _implementation_version = platform.python_version()  # Complete Guess
    elif _implementation == 'IronPython':
        _implementation_version = platform.python_version()  # Complete Guess
    else:
        _implementation_version = 'Unknown'

    try:
        p_system = platform.system()
        p_release = platform.release()
    except IOError:
        p_system = 'Unknown'
        p_release = 'Unknown'

    return " ".join(['%s/%s' % (name, __version__),
                     '%s/%s' % (_implementation, _implementation_version),
                     '%s/%s' % (p_system, p_release)])


def default_headers():
    return CaseInsensitiveDict({
        'User-Agent': default_user_agent(),
        'Accept-Encoding': ', '.join(('gzip', 'deflate')),
        'Accept': '*/*'
    })


def parse_header_links(value):
    """Return a dict of parsed link headers proxies.

    i.e. Link: <http:/.../front.jpeg>; rel=front; type="image/jpeg",<http://.../back.jpeg>; rel=back;type="image/jpeg"

    """

    links = []

    replace_chars = " '\""

    for val in value.split(","):
        try:
            url, params = val.split(";", 1)
        except ValueError:
            url, params = val, ''

        link = {}

        link["url"] = url.strip("<> '\"")

        for param in params.split(";"):
            try:
                key, value = param.split("=")
            except ValueError:
                break

            link[key.strip(replace_chars)] = value.strip(replace_chars)

        links.append(link)

    return links


# Null bytes; no need to recreate these on each call to guess_json_utf
_null = '\x00'.encode('ascii')  # encoding to ASCII for Python 3
_null2 = _null * 2
_null3 = _null * 3


def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None


def prepend_scheme_if_needed(url, new_scheme):
    '''Given a URL that may or may not have a scheme, prepend the given scheme.
    Does not replace a present scheme with the one provided as an argument.'''
    scheme, netloc, path, params, query, fragment = urlparse(url, new_scheme)

    # urlparse is a finicky beast, and sometimes decides that there isn't a
    # netloc present. Assume that it's being over-cautious, and switch netloc
    # and path if urlparse decided there was no netloc.
    if not netloc:
        netloc, path = path, netloc

    return urlunparse((scheme, netloc, path, params, query, fragment))


def get_auth_from_url(url):
    """Given a url with authentication components, extract them into a tuple of
    username,password."""
    parsed = urlparse(url)

    try:
        auth = (unquote(parsed.username), unquote(parsed.password))
    except (AttributeError, TypeError):
        auth = ('', '')

    return auth


def to_native_string(string, encoding='ascii'):
    """
    Given a string object, regardless of type, returns a representation of that
    string in the native string type, encoding and decoding where necessary.
    This assumes ASCII unless told otherwise.
    """
    out = None

    if isinstance(string, builtin_str):
        out = string
    else:
        if is_py2:
            out = string.encode(encoding)
        else:
            out = string.decode(encoding)

    return out