From: Ross Jones Date: Wed, 24 Oct 2012 14:34:45 +0000 Subject: Adding site analytics at /data/analytics X-Git-Url: http://maxious.lambdacomplex.org/git/?p=ckanext-ga-report.git&a=commitdiff&h=6d4975d515c59243bbf5779ea686e5c3d90e3cab --- Adding site analytics at /data/analytics - Allows for download as CSV - Also refactored the publisher urls to allow index page and a read for a specific publisher --- --- a/ckanext/ga_report/controller.py +++ b/ckanext/ga_report/controller.py @@ -1,15 +1,82 @@ import logging import operator -from ckan.lib.base import BaseController, c, render,request +from ckan.lib.base import BaseController, c, render, request, response +import sqlalchemy +from sqlalchemy import func, cast, Integer import ckan.model as model -from ga_model import GA_Url +from ga_model import GA_Url, GA_Stat log = logging.getLogger('ckanext.ga-report') + +def _get_month_name(str): + import calendar + from time import strptime + d = strptime('2012-10', '%Y-%m') + return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) + + +def _month_details(cls): + months = [] + vals = model.Session.query(cls.period_name).distinct().all() + for m in vals: + months.append( (m[0], _get_month_name(m))) + return sorted(months, key=operator.itemgetter(0), reverse=True) + + class GaReport(BaseController): + def csv(self, month): + import csv + + entries = model.Session.query(GA_Stat).\ + filter(GA_Stat.period_name==month).\ + order_by('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" + + writer = csv.writer(response) + writer.writerow(["Period", "Statistic", "Key", "Value"]) + + for entry in entries: + writer.writerow([entry.period_name.encode('utf-8'), + entry.stat_name.encode('utf-8'), + entry.key.encode('utf-8'), + entry.value.encode('utf-8')]) + def index(self): + + # Get the month details by fetching distinct values and determining the + # month names from the values. + c.months = _month_details(GA_Stat) + + # 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 = ''.join([m[1] for m in c.months if m[0]==c.month]) + + entries = model.Session.query(GA_Stat).\ + filter(GA_Stat.stat_name=='Totals').\ + filter(GA_Stat.period_name==c.month).all() + c.global_totals = [(s.key, s.value) for s in entries ] + + keys = { + 'Browser versions': 'browsers', + 'Operating Systems versions': 'os', + 'Social sources': 'social_networks', + 'Languages': 'languages', + 'Country': 'country' + } + + for k, v in keys.iteritems(): + entries = model.Session.query(GA_Stat).\ + filter(GA_Stat.stat_name==k).\ + filter(GA_Stat.period_name==c.month).\ + order_by('ga_stat.value::int desc').all() + setattr(c, v, [(s.key, s.value) for s in entries ]) + + return render('ga_report/site/index.html') @@ -19,26 +86,39 @@ the datasets associated with the publisher. """ - def _get_month_name(self, str): - import calendar - from time import strptime - d = strptime('2012-10', '%Y-%m') - return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) + def index(self): + # 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', c.months[0][0] if c.months else '') + c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) + + connection = model.Session.connection() + q = """ + select department_id, sum(pageviews::int) views, sum(visitors::int) visits + from ga_url + where department_id <> '' + and not url like '/publisher/%%' + and period_name=%s + group by department_id order by views desc limit 20; + """ + c.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 index(self, id): + def read(self, id): c.publisher = model.Group.get(id) 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 = [] - vals = model.Session.query(GA_Url.period_name).distinct().all() - for m in vals: - c.months.append( (m[0],self._get_month_name(m))) - - # Sort the months, so most recent is at the head of our list - c.months = sorted(c.months, key=operator.itemgetter(0), reverse=True) + 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', c.months[0][0] if c.months else '') @@ -52,11 +132,11 @@ entries = model.Session.query(GA_Url).\ filter(GA_Url.department_id==c.publisher.name).\ filter(GA_Url.period_name==c.month).\ - order_by('ga_url.pageviews desc')[:10] + order_by('ga_url.pageviews::int desc')[:20] for entry in entries: if entry.url.startswith('/dataset/'): p = model.Package.get(entry.url[len('/dataset/'):]) c.top_packages.append((p,entry.pageviews,entry.visitors)) - return render('ga_report/publisher/index.html') + return render('ga_report/publisher/read.html') --- a/ckanext/ga_report/plugin.py +++ b/ckanext/ga_report/plugin.py @@ -18,14 +18,24 @@ def after_map(self, map): map.connect( - '/data/analytics/', + '/data/analytics', controller='ckanext.ga_report.controller:GaReport', + action='index' + ) + map.connect( + '/data/analytics_{month}.csv', + controller='ckanext.ga_report.controller:GaReport', + action='csv' + ) + map.connect( + '/data/analytics/publisher/', + controller='ckanext.ga_report.controller:GaPublisherReport', action='index' ) map.connect( '/data/analytics/publisher/{id}', controller='ckanext.ga_report.controller:GaPublisherReport', - action='index' + action='read' ) return map --- a/ckanext/ga_report/templates/ga_report/publisher/index.html +++ b/ckanext/ga_report/templates/ga_report/publisher/index.html @@ -3,15 +3,13 @@ xmlns:xi="http://www.w3.org/2001/XInclude" py:strip=""> - Analytics for ${g.site_title} + Publisher Analytics for ${g.site_title}
-

Analytics for ${c.publisher.title}

+

Publisher Analytics

+

The top 20 publishers

-

Most viewed datasets

-

Note: this data does not include API calls

- -
+
+ + + + + +
+
+ +

${c.publisher.title} dataset list was viewed ${c.publisher_page_views} times in ${c.month_desc}

+ + + + + + + + + + + + + + +
DatasetViewsVisits
${h.link_to(package.title or package.name, h.url_for(controller='package', action='read', id=package.name))} + ${views}${visits}
+ + +
+ + + + + + + --- a/ckanext/ga_report/templates/ga_report/site/index.html +++ b/ckanext/ga_report/templates/ga_report/site/index.html @@ -1,1 +1,141 @@ -HAI Site + + + Site analytics + +
+

Site statistics

+ +
+
+ + +
+
+ +

Export data as CSV

+ +
+ +
+
+ + + + + + + + + + + +
NameValue
${name}${value}
+
+
+ + + + + + + + + + + +
NameValue
${name}${value}
+
+
+ + + + + + + + + + + +
NameValue
${name}${value}
+
+
+ + + + + + + + + + + +
NameValue
${name}${value}
+
+
+ + + + + + + + + + + +
NameValue
${name}${value}
+
+
+ + + + + + + + + + + +
NameValue
${name}${value}
+
+ + +
+
+ + + +
+ + + + + + + + + + +