|
import re |
|
import csv |
|
import sys |
import logging |
import logging |
import operator |
import operator |
from ckan.lib.base import BaseController, c, render, request, response |
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(str): |
def _get_month_name(strdate): |
import calendar |
import calendar |
from time import strptime |
from time import strptime |
d = strptime('2012-10', '%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))) |
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-disposition'] = 'attachment; filename=dgu_analytics_%s.csv' % (month) |
|
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).all() |
q = model.Session.query(GA_Stat).\ |
c.global_totals = [(s.key, s.value) for s in entries ] |
filter(GA_Stat.stat_name=='Totals') |
|
if c.month: |
|
q = q.filter(GA_Stat.period_name==c.month) |
|
entries = q.order_by('ga_stat.key').all() |
|
|
|
def clean_key(key, val): |
|
if key in ['Average time on site', 'Pages per visit', 'New visits']: |
|
val = "%.2f" % round(float(val), 2) |
|
if key == 'Average time on site': |
|
mins, secs = divmod(float(val), 60) |
|
hours, mins = divmod(mins, 60) |
|
val = '%02d:%02d:%02d (%s seconds) ' % (hours, mins, secs, val) |
|
if key == 'New visits': |
|
val = "%s%%" % val |
|
if key in ['Bounces', '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 ['Bounces', '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) |
|
|
|
def percent(num, total): |
|
p = 100 * float(num)/float(total) |
|
return "%.2f%%" % round(p, 2) |
|
|
|
# Get the total for each set of values and then set the value as |
|
# 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 self._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, |
|