Python 请求和持久会话

Question

我正在使用 requests 模块。我已经想出如何将数据提交到网站上的登录表单并检索会话密钥，但我看不到在后续请求中使用此会话密钥的明显方法。有人可以填写下面代码中的省略号或建议另一种方法吗？

 >>> import requests
>>> login_data =  {'formPosted': '1', 'login_email': '[e-mail]', 'password': 'pw'}
>>> r = requests.post('https://localhost/login.py', login_data)
>>>
>>> r.text
'You are being redirected <a href="profilePage?_ck=1349394964">here</a>'
>>> r.cookies
{'session_id_myapp': '127-0-0-1-825ff22a-6ed1-453b-aebc-5d3cf2987065'}
>>>
>>> r2 = requests.get('https://localhost/profile_data.json', ...)

原文由 ChrisGuest 发布，翻译遵循 CC BY-SA 4.0 许可协议

Answer 1

您可以使用以下方法轻松创建持久会话：

 s = requests.Session()

之后，继续您的请求：

 s.post('https://localhost/login.py', login_data)
# logged in! cookies saved for future requests.
r2 = s.get('https://localhost/profile_data.json', ...)
# cookies sent automatically!
# do whatever, s will keep your cookies intact :)

有关 Session 的更多信息： https ://requests.readthedocs.io/en/latest/user/advanced/#session-objects

原文由 Anuj Gupta 发布，翻译遵循 CC BY-SA 4.0 许可协议

Answer 2

其他答案有助于理解如何维持这样的会话。此外，我想提供一个类，它可以在脚本的不同运行（带有缓存文件）中保持会话。这意味着只有在需要时才执行正确的“登录”（超时或缓存中不存在会话）。它还支持通过后续调用“get”或“post”进行代理设置。

它是用 Python3 测试的。

将其用作您自己的代码的基础。以下代码片段随 GPL v3 一起发布

import pickle
import datetime
import os
from urllib.parse import urlparse
import requests

class MyLoginSession:
    """
    a class which handles and saves login sessions. It also keeps track of proxy settings.
    It does also maintine a cache-file for restoring session data from earlier
    script executions.
    """
    def __init__(self,
                 loginUrl,
                 loginData,
                 loginTestUrl,
                 loginTestString,
                 sessionFileAppendix = '_session.dat',
                 maxSessionTimeSeconds = 30 * 60,
                 proxies = None,
                 userAgent = 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.1',
                 debug = True,
                 forceLogin = False,
                 **kwargs):
        """
        save some information needed to login the session

        you'll have to provide 'loginTestString' which will be looked for in the
        responses html to make sure, you've properly been logged in

        'proxies' is of format { 'https' : 'https://user:pass@server:port', 'http' : ...
        'loginData' will be sent as post data (dictionary of id : value).
        'maxSessionTimeSeconds' will be used to determine when to re-login.
        """
        urlData = urlparse(loginUrl)

        self.proxies = proxies
        self.loginData = loginData
        self.loginUrl = loginUrl
        self.loginTestUrl = loginTestUrl
        self.maxSessionTime = maxSessionTimeSeconds
        self.sessionFile = urlData.netloc + sessionFileAppendix
        self.userAgent = userAgent
        self.loginTestString = loginTestString
        self.debug = debug

        self.login(forceLogin, **kwargs)

    def modification_date(self, filename):
        """
        return last file modification date as datetime object
        """
        t = os.path.getmtime(filename)
        return datetime.datetime.fromtimestamp(t)

    def login(self, forceLogin = False, **kwargs):
        """
        login to a session. Try to read last saved session from cache file. If this fails
        do proper login. If the last cache access was too old, also perform a proper login.
        Always updates session cache file.
        """
        wasReadFromCache = False
        if self.debug:
            print('loading or generating session...')
        if os.path.exists(self.sessionFile) and not forceLogin:
            time = self.modification_date(self.sessionFile)

            # only load if file less than 30 minutes old
            lastModification = (datetime.datetime.now() - time).seconds
            if lastModification < self.maxSessionTime:
                with open(self.sessionFile, "rb") as f:
                    self.session = pickle.load(f)
                    wasReadFromCache = True
                    if self.debug:
                        print("loaded session from cache (last access %ds ago) "
                              % lastModification)
        if not wasReadFromCache:
            self.session = requests.Session()
            self.session.headers.update({'user-agent' : self.userAgent})
            res = self.session.post(self.loginUrl, data = self.loginData,
                                    proxies = self.proxies, **kwargs)

            if self.debug:
                print('created new session with login' )
            self.saveSessionToCache()

        # test login
        res = self.session.get(self.loginTestUrl)
        if res.text.lower().find(self.loginTestString.lower()) < 0:
            raise Exception("could not log into provided site '%s'"
                            " (did not find successful login string)"
                            % self.loginUrl)

    def saveSessionToCache(self):
        """
        save session to a cache file
        """
        # always save (to update timeout)
        with open(self.sessionFile, "wb") as f:
            pickle.dump(self.session, f)
            if self.debug:
                print('updated session cache-file %s' % self.sessionFile)

    def retrieveContent(self, url, method = "get", postData = None, **kwargs):
        """
        return the content of the url with respect to the session.

        If 'method' is not 'get', the url will be called with 'postData'
        as a post request.
        """
        if method == 'get':
            res = self.session.get(url , proxies = self.proxies, **kwargs)
        else:
            res = self.session.post(url , data = postData, proxies = self.proxies, **kwargs)

        # the session has been updated on the server, so also update in cache
        self.saveSessionToCache()

        return res

使用上述类的代码片段可能如下所示：

 if __name__ == "__main__":
    # proxies = {'https' : 'https://user:pass@server:port',
    #           'http' : 'http://user:pass@server:port'}

    loginData = {'user' : 'usr',
                 'password' :  'pwd'}

    loginUrl = 'https://...'
    loginTestUrl = 'https://...'
    successStr = 'Hello Tom'
    s = MyLoginSession(loginUrl, loginData, loginTestUrl, successStr,
                       #proxies = proxies
                       )

    res = s.retrieveContent('https://....')
    print(res.text)

    # if, for instance, login via JSON values required try this:
    s = MyLoginSession(loginUrl, None, loginTestUrl, successStr,
                       #proxies = proxies,
                       json = loginData)

原文由 DomTomCat 发布，翻译遵循 CC BY-SA 3.0 许可协议