Added new method to get a recent score for a dataset
Added new method to get a recent score for a dataset

import logging import logging
import datetime import datetime
   
from ckan.lib.cli import CkanCommand from ckan.lib.cli import CkanCommand
# No other CKAN imports allowed until _load_config is run, # No other CKAN imports allowed until _load_config is run,
# or logging is disabled # or logging is disabled
   
   
class InitDB(CkanCommand): class InitDB(CkanCommand):
"""Initialise the extension's database tables """Initialise the extension's database tables
""" """
summary = __doc__.split('\n')[0] summary = __doc__.split('\n')[0]
usage = __doc__ usage = __doc__
max_args = 0 max_args = 0
min_args = 0 min_args = 0
   
def command(self): def command(self):
self._load_config() self._load_config()
   
import ckan.model as model import ckan.model as model
model.Session.remove() model.Session.remove()
model.Session.configure(bind=model.meta.engine) model.Session.configure(bind=model.meta.engine)
log = logging.getLogger('ckanext.ga-report') log = logging.getLogger('ckanext.ga-report')
   
import ga_model import ga_model
ga_model.init_tables() ga_model.init_tables()
log.info("DB tables are setup") log.info("DB tables are setup")
   
   
class GetAuthToken(CkanCommand): class GetAuthToken(CkanCommand):
""" Get's the Google auth token """ Get's the Google auth token
   
Usage: paster getauthtoken <credentials_file> Usage: paster getauthtoken <credentials_file>
   
Where <credentials_file> is the file name containing the details Where <credentials_file> is the file name containing the details
for the service (obtained from https://code.google.com/apis/console). for the service (obtained from https://code.google.com/apis/console).
By default this is set to credentials.json By default this is set to credentials.json
""" """
summary = __doc__.split('\n')[0] summary = __doc__.split('\n')[0]
usage = __doc__ usage = __doc__
max_args = 0 max_args = 0
min_args = 0 min_args = 0
   
def command(self): def command(self):
""" """
In this case we don't want a valid service, but rather just to In this case we don't want a valid service, but rather just to
force the user through the auth flow. We allow this to complete to force the user through the auth flow. We allow this to complete to
act as a form of verification instead of just getting the token and act as a form of verification instead of just getting the token and
assuming it is correct. assuming it is correct.
""" """
from ga_auth import init_service from ga_auth import init_service
init_service('token.dat', init_service('token.dat',
self.args[0] if self.args self.args[0] if self.args
else 'credentials.json') else 'credentials.json')
   
   
class LoadAnalytics(CkanCommand): class LoadAnalytics(CkanCommand):
"""Get data from Google Analytics API and save it """Get data from Google Analytics API and save it
in the ga_model in the ga_model
   
Usage: paster loadanalytics <tokenfile> <time-period> Usage: paster loadanalytics <tokenfile> <time-period>
   
Where <tokenfile> is the name of the auth token file from Where <tokenfile> is the name of the auth token file from
the getauthtoken step. the getauthtoken step.
   
And where <time-period> is: And where <time-period> is:
all - data for all time all - data for all time
latest - (default) just the 'latest' data latest - (default) just the 'latest' data
YYYY-MM - just data for the specific month YYYY-MM - just data for the specific month
""" """
summary = __doc__.split('\n')[0] summary = __doc__.split('\n')[0]
usage = __doc__ usage = __doc__
max_args = 2 max_args = 2
min_args = 1 min_args = 1
   
def __init__(self, name): def __init__(self, name):
super(LoadAnalytics, self).__init__(name) super(LoadAnalytics, self).__init__(name)
self.parser.add_option('-d', '--delete-first', self.parser.add_option('-d', '--delete-first',
action='store_true', action='store_true',
default=False, default=False,
dest='delete_first', dest='delete_first',
help='Delete data for the period first') help='Delete data for the period first')
self.parser.add_option('-s', '--slip_url_stats', self.parser.add_option('-s', '--skip_url_stats',
action='store_true', action='store_true',
default=False, default=False,
dest='skip_url_stats', dest='skip_url_stats',
help='Skip the download of URL data - just do site-wide stats') help='Skip the download of URL data - just do site-wide stats')
   
def command(self): def command(self):
self._load_config() self._load_config()
   
from download_analytics import DownloadAnalytics from download_analytics import DownloadAnalytics
from ga_auth import (init_service, get_profile_id) from ga_auth import (init_service, get_profile_id)
   
try: try:
svc = init_service(self.args[0], None) svc = init_service(self.args[0], None)
except TypeError: except TypeError:
print ('Have you correctly run the getauthtoken task and ' print ('Have you correctly run the getauthtoken task and '
'specified the correct token file?') 'specified the correct token file?')
return return
   
downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc), downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc),
delete_first=self.options.delete_first, delete_first=self.options.delete_first,
skip_url_stats=self.options.skip_url_stats) skip_url_stats=self.options.skip_url_stats)
   
time_period = self.args[1] if self.args and len(self.args) > 1 \ time_period = self.args[1] if self.args and len(self.args) > 1 \
else 'latest' else 'latest'
if time_period == 'all': if time_period == 'all':
downloader.all_() downloader.all_()
elif time_period == 'latest': elif time_period == 'latest':
downloader.latest() downloader.latest()
else: else:
# The month to use # The month to use
for_date = datetime.datetime.strptime(time_period, '%Y-%m') for_date = datetime.datetime.strptime(time_period, '%Y-%m')
downloader.specific_month(for_date) downloader.specific_month(for_date)
   
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, GA_Publisher from ga_model import GA_Url, GA_Stat, GA_ReferralStat, GA_Publisher
   
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):
'''Returns a list of all the month names''' '''Returns a list of all the month names'''
months = [] months = []
vals = model.Session.query(cls.period_name).filter(cls.period_name!='All').distinct().all() vals = model.Session.query(cls.period_name).filter(cls.period_name!='All').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', 'Bounces']: if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounce rate (home page)']:
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 in ['New visits','Bounces']: if key in ['New visits','Bounce rate (home page)']:
val = "%s%%" % val val = "%s%%" % val
if key in ['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 ['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]))
   
for k, v in keys.iteritems(): for k, v in keys.iteritems():
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[e.key] += int(e.value) d[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)
   
# 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 GaDatasetReport(BaseController): class GaDatasetReport(BaseController):
""" """
Displays the pageview and visit count for datasets Displays the pageview and visit count for datasets
with options to filter by publisher and time period. with options to filter by publisher and time period.
""" """
def publisher_csv(self, month): def publisher_csv(self, month):
''' '''
Returns a CSV of each publisher with the total number of dataset Returns a CSV of each publisher with the total number of dataset
views & visits. views & visits.
''' '''
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 Title", "Publisher Name", "Views", "Visits", "Period Name"]) writer.writerow(["Publisher Title", "Publisher Name", "Views", "Visits", "Period Name"])
   
for publisher,view,visit in _get_top_publishers(None): for publisher,view,visit in _get_top_publishers(None):
writer.writerow([publisher.title.encode('utf-8'), writer.writerow([publisher.title.encode('utf-8'),
publisher.name.encode('utf-8'), publisher.name.encode('utf-8'),
view, view,
visit, visit,
month]) month])
   
def dataset_csv(self, id='all', month='all'): def dataset_csv(self, id='all', month='all'):
''' '''
Returns a CSV with the number of views & visits for each dataset. Returns a CSV with the number of views & visits for each dataset.
   
:param id: A Publisher ID or None if you want for all :param id: A Publisher ID or None if you want for all
:param month: The time period, or 'all' :param month: The time period, or 'all'
''' '''
c.month = month if not month == 'all' else '' c.month = month if not month == 'all' else ''
if id != 'all': if id != 'all':
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; charset=utf-8" response.headers['Content-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = \ response.headers['Content-Disposition'] = \
str('attachment; filename=datasets_%s_%s.csv' % (c.publisher_name,