*.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/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.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 <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-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) | |
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') | |
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/' | |
#query = 'ga:pagePath=~^/User/' | |
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, | |
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": |