Changes to support % of bounces from /
Changes to support % of bounces from /

file:a/README.rst -> file:b/README.rst
--- a/README.rst
+++ b/README.rst
@@ -33,6 +33,10 @@
       googleanalytics.id = UA-1010101-1
       googleanalytics.account = Account name (i.e. data.gov.uk, see top level item at https://www.google.com/analytics)
       ga-report.period = monthly
+      ga-report.bounce_url = /data
+
+   The ga-report.bounce_url specifies the path to use when calculating bounces. For DGU this is /data
+   but you may want to set this to /.
 
    Note that your credentials will be readable by system administrators on your server. Rather than use sensitive account details, it is suggested you give access to the GA account to a new Google account that you create just for this purpose.
 

--- a/ckanext/ga_report/controller.py
+++ b/ckanext/ga_report/controller.py
@@ -70,15 +70,15 @@
         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']:
+            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)
-                if key == 'New visits':
+                if key in ['New visits','Bounces']:
                     val = "%s%%" % val
-            if key in ['Bounces', 'Total page views', 'Total visits']:
+            if key in ['Total page views', 'Total visits']:
                 val = int(val)
 
             return key, val
@@ -93,11 +93,12 @@
             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']:
+                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))
 
@@ -172,17 +173,13 @@
                 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 ])
+            setattr(c, v, [(k,_percent(v,total)) for k,v in entries ])
 
         return render('ga_report/site/index.html')
 
@@ -346,3 +343,8 @@
             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)
+

--- a/ckanext/ga_report/download_analytics.py
+++ b/ckanext/ga_report/download_analytics.py
@@ -94,6 +94,7 @@
                      self.get_full_period_name(period_name, period_complete_day),
                      start_date.strftime('%Y %m %d'),
                      end_date.strftime('%Y %m %d'))
+
             data = self.download(start_date, end_date, '~/dataset/[a-z0-9-_]+')
             log.info('Storing Dataset Analytics for period "%s"',
                      self.get_full_period_name(period_name, period_complete_day))
@@ -155,11 +156,6 @@
                                  max_results=10000,
                                  end_date=end_date).execute()
 
-        if os.getenv('DEBUG'):
-            import pprint
-            pprint.pprint(results)
-            print 'Total results: %s' % results.get('totalResults')
-
         packages = []
         for entry in results.get('rows'):
             (loc,pageviews,visits) = entry
@@ -207,18 +203,37 @@
         results = self.service.data().ga().get(
                                  ids='ga:' + self.profile_id,
                                  start_date=start_date,
-                                 metrics='ga:pageviewsPerVisit,ga:bounces,ga:avgTimeOnSite,ga:percentNewVisits,ga:visitors',
+                                 metrics='ga:pageviewsPerVisit,ga:avgTimeOnSite,ga:percentNewVisits,ga:visitors',
                                  max_results=10000,
                                  end_date=end_date).execute()
         result_data = results.get('rows')
         data = {
             'Pages per visit': result_data[0][0],
-            'Bounces': result_data[0][1],
-            'Average time on site': result_data[0][2],
-            'New visits': result_data[0][3],
-            'Total visits': result_data[0][4],
+            'Average time on site': result_data[0][1],
+            'New visits': result_data[0][2],
+            'Total visits': result_data[0][3],
         }
         ga_model.update_sitewide_stats(period_name, "Totals", data)
+
+        # Bounces from /data. This url is specified in configuration because
+        # for DGU we don't want /.
+        path = config.get('ga-report.bounce_url','/')
+        print path
+        results = self.service.data().ga().get(
+                                 ids='ga:' + self.profile_id,
+                                 filters='ga:pagePath=~%s$' % (path,),
+                                 start_date=start_date,
+                                 metrics='ga:bounces,ga:uniquePageviews',
+                                 dimensions='ga:pagePath',
+                                 max_results=10000,
+                                 end_date=end_date).execute()
+        result_data = results.get('rows')
+        for results in result_data:
+            if results[0] == path:
+                bounce, total = [float(x) for x in results[1:]]
+                pct = 100 * bounce/total
+                print "%d bounces from %d total == %s" % (bounce, total, pct)
+                ga_model.update_sitewide_stats(period_name, "Totals", {'Bounces': pct})
 
 
     def _locale_stats(self, start_date, end_date, period_name):