--- a/ckanext/ga_report/controller.py +++ b/ckanext/ga_report/controller.py @@ -9,7 +9,7 @@ import sqlalchemy from sqlalchemy import func, cast, Integer import ckan.model as model -from ga_model import GA_Url, GA_Stat, GA_ReferralStat +from ga_model import GA_Url, GA_Stat, GA_ReferralStat, GA_Publisher log = logging.getLogger('ckanext.ga-report') @@ -22,8 +22,9 @@ def _month_details(cls): + '''Returns a list of all the month names''' months = [] - vals = model.Session.query(cls.period_name).distinct().all() + vals = model.Session.query(cls.period_name).filter(cls.period_name!='All').distinct().all() for m in vals: months.append( (m[0], _get_month_name(m[0]))) return sorted(months, key=operator.itemgetter(0), reverse=True) @@ -70,15 +71,15 @@ 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 +94,12 @@ 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)) @@ -134,29 +136,7 @@ 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(): - - def clean_field(key): - if k != 'Browser versions': - return key - m = browser_version_re.match(key) - browser = m.groups()[0].strip() - ver = m.groups()[1] - parts = ver.split('.') - if len(parts) > 1: - if parts[1][0] == '0': - ver = parts[0] - else: - ver = "%s.%s" % (parts[0],parts[1]) - if browser in ['Safari','Android Browser']: # Special case complex version nums - ver = parts[0] - if len(ver) > 2: - ver = "%s%sX" % (ver[0], ver[1]) - - return "%s (%s)" % (browser, ver,) - q = model.Session.query(GA_Stat).\ filter(GA_Stat.stat_name==k) if c.month: @@ -172,17 +152,13 @@ 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') @@ -253,7 +229,6 @@ c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) c.top_publishers = _get_top_publishers() - return render('ga_report/publisher/index.html') def _get_packages(self, publisher=None, count=-1): @@ -261,43 +236,22 @@ if count == -1: count = sys.maxint - q = model.Session.query(GA_Url)\ + month = c.month or 'All' + + q = model.Session.query(GA_Url,model.Package)\ + .filter(model.Package.name==GA_Url.package_id)\ .filter(GA_Url.url.like('/dataset/%')) if publisher: q = q.filter(GA_Url.department_id==publisher.name) - if c.month: - q = q.filter(GA_Url.period_name==c.month) + q = q.filter(GA_Url.period_name==month) q = q.order_by('ga_url.visitors::int desc') - - if c.month: - top_packages = [] - for entry in q.limit(count): - package_name = entry.url[len('/dataset/'):] - p = model.Package.get(package_name) - if p: - top_packages.append((p, entry.pageviews, entry.visitors)) - else: - log.warning('Could not find package "%s"', package_name) - else: - ds = {} - for entry in q: - if len(ds) >= count: - break - package_name = entry.url[len('/dataset/'):] - p = model.Package.get(package_name) - if p: - if not p in ds: - ds[p] = {'views': 0, 'visits': 0} - ds[p]['views'] = ds[p]['views'] + int(entry.pageviews) - ds[p]['visits'] = ds[p]['visits'] + int(entry.visitors) - else: - log.warning('Could not find package "%s"', package_name) - - results = [] - for k, v in ds.iteritems(): - results.append((k,v['views'],v['visits'])) - - top_packages = sorted(results, key=operator.itemgetter(1), reverse=True) + top_packages = [] + for entry,package in q.limit(count): + if package: + top_packages.append((package, entry.pageviews, entry.visitors)) + else: + log.warning('Could not find package associated package') + return top_packages def read(self): @@ -333,15 +287,12 @@ else: c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) + month = c.month or 'All' 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) + entry = q.filter(GA_Url.period_name==c.month).first() + c.publisher_page_views = entry.pageviews if entry else 0 c.top_packages = self._get_packages(c.publisher, 20) @@ -352,33 +303,26 @@ Returns a list of the top 20 publishers by dataset visits. (The number to show can be varied with 'limit') ''' + month = c.month or 'All' 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 visits desc + where department_id <> '' + and period_name=%s + group by department_id order by visits 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) - + res = connection.execute(q, 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_publishers(): ''' @@ -393,3 +337,7 @@ publishers.append((pub.name, pub.title)) return publishers +def _percent(num, total): + p = 100 * float(num)/float(total) + return "%.2f%%" % round(p, 2) +