--- a/ckanext/ga_report/controller.py +++ b/ckanext/ga_report/controller.py @@ -1,13 +1,15 @@ import re +import csv +import sys 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') @@ -38,6 +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"]) @@ -67,15 +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']: 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 == 'New visits': + val = "%s%%" % val + if key in ['Bounces', 'Total page views', 'Total visits']: val = int(val) + return key, val c.global_totals = [] @@ -88,7 +93,7 @@ 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 ['Bounces', 'Total page views', 'Total visits']: v = sum(v) else: v = float(sum(v))/len(v) @@ -97,12 +102,38 @@ 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(): @@ -141,9 +172,17 @@ entries.append((key,val,)) entries = sorted(entries, key=operator.itemgetter(1), reverse=True) - setattr(c, v, [(k,v) for k,v in entries ]) - - + 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') @@ -153,6 +192,45 @@ Displays the pageview and visit count for specific publishers based on 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, + visit, + month]) + + def index(self): @@ -166,6 +244,11 @@ 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() + + 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 @@ -176,54 +259,31 @@ and period_name=%s """ q = q + """ - group by department_id order by views desc limit 20; + 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/%%' - c.top_publishers = [] + 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') - - - def read(self, id): - count = 20 - - c.publisher = model.Group.get(id) - if not c.publisher: - abort(404, 'A publisher with that name could not be found') - c.top_packages = [] # package, dataset_views in c.top_packages - - # Get the month details by fetching distinct values and determining the - # month names from the values. - c.months = _month_details(GA_Url) - - # 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' - else: - c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) - - c.publisher_page_views = 0 - q = model.Session.query(GA_Url).\ - filter(GA_Url.url=='/publisher/%s' % c.publisher.name) - if c.month: - entry = q.filter(GA_Url.period_name==c.month).first() - c.publisher_page_views = entry.pageviews if entry else 0 - else: - for e in q.all(): - c.publisher_page_views = c.publisher_page_views + int(e.pageviews) - - + 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: + count = sys.maxint + + top_packages = [] q = model.Session.query(GA_Url).\ - filter(GA_Url.department_id==c.publisher.name).\ + 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) @@ -232,7 +292,7 @@ if c.month: for entry in q[:count]: p = model.Package.get(entry.url[len('/dataset/'):]) - c.top_packages.append((p,entry.pageviews,entry.visitors)) + top_packages.append((p,entry.pageviews,entry.visitors)) else: ds = {} for entry in q.all(): @@ -248,7 +308,40 @@ for k, v in ds.iteritems(): results.append((k,v['views'],v['visits'])) - c.top_packages = sorted(results, key=operator.itemgetter(1), reverse=True) + top_packages = sorted(results, key=operator.itemgetter(1), reverse=True) + return top_packages + + + def read(self, id): + count = 20 + + c.publisher = model.Group.get(id) + if not c.publisher: + abort(404, 'A publisher with that name could not be found') + c.top_packages = [] # package, dataset_views in c.top_packages + + # Get the month details by fetching distinct values and determining the + # month names from the values. + c.months = _month_details(GA_Url) + + # 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' + else: + c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) + + c.publisher_page_views = 0 + q = model.Session.query(GA_Url).\ + filter(GA_Url.url=='/publisher/%s' % c.publisher.name) + if c.month: + entry = q.filter(GA_Url.period_name==c.month).first() + c.publisher_page_views = entry.pageviews if entry else 0 + else: + for e in q.all(): + c.publisher_page_views = c.publisher_page_views + int(e.pageviews) + + c.top_packages = self._get_packages(c.publisher, 20) return render('ga_report/publisher/read.html')