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

Changes to support % of bounces from /

13 files changed: (show all)
README.rst
ckanext/ga_report/controller.py
ckanext/ga_report/download_analytics.py
ckanext/ga_report/ga_model.py
ckanext/ga_report/helpers.py
ckanext/ga_report/plugin.py
ckanext/ga_report/report_model.py (deleted)
ckanext/ga_report/templates/ga_report/ga_popular_datasets.html (new)
ckanext/ga_report/templates/ga_report/ga_popular_single.html (new)
ckanext/ga_report/templates/ga_report/ga_util.html (new)
ckanext/ga_report/templates/ga_report/publisher/index.html
ckanext/ga_report/templates/ga_report/publisher/read.html
ckanext/ga_report/templates/ga_report/site/index.html

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

entries = model.Session.query(GA_Stat).\	q = model.Session.query(GA_Stat)
filter(GA_Stat.period_name==month).\	if month != 'all':
order_by('GA_Stat.stat_name, GA_Stat.key').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-Type'] = "text/csv; charset=utf-8"
	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 = request.params.get('month', c.months[0][0] if c.months else '')	c.month_desc = 'all months'
c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])	c.month = request.params.get('month', '')
	if c.month:
entries = model.Session.query(GA_Stat).\	c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
filter(GA_Stat.stat_name=='Totals').\
filter(GA_Stat.period_name==c.month).\	q = model.Session.query(GA_Stat).\
order_by('ga_stat.key').all()	filter(GA_Stat.stat_name=='Totals')
	if c.month:
c.global_totals = []	q = q.filter(GA_Stat.period_name==c.month)
for e in entries:	entries = q.order_by('ga_stat.key').all()
val = e.value
if e.key in ['Average time on site', 'Pages per visit', 'Percent new visits']:	def clean_key(key, val):
val = "%.2f" % round(float(e.value), 2)	if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounces']:
if e.key == 'Average time on site':	val = "%.2f" % round(float(val), 2)
	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)
e.key = '%s *' % e.key	if key in ['New visits','Bounces']:
c.global_totals.append((e.key, val))	val = "%s%%" % val
	if key in ['Total page views', 'Total visits']:
	val = int(val)

	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 ['Total page views', 'Total visits']:
	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 = {	keys = {
'Browser versions': 'browsers',	'Browser versions': 'browser_versions',
'Operating Systems versions': 'os',	'Browsers': 'browsers',
	'Operating Systems versions': 'os_versions',
	'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):
	return (name[:length] + '..') if len(name) > 60 else name

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

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

	q = model.Session.query(GA_ReferralStat.url,
	func.sum(GA_ReferralStat.count).label('count'))
	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)
	for entry in q.all():
	c.social_referrer_totals.append((shorten_name(entry[0]), fill_out_url(entry[0]),'',
	entry[1]))


	browser_version_re = re.compile("(.)$(.)$")
for k, v in keys.iteritems():	for k, v in keys.iteritems():
entries = model.Session.query(GA_Stat).\
filter(GA_Stat.stat_name==k).\	def clean_field(key):
filter(GA_Stat.period_name==c.month).\	if k != 'Browser versions':
order_by('ga_stat.value::int desc').all()	return key
setattr(c, v, [(s.key, s.value) for s in entries ])	m = browser_version_re.match(key)
	browser = m.groups()[0].strip()
	ver = m.groups()[1]
	parts = ver.split('.')
	if len(parts) > 1:
	if parts[1][0] == '0':
	ver = parts[0]
	else:
	ver = "%s.%s" % (parts[0],parts[1])
	if browser in ['Safari','Android Browser']: # Special case complex version nums
	ver = parts[0]
	if len(ver) > 2:
	ver = "%s%sX" % (ver[0], ver[1])

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

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

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

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

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

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

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



	def publisher_csv(self, id, month):

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

	packages = self._get_packages(c.publisher)
	response.headers['Content-Type'] = "text/csv; charset=utf-8"
	response.headers['Content-Disposition'] = \
	str('attachment; filename=%s_%s.csv' % (c.publisher.name, month,))

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

	for package,view,visit in packages:
	writer.writerow([package.title.encode('utf-8'),
	view,
	visit,
	month])



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_Url)	c.months = _month_details(GA_Url)

# 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 = request.params.get('month', c.months[0][0] if c.months else '')	c.month = request.params.get('month', '')
c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])	c.month_desc = 'all months'
	if c.month:
connection = model.Session.connection()	c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
q = """
select department_id, sum(pageviews::int) views, sum(visitors::int) visits	c.top_publishers = _get_publishers()
from ga_url
where department_id <> ''
and period_name=%s
group by department_id order by views desc limit 20;
"""
# Add this back (before and period_name =%s) if you want to ignore publisher
# homepage views
# and not url like '/publisher/%%'

c.top_publishers = []
res = connection.execute(q, c.month)
for row in res:
c.top_publishers.append((model.Group.get(row[0]), row[1], row[2]))

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


	def _get_packages(self, publisher, count=-1):
	if count == -1:
	count = sys.maxint

	top_packages = []
	q = model.Session.query(GA_Url).\
	filter(GA_Url.department_id==publisher.name).\
	filter(GA_Url.url.like('/dataset/%'))
	if c.month:
	q = q.filter(GA_Url.period_name==c.month)
	q = q.order_by('ga_url.pageviews::int desc')

	if c.month:
	for entry in q[:count]:
	p = model.Package.get(entry.url[len('/dataset/'):])
	top_packages.append((p,entry.pageviews,entry.visitors))
	else:
	ds = {}
	for entry in q.all():
	if len(ds) >= count:
	break
	p = model.Package.get(entry.url[len('/dataset/'):])
	if not p in ds:
	ds[p] = {'views':0, 'visits': 0}
	ds[p]['views'] = ds[p]['views'] + int(entry.pageviews)
	ds[p]['visits'] = ds[p]['visits'] + int(entry.visitors)

	results = []
	for k, v in ds.iteritems():
	results.append((k,v['views'],v['visits']))

	top_packages = sorted(results, key=operator.itemgetter(1), reverse=True)
	return top_packages


def read(self, id):	def read(self, id):
	count = 20

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')
c.top_packages = [] # package, dataset_views in c.top_packages	c.top_packages = [] # package, dataset_views in c.top_packages

# 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_Url)	c.months = _month_details(GA_Url)

# 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 = request.params.get('month', c.months[0][0] if c.months else '')	c.month = request.params.get('month', '')
c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])	if not c.month:
	c.month_desc = 'all months'
entry = model.Session.query(GA_Url).\	else:
filter(GA_Url.url=='/publisher/%s' % c.publisher.name).\	c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
filter(GA_Url.period_name==c.month).first()
c.publisher_page_views = entry.pageviews if entry else 0	c.publisher_page_views = 0
	q = model.Session.query(GA_Url).\
entries = model.Session.query(GA_Url).\	filter(GA_Url.url=='/publisher/%s' % c.publisher.name)
filter(GA_Url.department_id==c.publisher.name).\	if c.month:
filter(GA_Url.period_name==c.month).\	entry = q.filter(GA_Url.period_name==c.month).first()
order_by('ga_url.pageviews::int desc')[:20]	c.publisher_page_views = entry.pageviews if entry else 0
for entry in entries:	else:
if entry.url.startswith('/dataset/'):	for e in q.all():
p = model.Package.get(entry.url[len('/dataset/'):])	c.publisher_page_views = c.publisher_page_views + int(e.pageviews)
c.top_packages.append((p,entry.pageviews,entry.visitors))
	c.top_packages = self._get_packages(c.publisher, 20)

return render('ga_report/publisher/read.html')	return render('ga_report/publisher/read.html')

	def _get_publishers(limit=20):
	connection = model.Session.connection()
	q = """
	select department_id, sum(pageviews::int) views, sum(visitors::int) visits
	from ga_url
	where department_id <> ''"""
	if c.month:
	q = q + """
	and period_name=%s
	"""
	q = q + """
	group by department_id order by views desc
	"""
	if limit:
	q = q + " limit %s;" % (limit)

	# Add this back (before and period_name =%s) if you want to ignore publisher
	# homepage views
	# and not url like '/publisher/%%'

	top_publishers = []
	res = connection.execute(q, c.month)

	for row in res:
	g = model.Group.get(row[0])
	if g:
	top_publishers.append((g, row[1], row[2]))
	return top_publishers


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

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

import os	import os
import logging	import logging
import datetime	import datetime
	import collections
from pylons import config	from pylons import config

import ga_model	import ga_model

#from ga_client import GA	#from ga_client import GA

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

FORMAT_MONTH = '%Y-%m'	FORMAT_MONTH = '%Y-%m'

class DownloadAnalytics(object):	class DownloadAnalytics(object):
'''Downloads and stores analytics info'''	'''Downloads and stores analytics info'''

def __init__(self, service=None, profile_id=None):	def __init__(self, service=None, profile_id=None):
self.period = config['ga-report.period']	self.period = config['ga-report.period']
self.service = service	self.service = service
self.profile_id = profile_id	self.profile_id = profile_id


def specific_month(self, date):	def specific_month(self, date):
import calendar	import calendar

first_of_this_month = datetime.datetime(date.year, date.month, 1)	first_of_this_month = datetime.datetime(date.year, date.month, 1)
_, last_day_of_month = calendar.monthrange(int(date.year), int(date.month))	_, last_day_of_month = calendar.monthrange(int(date.year), int(date.month))
last_of_this_month = datetime.datetime(date.year, date.month, last_day_of_month)	last_of_this_month = datetime.datetime(date.year, date.month, last_day_of_month)
periods = ((date.strftime(FORMAT_MONTH),	periods = ((date.strftime(FORMAT_MONTH),
last_day_of_month,	last_day_of_month,
first_of_this_month, last_of_this_month),)	first_of_this_month, last_of_this_month),)
self.download_and_store(periods)	self.download_and_store(periods)


def latest(self):	def latest(self):
if self.period == 'monthly':	if self.period == 'monthly':
# from first of this month to today	# from first of this month to today
now = datetime.datetime.now()	now = datetime.datetime.now()
first_of_this_month = datetime.datetime(now.year, now.month, 1)	first_of_this_month = datetime.datetime(now.year, now.month, 1)
periods = ((now.strftime(FORMAT_MONTH),	periods = ((now.strftime(FORMAT_MONTH),
now.day,	now.day,
first_of_this_month, now),)	first_of_this_month, now),)
else:	else:
raise NotImplementedError	raise NotImplementedError
self.download_and_store(periods)	self.download_and_store(periods)


def for_date(self, for_date):	def for_date(self, for_date):
assert isinstance(since_date, datetime.datetime)	assert isinstance(since_date, datetime.datetime)
periods = [] # (period_name, period_complete_day, start_date, end_date)	periods = [] # (period_name, period_complete_day, start_date, end_date)
if self.period == 'monthly':	if self.period == 'monthly':
first_of_the_months_until_now = []	first_of_the_months_until_now = []
year = for_date.year	year = for_date.year
month = for_date.month	month = for_date.month
now = datetime.datetime.now()	now = datetime.datetime.now()
first_of_this_month = datetime.datetime(now.year, now.month, 1)	first_of_this_month = datetime.datetime(now.year, now.month, 1)
while True:	while True:
first_of_the_month = datetime.datetime(year, month, 1)	first_of_the_month = datetime.datetime(year, month, 1)
if first_of_the_month == first_of_this_month:	if first_of_the_month == first_of_this_month:
periods.append((now.strftime(FORMAT_MONTH),	periods.append((now.strftime(FORMAT_MONTH),
now.day,	now.day,
first_of_this_month, now))	first_of_this_month, now))
break	break
elif first_of_the_month < first_of_this_month:	elif first_of_the_month < first_of_this_month:
in_the_next_month = first_of_the_month + datetime.timedelta(40)	in_the_next_month = first_of_the_month + datetime.timedelta(40)
last_of_the_month = datetime.datetime(in_the_next_month.year,	last_of_the_month = datetime.datetime(in_the_next_month.year,
in_the_next_month.month, 1)\	in_the_next_month.month, 1)\
- datetime.timedelta(1)	- datetime.timedelta(1)
periods.append((now.strftime(FORMAT_MONTH), 0,	periods.append((now.strftime(FORMAT_MONTH), 0,
first_of_the_month, last_of_the_month))	first_of_the_month, last_of_the_month))
else:	else:
# first_of_the_month has got to the future somehow	# first_of_the_month has got to the future somehow
break	break
month += 1	month += 1
if month > 12:	if month > 12:
year += 1	year += 1
month = 1	month = 1
else:	else:
raise NotImplementedError	raise NotImplementedError
self.download_and_store(periods)	self.download_and_store(periods)

@staticmethod	@staticmethod
def get_full_period_name(period_name, period_complete_day):	def get_full_period_name(period_name, period_complete_day):
if period_complete_day:	if period_complete_day:
return period_name + ' (up to %ith)' % period_complete_day	return period_name + ' (up to %ith)' % period_complete_day
else:	else:
return period_name	return period_name


def download_and_store(self, periods):	def download_and_store(self, periods):
for period_name, period_complete_day, start_date, end_date in periods:	for period_name, period_complete_day, start_date, end_date in periods:
log.info('Downloading Analytics for period "%s" (%s - %s)',	log.info('Downloading Analytics for period "%s" (%s - %s)',
self.get_full_period_name(period_name, period_complete_day),	self.get_full_period_name(period_name, period_complete_day),
start_date.strftime('%Y %m %d'),	start_date.strftime('%Y %m %d'),
end_date.strftime('%Y %m %d'))	end_date.strftime('%Y %m %d'))

data = self.download(start_date, end_date, '~/dataset/[a-z0-9-_]+')	data = self.download(start_date, end_date, '~/dataset/[a-z0-9-_]+')
log.info('Storing Dataset Analytics for period "%s"',	log.info('Storing Dataset Analytics for period "%s"',
self.get_full_period_name(period_name, period_complete_day))	self.get_full_period_name(period_name, period_complete_day))
self.store(period_name, period_complete_day, data, )	self.store(period_name, period_complete_day, data, )

data = self.download(start_date, end_date, '~/publisher/[a-z0-9-_]+')	data = self.download(start_date, end_date, '~/publisher/[a-z0-9-_]+')
log.info('Storing Publisher Analytics for period "%s"',	log.info('Storing Publisher Analytics for period "%s"',
self.get_full_period_name(period_name, period_complete_day))	self.get_full_period_name(period_name, period_complete_day))
self.store(period_name, period_complete_day, data,)	self.store(period_name, period_complete_day, data,)

ga_model.update_publisher_stats(period_name) # about 30 seconds.	ga_model.update_publisher_stats(period_name) # about 30 seconds.
self.sitewide_stats( period_name )	self.sitewide_stats( period_name )

	self.update_social_info(period_name, start_date, end_date)

	def update_social_info(self, period_name, start_date, end_date):
	start_date = start_date.strftime('%Y-%m-%d')
	end_date = end_date.strftime('%Y-%m-%d')
	query = 'ga:hasSocialSourceReferral=~Yes$'
	metrics = 'ga:entrances'
	sort = '-ga:entrances'

	# 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:landingPagePath,ga:socialNetwork",
	max_results=10000,
	end_date=end_date).execute()
	data = collections.defaultdict(list)
	rows = results.get('rows',[])
	for row in rows:
	from ga_model import _normalize_url
	data[_normalize_url(row[0])].append( (row[1], int(row[2]),) )
	ga_model.update_social(period_name, data)


def download(self, start_date, end_date, path='~/dataset/[a-z0-9-_]+'):	def download(self, start_date, end_date, path='~/dataset/[a-z0-9-_]+'):
'''Get data from GA for a given time period'''	'''Get data from GA for a given time period'''
start_date = start_date.strftime('%Y-%m-%d')	start_date = start_date.strftime('%Y-%m-%d')
end_date = end_date.strftime('%Y-%m-%d')	end_date = end_date.strftime('%Y-%m-%d')
query = 'ga:pagePath=%s$' % path	query = 'ga:pagePath=%s$' % path
metrics = 'ga:uniquePageviews, ga:visitors'	metrics = 'ga:uniquePageviews, ga:visitors'
sort = '-ga:uniquePageviews'	sort = '-ga:uniquePageviews'

# Supported query params at	# Supported query params at
# https://developers.google.com/analytics/devguides/reporting/core/v3/reference	# https://developers.google.com/analytics/devguides/reporting/core/v3/reference
results = self.service.data().ga().get(	results = self.service.data().ga().get(
ids='ga:' + self.profile_id,	ids='ga:' + self.profile_id,
filters=query,	filters=query,
start_date=start_date,	start_date=start_date,
metrics=metrics,	metrics=metrics,
sort=sort,	sort=sort,
dimensions="ga:pagePath",	dimensions="ga:pagePath",
max_results=10000,	max_results=10000,
end_date=end_date).execute()	end_date=end_date).execute()

if os.getenv('DEBUG'):
import pprint
pprint.pprint(results)
print 'Total results: %s' % results.get('totalResults')

packages = []	packages = []
for entry in results.get('rows'):	for entry in results.get('rows'):
(loc,pageviews,visits) = entry	(loc,pageviews,visits) = entry
packages.append( ('http:/' + loc, pageviews, visits,) ) # Temporary hack	packages.append( ('http:/' + loc, pageviews, visits,) ) # Temporary hack
return dict(url=packages)	return dict(url=packages)

def store(self, period_name, period_complete_day, data):	def store(self, period_name, period_complete_day, data):
if 'url' in data:	if 'url' in data:
ga_model.update_url_stats(period_name, period_complete_day, data['url'])	ga_model.update_url_stats(period_name, period_complete_day, data['url'])

def sitewide_stats(self, period_name):	def sitewide_stats(self, period_name):
import calendar	import calendar
year, month = period_name.split('-')	year, month = period_name.split('-')
_, last_day_of_month = calendar.monthrange(int(year), int(month))	_, last_day_of_month = calendar.monthrange(int(year), int(month))

start_date = '%s-01' % period_name	start_date = '%s-01' % period_name
end_date = '%s-%s' % (period_name, last_day_of_month)	end_date = '%s-%s' % (period_name, last_day_of_month)
print 'Sitewide_stats for %s (%s -> %s)' % (period_name, start_date, end_date)	print 'Sitewide_stats for %s (%s -> %s)' % (period_name, start_date, end_date)

funcs = ['_totals_stats', '_social_stats', '_os_stats',	funcs = ['_totals_stats', '_social_stats', '_os_stats',
'_locale_stats', '_browser_stats', '_mobile_stats']	'_locale_stats', '_browser_stats', '_mobile_stats']
for f in funcs:	for f in funcs:
print ' + Fetching %s stats' % f.split('_')[1]	print ' + Fetching %s stats' % f.split('_')[1]
getattr(self, f)(start_date, end_date, period_name)	getattr(self, f)(start_date, end_date, period_name)

def _get_results(result_data, f):	def _get_results(result_data, f):
data = {}	data = {}
for result in result_data:	for result in result_data:
key = f(result)	key = f(result)
data[key] = data.get(key,0) + result[1]	data[key] = data.get(key,0) + result[1]
return data	return data

def _totals_stats(self, start_date, end_date, period_name):	def _totals_stats(self, start_date, end_date, period_name):
""" Fetches distinct totals, total pageviews etc """	""" Fetches distinct totals, total pageviews etc """
results = self.service.data().ga().get(	results = self.service.data().ga().get(
ids='ga:' + self.profile_id,	ids='ga:' + self.profile_id,
start_date=start_date,	start_date=start_date,
metrics='ga:uniquePageviews',	metrics='ga:uniquePageviews',
sort='-ga:uniquePageviews',	sort='-ga:uniquePageviews',
max_results=10000,	max_results=10000,
end_date=end_date).execute()	end_date=end_date).execute()
result_data = results.get('rows')	result_data = results.get('rows')
ga_model.update_sitewide_stats(period_name, "Totals", {'Total pageviews': result_data[0][0]})	ga_model.update_sitewide_stats(period_name, "Totals", {'Total page views': result_data[0][0]})

results = self.service.data().ga().get(	results = self.service.data().ga().get(
ids='ga:' + self.profile_id,	ids='ga:' + self.profile_id,
start_date=start_date,	start_date=start_date,
metrics='ga:pageviewsPerVisit,ga:bounces,ga:avgTimeOnSite,ga:percentNewVisits',	metrics='ga:pageviewsPerVisit,ga:avgTimeOnSite,ga:percentNewVisits,ga:visitors',
max_results=10000,	max_results=10000,
end_date=end_date).execute()	end_date=end_date).execute()
result_data = results.get('rows')	result_data = results.get('rows')
data = {	data = {
'Pages per visit': result_data[0][0],	'Pages per visit': result_data[0][0],
'Bounces': result_data[0][1],	'Average time on site': result_data[0][1],
'Average time on site': result_data[0][2],	'New visits': result_data[0][2],
'Percent new visits': result_data[0][3],	'Total visits': result_data[0][3],
}	}
ga_model.update_sitewide_stats(period_name, "Totals", data)	ga_model.update_sitewide_stats(period_name, "Totals", data)

	# Bounces from /data. This url is specified in configuration because
	# for DGU we don't want /.
	path = config.get('ga-report.bounce_url','/')
	print path
	results = self.service.data().ga().get(
	ids='ga:' + self.profile_id,
	filters='ga:pagePath=~%s$' % (path,),
	start_date=start_date,
	metrics='ga:bounces,ga:uniquePageviews',
	dimensions='ga:pagePath',
	max_results=10000,
	end_date=end_date).execute()
	result_data = results.get('rows')
	for results in result_data:
	if results[0] == path:
	bounce, total = [float(x) for x in results[1:]]
	pct = 100 * bounce/total
	print "%d bounces from %d total == %s" % (bounce, total, pct)
	ga_model.update_sitewide_stats(period_name, "Totals", {'Bounces': pct})


def _locale_stats(self, start_date, end_date, period_name):	def _locale_stats(self, start_date, end_date, period_name):
""" Fetches stats about language and country """	""" Fetches stats about language and country """
results = self.service.data().ga().get(	results = self.service.data().ga().get(
ids='ga:' + self.profile_id,	ids='ga:' + self.profile_id,
start_date=start_date,	start_date=start_date,
metrics='ga:uniquePageviews',	metrics='ga:uniquePageviews',
sort='-ga:uniquePageviews',	sort='-ga:uniquePageviews',
dimensions="ga:language,ga:country",	dimensions="ga:language,ga:country",
max_results=10000,	max_results=10000,
end_date=end_date).execute()	end_date=end_date).execute()
result_data = results.get('rows')	result_data = results.get('rows')
data = {}	data = {}
for result in result_data:	for result in result_data:
data[result[0]] = data.get(result[0], 0) + int(result[2])	data[result[0]] = data.get(result[0], 0) + int(result[2])
ga_model.update_sitewide_stats(period_name, "Languages", data)	ga_model.update_sitewide_stats(period_name, "Languages", data)

data = {}	data = {}
for result in result_data:	for result in result_data:
data[result[1]] = data.get(result[1], 0) + int(result[2])	data[result[1]] = data.get(result[1], 0) + int(result[2])
ga_model.update_sitewide_stats(period_name, "Country", data)	ga_model.update_sitewide_stats(period_name, "Country", data)


def _social_stats(self, start_date, end_date, period_name):	def _social_stats(self, start_date, end_date, period_name):
""" Finds out which social sites people are referred from """	""" Finds out which social sites people are referred from """
results = self.service.data().ga().get(	results = self.service.data().ga().get(
ids='ga:' + self.profile_id,	ids='ga:' + self.profile_id,
start_date=start_date,	start_date=start_date,
metrics='ga:uniquePageviews',	metrics='ga:uniquePageviews',
sort='-ga:uniquePageviews',	sort='-ga:uniquePageviews',
dimensions="ga:socialNetwork,ga:referralPath",	dimensions="ga:socialNetwork,ga:referralPath",
max_results=10000,	max_results=10000,
end_date=end_date).execute()	end_date=end_date).execute()
result_data = results.get('rows')	result_data = results.get('rows')
twitter_links = []	twitter_links = []
data = {}	data = {}
for result in result_data:	for result in result_data:
if not result[0] == '(not set)':	if not result[0] == '(not set)':
data[result[0]] = data.get(result[0], 0) + int(result[2])	data[result[0]] = data.get(result[0], 0) + int(result[2])
if result[0] == 'Twitter':	if result[0] == 'Twitter':
twitter_links.append(result[1])	twitter_links.append(result[1])
ga_model.update_sitewide_stats(period_name, "Social sources", data)	ga_model.update_sitewide_stats(period_name, "Social sources", data)


def _os_stats(self, start_date, end_date, period_name):	def _os_stats(self, start_date, end_date, period_name):
""" Operating system stats """	""" Operating system stats """
results = self.service.data().ga().get(	results = self.service.data().ga().get(
ids='ga:' + self.profile_id,	ids='ga:' + self.profile_id,
start_date=start_date,	start_date=start_date,
metrics='ga:uniquePageviews',	metrics='ga:uniquePageviews',
sort='-ga:uniquePageviews',	sort='-ga:uniquePageviews',
dimensions="ga:operatingSystem,ga:operatingSystemVersion",	dimensions="ga:operatingSystem,ga:operatingSystemVersion",
max_results=10000,	max_results=10000,
end_date=end_date).execute()	end_date=end_date).execute()
result_data = results.get('rows')	result_data = results.get('rows')
data = {}	data = {}
for result in result_data:	for result in result_data:
data[result[0]] = data.get(result[0], 0) + int(result[2])	data[result[0]] = data.get(result[0], 0) + int(result[2])
ga_model.update_sitewide_stats(period_name, "Operating Systems", data)	ga_model.update_sitewide_stats(period_name, "Operating Systems", data)

data = {}	data = {}
for result in result_data:	for result in result_data:
key = "%s (%s)" % (result[0],result[1])	key = "%s (%s)" % (result[0],result[1])
data[key] = result[2]	data[key] = result[2]
ga_model.update_sitewide_stats(period_name, "Operating Systems versions", data)	ga_model.update_sitewide_stats(period_name, "Operating Systems versions", data)


def _browser_stats(self, start_date, end_date, period_name):	def _browser_stats(self, start_date, end_date, period_name):
""" Information about browsers and browser versions """	""" Information about browsers and browser versions """
results = self.service.data().ga().get(	results = self.service.data().ga().get(
ids='ga:' + self.profile_id,	ids='ga:' + self.profile_id,
start_date=start_date,	start_date=start_date,
metrics='ga:uniquePageviews',	metrics='ga:uniquePageviews',
sort='-ga:uniquePageviews',	sort='-ga:uniquePageviews',
dimensions="ga:browser,ga:browserVersion",	dimensions="ga:browser,ga:browserVersion",
max_results=10000,	max_results=10000,
end_date=end_date).execute()	end_date=end_date).execute()
result_data = results.get('rows')	result_data = results.get('rows')
data = {}	data = {}
for result in result_data:	for result in result_data:
data[result[0]] = data.get(result[0], 0) + int(result[2])	data[result[0]] = data.get(result[0], 0) + int(result[2])
ga_model.update_sitewide_stats(period_name, "Browsers", data)	ga_model.update_sitewide_stats(period_name, "Browsers", data)

data = {}	data = {}
for result in result_data:	for result in result_data:
key = "%s (%s)" % (result[0], result[1])	key = "%s (%s)" % (result[0], result[1])
data[key] = result[2]	data[key] = result[2]
ga_model.update_sitewide_stats(period_name, "Browser versions", data)	ga_model.update_sitewide_stats(period_name, "Browser versions", data)


def _mobile_stats(self, start_date, end_date, period_name):	def _mobile_stats(self, start_date, end_date, period_name):
""" Info about mobile devices """	""" Info about mobile devices """

results = self.service.data().ga().get(	results = self.service.data().ga().get(
ids='ga:' + self.profile_id,	ids='ga:' + self.profile_id,
start_date=start_date,	start_date=start_date,
metrics='ga:uniquePageviews',	metrics='ga:uniquePageviews',
sort='-ga:uniquePageviews',	sort='-ga:uniquePageviews',
dimensions="ga:mobileDeviceBranding, ga:mobileDeviceInfo",	dimensions="ga:mobileDeviceBranding, ga:mobileDeviceInfo",
max_results=10000,	max_results=10000,
end_date=end_date).execute()	end_date=end_date).execute()

result_data = results.get('rows')	result_data = results.get('rows')
data = {}	data = {}
for result in result_data:	for result in result_data:
data[result[0]] = data.get(result[0], 0) + int(result[2])	data[result[0]] = data.get(result[0], 0) + int(result[2])
ga_model.update_sitewide_stats(period_name, "Mobile brands", data)	ga_model.update_sitewide_stats(period_name, "Mobile brands", data)

data = {}	data = {}
for result in result_data:	for result in result_data:
data[result[1]] = data.get(result[1], 0) + int(result[2])	data[result[1]] = data.get(result[1], 0) + int(result[2])
ga_model.update_sitewide_stats(period_name, "Mobile devices", data)	ga_model.update_sitewide_stats(period_name, "Mobile devices", data)

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

import re	import re
import uuid	import uuid

from sqlalchemy import Table, Column, MetaData	from sqlalchemy import Table, Column, MetaData
from sqlalchemy import types	from sqlalchemy import types
from sqlalchemy.sql import select	from sqlalchemy.sql import select
from sqlalchemy.orm import mapper	from sqlalchemy.orm import mapper
from sqlalchemy import func	from sqlalchemy import func

import ckan.model as model	import ckan.model as model
from ckan.lib.base import *	from ckan.lib.base import *

def make_uuid():	def make_uuid():
return unicode(uuid.uuid4())	return unicode(uuid.uuid4())

	metadata = MetaData()



class GA_Url(object):	class GA_Url(object):

def __init__(self, **kwargs):	def __init__(self, **kwargs):
for k,v in kwargs.items():	for k,v in kwargs.items():
setattr(self, k, v)	setattr(self, k, v)

class GA_Stat(object):

def __init__(self, **kwargs):
for k,v in kwargs.items():
setattr(self, k, v)

class GA_Publisher(object):

def __init__(self, **kwargs):
for k,v in kwargs.items():
setattr(self, k, v)


metadata = MetaData()
url_table = Table('ga_url', metadata,	url_table = Table('ga_url', metadata,
Column('id', types.UnicodeText, primary_key=True,	Column('id', types.UnicodeText, primary_key=True,
default=make_uuid),	default=make_uuid),
Column('period_name', types.UnicodeText),	Column('period_name', types.UnicodeText),
Column('period_complete_day', types.Integer),	Column('period_complete_day', types.Integer),
Column('pageviews', types.UnicodeText),	Column('pageviews', types.UnicodeText),
Column('visitors', types.UnicodeText),	Column('visitors', types.UnicodeText),
Column('url', types.UnicodeText),	Column('url', types.UnicodeText),
Column('department_id', types.UnicodeText),	Column('department_id', types.UnicodeText),
)	)
mapper(GA_Url, url_table)	mapper(GA_Url, url_table)


	class GA_Stat(object):

	def __init__(self, **kwargs):
	for k,v in kwargs.items():
	setattr(self, k, v)

stat_table = Table('ga_stat', metadata,	stat_table = Table('ga_stat', metadata,
Column('id', types.UnicodeText, primary_key=True,	Column('id', types.UnicodeText, primary_key=True,
default=make_uuid),	default=make_uuid),
Column('period_name', types.UnicodeText),	Column('period_name', types.UnicodeText),
Column('stat_name', types.UnicodeText),	Column('stat_name', types.UnicodeText),
Column('key', types.UnicodeText),	Column('key', types.UnicodeText),
Column('value', types.UnicodeText), )	Column('value', types.UnicodeText), )
mapper(GA_Stat, stat_table)	mapper(GA_Stat, stat_table)


	class GA_Publisher(object):

	def __init__(self, **kwargs):
	for k,v in kwargs.items():
	setattr(self, k, v)

pub_table = Table('ga_publisher', metadata,	pub_table = Table('ga_publisher', metadata,
Column('id', types.UnicodeText, primary_key=True,	Column('id', types.UnicodeText, primary_key=True,
default=make_uuid),	default=make_uuid),
Column('period_name', types.UnicodeText),	Column('period_name', types.UnicodeText),
Column('publisher_name', types.UnicodeText),	Column('publisher_name', types.UnicodeText),
Column('views', types.UnicodeText),	Column('views', types.UnicodeText),
Column('visitors', types.UnicodeText),	Column('visitors', types.UnicodeText),
Column('toplevel', types.Boolean, default=False),	Column('toplevel', types.Boolean, default=False),
Column('subpublishercount', types.Integer, default=0),	Column('subpublishercount', types.Integer, default=0),
Column('parent', types.UnicodeText),	Column('parent', types.UnicodeText),
)	)
mapper(GA_Publisher, pub_table)	mapper(GA_Publisher, pub_table)


	class GA_ReferralStat(object):

	def __init__(self, **kwargs):
	for k,v in kwargs.items():
	setattr(self, k, v)

	referrer_table = Table('ga_referrer', metadata,
	Column('id', types.UnicodeText, primary_key=True,
	default=make_uuid),
	Column('period_name', types.UnicodeText),
	Column('source', types.UnicodeText),
	Column('url', types.UnicodeText),
	Column('count', types.Integer),
	)
	mapper(GA_ReferralStat, referrer_table)



def init_tables():	def init_tables():
metadata.create_all(model.meta.engine)	metadata.create_all(model.meta.engine)


cached_tables = {}	cached_tables = {}


def get_table(name):	def get_table(name):
if name not in cached_tables:	if name not in cached_tables:
meta = MetaData()	meta = MetaData()
meta.reflect(bind=model.meta.engine)	meta.reflect(bind=model.meta.engine)
table = meta.tables[name]	table = meta.tables[name]
cached_tables[name] = table	cached_tables[name] = table
return cached_tables[name]	return cached_tables[name]


def _normalize_url(url):	def _normalize_url(url):
'''Strip off the hostname etc. Do this before storing it.	'''Strip off the hostname etc. Do this before storing it.

>>> normalize_url('http://data.gov.uk/dataset/weekly_fuel_prices')	>>> normalize_url('http://data.gov.uk/dataset/weekly_fuel_prices')
'/dataset/weekly_fuel_prices'	'/dataset/weekly_fuel_prices'
'''	'''
url = re.sub('https?://(www\.)?data.gov.uk', '', url)	# Deliberately leaving a /
return url	url = url.replace('http:/','')
	return '/' + '/'.join(url.split('/')[2:])


def _get_department_id_of_url(url):	def _get_department_id_of_url(url):
# e.g. /dataset/fuel_prices	# e.g. /dataset/fuel_prices
# e.g. /dataset/fuel_prices/resource/e63380d4	# e.g. /dataset/fuel_prices/resource/e63380d4
dataset_match = re.match('/dataset/([^/]+)(/.*)?', url)	dataset_match = re.match('/dataset/([^/]+)(/.*)?', url)
if dataset_match:	if dataset_match:
dataset_ref = dataset_match.groups()[0]	dataset_ref = dataset_match.groups()[0]
dataset = model.Package.get(dataset_ref)	dataset = model.Package.get(dataset_ref)
if dataset:	if dataset:
publisher_groups = dataset.get_groups('publisher')	publisher_groups = dataset.get_groups('publisher')
if publisher_groups:	if publisher_groups:
return publisher_groups[0].name	return publisher_groups[0].name
else:	else:
publisher_match = re.match('/publisher/([^/]+)(/.*)?', url)	publisher_match = re.match('/publisher/([^/]+)(/.*)?', url)
if publisher_match:	if publisher_match:
return publisher_match.groups()[0]	return publisher_match.groups()[0]


def update_sitewide_stats(period_name, stat_name, data):	def update_sitewide_stats(period_name, stat_name, data):
for k,v in data.iteritems():	for k,v in data.iteritems():
item = model.Session.query(GA_Stat).\	item = model.Session.query(GA_Stat).\
filter(GA_Stat.period_name==period_name).\	filter(GA_Stat.period_name==period_name).\
filter(GA_Stat.key==k).\	filter(GA_Stat.key==k).\
filter(GA_Stat.stat_name==stat_name).first()	filter(GA_Stat.stat_name==stat_name).first()
if item:	if item:
item.period_name = period_name	item.period_name = period_name
item.key = k	item.key = k
item.value = v	item.value = v
model.Session.add(item)	model.Session.add(item)
else:	else:
# create the row	# create the row
values = {'id': make_uuid(),	values = {'id': make_uuid(),
'period_name': period_name,	'period_name': period_name,
'key': k,	'key': k,
'value': v,	'value': v,
'stat_name': stat_name	'stat_name': stat_name
}	}
model.Session.add(GA_Stat(**values))	model.Session.add(GA_Stat(**values))
model.Session.commit()	model.Session.commit()



def update_url_stats(period_name, period_complete_day, url_data):	def update_url_stats(period_name, period_complete_day, url_data):
for url, views, visitors in url_data:	for url, views, visitors in url_data:
url = _normalize_url(url)	url = _normalize_url(url)
department_id = _get_department_id_of_url(url)	department_id = _get_department_id_of_url(url)

# see if the row for this url & month is in the table already	# see if the row for this url & month is in the table already
item = model.Session.query(GA_Url).\	item = model.Session.query(GA_Url).\
filter(GA_Url.period_name==period_name).\	filter(GA_Url.period_name==period_name).\
filter(GA_Url.url==url).first()	filter(GA_Url.url==url).first()
if item:	if item:
item.period_name = period_name	item.period_name = period_name
item.pageviews = views	item.pageviews = views
item.visitors = visitors	item.visitors = visitors
item.department_id = department_id	item.department_id = department_id
model.Session.add(item)	model.Session.add(item)
else:	else:
# create the row	# create the row
values = {'id': make_uuid(),	values = {'id': make_uuid(),
'period_name': period_name,	'period_name': period_name,
'period_complete_day': period_complete_day,	'period_complete_day': period_complete_day,
'url': url,	'url': url,
'pageviews': views,	'pageviews': views,
'visitors': visitors,	'visitors': visitors,
'department_id': department_id	'department_id': department_id
}	}
model.Session.add(GA_Url(**values))	model.Session.add(GA_Url(**values))
model.Session.commit()	model.Session.commit()


	def update_social(period_name, data):
	# Clean up first.
	model.Session.query(GA_ReferralStat).\
	filter(GA_ReferralStat.period_name==period_name).delete()

	for url,data in data.iteritems():
	for entry in data:
	source = entry[0]
	count = entry[1]

	item = model.Session.query(GA_ReferralStat).\
	filter(GA_ReferralStat.period_name==period_name).\
	filter(GA_ReferralStat.source==source).\
	filter(GA_ReferralStat.url==url).first()
	if item:
	item.count = item.count + count
	model.Session.add(item)
	else:
	# create the row
	values = {'id': make_uuid(),
	'period_name': period_name,
	'source': source,
	'url': url,
	'count': count,
	}
	model.Session.add(GA_ReferralStat(**values))
	model.Session.commit()

def update_publisher_stats(period_name):	def update_publisher_stats(period_name):
"""	"""
Updates the publisher stats from the data retrieved for /dataset/*	Updates the publisher stats from the data retrieved for /dataset/*
and /publisher/*. Will run against each dataset and generates the	and /publisher/*. Will run against each dataset and generates the
totals for the entire tree beneath each publisher.	totals for the entire tree beneath each publisher.
"""	"""
toplevel = get_top_level()	toplevel = get_top_level()
publishers = model.Session.query(model.Group).\	publishers = model.Session.query(model.Group).\
filter(model.Group.type=='publisher').\	filter(model.Group.type=='publisher').\
filter(model.Group.state=='active').all()	filter(model.Group.state=='active').all()
for publisher in publishers:	for publisher in publishers:
views, visitors, subpub = update_publisher(period_name, publisher, publisher.name)	views, visitors, subpub = update_publisher(period_name, publisher, publisher.name)
parent, parents = '', publisher.get_groups('publisher')	parent, parents = '', publisher.get_groups('publisher')
if parents:	if parents:
parent = parents[0].name	parent = parents[0].name
item = model.Session.query(GA_Publisher).\	item = model.Session.query(GA_Publisher).\
filter(GA_Publisher.period_name==period_name).\	filter(GA_Publisher.period_name==period_name).\
filter(GA_Publisher.publisher_name==publisher.name).first()	filter(GA_Publisher.publisher_name==publisher.name).first()
if item:	if item:
item.views = views	item.views = views
item.visitors = visitors	item.visitors = visitors
item.publisher_name = publisher.name	item.publisher_name = publisher.name
item.toplevel = publisher in toplevel	item.toplevel = publisher in toplevel
item.subpublishercount = subpub	item.subpublishercount = subpub
item.parent = parent	item.parent = parent
model.Session.add(item)	model.Session.add(item)
else:	else:
# create the row	# create the row
values = {'id': make_uuid(),	values = {'id': make_uuid(),
'period_name': period_name,	'period_name': period_name,
'publisher_name': publisher.name,	'publisher_name': publisher.name,
'views': views,	'views': views,
'visitors': visitors,	'visitors': visitors,
'toplevel': publisher in toplevel,	'toplevel': publisher in toplevel,
'subpublishercount': subpub,	'subpublishercount': subpub,
'parent': parent	'parent': parent
}	}
model.Session.add(GA_Publisher(**values))	model.Session.add(GA_Publisher(**values))
model.Session.commit()	model.Session.commit()


def update_publisher(period_name, pub, part=''):	def update_publisher(period_name, pub, part=''):
views,visitors,subpub = 0, 0, 0	views,visitors,subpub = 0, 0, 0
for publisher in go_down_tree(pub):	for publisher in go_down_tree(pub):
subpub = subpub + 1	subpub = subpub + 1
items = model.Session.query(GA_Url).\	items = model.Session.query(GA_Url).\
filter(GA_Url.period_name==period_name).\	filter(GA_Url.period_name==period_name).\
filter(GA_Url.department_id==publisher.name).all()	filter(GA_Url.department_id==publisher.name).all()
for item in items:	for item in items:
views = views + int(item.pageviews)	views = views + int(item.pageviews)
visitors = visitors + int(item.visitors)	visitors = visitors + int(item.visitors)

return views, visitors, (subpub-1)	return views, visitors, (subpub-1)


def get_top_level():	def get_top_level():
'''Returns the top level publishers.'''	'''Returns the top level publishers.'''
return model.Session.query(model.Group).\	return model.Session.query(model.Group).\
outerjoin(model.Member, model.Member.table_id == model.Group.id and \	outerjoin(model.Member, model.Member.table_id == model.Group.id and \
model.Member.table_name == 'group' and \	model.Member.table_name == 'group' and \
model.Member.state == 'active').\	model.Member.state == 'active').\
filter(model.Member.id==None).\	filter(model.Member.id==None).\
filter(model.Group.type=='publisher').\	filter(model.Group.type=='publisher').\
order_by(model.Group.name).all()	order_by(model.Group.name).all()

def get_children(publisher):	def get_children(publisher):
'''Finds child publishers for the given publisher (object). (Not recursive)'''	'''Finds child publishers for the given publisher (object). (Not recursive)'''
from ckan.model.group import HIERARCHY_CTE	from ckan.model.group import HIERARCHY_CTE
return model.Session.query(model.Group).\	return model.Session.query(model.Group).\
from_statement(HIERARCHY_CTE).params(id=publisher.id, type='publisher').\	from_statement(HIERARCHY_CTE).params(id=publisher.id, type='publisher').\
all()	all()

def go_down_tree(publisher):	def go_down_tree(publisher):
'''Provided with a publisher object, it walks down the hierarchy and yields each publisher,	'''Provided with a publisher object, it walks down the hierarchy and yields each publisher,
including the one you supply.'''	including the one you supply.'''
yield publisher	yield publisher
for child in get_children(publisher):	for child in get_children(publisher):
for grandchild in go_down_tree(child):	for grandchild in go_down_tree(child):
yield grandchild	yield grandchild

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

import logging	import logging
import operator	import operator
import ckan.lib.base as base	import ckan.lib.base as base
import ckan.model as model	import ckan.model as model

	from ckanext.ga_report.ga_model import GA_Url, GA_Publisher
	from ckanext.ga_report.controller import _get_publishers
_log = logging.getLogger(__name__)	_log = logging.getLogger(__name__)

	def popular_datasets(count=10):
	import random

	publisher = None
	publishers = _get_publishers(30)
	total = len(publishers)
	while not publisher or not datasets:
	rand = random.randrange(0, total)
	publisher = publishers[rand][0]
	if not publisher.state == 'active':
	publisher = None
	continue
	datasets = _datasets_for_publisher(publisher, 10)[:count]

	ctx = {
	'datasets': datasets,
	'publisher': publisher
	}
	return base.render_snippet('ga_report/ga_popular_datasets.html', **ctx)

	def single_popular_dataset(top=20):
	import random

	datasets = {}
	rand = random.randrange(0, top)
	entry = model.Session.query(GA_Url).\
	filter(GA_Url.url.like('/dataset/%')).\
	order_by('ga_url.pageviews::int desc')[rand]


	dataset = None
	while not dataset:
	dataset = model.Package.get(entry.url[len('/dataset/'):])
	if dataset and not dataset.state == 'active':
	dataset = None
	else:
	publisher = model.Group.get(entry.department_id)

	ctx = {
	'dataset': dataset,
	'publisher': publisher
	}
	return base.render_snippet('ga_report/ga_popular_single.html', **ctx)


def most_popular_datasets(publisher, count=20):	def most_popular_datasets(publisher, count=20):
from ckanext.ga_report.ga_model import GA_Url

if not publisher:	if not publisher:
_log.error("No valid publisher passed to 'most_popular_datasets'")	_log.error("No valid publisher passed to 'most_popular_datasets'")
return ""	return ""

datasets = {}	results = _datasets_for_publisher(publisher, count)
entries = model.Session.query(GA_Url).\
filter(GA_Url.department_id==publisher.name).\
filter(GA_Url.url.like('/dataset/%')).\
order_by('ga_url.pageviews::int desc')[:count]
for entry in entries:
p = model.Package.get(entry.url[len('/dataset/'):])
if not p in datasets:
datasets[p] = {'views':0, 'visits': 0}
datasets[p]['views'] = datasets[p]['views'] + int(entry.pageviews)
datasets[p]['visits'] = datasets[p]['visits'] + int(entry.visitors)

results = []
for k, v in datasets.iteritems():
results.append((k,v['views'],v['visits']))

results = sorted(results, key=operator.itemgetter(1), reverse=True)

ctx = {	ctx = {
'dataset_count': len(datasets),	'dataset_count': len(datasets),
'datasets': results,	'datasets': results,

'publisher': publisher	'publisher': publisher
}	}

return base.render_snippet('ga_report/publisher/popular.html', **ctx)	return base.render_snippet('ga_report/publisher/popular.html', **ctx)

	def _datasets_for_publisher(publisher, count):
	datasets = {}
	entries = model.Session.query(GA_Url).\
	filter(GA_Url.department_id==publisher.name).\
	filter(GA_Url.url.like('/dataset/%')).\
	order_by('ga_url.pageviews::int desc').all()
	for entry in entries:
	if len(datasets) < count:
	p = model.Package.get(entry.url[len('/dataset/'):])
	if not p in datasets:
	datasets[p] = {'views':0, 'visits': 0}
	datasets[p]['views'] = datasets[p]['views'] + int(entry.pageviews)
	datasets[p]['visits'] = datasets[p]['visits'] + int(entry.visitors)

	results = []
	for k, v in datasets.iteritems():
	results.append((k,v['views'],v['visits']))

	return sorted(results, key=operator.itemgetter(1), reverse=True)

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

import logging	import logging
import ckan.lib.helpers as h	import ckan.lib.helpers as h
import ckan.plugins as p	import ckan.plugins as p
from ckan.plugins import implements, toolkit	from ckan.plugins import implements, toolkit

	from ckanext.ga_report.helpers import (most_popular_datasets,
	popular_datasets,
	single_popular_dataset)

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

class GAReportPlugin(p.SingletonPlugin):	class GAReportPlugin(p.SingletonPlugin):
implements(p.IConfigurer, inherit=True)	implements(p.IConfigurer, inherit=True)
implements(p.IRoutes, inherit=True)	implements(p.IRoutes, inherit=True)
implements(p.ITemplateHelpers, inherit=True)	implements(p.ITemplateHelpers, inherit=True)

def update_config(self, config):	def update_config(self, config):
toolkit.add_template_directory(config, 'templates')	toolkit.add_template_directory(config, 'templates')
toolkit.add_public_directory(config, 'public')	toolkit.add_public_directory(config, 'public')

def get_helpers(self):	def get_helpers(self):
"""	"""
A dictionary of extra helpers that will be available to provide	A dictionary of extra helpers that will be available to provide
ga report info to templates.	ga report info to templates.
"""	"""
from ckanext.ga_report.helpers import most_popular_datasets
return {	return {
'ga_report_installed': lambda: True,	'ga_report_installed': lambda: True,
	'popular_datasets': popular_datasets,
'most_popular_datasets': most_popular_datasets,	'most_popular_datasets': most_popular_datasets,
	'single_popular_dataset': single_popular_dataset
}	}

def after_map(self, map):	def after_map(self, map):
map.connect(	map.connect(
'/data/analytics/publisher',	'/data/site-usage/publisher',
controller='ckanext.ga_report.controller:GaPublisherReport',	controller='ckanext.ga_report.controller:GaPublisherReport',
action='index'	action='index'
)	)
map.connect(	map.connect(
'/data/analytics/publisher/{id}',	'/data/site-usage/publisher_{month}.csv',
	controller='ckanext.ga_report.controller:GaPublisherReport',
	action='csv'
	)
	map.connect(
	'/data/site-usage/publisher/{id}_{month}.csv',
	controller='ckanext.ga_report.controller:GaPublisherReport',
	action='publisher_csv'
	)
	map.connect(
	'/data/site-usage/publisher/{id}',
controller='ckanext.ga_report.controller:GaPublisherReport',	controller='ckanext.ga_report.controller:GaPublisherReport',
action='read'	action='read'
)	)
map.connect(	map.connect(
'/data/analytics',	'/data/site-usage',
controller='ckanext.ga_report.controller:GaReport',	controller='ckanext.ga_report.controller:GaReport',
action='index'	action='index'
)	)
map.connect(	map.connect(
'/data/analytics/data_{month}.csv',	'/data/site-usage/data_{month}.csv',
controller='ckanext.ga_report.controller:GaReport',	controller='ckanext.ga_report.controller:GaReport',
action='csv'	action='csv'
)	)
return map	return map

file:a/ckanext/ga_report/report_model.py (deleted)

file:b/ckanext/ga_report/templates/ga_report/ga_popular_datasets.html (new)

	<html xmlns:py="http://genshi.edgewall.org/"
	xmlns:i18n="http://genshi.edgewall.org/i18n"
	xmlns:xi="http://www.w3.org/2001/XInclude"
	py:strip="">

	<div class="popular_datasets">
	<div class="pull-right">
	<a href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='index')}" class="btn btn-primary">More popular datasets »</a>
	</div>
	<h2>Popular datasets</h2>
	<h4>${publisher.title}</h4>
	<ul>
	<py:for each="dataset, _, _ in datasets">
	<li>
	<span>${h.link_to(dataset.title, h.url_for(controller='package', action='read', id=dataset.name))}</span>
	<div>${h.truncate(dataset.notes, length=80, whole_word=True)}</div>
	</li>
	</py:for>
	</ul>

	</div>

	</html>

file:b/ckanext/ga_report/templates/ga_report/ga_popular_single.html (new)

	<html xmlns:py="http://genshi.edgewall.org/"
	xmlns:i18n="http://genshi.edgewall.org/i18n"
	xmlns:xi="http://www.w3.org/2001/XInclude"
	py:strip="">


	<div class="popular_datasets">
	<h2>Featured dataset</h2>

	<h3>${h.link_to(dataset.title, h.url_for(controller='package', action='read', id=dataset.name))}</h3> <div>${h.truncate(dataset.notes, length=200, whole_word=True)}</div>
	<p></p>
	<div>
	<a href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='index')}" class="btn btn-primary">More popular datasets</a>
	<a href="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='index')}" class="btn btn-primary">All usage data</a>
	</div>
	</div>


	</html>

file:b/ckanext/ga_report/templates/ga_report/ga_util.html (new)

	<html
	xmlns="http://www.w3.org/1999/xhtml"
	xmlns:i18n="http://genshi.edgewall.org/i18n"
	xmlns:py="http://genshi.edgewall.org/"
	xmlns:xi="http://www.w3.org/2001/XInclude"
	py:strip=""
	>

	<table py:def="social_table(items, with_source=False)" class="table table-condensed table-bordered table-striped">
	<tr>
	<th>Name</th>
	<th py:if="with_source">Source</th>
	<th>Visits</th>
	</tr>
	<py:for each="name, url, source, count in items">
	<tr>
	<td><a href="${url}">${name}</a></td>
	<td py:if="with_source">${source}</td>
	<td>${count}</td>
	</tr>
	</py:for>
	</table>


	<table py:def="stat_table(items, title='Views')" class="table table-condensed table-bordered table-striped">
	<tr>
	<th>Name</th>
	<th>% ${title}</th>
	</tr>
	<py:for each="name, value in items">
	<tr>
	<td>${name}</td>
	<td>${value}</td>
	</tr>
	</py:for>
	</table>


	<div py:def="usage_nav(active_name,publisher)" id="minornavigation">
	<div id="minornavigation-bg-left">
	<div id="minornavigation-bg-right">
	<ul class="nav nav-pills">
	<li py:attrs="{'class': 'active' if active_name=='Site-wide' else None}"><a py:attrs="{'class': 'active' if active_name=='Site-wide' else None}" href="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='index')}"><img src="/images/icons/page_white.png" height="16px" width="16px" alt="None" class="inline-icon "/> Site-wide</a></li>
	<li py:attrs="{'class': 'active' if active_name=='Publishers' else None}">
	<a py:attrs="{'class': 'active' if active_name=='Publishers' else None}" href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='index')}"><img src="/images/icons/page_white.png" height="16px" width="16px" alt="None" class="inline-icon "/> Publishers</a>
	</li>
	<li py:if="publisher" class="active">
	<a class="active" href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='read', id=publisher.name)}"><img src="/images/icons/page_white.png" height="16px" width="16px" alt="None" class="inline-icon "/>${publisher.title}</a>
	</li>

	</ul>
	</div>
	</div>
	</div>


	</html>

file:a/ckanext/ga_report/templates/ga_report/publisher/index.html -> file:b/ckanext/ga_report/templates/ga_report/publisher/index.html

<html xmlns:py="http://genshi.edgewall.org/"	<html xmlns:py="http://genshi.edgewall.org/"
xmlns:i18n="http://genshi.edgewall.org/i18n"	xmlns:i18n="http://genshi.edgewall.org/i18n"
xmlns:xi="http://www.w3.org/2001/XInclude"	xmlns:xi="http://www.w3.org/2001/XInclude"
py:strip="">	py:strip="">

	<xi:include href="../ga_util.html" />

<py:def function="page_title">Publisher Analytics for ${g.site_title}</py:def>	<py:def function="page_title">Publisher Analytics for ${g.site_title}</py:def>

<py:match path="primarysidebar">	<py:match path="primarysidebar">
<li class="widget-container boxed widget_text">	<li class="widget-container boxed widget_text">
<h4>Publishers</h4>	<h4>Publishers</h4>
<p>The table shows the top 20 publishers as recorded by page views of datasets owned by that publisher, and the number of visits to each publisher's home page.</p>	<p>
	Dataset views records the number of times a specific dataset page has been viewed. Visits records the number of unique site visits.
	</p>
	<p>
	Note: this data does not include API calls.
	</p>
	</li>
	<li class="widget-container boxed widget_text">
	<h4>Download</h4>
	<p><center>
	<a class="btn button" href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='csv',month=c.month or 'all')}">Download as CSV</a></center>
	</p>
</li>	</li>
</py:match>	</py:match>


<div py:match="content">	<div py:match="content">
<h1>Publisher Analytics</h1>
<h2>The top 20 publishers</h2>	<h1>Site Usage</h1>

	${usage_nav('Publishers', None)}


<form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='index')}" method="get">	<form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='index')}" method="get">
<div class="controls">	<div class="controls">
<select name="month">	<select name="month">
	<option value='' py:attrs="{'selected': 'selected' if not c.month else None}">All months</option>

<py:for each="val,desc in c.months">	<py:for each="val,desc in c.months">
<option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option>	<option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option>
</py:for>	</py:for>
</select>	</select>
<input class="btn button" type='submit' value="Update"/>	<input class="btn button" type='submit' value="Update"/>
</div>	</div>
</form>	</form>

<table class="table table-condensed table-bordered table-striped">	<table class="table table-condensed table-bordered table-striped">
<tr>	<tr>
<th>Publisher</th>	<th>Publisher</th>
<th>Dataset Views</th>	<th>Dataset Views</th>
<th>Visits</th>	<th>Visits</th>
</tr>	</tr>
<py:for each="publisher, views, visits in c.top_publishers">	<py:for each="publisher, views, visits in c.top_publishers">
<tr>	<tr>
<td>${h.link_to(publisher.title, h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport', action='read', id=publisher.name))}	<td>${h.link_to(publisher.title, h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport', action='read', id=publisher.name))}
</td>	</td>
<td>${views}</td>	<td>${views}</td>
<td>${visits}</td>	<td>${visits}</td>
</tr>	</tr>
</py:for>	</py:for>
</table>	</table>


</div>	</div>

<xi:include href="../../layout.html" />	<xi:include href="../../layout.html" />

<py:def function="optional_footer">	<py:def function="optional_footer">
<script type='text/javascript'>	<script type='text/javascript'>
$('.nav-tabs li a').click(function (e) {	$('.nav-tabs li a').click(function (e) {
e.preventDefault();	e.preventDefault();
$(this).tab('show');	$(this).tab('show');
})	})
</script>	</script>
</py:def>	</py:def>

</html>	</html>

file:a/ckanext/ga_report/templates/ga_report/publisher/read.html -> file:b/ckanext/ga_report/templates/ga_report/publisher/read.html

<html xmlns:py="http://genshi.edgewall.org/"	<html xmlns:py="http://genshi.edgewall.org/"
xmlns:i18n="http://genshi.edgewall.org/i18n"	xmlns:i18n="http://genshi.edgewall.org/i18n"
xmlns:xi="http://www.w3.org/2001/XInclude"	xmlns:xi="http://www.w3.org/2001/XInclude"
py:strip="">	py:strip="">

	<xi:include href="../ga_util.html" />

<py:def function="page_title">Analytics for ${g.site_title}</py:def>	<py:def function="page_title">Analytics for ${g.site_title}</py:def>

<py:match path="primarysidebar">	<py:match path="primarysidebar">
	<li class="widget-container boxed widget_text">
	<h4>Publishers</h4>
	<p>
	Dataset views records the number of times a specific dataset page has been viewed for <a href="${h.url_for(controller='ckanext.dgu.controllers.publisher:PublisherController',action='read',id=c.publisher.name)}">${c.publisher.title}</a>. Visits records the number of unique site visits.
	</p>
	<p>
	Note: this data does not include API calls.
	</p>
	</li>

<li class="widget-container boxed widget_text">	<li class="widget-container boxed widget_text">
<h4>${c.publisher.title}</h4>	<h4>Download</h4>
<p>	<p><center>
The table shows the top 20 most viewed datasets belonging to ${c.publisher.title}.	<a class="btn button" href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='publisher_csv',id=c.publisher.name,month=c.month or 'all')}">Download as CSV</a></center>
</p>	</p>
<p>
As well as showing the number of views within ${c.month_desc}, it will also show the
number of visitors that viewed each dataset.
</p>
<p>The dataset list page for <a href="${h.url_for(controller='ckanext.dgu.controllers.publisher:PublisherController', action='read', id=c.publisher.name)}">${c.publisher.title}</a> was viewed ${c.publisher_page_views} times during ${c.month_desc}</p>
<p>View the <a href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport', action='index')}">publishers</a> leaderboard</p>
</li>	</li>
</py:match>	</py:match>


<div py:match="content">	<div py:match="content">
<h1>Analytics for ${c.publisher.title}</h1>	<h1>Site Usage</h1>

<h2>Top 20 most viewed datasets</h2>	${usage_nav(c.publisher.title, c.publisher)}
<p><em>Note: this data does not include API calls</em></p>

<form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='read',id=c.publisher.name)}" method="get">	<form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='read',id=c.publisher.name)}" method="get">
<div class="controls">	<div class="controls">
<select name="month">	<select name="month">
	<option value='' py:attrs="{'selected': 'selected' if not c.month else None}">All months</option>
<py:for each="val,desc in c.months">	<py:for each="val,desc in c.months">
<option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option>	<option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option>
</py:for>	</py:for>
</select>	</select>
<input class="btn button" type='submit' value="Update"/>	<input class="btn button" type='submit' value="Update"/>
</div>	</div>
</form>	</form>

<table class="table table-condensed table-bordered table-striped">	<table class="table table-condensed table-bordered table-striped">
<tr>	<tr>
<th>Dataset</th>	<th>Dataset</th>
<th>Views</th>	<th>Views</th>
<th>Visits</th>	<th>Visits</th>
</tr>	</tr>
<py:for each="package, views, visits in c.top_packages">	<py:for each="package, views, visits in c.top_packages">
<tr>	<tr>
<td>${h.link_to(package.title or package.name, h.url_for(controller='package', action='read', id=package.name))}	<td>${h.link_to(package.title or package.name, h.url_for(controller='package', action='read', id=package.name))}
</td>	</td>
<td>${views}</td>	<td>${views}</td>
<td>${visits}</td>	<td>${visits}</td>
</tr>	</tr>
</py:for>	</py:for>
</table>	</table>


</div>	</div>

<xi:include href="../../layout.html" />	<xi:include href="../../layout.html" />
</html>	</html>

file:a/ckanext/ga_report/templates/ga_report/site/index.html -> file:b/ckanext/ga_report/templates/ga_report/site/index.html

<html xmlns:py="http://genshi.edgewall.org/"	<html xmlns:py="http://genshi.edgewall.org/"
xmlns:i18n="http://genshi.edgewall.org/i18n"	xmlns:i18n="http://genshi.edgewall.org/i18n"
xmlns:xi="http://www.w3.org/2001/XInclude"	xmlns:xi="http://www.w3.org/2001/XInclude"
py:strip="">	py:strip="">

<py:def function="page_title">Site analytics</py:def>	<xi:include href="../ga_util.html" />

	<py:def function="page_title">Site usage</py:def>

<py:match path="primarysidebar">	<py:match path="primarysidebar">
<li class="widget-container boxed widget_text">	<li class="widget-container boxed widget_text">
<h4>Statistics</h4>	<h4>Site-wide</h4>
<p>It is possible to <a href="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='csv',month=c.month)}">export the analytics data</a> as a CSV file, which contains all of the information for ${c.month_desc}</p>	<p>
	Note: this data does not include API calls and some values have been rounded up to 2 decimal places. Where there are a large number of browser versions they have been grouped together.
	</p>
</li>	</li>
<li class="widget-container boxed widget_text">	<li class="widget-container boxed widget_text">
<h4>Publisher statistics</h4>	<h4>Download</h4>
<p>You can view statistics about specific publishers at the <a href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='index')}">Publisher Analytics</a> page</p>	<p><center>
	<a class="btn button" href="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='csv',month=c.month or 'all')}">Download as CSV</a></center>
	</p>
	</li>

</li>
</py:match>	</py:match>

<div py:match="content">	<div py:match="content">
<h1>Site statistics</h1>	<h1>Site Usage</h1>
	${usage_nav('Site-wide', None)}

<form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='index')}" method="get">	<form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='index')}" method="get">
<div class="controls">	<div class="controls">
<select name="month">	<select name="month">
	<option value='' py:attrs="{'selected': 'selected' if not c.month else None}">All months</option>

<py:for each="val,desc in c.months">	<py:for each="val,desc in c.months">
<option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option>	<option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option>
</py:for>	</py:for>
</select>	</select>
<input class="btn button" type='submit' value="Update"/>	<input class="btn button" type='submit' value="Update"/>
</div>	</div>
</form>	</form>

<div class="tabbable">	<div class="tabbable">
<ul class="nav nav-tabs">	<ul class="nav nav-tabs">
<li class="active"><a href="#totals" data-toggle="tab">Totals</a></li>	<li class="active"><a href="#totals" data-toggle="tab">Totals</a></li>
<li><a href="#browsers" data-toggle="tab">Browsers</a></li>	<li class="dropdown">
<li><a href="#os" data-toggle="tab">Operating Systems</a></li>	<a href="#browsers" class="dropdown-toggle" data-toggle="dropdown">Browsers
<li><a href="#social_networks" data-toggle="tab">Social Networks</a></li>	<b class="caret"></b></a>
	<ul class="dropdown-menu">
	<li><a href="#browsers_names" data-toggle="tab">Browsers</a></li>
	<li><a href="#browsers_versions" data-toggle="tab">Versions</a></li>
	</ul>
	</li>
	<li class="dropdown">
	<a href="#browsers" class="dropdown-toggle" data-toggle="dropdown">Operating<br/>Systems
	<b class="caret"></b></a>
	<ul class="dropdown-menu">
	<li><a href="#os" data-toggle="tab">Operating Systems</a></li>
	<li><a href="#os_versions" data-toggle="tab">Versions</a></li>
	</ul>
	</li>
	<li class="dropdown">
	<a href="#browsers" class="dropdown-toggle" data-toggle="dropdown">Social Networks
	<b class="caret"></b></a>
	<ul class="dropdown-menu">
	<li><a href="#social_networks" data-toggle="tab">All networks</a></li>
	<li><a href="#social_referrals_totals" data-toggle="tab">Referral links</a></li>
	</ul>
	</li>

	<li><a href="#social_networks" data-toggle="tab"></a></li>
<li><a href="#languages" data-toggle="tab">Languages</a></li>	<li><a href="#languages" data-toggle="tab">Languages</a></li>
<li><a href="#country" data-toggle="tab">Country</a></li>	<li><a href="#country" data-toggle="tab">Country</a></li>
</ul>	</ul>
<div class="tab-content">	<div class="tab-content">
<div class="tab-pane active" id="totals">	<div class="tab-pane active" id="totals">
<table class="table table-condensed table-bordered table-striped">	<table class="table table-condensed table-bordered table-striped">
<tr>	<tr>
<th>Name</th>	<th>Name</th>
<th>Value</th>	<th>Value</th>
</tr>	</tr>
<py:for each="name, value in c.global_totals">	<py:for each="name, value in c.global_totals">
<tr>	<tr>
<td>${name}</td>	<td>${name}</td>
<td>${value}</td>	<td>${value}</td>
</tr>	</tr>
</py:for>	</py:for>
</table>	</table>

<p>* Values are rounded up to 2 decimal places.</p>
</div>	</div>
<div class="tab-pane" id="browsers">	<div class="tab-pane" id="browsers_versions">
<table class="table table-condensed table-bordered table-striped">	${stat_table(c.browser_versions)}
<tr>	</div>
<th>Name</th>	<div class="tab-pane" id="browsers_names">
<th>Value</th>	${stat_table(c.browsers)}
</tr>	</div>
<py:for each="name, value in c.browsers">	<div class="tab-pane" id="os">
<tr>	${stat_table(c.os)}
<td>${name}</td>	</div>
<td>${value}</td>	<div class="tab-pane" id="os_versions">
</tr>	${stat_table(c.os_versions)}
</py:for>	</div>
</table>	<div class="tab-pane" id="social_referrals_totals">
</div>	<p>Number of visits to urls referred from social networks</p>
<div class="tab-pane" id="os">	${social_table(c.social_referrer_totals)}
<table class="table table-condensed table-bordered table-striped">
<tr>
<th>Name</th>
<th>Value</th>
</tr>
<py:for each="name, value in c.os">
<tr>
<td>${name}</td>
<td>${value}</td>
</tr>
</py:for>
</table>
</div>	</div>
<div class="tab-pane" id="social_networks">	<div class="tab-pane" id="social_networks">
<table class="table table-condensed table-bordered table-striped">	<p>Percentage of visits referred from these social networks</p>
<tr>
<th>Name</th>	${stat_table(c.social_networks, 'Visits')}
<th>Value</th>
</tr>
<py:for each="name, value in c.social_networks">
<tr>
<td>${name}</td>
<td>${value}</td>
</tr>
</py:for>
</table>
</div>	</div>
<div class="tab-pane" id="languages">	<div class="tab-pane" id="languages">
<table class="table table-condensed table-bordered table-striped">	${stat_table(c.languages)}
<tr>
<th>Name</th>
<th>Value</th>
</tr>
<py:for each="name, value in c.languages">
<tr>
<td>${name}</td>
<td>${value}</td>
</tr>
</py:for>
</table>
</div>	</div>
<div class="tab-pane" id="country">	<div class="tab-pane" id="country">
<table class="table table-condensed table-bordered table-striped">	${stat_table(c.country)}
<tr>
<th>Name</th>
<th>Value</th>
</tr>
<py:for each="name, value in c.country">
<tr>
<td>${name}</td>
<td>${value}</td>
</tr>
</py:for>
</table>
</div>	</div>


</div>	</div>
</div>	</div>



</div>	</div>

<xi:include href="../../layout.html" />	<xi:include href="../../layout.html" />

<py:def function="optional_footer">	<py:def function="optional_footer">
<script type='text/javascript'>	<script type='text/javascript'>
	$('.dropdown-toggle').dropdown();
$('.nav-tabs li a').click(function (e) {	$('.nav-tabs li a').click(function (e) {
e.preventDefault();	e.preventDefault();
$(this).tab('show');	$(this).tab('show');
})	})
	alert(window.location.hash);
</script>	</script>
</py:def>	</py:def>
</html>	</html>

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/