gitphp 0.2.9.1 :: ckanext-ga-report.git/commitdiff

Changes to support % of bounces from /

3 files changed: (show all)
README.rst
ckanext/ga_report/controller.py
ckanext/ga_report/download_analytics.py

file:a/README.rst -> file:b/README.rst

file:a/ckanext/ga_report/controller.py -> file:b/ckanext/ga_report/controller.py

import re	import re
import csv	import csv
import sys	import sys
import logging	import logging
import operator	import operator
import collections	import collections
from ckan.lib.base import (BaseController, c, g, render, request, response, abort)	from ckan.lib.base import (BaseController, c, g, render, request, response, abort)

import sqlalchemy	import sqlalchemy
from sqlalchemy import func, cast, Integer	from sqlalchemy import func, cast, Integer
import ckan.model as model	import ckan.model as model
from ga_model import GA_Url, GA_Stat, GA_ReferralStat	from ga_model import GA_Url, GA_Stat, GA_ReferralStat

log = logging.getLogger('ckanext.ga-report')	log = logging.getLogger('ckanext.ga-report')


def _get_month_name(strdate):	def _get_month_name(strdate):
import calendar	import calendar
from time import strptime	from time import strptime
d = strptime(strdate, '%Y-%m')	d = strptime(strdate, '%Y-%m')
return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year)	return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year)


def _month_details(cls):	def _month_details(cls):
months = []	months = []
vals = model.Session.query(cls.period_name).distinct().all()	vals = model.Session.query(cls.period_name).distinct().all()
for m in vals:	for m in vals:
months.append( (m[0], _get_month_name(m[0])))	months.append( (m[0], _get_month_name(m[0])))
return sorted(months, key=operator.itemgetter(0), reverse=True)	return sorted(months, key=operator.itemgetter(0), reverse=True)


class GaReport(BaseController):	class GaReport(BaseController):

def csv(self, month):	def csv(self, month):
import csv	import csv

q = model.Session.query(GA_Stat)	q = model.Session.query(GA_Stat)
if month != 'all':	if month != 'all':
q = q.filter(GA_Stat.period_name==month)	q = q.filter(GA_Stat.period_name==month)
entries = q.order_by('GA_Stat.period_name, GA_Stat.stat_name, GA_Stat.key').all()	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-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = str('attachment; filename=stats_%s.csv' % (month,))	response.headers['Content-Disposition'] = str('attachment; filename=stats_%s.csv' % (month,))

writer = csv.writer(response)	writer = csv.writer(response)
writer.writerow(["Period", "Statistic", "Key", "Value"])	writer.writerow(["Period", "Statistic", "Key", "Value"])

for entry in entries:	for entry in entries:
writer.writerow([entry.period_name.encode('utf-8'),	writer.writerow([entry.period_name.encode('utf-8'),
entry.stat_name.encode('utf-8'),	entry.stat_name.encode('utf-8'),
entry.key.encode('utf-8'),	entry.key.encode('utf-8'),
entry.value.encode('utf-8')])	entry.value.encode('utf-8')])

def index(self):	def index(self):

# Get the month details by fetching distinct values and determining the	# Get the month details by fetching distinct values and determining the
# month names from the values.	# month names from the values.
c.months = _month_details(GA_Stat)	c.months = _month_details(GA_Stat)

# Work out which month to show, based on query params of the first item	# Work out which month to show, based on query params of the first item
c.month_desc = 'all months'	c.month_desc = 'all months'
c.month = request.params.get('month', '')	c.month = request.params.get('month', '')
if c.month:	if c.month:
c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])	c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])

q = model.Session.query(GA_Stat).\	q = model.Session.query(GA_Stat).\
filter(GA_Stat.stat_name=='Totals')	filter(GA_Stat.stat_name=='Totals')
if c.month:	if c.month:
q = q.filter(GA_Stat.period_name==c.month)	q = q.filter(GA_Stat.period_name==c.month)
entries = q.order_by('ga_stat.key').all()	entries = q.order_by('ga_stat.key').all()

def clean_key(key, val):	def clean_key(key, val):
if key in ['Average time on site', 'Pages per visit', 'New visits']:	if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounces']:
val = "%.2f" % round(float(val), 2)	val = "%.2f" % round(float(val), 2)
if key == 'Average time on site':	if key == 'Average time on site':
mins, secs = divmod(float(val), 60)	mins, secs = divmod(float(val), 60)
hours, mins = divmod(mins, 60)	hours, mins = divmod(mins, 60)
val = '%02d:%02d:%02d (%s seconds) ' % (hours, mins, secs, val)	val = '%02d:%02d:%02d (%s seconds) ' % (hours, mins, secs, val)
if key == 'New visits':	if key in ['New visits','Bounces']:
val = "%s%%" % val	val = "%s%%" % val
if key in ['Bounces', 'Total page views', 'Total visits']:	if key in ['Total page views', 'Total visits']:
val = int(val)	val = int(val)

return key, val	return key, val

c.global_totals = []	c.global_totals = []
if c.month:	if c.month:
for e in entries:	for e in entries:
key, val = clean_key(e.key, e.value)	key, val = clean_key(e.key, e.value)
c.global_totals.append((key, val))	c.global_totals.append((key, val))
else:	else:
d = collections.defaultdict(list)	d = collections.defaultdict(list)
for e in entries:	for e in entries:
d[e.key].append(float(e.value))	d[e.key].append(float(e.value))
for k, v in d.iteritems():	for k, v in d.iteritems():
if k in ['Bounces', 'Total page views', 'Total visits']:	if k in ['Total page views', 'Total visits']:
v = sum(v)	v = sum(v)
else:	else:
v = float(sum(v))/len(v)	v = float(sum(v))/len(v)
key, val = clean_key(k,v)	key, val = clean_key(k,v)

c.global_totals.append((key, val))	c.global_totals.append((key, val))
c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0))	c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0))

keys = {	keys = {
'Browser versions': 'browser_versions',	'Browser versions': 'browser_versions',
'Browsers': 'browsers',	'Browsers': 'browsers',
'Operating Systems versions': 'os_versions',	'Operating Systems versions': 'os_versions',
'Operating Systems': 'os',	'Operating Systems': 'os',
'Social sources': 'social_networks',	'Social sources': 'social_networks',
'Languages': 'languages',	'Languages': 'languages',
'Country': 'country'	'Country': 'country'
}	}

def shorten_name(name, length=60):	def shorten_name(name, length=60):
return (name[:length] + '..') if len(name) > 60 else name	return (name[:length] + '..') if len(name) > 60 else name

def fill_out_url(url):	def fill_out_url(url):
import urlparse	import urlparse
return urlparse.urljoin(g.site_url, url)	return urlparse.urljoin(g.site_url, url)

c.social_referrer_totals, c.social_referrers = [], []	c.social_referrer_totals, c.social_referrers = [], []
q = model.Session.query(GA_ReferralStat)	q = model.Session.query(GA_ReferralStat)
q = q.filter(GA_ReferralStat.period_name==c.month) if c.month else q	q = q.filter(GA_ReferralStat.period_name==c.month) if c.month else q
q = q.order_by('ga_referrer.count::int desc')	q = q.order_by('ga_referrer.count::int desc')
for entry in q.all():	for entry in q.all():
c.social_referrers.append((shorten_name(entry.url), fill_out_url(entry.url),	c.social_referrers.append((shorten_name(entry.url), fill_out_url(entry.url),
entry.source,entry.count))	entry.source,entry.count))

q = model.Session.query(GA_ReferralStat.url,	q = model.Session.query(GA_ReferralStat.url,
func.sum(GA_ReferralStat.count).label('count'))	func.sum(GA_ReferralStat.count).label('count'))
q = q.filter(GA_ReferralStat.period_name==c.month) if c.month else q	q = q.filter(GA_ReferralStat.period_name==c.month) if c.month else q
q = q.order_by('count desc').group_by(GA_ReferralStat.url)	q = q.order_by('count desc').group_by(GA_ReferralStat.url)
for entry in q.all():	for entry in q.all():
c.social_referrer_totals.append((shorten_name(entry[0]), fill_out_url(entry[0]),'',	c.social_referrer_totals.append((shorten_name(entry[0]), fill_out_url(entry[0]),'',
entry[1]))	entry[1]))


browser_version_re = re.compile("(.)$(.)$")	browser_version_re = re.compile("(.)$(.)$")
for k, v in keys.iteritems():	for k, v in keys.iteritems():

def clean_field(key):	def clean_field(key):
if k != 'Browser versions':	if k != 'Browser versions':
return key	return key
m = browser_version_re.match(key)	m = browser_version_re.match(key)
browser = m.groups()[0].strip()	browser = m.groups()[0].strip()
ver = m.groups()[1]	ver = m.groups()[1]
parts = ver.split('.')	parts = ver.split('.')
if len(parts) > 1:	if len(parts) > 1:
if parts[1][0] == '0':	if parts[1][0] == '0':
ver = parts[0]	ver = parts[0]
else:	else:
ver = "%s.%s" % (parts[0],parts[1])	ver = "%s.%s" % (parts[0],parts[1])
if browser in ['Safari','Android Browser']: # Special case complex version nums	if browser in ['Safari','Android Browser']: # Special case complex version nums
ver = parts[0]	ver = parts[0]
if len(ver) > 2:	if len(ver) > 2:
ver = "%s%sX" % (ver[0], ver[1])	ver = "%s%sX" % (ver[0], ver[1])

return "%s (%s)" % (browser, ver,)	return "%s (%s)" % (browser, ver,)

q = model.Session.query(GA_Stat).\	q = model.Session.query(GA_Stat).\
filter(GA_Stat.stat_name==k)	filter(GA_Stat.stat_name==k)
if c.month:	if c.month:
entries = []	entries = []
q = q.filter(GA_Stat.period_name==c.month).\	q = q.filter(GA_Stat.period_name==c.month).\
order_by('ga_stat.value::int desc')	order_by('ga_stat.value::int desc')

d = collections.defaultdict(int)	d = collections.defaultdict(int)
for e in q.all():	for e in q.all():
d[clean_field(e.key)] += int(e.value)	d[clean_field(e.key)] += int(e.value)
entries = []	entries = []
for key, val in d.iteritems():	for key, val in d.iteritems():
entries.append((key,val,))	entries.append((key,val,))
entries = sorted(entries, key=operator.itemgetter(1), reverse=True)	entries = sorted(entries, key=operator.itemgetter(1), reverse=True)

def percent(num, total):
p = 100 * float(num)/float(total)
return "%.2f%%" % round(p, 2)

# Get the total for each set of values and then set the value as	# Get the total for each set of values and then set the value as
# a percentage of the total	# a percentage of the total
if k == 'Social sources':	if k == 'Social sources':
total = sum([x for n,x in c.global_totals if n == 'Total visits'])	total = sum([x for n,x in c.global_totals if n == 'Total visits'])
else:	else:
total = sum([num for _,num in entries])	total = sum([num for _,num in entries])
setattr(c, v, [(k,percent(v,total)) for k,v in entries ])	setattr(c, v, [(k,_percent(v,total)) for k,v in entries ])

return render('ga_report/site/index.html')	return render('ga_report/site/index.html')


class GaPublisherReport(BaseController):	class GaPublisherReport(BaseController):
"""	"""
Displays the pageview and visit count for specific publishers based on	Displays the pageview and visit count for specific publishers based on
the datasets associated with the publisher.	the datasets associated with the publisher.
"""	"""
def csv(self, month):	def csv(self, month):

c.month = month if not month =='all' else ''	c.month = month if not month =='all' else ''
response.headers['Content-Type'] = "text/csv; charset=utf-8"	response.headers['Content-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = str('attachment; filename=publishers_%s.csv' % (month,))	response.headers['Content-Disposition'] = str('attachment; filename=publishers_%s.csv' % (month,))

writer = csv.writer(response)	writer = csv.writer(response)
writer.writerow(["Publisher", "Views", "Visits", "Period Name"])	writer.writerow(["Publisher", "Views", "Visits", "Period Name"])

for publisher,view,visit in _get_publishers(None):	for publisher,view,visit in _get_publishers(None):
writer.writerow([publisher.title.encode('utf-8'),	writer.writerow([publisher.title.encode('utf-8'),
view,	view,
visit,	visit,
month])	month])



def publisher_csv(self, id, month):	def publisher_csv(self, id, month):

c.month = month if not month =='all' else ''	c.month = month if not month =='all' else ''
c.publisher = model.Group.get(id)	c.publisher = model.Group.get(id)
if not c.publisher:	if not c.publisher:
abort(404, 'A publisher with that name could not be found')	abort(404, 'A publisher with that name could not be found')

packages = self._get_packages(c.publisher)	packages = self._get_packages(c.publisher)
response.headers['Content-Type'] = "text/csv; c

ckanext-ga-report	ckanext-ga-report
=================	=================

Status: Development	Status: Development

CKAN Version: 1.7.1+	CKAN Version: 1.7.1+


Overview	Overview
--------	--------

For creating detailed reports of CKAN analytics, including totals per group.	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).	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:	Contents of this extension:

* Use the CLI tool to download Google Analytics data for each time period into this extension's database tables	* 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	* Users can view the data as web page reports


Installation	Installation
------------	------------

1. Activate you CKAN python environment and install this extension's software::	1. Activate you CKAN python environment and install this extension's software::

$ pyenv/bin/activate	$ pyenv/bin/activate
$ pip install -e git+https://github.com/datagovuk/ckanext-ga-report.git#egg=ckanext-ga-report	$ 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::	2. Ensure you development.ini (or similar) contains the info about your Google Analytics account and configuration::

googleanalytics.id = UA-1010101-1	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.account = Account name (i.e. data.gov.uk, see top level item at https://www.google.com/analytics)
ga-report.period = monthly	ga-report.period = monthly
	ga-report.bounce_url = /data

	The ga-report.bounce_url specifies the path to use when calculating bounces. For DGU this is /data
	but you may want to set this to /.

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.	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)::	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	$ paster initdb --config=../ckan/development.ini

4. Enable the extension in your CKAN config file by adding it to ``ckan.plugins``::	4. Enable the extension in your CKAN config file by adding it to ``ckan.plugins``::

ckan.plugins = ga-report	ckan.plugins = ga-report


Authorization	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:	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>`_	1. Visit the `Google APIs Console <https://code.google.com/apis/console>`_

2. Sign-in and create a project or use an existing project.	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.	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>`_	4. Go to the `API Access pane <https://code.google.com/apis/console/#:access>`_

5. Click Create an OAuth 2.0 client ID....	5. Click Create an OAuth 2.0 client ID....

6. Fill out the Branding Information fields and click Next.	6. Fill out the Branding Information fields and click Next.

7. In Client ID Settings, set Application type to Installed application.	7. In Client ID Settings, set Application type to Installed application.

8. Click Create client ID	8. Click Create client ID

9. The details you need below are Client ID, Client secret, and Redirect URIs	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	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	following command, which will store your oauth token in a file called token.dat once you have finished
giving permission in the browser::	giving permission in the browser::

$ paster getauthtoken --config=../ckan/development.ini	$ paster getauthtoken --config=../ckan/development.ini


Tutorial	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::	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	$ 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	The value after the token file is how much data you want to retrieve, this can be

* all - data for all time (since 2010)	* all - data for all time (since 2010)

* latest - (default) just the 'latest' data	* latest - (default) just the 'latest' data

* YYYY-MM-DD - just data for all time periods going back to (and including) this date	* YYYY-MM-DD - just data for all time periods going back to (and including) this date



Software Licence	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).	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/	OGL terms: http://www.nationalarchives.gov.uk/doc/open-government-licence/