Adding new social network referral information
Adding new social network referral information

--- 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')
 
@@ -70,19 +70,16 @@
         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)
-                if key == 'Percent new visits':
-                    key = 'New visits'
+                if key == 'New visits':
                     val = "%s%%" % val
-            if key in ['Bounces', 'Total pageviews']:
+            if key in ['Bounces', 'Total page views', 'Total visits']:
                 val = int(val)
-                if key == 'Total pageviews':
-                    key = 'Total page views'
 
             return key, val
 
@@ -96,7 +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)
@@ -113,6 +110,30 @@
             '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():
@@ -157,7 +178,10 @@
 
             # Get the total for each set of values and then set the value as
             # a percentage of the total
-            total = sum([num for _,num in entries])
+            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')

--- a/ckanext/ga_report/download_analytics.py
+++ b/ckanext/ga_report/download_analytics.py
@@ -1,7 +1,7 @@
 import os
 import logging
 import datetime
-
+import collections
 from pylons import config
 
 import ga_model
@@ -94,7 +94,6 @@
                      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))
@@ -107,6 +106,33 @@
 
             ga_model.update_publisher_stats(period_name) # about 30 seconds.
             self.sitewide_stats( period_name )
+
+            self.update_social_info(period_name, start_date, end_date)
+
+    def update_social_info(self, period_name, start_date, end_date):
+        start_date = start_date.strftime('%Y-%m-%d')
+        end_date = end_date.strftime('%Y-%m-%d')
+        query = 'ga:hasSocialSourceReferral=~Yes$'
+        metrics = 'ga:entrances'
+        sort = '-ga:entrances'
+
+        # Supported query params at
+        # https://developers.google.com/analytics/devguides/reporting/core/v3/reference
+        results = self.service.data().ga().get(
+                                 ids='ga:' + self.profile_id,
+                                 filters=query,
+                                 start_date=start_date,
+                                 metrics=metrics,
+                                 sort=sort,
+                                 dimensions="ga:landingPagePath,ga:socialNetwork",
+                                 max_results=10000,
+                                 end_date=end_date).execute()
+        data = collections.defaultdict(list)
+        rows = results.get('rows',[])
+        for row in rows:
+            from ga_model import _normalize_url
+            data[_normalize_url(row[0])].append( (row[1], int(row[2]),) )
+        ga_model.update_social(period_name, data)
 
 
     def download(self, start_date, end_date, path='~/dataset/[a-z0-9-_]+'):
@@ -176,12 +202,12 @@
                                  max_results=10000,
                                  end_date=end_date).execute()
         result_data = results.get('rows')
-        ga_model.update_sitewide_stats(period_name, "Totals", {'Total pageviews': result_data[0][0]})
-
-        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_model.update_sitewide_stats(period_name, "Totals", {'Total page views': result_data[0][0]})
+
+        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',
                                  max_results=10000,
                                  end_date=end_date).execute()
         result_data = results.get('rows')
@@ -189,7 +215,8 @@
             'Pages per visit': result_data[0][0],
             'Bounces': result_data[0][1],
             'Average time on site': result_data[0][2],
-            'Percent new visits': result_data[0][3],
+            'New visits': result_data[0][3],
+            'Total visits': result_data[0][4],
         }
         ga_model.update_sitewide_stats(period_name, "Totals", data)
 

--- a/ckanext/ga_report/ga_model.py
+++ b/ckanext/ga_report/ga_model.py
@@ -13,6 +13,8 @@
 def make_uuid():
     return unicode(uuid.uuid4())
 
+metadata = MetaData()
+
 
 
 class GA_Url(object):
@@ -21,20 +23,6 @@
         for k,v in kwargs.items():
             setattr(self, k, v)
 
-class GA_Stat(object):
-
-    def __init__(self, **kwargs):
-        for k,v in kwargs.items():
-            setattr(self, k, v)
-
-class GA_Publisher(object):
-
-    def __init__(self, **kwargs):
-        for k,v in kwargs.items():
-            setattr(self, k, v)
-
-
-metadata = MetaData()
 url_table = Table('ga_url', metadata,
                       Column('id', types.UnicodeText, primary_key=True,
                              default=make_uuid),
@@ -47,6 +35,13 @@
                 )
 mapper(GA_Url, url_table)
 
+
+class GA_Stat(object):
+
+    def __init__(self, **kwargs):
+        for k,v in kwargs.items():
+            setattr(self, k, v)
+
 stat_table = Table('ga_stat', metadata,
                   Column('id', types.UnicodeText, primary_key=True,
                          default=make_uuid),
@@ -56,6 +51,12 @@
                   Column('value', types.UnicodeText), )
 mapper(GA_Stat, stat_table)
 
+
+class GA_Publisher(object):
+
+    def __init__(self, **kwargs):
+        for k,v in kwargs.items():
+            setattr(self, k, v)
 
 pub_table = Table('ga_publisher', metadata,
                   Column('id', types.UnicodeText, primary_key=True,
@@ -71,6 +72,24 @@
 mapper(GA_Publisher, pub_table)
 
 
+class GA_ReferralStat(object):
+
+    def __init__(self, **kwargs):
+        for k,v in kwargs.items():
+            setattr(self, k, v)
+
+referrer_table = Table('ga_referrer', metadata,
+                      Column('id', types.UnicodeText, primary_key=True,
+                             default=make_uuid),
+                      Column('period_name', types.UnicodeText),
+                      Column('source', types.UnicodeText),
+                      Column('url', types.UnicodeText),
+                      Column('count', types.Integer),
+                )
+mapper(GA_ReferralStat, referrer_table)
+
+
+
 def init_tables():
     metadata.create_all(model.meta.engine)
 
@@ -93,8 +112,9 @@
     >>> normalize_url('http://data.gov.uk/dataset/weekly_fuel_prices')
     '/dataset/weekly_fuel_prices'
     '''
-    url = re.sub('https?://(www\.)?data.gov.uk', '', url)
-    return url
+    # Deliberately leaving a /
+    url = url.replace('http:/','')
+    return '/' + '/'.join(url.split('/')[2:])
 
 
 def _get_department_id_of_url(url):
@@ -167,6 +187,33 @@
         model.Session.commit()
 
 
+def update_social(period_name, data):
+    # Clean up first.
+    model.Session.query(GA_ReferralStat).\
+        filter(GA_ReferralStat.period_name==period_name).delete()
+
+    for url,data in data.iteritems():
+        for entry in data:
+            source = entry[0]
+            count = entry[1]
+
+            item = model.Session.query(GA_ReferralStat).\
+                filter(GA_ReferralStat.period_name==period_name).\
+                filter(GA_ReferralStat.source==source).\
+                filter(GA_ReferralStat.url==url).first()
+            if item:
+                item.count = item.count + count
+                model.Session.add(item)
+            else:
+                # create the row
+                values = {'id': make_uuid(),
+                          'period_name': period_name,
+                          'source': source,
+                          'url': url,
+                          'count': count,
+                         }
+                model.Session.add(GA_ReferralStat(**values))
+            model.Session.commit()
 
 def update_publisher_stats(period_name):
     """

--- a/ckanext/ga_report/templates/ga_report/ga_util.html
+++ b/ckanext/ga_report/templates/ga_report/ga_util.html
@@ -15,10 +15,26 @@
  </table>
 
 
-<table py:def="stat_table(items)" class="table table-condensed table-bordered table-striped">
+<table py:def="social_table(items, with_source=False)" class="table table-condensed table-bordered table-striped">
     <tr>
         <th>Name</th>
-        <th>% Views</th>
+        <th py:if="with_source">Source</th>
+        <th>Visits</th>
+    </tr>
+    <py:for each="name, url, source, count in items">
+    <tr>
+        <td><a href="${url}">${name}</a></td>
+        <td py:if="with_source">${source}</td>
+        <td>${count}</td>
+    </tr>
+    </py:for>
+ </table>
+
+
+<table py:def="stat_table(items, title='Views')" class="table table-condensed table-bordered table-striped">
+    <tr>
+        <th>Name</th>
+        <th>% ${title}</th>
     </tr>
     <py:for each="name, value in items">
     <tr>

--- a/ckanext/ga_report/templates/ga_report/site/index.html
+++ b/ckanext/ga_report/templates/ga_report/site/index.html
@@ -25,7 +25,6 @@
 
   <div py:match="content">
       <h1>Site Usage</h1>
-
       ${usage_nav('Site-wide', None)}
 
       <form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='index')}" method="get">
@@ -60,7 +59,16 @@
                 <li><a href="#os_versions" data-toggle="tab">Versions</a></li>
             </ul>
         </li>
-        <li><a href="#social_networks" data-toggle="tab">Social Networks</a></li>
+        <li class="dropdown">
+            <a href="#browsers" class="dropdown-toggle" data-toggle="dropdown">Social Networks
+                <b class="caret"></b></a>
+            <ul class="dropdown-menu">
+                <li><a href="#social_networks" data-toggle="tab">All networks</a></li>
+                <li><a href="#social_referrals_totals" data-toggle="tab">Referral links</a></li>
+            </ul>
+        </li>
+
+        <li><a href="#social_networks" data-toggle="tab"></a></li>
         <li><a href="#languages" data-toggle="tab">Languages</a></li>
         <li><a href="#country" data-toggle="tab">Country</a></li>
       </ul>
@@ -91,8 +99,14 @@
          <div class="tab-pane" id="os_versions">
              ${stat_table(c.os_versions)}
          </div>
+        <div class="tab-pane" id="social_referrals_totals">
+            <p>Number of visits to urls referred from social networks</p>
+            ${social_table(c.social_referrer_totals)}
+        </div>
         <div class="tab-pane" id="social_networks">
-             ${stat_table(c.social_networks)}
+            <p>Percentage of visits referred from these social networks</p>
+
+             ${stat_table(c.social_networks, 'Visits')}
         </div>
         <div class="tab-pane" id="languages">
              ${stat_table(c.languages)}
@@ -118,6 +132,7 @@
           e.preventDefault();
           $(this).tab('show');
         })
+        alert(window.location.hash);
     </script>
   </py:def>
 </html>