From: Ross Jones Date: Tue, 09 Oct 2012 12:03:45 +0000 Subject: Implement oauth2 for accessing google analytics X-Git-Url: http://maxious.lambdacomplex.org/git/?p=ckanext-ga-report.git&a=commitdiff&h=1682c0e4872c15935aa1f41838e29b6d44168069 --- Implement oauth2 for accessing google analytics - Provided a command (getauthtoken) to go through the auth flow and have the user's oauth credentials written to local disk. - Make sure loadanalytics command uses the token file to authenticate on the request - Added documentation on how to get the credentials (from google) to allow for the oauth2 flow. - Added google-api-client to the requirements --- --- a/.gitignore +++ b/.gitignore @@ -15,6 +15,10 @@ develop-eggs .installed.cfg +# Private info +credentials.json +token.dat + # Installer logs pip-log.txt --- a/README.rst +++ b/README.rst @@ -46,12 +46,43 @@ ckan.plugins = ga-report +Authorization +-------------- + +Before you can access the data, you need to set up the OAUTH details which you can do by following the `instructions `_ the outcome of which will be a file called credentials.json which should look like credentials.json.template with the relevant fields completed. These steps are below for convenience: + +1. Visit the `Google APIs Console `_ + +2. Sign-in and create a project or use an existing project. + +3. In the `Services pane `_ , activate Analytics API for your project. If prompted, read and accept the terms of service. + +4. Go to the `API Access pane `_ + +5. Click Create an OAuth 2.0 client ID.... + +6. Fill out the Branding Information fields and click Next. + +7. In Client ID Settings, set Application type to Installed application. + +8. Click Create client ID + +9. The details you need below are Client ID, Client secret, and Redirect URIs + + +Once you have set up your credentials.json file you can generate an oauth token file by using the +following command, which will store your oauth token in a file called token.dat once you have finished +giving permission in the browser. + + $ paster getauthtoken --config=../ckan/development.ini + + Tutorial -------- -Download some GA data and store it in CKAN's db. (Ensure your CKAN pyenv is still activated, run the command from ``src/ckanext-ga-report``, alter the ``--config`` option to point to your site config file):: +Download some GA data and store it in CKAN's db. (Ensure your CKAN pyenv is still activated, run the command from ``src/ckanext-ga-report``, alter the ``--config`` option to point to your site config file) and specifying the name of your auth file (token.dat by default) from the previous step:: - $ paster loadanalytics latest --config=../ckan/development.ini + $ paster loadanalytics token.dat latest --config=../ckan/development.ini Software Licence --- a/ckanext/ga_report/command.py +++ b/ckanext/ga_report/command.py @@ -23,13 +23,31 @@ ga_model.init_tables() log.info("DB tables are setup") + +class GetAuthToken(CkanCommand): + """ Get's the Google auth token + """ + summary = __doc__.split('\n')[0] + usage = __doc__ + max_args = 0 + min_args = 0 + + def command(self): + from ga_auth import initialize_service + initialize_service('token.dat', + self.args[0] if self.args + else 'credentials.json') + class LoadAnalytics(CkanCommand): """Get data from Google Analytics API and save it in the ga_model - Usage: paster loadanalytics + Usage: paster loadanalytics - Where is: + Where is the name of the auth token file from + the getauthtoken step. + + And where is: all - data for all time latest - (default) just the 'latest' data YYYY-MM-DD - just data for all time periods going @@ -37,16 +55,24 @@ """ summary = __doc__.split('\n')[0] usage = __doc__ - max_args = 1 - min_args = 0 + max_args = 2 + min_args = 1 def command(self): self._load_config() + from ga_auth import initialize_service + try: + svc = initialize_service(self.args[0], None) + except TypeError: + print 'Have you correctly run the getauthtoken task and specified the correct file here' + return + from download_analytics import DownloadAnalytics - downloader = DownloadAnalytics() - - time_period = self.args[0] if self.args else 'latest' + from ga_auth import get_profile_id + downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc)) + + time_period = self.args[1] if self.args and len(self.args) > 1 else 'latest' if time_period == 'all': downloader.all_() elif time_period == 'latest': --- a/ckanext/ga_report/download_analytics.py +++ b/ckanext/ga_report/download_analytics.py @@ -4,7 +4,8 @@ from pylons import config import ga_model -from ga_client import GA + +#from ga_client import GA log = logging.getLogger('ckanext.ga-report') @@ -12,12 +13,16 @@ class DownloadAnalytics(object): '''Downloads and stores analytics info''' - def __init__(self): + + def __init__(self, service=None, profile_id=None): self.period = config['ga-report.period'] - + self.service = service + self.profile_id = profile_id + + def all_(self): - pass - + self.since_date(datetime.datetime(2010, 1, 1)) + def latest(self): if self.period == 'monthly': # from first of this month to today @@ -49,8 +54,8 @@ break elif first_of_the_month < first_of_this_month: in_the_next_month = first_of_the_month + datetime.timedelta(40) - last_of_the_month == datetime.datetime(in_the_next_month.year, - in_the_next_month.month, a)\ + last_of_the_month = datetime.datetime(in_the_next_month.year, + in_the_next_month.month, 1)\ - datetime.timedelta(1) periods.append((now.strftime(FORMAT_MONTH), 0, first_of_the_month, last_of_the_month)) @@ -71,7 +76,7 @@ return period_name + ' (up to %ith)' % period_complete_day else: return period_name - + def download_and_store(self, periods): for period_name, period_complete_day, start_date, end_date in periods: @@ -84,8 +89,8 @@ self.get_full_period_name(period_name, period_complete_day)) self.store(period_name, period_complete_day, data) - @classmethod - def download(cls, start_date, end_date): + + def download(self, start_date, end_date): '''Get data from GA for a given time period''' start_date = start_date.strftime('%Y-%m-%d') end_date = end_date.strftime('%Y-%m-%d') @@ -93,22 +98,45 @@ #query = 'ga:pagePath=~^%s,ga:pagePath=~^%s' % \ # (PACKAGE_URL, self.resource_url_tag) query = 'ga:pagePath=~^/dataset/' + #query = 'ga:pagePath=~^/User/' metrics = 'ga:uniquePageviews' sort = '-ga:uniquePageviews' - for entry in GA.ga_query(query_filter=query, - from_date=start_date, + + # Supported query params at + # https://developers.google.com/analytics/devguides/reporting/core/v3/reference + results = self.service.data().ga().get( + ids='ga:' + self.profile_id, + filters=query, + start_date=start_date, metrics=metrics, sort=sort, - to_date=end_date): - print entry - import pdb; pdb.set_trace() - for dim in entry.dimension: - if dim.name == "ga:pagePath": - package = dim.value - count = entry.get_metric( - 'ga:uniquePageviews').value or 0 - packages[package] = int(count) - return packages + end_date=end_date).execute() + self.print_results(results) + +# for entry in GA.ga_query(query_filter=query, +# from_date=start_date, +# metrics=metrics, +# sort=sort, +# to_date=end_date): +# print entry, type(entry) +# import pdb; pdb.set_trace() +# for dim in entry.dimension: +# if dim.name == "ga:pagePath": +# package = dim.value +# count = entry.get_metric( +# 'ga:uniquePageviews').value or 0 +# packages[package] = int(count) + return [] + + def print_results(self, results): + import pprint + pprint.pprint(results) + if results: + print 'Profile: %s' % results.get('profileInfo').get('profileName') + print 'Total results: %s' % results.get('totalResults') + print 'Total Visits: %s' % results.get('rows', [[-1]])[0][0] + else: + print 'No results found' def store(self, period_name, period_complete_day, data): if 'url' in data: --- /dev/null +++ b/ckanext/ga_report/ga_auth.py @@ -1,1 +1,45 @@ +import httplib2 +from apiclient.discovery import build +from oauth2client.client import flow_from_clientsecrets +from oauth2client.file import Storage +from oauth2client.tools import run +from pylons import config + + +def _prepare_credentials( token_filename, credentials_filename ): + storage = Storage( token_filename ) + credentials = storage.get() + + if credentials is None or credentials.invalid: + flow = flow_from_clientsecrets(credentials_filename, + scope='https://www.googleapis.com/auth/analytics.readonly', + message="Can't find the credentials file") + credentials = run(flow, storage) + + return credentials + +def initialize_service( token_file, credentials_file ): + http = httplib2.Http() + + credentials = _prepare_credentials(token_file, credentials_file) + http = credentials.authorize(http) # authorize the http object + + return build('analytics', 'v3', http=http) + +def get_profile_id(service): + # Get a list of all Google Analytics accounts for this user + accounts = service.management().accounts().list().execute() + + if accounts.get('items'): + firstAccountId = accounts.get('items')[0].get('id') + webPropertyId = config.get('googleanalytics.id') + profiles = service.management().profiles().list( + accountId=firstAccountId, + webPropertyId=webPropertyId).execute() + + if profiles.get('items'): + # return the first Profile ID + return profiles.get('items')[0].get('id') + + return None --- /dev/null +++ b/credentials.json.template @@ -1,1 +1,11 @@ +{ + "installed": { + "client_id": "", + "client_secret": "", + "redirect_uris": [""], + "auth_uri": "https://accounts.google.com/o/oauth2/auth", + "token_uri": "https://accounts.google.com/o/oauth2/token" + } +} + --- a/setup.py +++ b/setup.py @@ -20,7 +20,8 @@ include_package_data=True, zip_safe=False, install_requires=[ - 'gdata' + 'gdata', + 'google-api-python-client' ], entry_points=\ """