Python - requests库 学习笔记（持续更新）

__title__ = 'requests'
__description__ = 'Python HTTP for Humans.'
__url__ = 'https://requests.readthedocs.io'
__version__ = '2.24.0'
__build__ = 0x022400
__author__ = 'Kenneth Reitz'
__author_email__ = 'me@kennethreitz.org'
__license__ = 'Apache 2.0'
__copyright__ = 'Copyright 2020 Kenneth Reitz'
__cake__ = u'\u2728 \U0001f370 \u2728'

   >>> import requests
   >>> r = requests.get('https://www.python.org')
   >>> r.status_code
   200
   >>> b'Python is a programming language' in r.content
   True

   >>> payload = dict(key1='value1', key2='value2')
   >>> r = requests.post('https://httpbin.org/post', data=payload)
   >>> print(r.text)
   {
     ...
     "form": {
       "key1": "value1",
       "key2": "value2"
     },
     ...
   }

from . import sessions

def request(method, url, **kwargs):
    with sessions.Session() as session:
        return session.request(method=method, url=url, **kwargs)

def get(url, params=None, **kwargs):
    kwargs.setdefault('allow_redirects', True)
    return request('get', url, params=params, **kwargs)

def options(url, **kwargs):
    kwargs.setdefault('allow_redirects', True)
    return request('options', url, **kwargs)

def head(url, **kwargs):
    kwargs.setdefault('allow_redirects', False)
    return request('head', url, **kwargs)

def post(url, data=None, json=None, **kwargs):
    return request('post', url, data=data, json=json, **kwargs)

def put(url, data=None, **kwargs):
    return request('put', url, data=data, **kwargs)

def patch(url, data=None, **kwargs):
    return request('patch', url, data=data, **kwargs)

def delete(url, **kwargs):
    return request('delete', url, **kwargs)

kwargs.setdefault('allow_redirects', True)

def request(method, url, **kwargs):
    with sessions.Session() as session:
        return session.request(method=method, url=url, **kwargs)

req = requests.request('GET', 'https://httpbin.org/get')

req = requests.get('https://httpbin.org/get')

s = requests.Session()
s.get('https://httpbin.org/get')

with requests.Session() as s:
     s.get('https://httpbin.org/get')

    def __enter__(self):
        return self

    def __exit__(self, *args):
        self.close()

def request(self, method, url,
            params=None, data=None, headers=None, cookies=None, files=None,
            auth=None, timeout=None, allow_redirects=True, proxies=None,
            hooks=None, stream=None, verify=None, cert=None, json=None):  
 
        # Create the Request.
        req = Request(
            method=method.upper(),
            url=url,
            headers=headers,
            files=files,
            data=data or {},
            json=json,
            params=params or {},
            auth=auth,
            cookies=cookies,
            hooks=hooks,
        )
        prep = self.prepare_request(req)
        proxies = proxies or {}
        settings = self.merge_environment_settings(prep.url, proxies, stream, verify, cert)

        # Send the request.
        send_kwargs = {'timeout': timeout, 'allow_redirects': allow_redirects,}
        send_kwargs.update(settings)
        resp = self.send(prep, **send_kwargs)
        return resp

req = requests.Request('GET', 'https://httpbin.org/get')
r = req.prepare()
s = requests.Session()
s.send(r)

    def prepare_url(self, url, params):

        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

    def request(self, method, url, fields=None, headers=None, **urlopen_kw):
        """
        Make a request using :meth:`urlopen` with the appropriate encoding of
        ``fields`` based on the ``method`` used.

        This is a convenience method that requires the least amount of manual
        effort. It can be used in most situations, while still having the
        option to drop down to more specific methods when necessary, such as
        :meth:`request_encode_url`, :meth:`request_encode_body`,
        or even the lowest level :meth:`urlopen`.
        """
        method = method.upper()

        urlopen_kw["request_url"] = url

        if method in self._encode_url_methods:
            return self.request_encode_url(
                method, url, fields=fields, headers=headers, **urlopen_kw
            )
        else:
            return self.request_encode_body(
                method, url, fields=fields, headers=headers, **urlopen_kw
            )

    def request_encode_url(self, method, url, fields=None, headers=None, **urlopen_kw):
        """
        Make a request using :meth:`urlopen` with the ``fields`` encoded in
        the url. This is useful for request methods like GET, HEAD, DELETE, etc.
        """
        if headers is None:
            headers = self.headers

        extra_kw = {"headers": headers}
        extra_kw.update(urlopen_kw)

        if fields:
            url += "?" + urlencode(fields)

        return self.urlopen(method, url, **extra_kw)

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

        self.headers = CaseInsensitiveDict()
        if headers:
            for header in headers.items():
                # Raise exception on invalid header value.
                check_header_validity(header)
                name, value = header
                self.headers[to_native_string(name)] = value

    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_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))
        ])

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

            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

req_data = {'req_data': 123}
requests.post(url, data=json.dumps(req_data))

requests.post(url, json=req_data)

    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_hooks(self, hooks):
        """Prepares the given hooks."""
        # hooks can be passed as None to the prepare method and to this
        # method. To prevent iterating over None, simply use an empty list
        # if hooks is False-y
        hooks = hooks or []
        for event in hooks:
            self.register_hook(event, hooks[event])

# 钩子函数1
def no_change_url(r, *args, **kwargs):
    print("no_change_url: " + r.url)
    return r

# 钩子函数2
def change_url(r, *args, **kwargs):
    r.url = 'http://change.url'
    print("changed_url: " + r.url)
    return r

# tips: http://httpbin.org能够用于测试http请求和响应
url = 'http://httpbin.org/cookies'

response = requests.get(url, hooks=dict(response=no_change_url))
print("result_url: " + response.url)  # result_url: http://httpbin.org/

response = requests.get(url, hooks=dict(response=change_url))
print("result_url: " + response.url)  # result_url: http://change.url

url = 'http://httpbin.org/cookies'
response = requests.get(url, hooks=dict(response=[no_change_url, change_url]))
print("result_url: " + response.url)  # result_url: http://change.url

    def build_response(self, req, resp):
        """Builds a :class:`Response <requests.Response>` object from a urllib3
        response. This should not be called from user code, and is only exposed
        for use when subclassing the
        :class:`HTTPAdapter <requests.adapters.HTTPAdapter>`

        :param req: The :class:`PreparedRequest <PreparedRequest>` used to generate the response.
        :param resp: The urllib3 response object.
        :rtype: requests.Response
        """
        response = Response()

        # Fallback to None if there's no status_code, for whatever reason.
        response.status_code = getattr(resp, 'status', None)

        # Make headers case-insensitive.
        response.headers = CaseInsensitiveDict(getattr(resp, 'headers', {}))

        # Set encoding.
        response.encoding = get_encoding_from_headers(response.headers)
        response.raw = resp
        response.reason = response.raw.reason

        if isinstance(req.url, bytes):
            response.url = req.url.decode('utf-8')
        else:
            response.url = req.url

        # Add new cookies from the server.
        extract_cookies_to_jar(response.cookies, req, resp)

        # Give the Response some context.
        response.request = req
        response.connection = self

        return response

        # Response manipulation hooks
        r = dispatch_hook('response', hooks, r, **kwargs)

        # Persist cookies
        if r.history:
            # If the hooks create history then we want those cookies too
            for resp in r.history:
                extract_cookies_to_jar(self.cookies, resp.request, resp.raw)

        extract_cookies_to_jar(self.cookies, request, r.raw)

        # Redirect resolving generator.
        gen = self.resolve_redirects(r, request, **kwargs)

        # Resolve redirects if allowed.
        history = [resp for resp in gen] if allow_redirects else []

        # Shuffle things around if there's history.
        if history:
            # Insert the first (original) request at the start
            history.insert(0, r)
            # Get the last request made
            r = history.pop()
            r.history = history

        # If redirects aren't being followed, store the response on the Request for Response.next().
        if not allow_redirects:
            try:
                r._next = next(self.resolve_redirects(r, request, yield_requests=True, **kwargs))
            except StopIteration:
                pass

        if not stream:
            r.content

        return r

import requests

url = 'http://httpbin.org/post'
resp = requests.post(url)
print(resp.status_code)  # http状态码
print(resp.content)  # 返回bytes型的二进制数据
print(resp.text)  # 返回unicode型的文本数据
print(resp.json())  # 字典型的数据
print(resp.url)  # 请求的url

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

        # 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):
            content = str(self.content, errors='replace')

        return content

    def json(self, **kwargs):
        r"""Returns the json-encoded content of a response, if any."""
        if not self.encoding and self.content and len(self.content) > 3:
            encoding = guess_json_utf(self.content)
            if encoding is not None:
                try:
                    return complexjson.loads(
                        self.content.decode(encoding), **kwargs
                    )
                except UnicodeDecodeError:
                    pass
        return complexjson.loads(self.text, **kwargs)

import requests
import json

url = 'http://httpbin.org/post'
resp = requests.post(url)
response = resp.content
print(json.loads(response))

import requests

url = 'http://httpbin.org/post'
resp = requests.post(url)
print(resp.json())

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

        http_error_msg = ''
        if isinstance(self.reason, bytes):
            try:
                reason = self.reason.decode('utf-8')
            except UnicodeDecodeError:
                reason = self.reason.decode('iso-8859-1')
        else:
            reason = self.reason

        if 400 <= self.status_code < 500:
            http_error_msg = u'%s Client Error: %s for url: %s' % (self.status_code, reason, self.url)
        elif 500 <= self.status_code < 600:
            http_error_msg = u'%s Server Error: %s for url: %s' % (self.status_code, reason, self.url)

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