--- a/ckanext/ga_report/controller.py +++ b/ckanext/ga_report/controller.py @@ -4,12 +4,12 @@ import logging import operator import collections -from ckan.lib.base import BaseController, c, render, request, response, abort +from ckan.lib.base import (BaseController, c, g, render, request, response, abort) import sqlalchemy from sqlalchemy import func, cast, Integer 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') @@ -40,6 +40,7 @@ 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-Disposition'] = str('attachment; filename=stats_%s.csv' % (month,)) writer = csv.writer(response) writer.writerow(["Period", "Statistic", "Key", "Value"]) @@ -57,7 +58,7 @@ c.months = _month_details(GA_Stat) # Work out which month to show, based on query params of the first item - c.month_desc = 'all time' + c.month_desc = 'all months' c.month = request.params.get('month', '') if c.month: c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) @@ -69,15 +70,17 @@ entries = q.order_by('ga_stat.key').all() def clean_key(key, val): - if key in ['Average time on site', 'Pages per visit', 'Percent new visits']: + if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounces']: 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) - key = '%s *' % key - if key in ['Bounces', 'Total pageviews']: + if key in ['New visits','Bounces']: + val = "%s%%" % val + if key in ['Total page views', 'Total visits']: val = int(val) + return key, val c.global_totals = [] @@ -90,21 +93,48 @@ for e in entries: d[e.key].append(float(e.value)) for k, v in d.iteritems(): - if k in ['Bounces', 'Total pageviews']: + 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 = { - 'Browser versions': 'browsers', - 'Operating Systems versions': 'os', + 'Browser versions': 'browser_versions', + 'Browsers': 'browsers', + 'Operating Systems versions': 'os_versions', + 'Operating Systems': 'os', 'Social sources': 'social_networks', 'Languages': 'languages', '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(): @@ -143,9 +173,13 @@ entries.append((key,val,)) entries = sorted(entries, key=operator.itemgetter(1), reverse=True) - setattr(c, v, [(k,v) for k,v in entries ]) - - + # 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') @@ -156,17 +190,15 @@ the datasets associated with the publisher. """ def csv(self, month): - #q = model.Session.query(GA_Stat) - #if month != '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() + 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): + for publisher,view,visit in _get_publishers(None): writer.writerow([publisher.title.encode('utf-8'), view, visit, @@ -183,6 +215,8 @@ 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"]) @@ -203,42 +237,14 @@ # Work out which month to show, based on query params of the first item c.month = request.params.get('month', '') - c.month_desc = 'all time' + c.month_desc = 'all months' if c.month: c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) - c.top_publishers = self._get_publishers() + c.top_publishers = _get_publishers() return render('ga_report/publisher/index.html') - def _get_publishers(self, 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 _get_packages(self, publisher, count=-1): if count == -1: @@ -290,7 +296,7 @@ # Work out which month to show, based on query params of the first item c.month = request.params.get('month', '') if not c.month: - c.month_desc = 'all time' + c.month_desc = 'all months' else: c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) @@ -308,3 +314,37 @@ 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) +