使用 OAuth 2.0 和服务帐户检索 Google 协作平台的域索引提要

Question

我需要开始使用 python 脚本抓取这个网址：https://sites.google.com/a/domain.com/sites/system/app/pages/meta/domainIndex。

如何通过服务帐户使用 OAuth2.0 授权此 Google 站点 URL。

在 OAuth1.0 的情况下，我们已经将请求发送到 https://www.google.com/accounts/ClientLogin 并提取作为令牌接收的令牌并授权 URL。

OAuth 1.0 身份验证

url = 'https://www.google.com/accounts/ClientLogin'
request = urllib.urlencode({
    'accountType': 'HOSTED',
    'Email': 'admin@dmian.com',
    'Passwd': 'userPassword',
    'service': 'jotspot'})

#.. Fetch the url: https://www.google.com/accounts/ClientLogin and extract the token

headers = {
    'Authorization': 'GoogleLogin auth=' + token,
    'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; fr; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15 ( .NET CLR 3.5.30729)',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    'Host': 'sites.google.com',
    'Connection': 'keep-alive'
}

# .. Fetch the Google Site url with below headers

Answer 1

前段时间，我为自己编写了一个类来使用 Google API 处理 OAuth2 身份验证。它可以作为你的一个例子。而且，是的，您需要注册一个“应用程序”，但这只是为了获取客户端 ID/秘密。

一些注意事项：

• 该类使用“离线”访问类型来获取可以存储并在未来重复使用的凭据。

• settings 变量包含一个类的实例，该类存储我的所有设置，在本例中，是之前获得的 google api 凭据。

• GAuthDialog 是一个对话框，向用户显示用户名/密码登录并读取 google 生成的代码。

• execute 方法封装了任何需要访问 API 和身份验证的方法。

该类可以如下使用，例如对于谷歌驱动器：

self._gapi = GApi(settings, 'https://www.googleapis.com/auth/drive.readonly', 'drive', 'v2')
self._gapi.execute(self.get_file_list)

然后我们有：

def get_file_list(self):
    query="query"
    children = self._gapi.service.files().list(q=query).execute()

下面是类的代码：

from oauth2client.client import OAuth2WebServerFlow, Credentials, AccessTokenRefreshError
from apiclient.discovery import build
from googleapiclient.errors import HttpError
import httplib2

class GApi():

    class CredentialsError(Exception):
        pass

    # App credentials from developers console
    __client_id = ''
    __client_secret = ''

    # Redirect URI for installed (non-web) apps
    __redirect_uri = 'urn:ietf:wg:oauth:2.0:oob'

    def __init__(self, settings, scopes, service_name, version):
        self.__settings = settings
        self.__scopes = scopes
        self.__service_name = service_name
        self.__version = version
        self.__service = None
        self.__credentials = None
        # Try restoring credentials from settings
        if self.__settings.get_gapi_credentials(self.__service_name):
            self.__credentials = Credentials.new_from_json(
                self.__settings.get_gapi_credentials(self.__service_name))

    @property
    def service(self):
        return self.__service

    def execute(self, method, *args, **kwargs):
        self.__setup()
        try:
            return method(*args, **kwargs)
        except AccessTokenRefreshError:
            pass  # Will re-authenticate below
        except HttpError as err:
            # Rethrow since HttpError has a bug in str()
            raise Exception("Response: %s, Content: %s" %
                            (str(err.resp), str(err.content)))
        # Try re-authenticating
        self.__reauthenticate()
        try:
            return method(**kwargs)
        except HttpError as err:
            # Rethrow since HttpError has a bug in str()
            raise Exception("Response: %s, Content: %s" %
                            (str(err.resp), str(err.content)))

    def __obtain_credentials(self):
        # Initialize the flow
        flow = OAuth2WebServerFlow(self.__client_id, self.__client_secret,
                                   self.__scopes, redirect_uri=self.__redirect_uri)
        flow.params['access_type'] = 'offline'
        # Run through the OAuth flow and retrieve credentials
        uri = flow.step1_get_authorize_url()
        # Get code from dialog
        dialog = GAuthDialog(uri)
        if dialog.exec() == QtWidgets.QDialog.Accepted and dialog.auth_code:
            # Get the new credentials
            self.__credentials = flow.step2_exchange(dialog.auth_code)
            # Set them in settings
            self.__settings.set_gapi_credentials(
                self.__service_name, self.__credentials.to_json())
        else:
            self.__credentials = None
            self.__settings.set_gapi_credentials(self.__service_name, None)

    def __reauthenticate(self):
        self.__credentials = None
        self.__service = None
        self.__setup()

    def __setup(self):
        # Do we have credentials?
        if not self.__credentials:
            self.__obtain_credentials()
        # Check if we got credentials
        if self.__credentials:
            # Do we have service?
            if not self.__service:
                # Create an httplib2.Http object and authorize it with our credentials
                http = httplib2.Http()
                http = self.__credentials.authorize(http)
                self.__service = build(self.__service_name,
                                       self.__version, http=http)
        else:
            raise GApi.CredentialsError