為了產生PreparedRequest，需要先建立的物件，使用方式如下
import requests
req = requests.Request('GET', 'https://httpbin.org/get')
req.prepare()
# <PreparedRequest [GET]>
為什麼不直接用PreparedRequest而還要多一層Request呢?
目前感覺Request是設計給使用者可以指定客製化參數的物件，而PreparedRequest會將相關客製化參數進一步轉換成HTTP protocol的資訊(method, url, headers, cookies, body, auth)，讓HTTPAdapter執行
使用方式如下
import requests
req = requests.Request('GET', 'https://httpbin.org/get')
# <PreparedRequest [GET]>
r = req.prepare()
s = requests.Session()
s.send(r)
prepare針對method, url, headers, cookies, body, auth進一步處理
class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
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()
#: integer denoting starting position of a readable file-like body.
self._body_position = None
def prepare(self,
method=None, url=None, headers=None, files=None, data=None,
params=None, auth=None, cookies=None, hooks=None, json=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, json)
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)
...
...
urllib3.util的parse_url拆解url
IDNA encodingdef prepare_url(self, url, params):
"""Prepares the given HTTP URL."""
#: Accept objects that have string representations.
#: We're unable to blindly call unicode/str functions
#: as this will include the bytestring indicator (b'')
#: on python 3.x.
#: https://github.com/psf/requests/pull/2238
if isinstance(url, bytes):
url = url.decode('utf8')
else:
url = unicode(url) if is_py2 else str(url)
# Remove leading whitespaces from url
url = url.lstrip()
# Don't do any URL preparation for non-HTTP schemes like `mailto`,
# `data` etc to work around exceptions from `url_parse`, which
# handles RFC 3986 only.
if ':' in url and not url.lower().startswith('http'):
self.url = url
return
# Support for unicode domain names and paths.
try:
scheme, auth, host, port, path, query, fragment = parse_url(url)
except LocationParseError as e:
raise InvalidURL(*e.args)
if not scheme:
error = ("Invalid URL {0!r}: No schema supplied. Perhaps you meant http://{0}?")
error = error.format(to_native_string(url, 'utf8'))
raise MissingSchema(error)
if not host:
raise InvalidURL("Invalid URL %r: No host supplied" % url)
# In general, we want to try IDNA encoding the hostname if the string contains
# non-ASCII characters. This allows users to automatically get the correct IDNA
# behaviour. For strings containing only ASCII characters, we need to also verify
# it doesn't start with a wildcard (*), before allowing the unencoded hostname.
if not unicode_is_ascii(host):
try:
host = self._get_idna_encoded_host(host)
except UnicodeError:
raise InvalidURL('URL has an invalid label.')
elif host.startswith(u'*'):
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')
if isinstance(params, (str, bytes)):
params = to_native_string(params)
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
multipart/form-data方式發送requestsapplication/x-www-form-urlencoded方式發送requestsdef prepare_body(self, data, files, json=None):
"""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
if not data and json is not None:
# urllib3 requires a bytes-like body. Python 2's json.dumps
# provides this natively, but Python 3 gives a Unicode string.
content_type = 'application/json'
body = complexjson.dumps(json)
if not isinstance(body, bytes):
body = body.encode('utf-8')
is_stream = all([
hasattr(data, '__iter__'),
not isinstance(data, (basestring, list, tuple, Mapping))
])
try:
length = super_len(data)
except (TypeError, AttributeError, UnsupportedOperation):
length = None
if is_stream:
body = data
if getattr(body, 'tell', None) is not None:
# Record the current file position before reading.
# This will allow us to rewind a file in the event
# of a redirect.
try:
self._body_position = body.tell()
except (IOError, OSError):
# This differentiates from None, allowing us to catch
# a failed `tell()` later when trying to rewind the body
self._body_position = object()
if files:
raise NotImplementedError('Streamed bodies and files are mutually exclusive.')
if length:
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, basestring) 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 ('content-type' not in self.headers):
self.headers['Content-Type'] = content_type
self.body = body
iThome鐵人賽
看影片追技術