aboutsummaryrefslogtreecommitdiff
path: root/requests/models.py
blob: ae46a83185cdec139d332b06d02c892376e5eaf9 (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
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
# -*- coding: utf-8 -*-

"""
requests.models
~~~~~~~~~~~~~~~

This module contains the primary objects that power Requests.
"""

import collections
import logging
import datetime

from io import BytesIO, UnsupportedOperation
from .hooks import default_hooks
from .structures import CaseInsensitiveDict

from .auth import HTTPBasicAuth
from .cookies import cookiejar_from_dict, get_cookie_header
from .packages.urllib3.fields import RequestField
from .packages.urllib3.filepost import encode_multipart_formdata
from .packages.urllib3.util import parse_url
from .packages.urllib3.exceptions import DecodeError
from .exceptions import (
    HTTPError, RequestException, MissingSchema, InvalidURL,
    ChunkedEncodingError, ContentDecodingError)
from .utils import (
    guess_filename, get_auth_from_url, requote_uri,
    stream_decode_response_unicode, to_key_val_list, parse_header_links,
    iter_slices, guess_json_utf, super_len, to_native_string)
from .compat import (
    cookielib, urlunparse, urlsplit, urlencode, str, bytes, StringIO,
    is_py2, chardet, json, builtin_str, basestring, IncompleteRead)

CONTENT_CHUNK_SIZE = 10 * 1024
ITER_CHUNK_SIZE = 512

log = logging.getLogger(__name__)


class RequestEncodingMixin(object):
    @property
    def path_url(self):
        """Build the path URL to use."""

        url = []

        p = urlsplit(self.url)

        path = p.path
        if not path:
            path = '/'

        url.append(path)

        query = p.query
        if query:
            url.append('?')
            url.append(query)

        return ''.join(url)

    @staticmethod
    def _encode_params(data):
        """Encode parameters in a piece of data.

        Will successfully encode parameters when passed as a dict or a list of
        2-tuples. Order is retained if data is a list of 2-tuples but arbitrary
        if parameters are supplied as a dict.
        """

        if isinstance(data, (str, bytes)):
            return data
        elif hasattr(data, 'read'):
            return data
        elif hasattr(data, '__iter__'):
            result = []
            for k, vs in to_key_val_list(data):
                if isinstance(vs, basestring) or not hasattr(vs, '__iter__'):
                    vs = [vs]
                for v in vs:
                    if v is not None:
                        result.append(
                            (k.encode('utf-8') if isinstance(k, str) else k,
                             v.encode('utf-8') if isinstance(v, str) else v))
            return urlencode(result, doseq=True)
        else:
            return data

    @staticmethod
    def _encode_files(files, data):
        """Build the body for a multipart/form-data request.

        Will successfully encode files when passed as a dict or a list of
        2-tuples. Order is retained if data is a list of 2-tuples but arbitrary
        if parameters are supplied as a dict.

        """
        if (not files):
            raise ValueError("Files must be provided.")
        elif isinstance(data, basestring):
            raise ValueError("Data must not be a string.")

        new_fields = []
        fields = to_key_val_list(data or {})
        files = to_key_val_list(files or {})

        for field, val in fields:
            if isinstance(val, basestring) or not hasattr(val, '__iter__'):
                val = [val]
            for v in val:
                if v is not None:
                    # Don't call str() on bytestrings: in Py3 it all goes wrong.
                    if not isinstance(v, bytes):
                        v = str(v)

                    new_fields.append(
                        (field.decode('utf-8') if isinstance(field, bytes) else field,
                         v.encode('utf-8') if isinstance(v, str) else v))

        for (k, v) in files:
            # support for explicit filename
            ft = None
            fh = None
            if isinstance(v, (tuple, list)):
                if len(v) == 2:
                    fn, fp = v
                elif len(v) == 3:
                    fn, fp, ft = v
                else:
                    fn, fp, ft, fh = v
            else:
                fn = guess_filename(v) or k
                fp = v
            if isinstance(fp, str):
                fp = StringIO(fp)
            if isinstance(fp, bytes):
                fp = BytesIO(fp)

            rf = RequestField(name=k, data=fp.read(),
                              filename=fn, headers=fh)
            rf.make_multipart(content_type=ft)
            new_fields.append(rf)

        body, content_type = encode_multipart_formdata(new_fields)

        return body, content_type


class RequestHooksMixin(object):
    def register_hook(self, event, hook):
        """Properly register a hook."""

        if event not in self.hooks:
            raise ValueError('Unsupported event specified, with event name "%s"' % (event))

        if isinstance(hook, collections.Callable):
            self.hooks[event].append(hook)
        elif hasattr(hook, '__iter__'):
            self.hooks[event].extend(h for h in hook if isinstance(h, collections.Callable))

    def deregister_hook(self, event, hook):
        """Deregister a previously registered hook.
        Returns True if the hook existed, False if not.
        """

        try:
            self.hooks[event].remove(hook)
            return True
        except ValueError:
            return False


class Request(RequestHooksMixin):
    """A user-created :class:`Request <Request>` object.

    Used to prepare a :class:`PreparedRequest <PreparedRequest>`, which is sent to the server.

    :param method: HTTP method to use.
    :param url: URL to send.
    :param headers: dictionary of headers to send.
    :param files: dictionary of {filename: fileobject} files to multipart upload.
    :param data: the body to attach the request. If a dictionary is provided, form-encoding will take place.
    :param params: dictionary of URL parameters to append to the URL.
    :param auth: Auth handler or (user, pass) tuple.
    :param cookies: dictionary or CookieJar of cookies to attach to this request.
    :param hooks: dictionary of callback hooks, for internal usage.

    Usage::

      >>> import requests
      >>> req = requests.Request('GET', 'http://httpbin.org/get')
      >>> req.prepare()
      <PreparedRequest [GET]>

    """
    def __init__(self,
        method=None,
        url=None,
        headers=None,
        files=None,
        data=None,
        params=None,
        auth=None,
        cookies=None,
        hooks=None):

        # Default empty dicts for dict params.
        data = [] if data is None else data
        files = [] if files is None else files
        headers = {} if headers is None else headers
        params = {} if params is None else params
        hooks = {} if hooks is None else hooks

        self.hooks = default_hooks()
        for (k, v) in list(hooks.items()):
            self.register_hook(event=k, hook=v)

        self.method = method
        self.url = url
        self.headers = headers
        self.files = files
        self.data = data
        self.params = params
        self.auth = auth
        self.cookies = cookies

    def __repr__(self):
        return '<Request [%s]>' % (self.method)

    def prepare(self):
        """Constructs a :class:`PreparedRequest <PreparedRequest>` for transmission and returns it."""
        p = PreparedRequest()
        p.prepare(
            method=self.method,
            url=self.url,
            headers=self.headers,
            files=self.files,
            data=self.data,
            params=self.params,
            auth=self.auth,
            cookies=self.cookies,
            hooks=self.hooks,
        )
        return p


class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
    """The fully mutable :class:`PreparedRequest <PreparedRequest>` object,
    containing the exact bytes that will be sent to the server.

    Generated from either a :class:`Request <Request>` object or manually.

    Usage::

      >>> import requests
      >>> req = requests.Request('GET', 'http://httpbin.org/get')
      >>> r = req.prepare()
      <PreparedRequest [GET]>

      >>> s = requests.Session()
      >>> s.send(r)
      <Response [200]>

    """

    def __init__(self):
        #: HTTP verb to send to the server.
        self.method = None
        #: HTTP URL to send the request to.
        self.url = None
        #: dictionary of HTTP headers.
        self.headers = None
        # The `CookieJar` used to create the Cookie header will be stored here
        # after prepare_cookies is called
        self._cookies = None
        #: request body to send to the server.
        self.body = None
        #: dictionary of callback hooks, for internal usage.
        self.hooks = default_hooks()

    def prepare(self, method=None, url=None, headers=None, files=None,
                data=None, params=None, auth=None, cookies=None, hooks=None):
        """Prepares the entire request with the given parameters."""

        self.prepare_method(method)
        self.prepare_url(url, params)
        self.prepare_headers(headers)
        self.prepare_cookies(cookies)
        self.prepare_body(data, files)
        self.prepare_auth(auth, url)
        # Note that prepare_auth must be last to enable authentication schemes
        # such as OAuth to work on a fully prepared request.

        # This MUST go after prepare_auth. Authenticators could add a hook
        self.prepare_hooks(hooks)

    def __repr__(self):
        return '<PreparedRequest [%s]>' % (self.method)

    def copy(self):
        p = PreparedRequest()
        p.method = self.method
        p.url = self.url
        p.headers = self.headers.copy()
        p._cookies = self._cookies.copy()
        p.body = self.body
        p.hooks = self.hooks
        return p

    def prepare_method(self, method):
        """Prepares the given HTTP method."""
        self.method = method
        if self.method is not None:
            self.method = self.method.upper()

    def prepare_url(self, url, params):
        """Prepares the given HTTP URL."""
        #: Accept objects that have string representations.
        try:
            url = unicode(url)
        except NameError:
            # We're on Python 3.
            url = str(url)
        except UnicodeDecodeError:
            pass

        # Don't do any URL preparation for oddball schemes
        if ':' in url and not url.lower().startswith('http'):
            self.url = url
            return

        # Support for unicode domain names and paths.
        scheme, auth, host, port, path, query, fragment = parse_url(url)

        if not scheme:
            raise MissingSchema("Invalid URL {0!r}: No schema supplied. "
                                "Perhaps you meant http://{0}?".format(url))

        if not host:
            raise InvalidURL("Invalid URL %r: No host supplied" % url)

        # Only want to apply IDNA to the hostname
        try:
            host = host.encode('idna').decode('utf-8')
        except UnicodeError:
            raise InvalidURL('URL has an invalid label.')

        # Carefully reconstruct the network location
        netloc = auth or ''
        if netloc:
            netloc += '@'
        netloc += host
        if port:
            netloc += ':' + str(port)

        # Bare domains aren't valid URLs.
        if not path:
            path = '/'

        if is_py2:
            if isinstance(scheme, str):
                scheme = scheme.encode('utf-8')
            if isinstance(netloc, str):
                netloc = netloc.encode('utf-8')
            if isinstance(path, str):
                path = path.encode('utf-8')
            if isinstance(query, str):
                query = query.encode('utf-8')
            if isinstance(fragment, str):
                fragment = fragment.encode('utf-8')

        enc_params = self._encode_params(params)
        if enc_params:
            if query:
                query = '%s&%s' % (query, enc_params)
            else:
                query = enc_params

        url = requote_uri(urlunparse([scheme, netloc, path, None, query, fragment]))
        self.url = url

    def prepare_headers(self, headers):
        """Prepares the given HTTP headers."""

        if headers:
            self.headers = CaseInsensitiveDict((to_native_string(name), value) for name, value in headers.items())
        else:
            self.headers = CaseInsensitiveDict()

    def prepare_body(self, data, files):
        """Prepares the given HTTP body data."""

        # Check if file, fo, generator, iterator.
        # If not, run through normal process.

        # Nottin' on you.
        body = None
        content_type = None
        length = None

        is_stream = all([
            hasattr(data, '__iter__'),
            not isinstance(data, basestring),
            not isinstance(data, list),
            not isinstance(data, dict)
        ])

        try:
            length = super_len(data)
        except (TypeError, AttributeError, UnsupportedOperation):
            length = None

        if is_stream:
            body = data

            if files:
                raise NotImplementedError('Streamed bodies and files are mutually exclusive.')

            if length is not None:
                self.headers['Content-Length'] = builtin_str(length)
            else:
                self.headers['Transfer-Encoding'] = 'chunked'
        else:
            # Multi-part file uploads.
            if files:
                (body, content_type) = self._encode_files(files, data)
            else:
                if data:
                    body = self._encode_params(data)
                    if isinstance(data, str) or isinstance(data, builtin_str) or hasattr(data, 'read'):
                        content_type = None
                    else:
                        content_type = 'application/x-www-form-urlencoded'

            self.prepare_content_length(body)

            # Add content-type if it wasn't explicitly provided.
            if (content_type) and (not 'content-type' in self.headers):
                self.headers['Content-Type'] = content_type

        self.body = body

    def prepare_content_length(self, body):
        if hasattr(body, 'seek') and hasattr(body, 'tell'):
            body.seek(0, 2)
            self.headers['Content-Length'] = builtin_str(body.tell())
            body.seek(0, 0)
        elif body is not None:
            l = super_len(body)
            if l:
                self.headers['Content-Length'] = builtin_str(l)
        elif self.method not in ('GET', 'HEAD'):
            self.headers['Content-Length'] = '0'

    def prepare_auth(self, auth, url=''):
        """Prepares the given HTTP auth data."""

        # If no Auth is explicitly provided, extract it from the URL first.
        if auth is None:
            url_auth = get_auth_from_url(self.url)
            auth = url_auth if any(url_auth) else None

        if auth:
            if isinstance(auth, tuple) and len(auth) == 2:
                # special-case basic HTTP auth
                auth = HTTPBasicAuth(*auth)

            # Allow auth to make its changes.
            r = auth(self)

            # Update self to reflect the auth changes.
            self.__dict__.update(r.__dict__)

            # Recompute Content-Length
            self.prepare_content_length(self.body)

    def prepare_cookies(self, cookies):
        """Prepares the given HTTP cookie data."""

        if isinstance(cookies, cookielib.CookieJar):
            self._cookies = cookies
        else:
            self._cookies = cookiejar_from_dict(cookies)

        cookie_header = get_cookie_header(self._cookies, self)
        if cookie_header is not None:
            self.headers['Cookie'] = cookie_header

    def prepare_hooks(self, hooks):
        """Prepares the given hooks."""
        for event in hooks:
            self.register_hook(event, hooks[event])


class Response(object):
    """The :class:`Response <Response>` object, which contains a
    server's response to an HTTP request.
    """

    __attrs__ = [
        '_content',
        'status_code',
        'headers',
        'url',
        'history',
        'encoding',
        'reason',
        'cookies',
        'elapsed',
        'request',
    ]

    def __init__(self):
        super(Response, self).__init__()

        self._content = False
        self._content_consumed = False

        #: Integer Code of responded HTTP Status.
        self.status_code = None

        #: Case-insensitive Dictionary of Response Headers.
        #: For example, ``headers['content-encoding']`` will return the
        #: value of a ``'Content-Encoding'`` response header.
        self.headers = CaseInsensitiveDict()

        #: File-like object representation of response (for advanced usage).
        #: Use of ``raw`` requires that ``stream=True`` be set on the request.
        # This requirement does not apply for use internally to Requests.
        self.raw = None

        #: Final URL location of Response.
        self.url = None

        #: Encoding to decode with when accessing r.text.
        self.encoding = None

        #: A list of :class:`Response <Response>` objects from
        #: the history of the Request. Any redirect responses will end
        #: up here. The list is sorted from the oldest to the most recent request.
        self.history = []

        self.reason = None

        #: A CookieJar of Cookies the server sent back.
        self.cookies = cookiejar_from_dict({})

        #: The amount of time elapsed between sending the request
        #: and the arrival of the response (as a timedelta)
        self.elapsed = datetime.timedelta(0)

    def __getstate__(self):
        # Consume everything; accessing the content attribute makes
        # sure the content has been fully read.
        if not self._content_consumed:
            self.content

        return dict(
            (attr, getattr(self, attr, None))
            for attr in self.__attrs__
        )

    def __setstate__(self, state):
        for name, value in state.items():
            setattr(self, name, value)

        # pickled objects do not have .raw
        setattr(self, '_content_consumed', True)

    def __repr__(self):
        return '<Response [%s]>' % (self.status_code)

    def __bool__(self):
        """Returns true if :attr:`status_code` is 'OK'."""
        return self.ok

    def __nonzero__(self):
        """Returns true if :attr:`status_code` is 'OK'."""
        return self.ok

    def __iter__(self):
        """Allows you to use a response as an iterator."""
        return self.iter_content(128)

    @property
    def ok(self):
        try:
            self.raise_for_status()
        except RequestException:
            return False
        return True

    @property
    def apparent_encoding(self):
        """The apparent encoding, provided by the lovely Charade library
        (Thanks, Ian!)."""
        return chardet.detect(self.content)['encoding']

    def iter_content(self, chunk_size=1, decode_unicode=False):
        """Iterates over the response data.  When stream=True is set on the
        request, this avoids reading the content at once into memory for
        large responses.  The chunk size is the number of bytes it should
        read into memory.  This is not necessarily the length of each item
        returned as decoding can take place.
        """
        if self._content_consumed:
            # simulate reading small chunks of the content
            return iter_slices(self._content, chunk_size)

        def generate():
            try:
                # Special case for urllib3.
                try:
                    for chunk in self.raw.stream(chunk_size,
                                                 decode_content=True):
                        yield chunk
                except IncompleteRead as e:
                    raise ChunkedEncodingError(e)
                except DecodeError as e:
                    raise ContentDecodingError(e)
            except AttributeError:
                # Standard file-like object.
                while True:
                    chunk = self.raw.read(chunk_size)
                    if not chunk:
                        break
                    yield chunk

            self._content_consumed = True

        gen = generate()

        if decode_unicode:
            gen = stream_decode_response_unicode(gen, self)

        return gen

    def iter_lines(self, chunk_size=ITER_CHUNK_SIZE, decode_unicode=None):
        """Iterates over the response data, one line at a time.  When
        stream=True is set on the request, this avoids reading the
        content at once into memory for large responses.
        """

        pending = None

        for chunk in self.iter_content(chunk_size=chunk_size,
                                       decode_unicode=decode_unicode):

            if pending is not None:
                chunk = pending + chunk
            lines = chunk.splitlines()

            if lines and lines[-1] and chunk and lines[-1][-1] == chunk[-1]:
                pending = lines.pop()
            else:
                pending = None

            for line in lines:
                yield line

        if pending is not None:
            yield pending

    @property
    def content(self):
        """Content of the response, in bytes."""

        if self._content is False:
            # Read the contents.
            try:
                if self._content_consumed:
                    raise RuntimeError(
                        'The content for this response was already consumed')

                if self.status_code == 0:
                    self._content = None
                else:
                    self._content = bytes().join(self.iter_content(CONTENT_CHUNK_SIZE)) or bytes()

            except AttributeError:
                self._content = None

        self._content_consumed = True
        # don't need to release the connection; that's been handled by urllib3
        # since we exhausted the data.
        return self._content

    @property
    def text(self):
        """Content of the response, in unicode.

        If Response.encoding is None, encoding will be guessed using
        ``chardet``.

        The encoding of the response content is determined based soley on HTTP
        headers, following RFC 2616 to the letter. If you can take advantage of
        non-HTTP knowledge to make a better guess at the encoding, you should
        set ``r.encoding`` appropriately before accessing this property.
        """

        # Try charset from content-type
        content = None
        encoding = self.encoding

        if not self.content:
            return str('')

        # Fallback to auto-detected encoding.
        if self.encoding is None:
            encoding = self.apparent_encoding

        # Decode unicode from given encoding.
        try:
            content = str(self.content, encoding, errors='replace')
        except (LookupError, TypeError):
            # A LookupError is raised if the encoding was not found which could
            # indicate a misspelling or similar mistake.
            #
            # A TypeError can be raised if encoding is None
            #
            # So we try blindly encoding.
            content = str(self.content, errors='replace')

        return content

    def json(self, **kwargs):
        """Returns the json-encoded content of a response, if any.

        :param \*\*kwargs: Optional arguments that ``json.loads`` takes.
        """

        if not self.encoding and len(self.content) > 3:
            # No encoding set. JSON RFC 4627 section 3 states we should expect
            # UTF-8, -16 or -32. Detect which one to use; If the detection or
            # decoding fails, fall back to `self.text` (using chardet to make
            # a best guess).
            encoding = guess_json_utf(self.content)
            if encoding is not None:
                return json.loads(self.content.decode(encoding), **kwargs)
        return json.loads(self.text, **kwargs)

    @property
    def links(self):
        """Returns the parsed header links of the response, if any."""

        header = self.headers.get('link')

        # l = MultiDict()
        l = {}

        if header:
            links = parse_header_links(header)

            for link in links:
                key = link.get('rel') or link.get('url')
                l[key] = link

        return l

    def raise_for_status(self):
        """Raises stored :class:`HTTPError`, if one occurred."""

        http_error_msg = ''

        if 400 <= self.status_code < 500:
            http_error_msg = '%s Client Error: %s' % (self.status_code, self.reason)

        elif 500 <= self.status_code < 600:
            http_error_msg = '%s Server Error: %s' % (self.status_code, self.reason)

        if http_error_msg:
            raise HTTPError(http_error_msg, response=self)

    def close(self):
        """Closes the underlying file descriptor and releases the connection
        back to the pool.

        *Note: Should not normally need to be called explicitly.*
        """
        return self.raw.release_conn()