Done integrating graphs onto site_usage/publishers and site_usage/datasets. Including some interesting queries.
Done integrating graphs onto site_usage/publishers and site_usage/datasets. Including some interesting queries.

import logging import logging
import datetime import datetime
import os import os
   
from pylons import config from pylons import config
   
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 FixTimePeriods(CkanCommand):
  """
  Fixes the 'All' records for GA_Urls
   
  It is possible that older urls that haven't recently been visited
  do not have All records. This command will traverse through those
  records and generate valid All records for them.
  """
  summary = __doc__.split('\n')[0]
  usage = __doc__
  max_args = 0
  min_args = 0
   
  def __init__(self, name):
  super(FixTimePeriods, self).__init__(name)
   
  def command(self):
  import ckan.model as model
  from ga_model import post_update_url_stats
  self._load_config()
  model.Session.remove()
  model.Session.configure(bind=model.meta.engine)
   
  log = logging.getLogger('ckanext.ga_report')
   
  log.info("Updating 'All' records for old URLs")
  post_update_url_stats()
  log.info("Processing complete")
   
   
   
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 <time-period> Usage: paster loadanalytics <time-period>
   
Where <time-period> is: 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 = 1 max_args = 1
min_args = 0 min_args = 0
   
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', '--skip_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)
   
ga_token_filepath = os.path.expanduser(config.get('googleanalytics.token.filepath', '')) ga_token_filepath = os.path.expanduser(config.get('googleanalytics.token.filepath', ''))
if not ga_token_filepath: if not ga_token_filepath:
print 'ERROR: In the CKAN config you need to specify the filepath of the ' \ print 'ERROR: In the CKAN config you need to specify the filepath of the ' \
'Google Analytics token file under key: googleanalytics.token.filepath' 'Google Analytics token file under key: googleanalytics.token.filepath'
return return
   
try: try:
svc = init_service(ga_token_filepath, None) svc = init_service(ga_token_filepath, 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 in the CKAN config under ' 'specified the correct token file in the CKAN config under '
'"googleanalytics.token.filepath"?') '"googleanalytics.token.filepath"?')
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[0] if self.args else 'latest' time_period = self.args[0] if self.args 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 json
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')
   
  DOWNLOADS_AVAILABLE_FROM = '2012-12'
   
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 _get_unix_epoch(strdate):
def _month_details(cls): from time import strptime,mktime
  d = strptime(strdate, '%Y-%m')
  return int(mktime(d))
   
  def _month_details(cls, stat_key=None):
''' '''
Returns a list of all the periods for which we have data, unfortunately Returns a list of all the periods for which we have data, unfortunately
knows too much about the type of the cls being passed as GA_Url has a knows too much about the type of the cls being passed as GA_Url has a
more complex query more complex query
   
This may need extending if we add a period_name to the stats This may need extending if we add a period_name to the stats
''' '''
months = [] months = []
day = None day = None
   
vals = model.Session.query(cls.period_name,cls.period_complete_day)\ q = model.Session.query(cls.period_name,cls.period_complete_day)\
.filter(cls.period_name!='All').distinct(cls.period_name)\ .filter(cls.period_name!='All').distinct(cls.period_name)
.order_by("period_name desc").all() if stat_key:
  q= q.filter(cls.stat_name==stat_key)
   
  vals = q.order_by("period_name desc").all()
   
if vals and vals[0][1]: if vals and vals[0][1]:
day = int(vals[0][1]) day = int(vals[0][1])
ordinal = 'th' if 11 <= day <= 13 \ ordinal = 'th' if 11 <= day <= 13 \
else {1:'st',2:'nd',3:'rd'}.get(day % 10, 'th') else {1:'st',2:'nd',3:'rd'}.get(day % 10, 'th')
day = "{day}{ordinal}".format(day=day, ordinal=ordinal) day = "{day}{ordinal}".format(day=day, ordinal=ordinal)
   
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 months, day return months, day
   
   
class GaReport(BaseController): class GaReport(BaseController):
   
def csv(self, month): def csv(self, month):
import csv import csv
   
q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name!='Downloads') q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name!='Downloads')
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.value.encode('utf-8')])  
   
def csv_downloads(self, month):  
import csv  
   
q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name=='Downloads')  
if month != 'all':  
q = q.filter(GA_Stat.period_name==month)  
entries = q.order_by('GA_Stat.period_name, GA_Stat.key').all()  
   
response.headers['Content-Type'] = "text/csv; charset=utf-8"  
response.headers['Content-Disposition'] = str('attachment; filename=downloads_%s.csv' % (month,))  
   
writer = csv.writer(response)  
writer.writerow(["Period", "Resource URL", "Count"])  
   
for entry in entries:  
writer.writerow([entry.period_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, c.day = _month_details(GA_Stat) c.months, c.day = _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', 'Bounce rate (home page)']: 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','Bounce rate (home page)']: 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
   
  # Query historic values for sparkline rendering
  sparkline_query = model.Session.query(GA_Stat)\
  .filter(GA_Stat.stat_name=='Totals')\
  .order_by(GA_Stat.period_name)
  sparkline_data = {}
  for x in sparkline_query:
  sparkline_data[x.key] = sparkline_data.get(x.key,[])
  key, val = clean_key(x.key,float(x.value))
  tooltip = '%s: %s' % (_get_month_name(x.period_name), val)
  sparkline_data[x.key].append( (tooltip,x.value) )
  # Trim the latest month, as it looks like a huge dropoff
  for key in sparkline_data:
  sparkline_data[key] = sparkline_data[key][:-1]
   
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)) sparkline = sparkline_data[e.key]
  c.global_totals.append((key, val, sparkline))
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))/float(len(v)) v = float(sum(v))/float(len(v))
  sparkline = sparkline_data[k]
key, val = clean_key(k,v) key, val = clean_key(k,v)
   
c.global_totals.append((key, val)) c.global_totals.append((key, val, sparkline))
c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0)) # Sort the global totals into a more pleasant order
  def sort_func(x):
  key = x[0]
  total_order = ['Total page views','Total visits','Pages per visit']
&nbs