From: Ross Jones Date: Tue, 09 Oct 2012 16:16:33 +0000 Subject: Packages up the data from Analytics. X-Git-Url: http://maxious.lambdacomplex.org/git/?p=ckanext-ga-report.git&a=commitdiff&h=f3afebc6bea83666f60ad90418d9fe490f96928a --- Packages up the data from Analytics. - Makes sure we get the right account by requiring a new googleanalytics.account config option which will be used to look up the correct account details. - Changed the model to use the sqlalchemy orm and made sure it does the updates correctly. - Still need to collect further info (such as the group details) --- --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,6 @@ *.py[co] +*.py~ +.gitignore # Packages *.egg @@ -13,6 +15,10 @@ develop-eggs .installed.cfg +# Private info +credentials.json +token.dat + # Installer logs pip-log.txt --- a/README.md +++ /dev/null @@ -1,4 +1,1 @@ -ckanext-ga-report -================= -For creating detailed reports of CKAN analytics, sliced by group --- /dev/null +++ b/README.rst @@ -1,1 +1,104 @@ +ckanext-ga-report +================= +**Status:** Development + +**CKAN Version:** 1.7.1+ + + +Overview +-------- + +For creating detailed reports of CKAN analytics, including totals per group. + +Whereas ckanext-googleanalytics focusses on providing page view stats a recent period and for all time (aimed at end users), ckanext-ga-report is more interested in building regular periodic reports (more for site managers to monitor). + +Contents of this extension: + + * Use the CLI tool to download Google Analytics data for each time period into this extension's database tables + + * Users can view the data as web page reports + + +Installation +------------ + +1. Activate you CKAN python environment and install this extension's software:: + + $ pyenv/bin/activate + $ pip install -e git+https://github.com/okfn/ckanext-ga-report.git#egg=ckanext-ga-report + +2. Ensure you development.ini (or similar) contains the info about your Google Analytics account and configuration:: + + googleanalytics.id = UA-1010101-1 + googleanalytics.account = Account name (i.e. data.gov.uk, see top level item at https://www.google.com/analytics) + googleanalytics.username = googleaccount@gmail.com + googleanalytics.password = googlepassword + ga-report.period = monthly + + Note that your password will be readable by system administrators on your server. Rather than use sensitive account details, it is suggested you give access to the GA account to a new Google account that you create just for this purpose. + +3. Set up this extension's database tables using a paster command. (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):: + + $ paster initdb --config=../ckan/development.ini + +4. Enable the extension in your CKAN config file by adding it to ``ckan.plugins``:: + + 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) and specifying the name of your auth file (token.dat by default) from the previous step:: + + $ paster loadanalytics token.dat latest --config=../ckan/development.ini + +The value after the token file is how much data you want to retrieve, this can be + +* **all** - data for all time (since 2010) + +* **latest** - (default) just the 'latest' data + +* **YYYY-MM-DD** - just data for all time periods going back to (and including) this date + + + +Software Licence +================ + +This software is developed by Cabinet Office. It is Crown Copyright and opened up under the Open Government Licence (OGL) (which is compatible with Creative Commons Attibution License). + +OGL terms: http://www.nationalarchives.gov.uk/doc/open-government-licence/ + --- /dev/null +++ b/ckanext/__init__.py @@ -1,1 +1,8 @@ +# this is a namespace package +try: + import pkg_resources + pkg_resources.declare_namespace(__name__) +except ImportError: + import pkgutil + __path__ = pkgutil.extend_path(__path__, __name__) --- /dev/null +++ b/ckanext/ga_report/__init__.py @@ -1,1 +1,8 @@ +# this is a namespace package +try: + import pkg_resources + pkg_resources.declare_namespace(__name__) +except ImportError: + import pkgutil + __path__ = pkgutil.extend_path(__path__, __name__) --- /dev/null +++ b/ckanext/ga_report/command.py @@ -1,1 +1,101 @@ +import logging +import datetime +from ckan.lib.cli import CkanCommand +# No other CKAN imports allowed until _load_config is run, +# or logging is disabled + + +class InitDB(CkanCommand): + """Initialise the extension's database tables + """ + summary = __doc__.split('\n')[0] + usage = __doc__ + max_args = 0 + min_args = 0 + + def command(self): + self._load_config() + + import ckan.model as model + model.Session.remove() + model.Session.configure(bind=model.meta.engine) + log = logging.getLogger('ckanext.ga-report') + + import ga_model + ga_model.init_tables() + log.info("DB tables are setup") + + +class GetAuthToken(CkanCommand): + """ Get's the Google auth token + + Usage: paster getauthtoken + + Where is the file name containing the details + for the service (obtained from https://code.google.com/apis/console). + By default this is set to credentials.json + """ + summary = __doc__.split('\n')[0] + usage = __doc__ + max_args = 0 + min_args = 0 + + def command(self): + """ + In this case we don't want a valid service, but rather just to + force the user through the auth flow. We allow this to complete to + act as a form of verification instead of just getting the token and + assuming it is correct. + """ + from ga_auth import init_service + init_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 + + 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 + back to (and including) this date + """ + summary = __doc__.split('\n')[0] + usage = __doc__ + max_args = 2 + min_args = 1 + + def command(self): + self._load_config() + + from download_analytics import DownloadAnalytics + from ga_auth import (init_service, get_profile_id) + + try: + svc = init_service(self.args[0], None) + except TypeError: + print ('Have you correctly run the getauthtoken task and ' + 'specified the correct file here') + return + + 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': + downloader.latest() + else: + since_date = datetime.datetime.strptime(time_period, '%Y-%m-%d') + downloader.since_date(since_date) + --- /dev/null +++ b/ckanext/ga_report/controller.py @@ -1,1 +1,10 @@ +import logging +from ckan.lib.base import BaseController, c, render +import report_model +log = logging.getLogger('ckanext.ga-report') + +class GaReport(BaseController): + def index(self): + return render('index.html') + --- /dev/null +++ b/ckanext/ga_report/download_analytics.py @@ -1,1 +1,138 @@ +import logging +import datetime +from pylons import config + +import ga_model + +#from ga_client import GA + +log = logging.getLogger('ckanext.ga-report') + +FORMAT_MONTH = '%Y-%m' + +class DownloadAnalytics(object): + '''Downloads and stores analytics info''' + + 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): + self.since_date(datetime.datetime(2010, 1, 1)) + + def latest(self): + if self.period == 'monthly': + # from first of this month to today + now = datetime.datetime.now() + first_of_this_month = datetime.datetime(now.year, now.month, 1) + periods = ((now.strftime(FORMAT_MONTH), + now.day, + first_of_this_month, now),) + else: + raise NotImplementedError + self.download_and_store(periods) + + + def since_date(self, since_date): + assert isinstance(since_date, datetime.datetime) + periods = [] # (period_name, period_complete_day, start_date, end_date) + if self.period == 'monthly': + first_of_the_months_until_now = [] + year = since_date.year + month = since_date.month + now = datetime.datetime.now() + first_of_this_month = datetime.datetime(now.year, now.month, 1) + while True: + first_of_the_month = datetime.datetime(year, month, 1) + if first_of_the_month == first_of_this_month: + periods.append((now.strftime(FORMAT_MONTH), + now.day, + first_of_this_month, now)) + 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, 1)\ + - datetime.timedelta(1) + periods.append((now.strftime(FORMAT_MONTH), 0, + first_of_the_month, last_of_the_month)) + else: + # first_of_the_month has got to the future somehow + break + month += 1 + if month > 12: + year += 1 + month = 1 + else: + raise NotImplementedError + self.download_and_store(periods) + + @staticmethod + def get_full_period_name(period_name, period_complete_day): + if period_complete_day: + 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: + log.info('Downloading Analytics for period "%s" (%s - %s)', + self.get_full_period_name(period_name, period_complete_day), + start_date.strftime('%Y %m %d'), + end_date.strftime('%Y %m %d')) + data = self.download(start_date, end_date) + log.info('Storing Analytics for period "%s"', + self.get_full_period_name(period_name, period_complete_day)) + self.store(period_name, period_complete_day, data) + + + 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') + # url + #query = 'ga:pagePath=~^%s,ga:pagePath=~^%s' % \ + # (PACKAGE_URL, self.resource_url_tag) + query = 'ga:pagePath=~/dataset/[a-z0-9-]+$' + metrics = 'ga:uniquePageviews' + sort = '-ga:uniquePageviews' + + # 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, + dimensions="ga:pagePath", + end_date=end_date).execute() + + import pprint + pprint.pprint(results) + print 'Total results: %s' % results.get('totalResults') + + packages = [] + for entry in results.get('rows'): + (loc,size,) = entry + packages.append( ('http:/' + loc,size, '',) ) + return dict(url=packages) + + def print_results(self, results): + import pprint + pprint.pprint(results) + if results: + print 'Profile: %s' % results.get('profileInfo').get('profileName') + + 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: + ga_model.update_url_stats(period_name, period_complete_day, data['url']) + --- /dev/null +++ b/ckanext/ga_report/ga_auth.py @@ -1,1 +1,70 @@ +import os +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): + """ + Either returns the user's oauth credentials or uses the credentials + file to generate a token (by forcing the user to login in the browser) + """ + 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 init_service(token_file, credentials_file): + """ + Given a file containing the user's oauth token (and another with + credentials in case we need to generate the token) will return a + service object representing the analytics API. + """ + 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 the profile ID for this user and the service specified by the + 'googleanalytics.id' configuration option. This function iterates + over all of the accounts available to the user who invoked the + service to find one where the account name matches (in case the + user has several). + """ + accounts = service.management().accounts().list().execute() + + if not accounts.get('items'): + return None + + accountName = config.get('googleanalytics.account') + webPropertyId = config.get('googleanalytics.id') + for acc in accounts.get('items'): + if acc.get('name') == accountName: + accountId = acc.get('id') + + webproperties = service.management().webproperties().list(accountId=accountId).execute() + + profiles = service.management().profiles().list( + accountId=accountId, webPropertyId=webPropertyId).execute() + + if profiles.get('items'): + return profiles.get('items')[0].get('id') + + return None + --- /dev/null +++ b/ckanext/ga_report/ga_model.py @@ -1,1 +1,102 @@ +import re +import uuid +from sqlalchemy import Table, Column, MetaData +from sqlalchemy import types +from sqlalchemy.sql import select +from sqlalchemy.orm import mapper +from sqlalchemy import func + +import ckan.model as model +from ckan.lib.base import * + +def make_uuid(): + return unicode(uuid.uuid4()) + + + +class GA_Url(object): + + def __init__(self, **kwargs): + for k,v in kwargs.items(): + setattr(self, k, v) + + +metadata = MetaData() +url_table = Table('ga_url', metadata, + Column('id', types.UnicodeText, primary_key=True, + default=make_uuid), + Column('period_name', types.UnicodeText), + Column('period_complete_day', types.Integer), + Column('visits', types.Integer), + Column('url', types.UnicodeText), + Column('next_page', types.UnicodeText), + ) +mapper(GA_Url, url_table) + + +def init_tables(): + metadata.create_all(model.meta.engine) + + +cached_tables = {} + + +def get_table(name): + if name not in cached_tables: + meta = MetaData() + meta.reflect(bind=model.meta.engine) + table = meta.tables[name] + cached_tables[name] = table + return cached_tables[name] + + +def _normalize_url(url): + '''Strip off the hostname etc. Do this before storing it. + + >>> normalize_url('http://data.gov.uk/dataset/weekly_fuel_prices') + '/dataset/weekly_fuel_prices' + ''' + url = re.sub('https?://(www\.)?data.gov.uk', '', url) + return url + + +def _get_department_id_of_url(url): + # e.g. /dataset/fuel_prices + # e.g. /dataset/fuel_prices/resource/e63380d4 + dataset_match = re.match('/dataset/([^/]+)(/.*)?', url) + if dataset_match: + dataset_ref = dataset_match.groups()[0] + dataset = model.Package.get(dataset_ref) + if dataset: + publisher_groups = dataset.get_groups('publisher') + if publisher_groups: + return publisher_groups[0].id + + +def update_url_stats(period_name, period_complete_day, url_data): + table = get_table('ga_url') + for url, views, next_page in url_data: + url = _normalize_url(url) + department_id = _get_department_id_of_url(url) + # see if the row for this url & month is in the table already + item = model.Session.query(GA_Url).filter(GA_Url.period_name==period_name).filter(GA_Url.url==url).first() + if item: + item.period_name = period_complete_day=period_complete_day + item.views = views + item.department_id = department_id + item.next_page = next_page + model.Session.add(item) + else: + # create the row + values = {'id': make_uuid(), + 'period_name': period_name, + 'period_complete_day': period_complete_day, + 'url': url, + 'views': views, + 'department_id': department_id, + 'next_page': next_page} + obj = GA_Url(**values) + model.Session.add(obj) + model.Session.commit() + --- /dev/null +++ b/ckanext/ga_report/plugin.py @@ -1,1 +1,26 @@ +import logging +import ckan.lib.helpers as h +from ckan.plugins import implements, toolkit +import gasnippet +import commands +import dbutil +log = logging.getLogger('ckanext.ga-report') + +class GoogleAnalyticsPlugin(p.SingletonPlugin): + implements(p.IConfigurer, inherit=True) + implements(p.IRoutes, inherit=True) + + def update_config(self, config): + toolkit.add_template_directory(config, 'templates') + toolkit.add_public_directory(config, 'public') + + def after_map(self, map): + map.connect( + '/data/analytics/index', + controller='ckanext.ga-report.controller:GaReport', + action='index' + ) + return map + + --- /dev/null +++ b/ckanext/ga_report/report_model.py --- /dev/null +++ b/ckanext/ga_report/tests/test_auth.py @@ -1,1 +1,41 @@ +import os +from nose.tools import assert_equal +from ckanext.ga_report.ga_auth import (init_service, get_profile_id) +class TestAuth: + + @classmethod + def setup_class(cls): + if not os.path.exists("token.dat") or not os.path.exists("credentials.json"): + print '*' * 60 + print "Tests may not run without first having run the auth process" + print '*' * 60 + + @classmethod + def teardown_class(cls): + pass + + def test_init(self): + try: + res = init_service(None, None) + assert False, "Init service worked without credentials or tokens" + except TypeError: + pass + + def test_init_with_token(self): + res = init_service("token.dat", None) + assert res is not None, "Init service worked without credentials" + + def test_init_with_token_and_credentials(self): + res = init_service("token.dat", "credentials.json") + assert res is not None, "Unable to create service with valid details" + + def test_init_with_redentials(self): + #res = init_service("", "credentials.json") + # Triggers the auth flow via the browser + pass + + def test_get_profile(self): + svc = init_service("token.dat", "credentials.json") + profile = get_profile_id(svc) + assert profile is not None, "Unable to find a profile given configured UA id and user details" --- /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" + } +} + --- /dev/null +++ b/setup.py @@ -1,1 +1,37 @@ +from setuptools import setup, find_packages +import sys, os +version = '0.1' + +setup( + name='ckanext-ga-report', + version=version, + description="GA reporting for CKAN", + long_description="""\ + """, + classifiers=[], # Get strings from http://pypi.python.org/pypi?%3Aaction=list_classifiers + keywords='', + author='David Read', + author_email='david.read@hackneyworkshop.com', + url='', + license='', + packages=find_packages(exclude=['ez_setup', 'examples', 'tests']), + namespace_packages=['ckanext', 'ckanext.ga_report'], + include_package_data=True, + zip_safe=False, + install_requires=[ + 'gdata', + 'google-api-python-client' + ], + entry_points=\ + """ + [ckan.plugins] + # Add plugins here, eg + ga-report=ckanext.ga_report.plugin:GaReportPlugin + + [paste.paster_command] + loadanalytics = ckanext.ga_report.command:LoadAnalytics + initdb = ckanext.ga_report.command:InitDB + """, +) +