| *.py[co] | *.py[co] |
| *.py~ | |
| .gitignore | |
| # Packages | # Packages |
| *.egg | *.egg |
| *.egg-info | *.egg-info |
| dist | dist |
| build | build |
| eggs | eggs |
| parts | parts |
| bin | bin |
| var | var |
| sdist | sdist |
| develop-eggs | develop-eggs |
| .installed.cfg | .installed.cfg |
| # Private info | |
| credentials.json | |
| token.dat | |
| # Installer logs | # Installer logs |
| pip-log.txt | pip-log.txt |
| # Unit test / coverage reports | # Unit test / coverage reports |
| .coverage | .coverage |
| .tox | .tox |
| #Translations | #Translations |
| *.mo | *.mo |
| #Mr Developer | #Mr Developer |
| .mr.developer.cfg | .mr.developer.cfg |
| ckanext-ga-report | |
| ================= | |
| For creating detailed reports of CKAN analytics, sliced by group |
| 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/datagovuk/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) | |
| ga-report.period = monthly | |
| Note that your credentials 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 <https://developers.google.com/analytics/resources/tutorials/hello-analytics-api>`_ 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 <https://code.google.com/apis/console>`_ | |
| 2. Sign-in and create a project or use an existing project. | |
| 3. In the `Services pane <https://code.google.com/apis/console#:services>`_ , activate Analytics API for your project. If prompted, read and accept the terms of service. | |
| 4. Go to the `API Access pane <https://code.google.com/apis/console/#:access>`_ | |
| 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/ | |
| # this is a namespace package | |
| try: | |
| import pkg_resources | |
| pkg_resources.declare_namespace(__name__) | |
| except ImportError: | |
| import pkgutil | |
| __path__ = pkgutil.extend_path(__path__, __name__) | |
| # this is a namespace package | |
| try: | |
| import pkg_resources | |
| pkg_resources.declare_namespace(__name__) | |
| except ImportError: | |
| import pkgutil | |
| __path__ = pkgutil.extend_path(__path__, __name__) | |
| 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 <credentials_file> | |
| Where <credentials_file> 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 <tokenfile> <time-period> | |
| Where <tokenfile> is the name of the auth token file from | |
| the getauthtoken step. | |
| And where <time-period> is: | |
| all - data for all time | |
| latest - (default) just the 'latest' data | |
| YYYY-MM - just data for the specific month | |
| """ | |
| 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: | |
| # The month to use | |
| for_date = datetime.datetime.strptime(time_period, '%Y-%m') | |
| downloader.specific_month(for_date) | |
| import re | |
| import csv | |
| import sys | |
| import logging | |
| import operator | |
| import collections | |
| from ckan.lib.base import BaseController, c, render, request, response, abort | |
| import sqlalchemy | |
| from sqlalchemy import func, cast, Integer | |
| import ckan.model as model | |
| from ga_model import GA_Url, GA_Stat | |
| log = logging.getLogger('ckanext.ga-report') | |
| def _get_month_name(strdate): | |
| import calendar | |
| from time import strptime | |
| d = strptime(strdate, '%Y-%m') | |
| return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) | |
| def _month_details(cls): | |
| months = [] | |
| vals = model.Session.query(cls.period_name).distinct().all() | |
| for m in vals: | |
| months.append( (m[0], _get_month_name(m[0]))) | |
| return sorted(months, key=operator.itemgetter(0), reverse=True) | |
| class GaReport(BaseController): | |
| def csv(self, month): | |
| import csv | |
| q = model.Session.query(GA_Stat) | |
| if month != 'all': | |
| q = q.filter(GA_Stat.period_name==month) | |
| entries = q.order_by('GA_Stat.period_name, GA_Stat.stat_name, GA_Stat.key').all() | |
| response.headers['Content-Type'] = "text/csv; charset=utf-8" | |
| response.headers['Content-Disposition'] = str('attachment; filename=stats_%s.csv' % (month,)) | |
| writer = csv.writer(response) | |
| writer.writerow(["Period", "Statistic", "Key", "Value"]) | |
| for entry in entries: | |
| writer.writerow([entry.period_name.encode('utf-8'), | |
| entry.stat_name.encode('utf-8'), | |
| entry.key.encode('utf-8'), | |
| entry.value.encode('utf-8')]) | |
| def index(self): | |
| # Get the month details by fetching distinct values and determining the | |
| # month names from the values. | |
| c.months = _month_details(GA_Stat) | |
| # Work out which month to show, based on query params of the first item | |
| c.month_desc = 'all time' | |
| c.month = request.params.get('month', '') | |
| if c.month: | |
| c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) | |
| q = model.Session.query(GA_Stat).\ | |
| filter(GA_Stat.stat_name=='Totals') | |
| if c.month: | |
| q = q.filter(GA_Stat.period_name==c.month) | |
| entries = q.order_by('ga_stat.key').all() | |
| def clean_key(key, val): | |
| if key in ['Average time on site', 'Pages per visit', 'Percent new visits']: | |
| val = "%.2f" % round(float(val), 2) | |
| if key == 'Average time on site': | |
| mins, secs = divmod(float(val), 60) | |
| hours, mins = divmod(mins, 60) | |
| val = '%02d:%02d:%02d (%s seconds) ' % (hours, mins, secs, val) | |
| if key == 'Percent new visits': | |
| key = 'New visits' | |
| val = "%s%%" % val | |
| if key in ['Bounces', 'Total pageviews']: | |
| val = int(val) | |
| if key == 'Total pageviews': | |
| key = 'Total page views' | |
| return key, val | |
| c.global_totals = [] | |
| if c.month: | |
| for e in entries: | |
| key, val = clean_key(e.key, e.value) | |
| c.global_totals.append((key, val)) | |
| else: | |
| d = collections.defaultdict(list) | |
| for e in entries: | |
| d[e.key].append(float(e.value)) | |
| for k, v in d.iteritems(): | |
| if k in ['Bounces', 'Total pageviews']: | |
| v = sum(v) | |
| else: | |
| v = float(sum(v))/len(v) | |
| key, val = clean_key(k,v) | |
| c.global_totals.append((key, val)) | |
| c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0)) | |
| keys = { | |
| 'Browser versions': 'browser_versions', | |
| 'Browsers': 'browsers', | |
| 'Operating Systems versions': 'os_versions', | |
| 'Operating Systems': 'os', | |
| 'Social sources': 'social_networks', | |
| 'Languages': 'languages', | |
| 'Country': 'country' | |
| } | |
| browser_version_re = re.compile("(.*)\((.*)\)") | |
| for k, v in keys.iteritems(): | |
| def clean_field(key): | |
| if k != 'Browser versions': | |
| return key | |
| m = browser_version_re.match(key) | |
| bro |