| import re | |
| import csv | |
| import sys | |
| import logging | import logging |
| import operator | import operator |
| from ckan.lib.base import BaseController, c, render, request, response | import collections |
| from ckan.lib.base import (BaseController, c, g, render, request, response, abort) | |
| import sqlalchemy | import sqlalchemy |
| from sqlalchemy import func, cast, Integer | from sqlalchemy import func, cast, Integer |
| import ckan.model as model | 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') | log = logging.getLogger('ckanext.ga-report') |
| def _get_month_name(strdate): | def _get_month_name(strdate): |
| import calendar | import calendar |
| from time import strptime | from time import strptime |
| d = strptime(strdate, '%Y-%m') | d = strptime(strdate, '%Y-%m') |
| return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) | return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) |
| def _month_details(cls): | def _month_details(cls): |
| months = [] | months = [] |
| vals = model.Session.query(cls.period_name).distinct().all() | vals = model.Session.query(cls.period_name).distinct().all() |
| for m in vals: | for m in vals: |
| months.append( (m[0], _get_month_name(m[0]))) | months.append( (m[0], _get_month_name(m[0]))) |
| return sorted(months, key=operator.itemgetter(0), reverse=True) | return sorted(months, key=operator.itemgetter(0), reverse=True) |
| class GaReport(BaseController): | class GaReport(BaseController): |
| def csv(self, month): | def csv(self, month): |
| import csv | import csv |
| entries = model.Session.query(GA_Stat).\ | q = model.Session.query(GA_Stat) |
| filter(GA_Stat.period_name==month).\ | if month != 'all': |
| order_by('GA_Stat.stat_name, GA_Stat.key').all() | q = q.filter(GA_Stat.period_name==month) |
| entries = q.order_by('GA_Stat.period_name, 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" | 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 = csv.writer(response) |
| writer.writerow(["Period", "Statistic", "Key", "Value"]) | writer.writerow(["Period", "Statistic", "Key", "Value"]) |
| for entry in entries: | for entry in entries: |
| writer.writerow([entry.period_name.encode('utf-8'), | writer.writerow([entry.period_name.encode('utf-8'), |
| entry.stat_name.encode('utf-8'), | entry.stat_name.encode('utf-8'), |
| entry.key.encode('utf-8'), | entry.key.encode('utf-8'), |
| entry.value.encode('utf-8')]) | entry.value.encode('utf-8')]) |
| def index(self): | def index(self): |
| # Get the month details by fetching distinct values and determining the | # Get the month details by fetching distinct values and determining the |
| # month names from the values. | # month names from the values. |
| c.months = _month_details(GA_Stat) | c.months = _month_details(GA_Stat) |
| # Work out which month to show, based on query params of the first item | # 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 = 'all months' |
| c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) | c.month = request.params.get('month', '') |
| if c.month: | |
| entries = model.Session.query(GA_Stat).\ | c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) |
| filter(GA_Stat.stat_name=='Totals').\ | |
| filter(GA_Stat.period_name==c.month).\ | q = model.Session.query(GA_Stat).\ |
| order_by('ga_stat.key').all() | filter(GA_Stat.stat_name=='Totals') |
| c.global_totals = [(s.key, s.value) for s in entries ] | if c.month: |
| q = q.filter(GA_Stat.period_name==c.month) | |
| 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', '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 in ['New visits','Bounces']: | |
| val = "%s%%" % val | |
| if key in ['Total page views', 'Total visits']: | |
| val = int(val) | |
| return key, val | |
| c.global_totals = [] | |
| if c.month: | |
| for e in entries: | |
| key, val = clean_key(e.key, e.value) | |
| c.global_totals.append((key, val)) | |
| else: | |
| d = collections.defaultdict(list) | |
| for e in entries: | |
| d[e.key].append(float(e.value)) | |
| for k, v in d.iteritems(): | |
| 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)) | |
| keys = { | keys = { |
| 'Browser versions': 'browsers', | 'Browser versions': 'browser_versions', |
| 'Operating Systems versions': 'os', | 'Browsers': 'browsers', |
| 'Operating Systems versions': 'os_versions', | |
| 'Operating Systems': 'os', | |
| 'Social sources': 'social_networks', | 'Social sources': 'social_networks', |
| 'Languages': 'languages', | 'Languages': 'languages', |
| 'Country': 'country' | '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])) | |
| for k, v in keys.iteritems(): | for k, v in keys.iteritems(): |
| entries = model.Session.query(GA_Stat).\ | q = model.Session.query(GA_Stat).\ |
| filter(GA_Stat.stat_name==k).\ | filter(GA_Stat.stat_name==k) |
| filter(GA_Stat.period_name==c.month).\ | if c.month: |
| order_by('ga_stat.value::int desc').all() | entries = [] |
| setattr(c, v, [(s.key, s.value) for s in entries ]) | q = q.filter(GA_Stat.period_name==c.month).\ |
| order_by('ga_stat.value::int desc') | |
| d = collections.defaultdict(int) | |
| for e in q.all(): | |
| d[e.key] += int(e.value) | |
| entries = [] | |
| for key, val in d.iteritems(): | |
| entries.append((key,val,)) | |
| entries = sorted(entries, key=operator.itemgetter(1), reverse=True) | |
| # 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') | return render('ga_report/site/index.html') |
| class GaPublisherReport(BaseController): | class GaDatasetReport(BaseController): |
| """ | """ |
| Displays the pageview and visit count for specific publishers based on | Displays the pageview and visit count for datasets |
| the datasets associated with the publisher. | with options to filter by publisher and time period. |
| """ | """ |
| def publisher_csv(self, month): | |
| def index(self): | ''' |
| try: | Returns a CSV of each publisher with the total number of dataset |
| # Get the month details by fetching distinct values and determining the | views & visits. |
| # month names from the values. | ''' |
| c.months = _month_details(GA_Url) | c.month = month if not month == 'all' else '' |
| response.headers['Content-Type'] = "text/csv; charset=utf-8" | |
| # Work out which month to show, based on query params of the first item | response.headers['Content-Disposition'] = str('attachment; filename=publishers_%s.csv' % (month,)) |
| 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]) | writer = csv.writer(response) |
| writer.writerow(["Publisher Title", "Publisher Name", "Views", "Visits", "Period Name"]) | |
| connection = model.Session.connection() | |
| q = """ | for publisher,view,visit in _get_top_publishers(None): |
| select department_id, sum(pageviews::int) views, sum(visitors::int) visits | writer.writerow([publisher.title.encode('utf-8'), |
| from ga_url | publisher.name.encode('utf-8'), |
| where department_id <> '' | view, |
| and not url like '/publisher/%%' | visit, |
| and period_name=%s | month]) |
| group by department_id order by views desc limit 20; | |
| """ | def dataset_csv(self, id='all', month='all'): |
| c.top_publishers = [] | ''' |
| res = connection.execute(q, c.month) | Returns a CSV with the number of views & visits for each dataset. |
| for row in res: | |
| c.top_publishers.append((model.Group.get(row[0]), row[1], row[2])) | :param id: A Publisher ID or None if you want for all |
| except Exception as e: | :param month: The time period, or 'all' |
| raise e | ''' |
| return render('ga_report/publisher/index.html') | c.month = month if not month == 'all' else '' |
| if id != 'all': | |
| c.publisher = model.Group.get(id) | |
| def read(self, id): | if not c.publisher: |
| c.publisher = model.Group.get(id) | abort(404, 'A publisher with that name could not be found') |
| c.top_packages = [] # package, dataset_views in c.top_packages | |
| packages = self._get_packages(c.publisher) | |
| response.headers['Content-Type'] = "text/csv; charset=utf-8" | |
| response.headers['Content-Disposition'] = \ | |
| str('attachment; filename=datasets_%s_%s.csv' % (c.publisher_name, month,)) | |
| writer = csv.writer(response) | |
| writer.writerow(["Dataset Title", "Dataset Name", "Views", "Visits", "Period Name"]) | |
| for package,view,visit in packages: | |
| writer.writerow([package.title.encode('utf-8'), | |
| package.name.encode('utf-8'), | |
| view, | |
| visit, | |
| month]) | |
| def publishers(self): | |
| '''A list of publishers and the number of views/visits for each''' | |
| # Get the month details by fetching distinct values and determining the | # Get the month details by fetching distinct values and determining the |
| # month names from the values. | # month names from the values. |
| c.months = _month_details(GA_Url) | c.months = _month_details(GA_Url) |
| # Work out which month to show, based on query params of the first item | # 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 = request.params.get('month', '') |
| c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) | c.month_desc = 'all months' |
| if c.month: | |
| entry = model.Session.query(GA_Url).\ | c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) |
| filter(GA_Url.url=='/publisher/%s' % c.publisher.name).\ | |
| filter(GA_Url.period_name==c.month).first() | c.top_publishers = _get_top_publishers() |
| c.publisher_page_views = entry.pageviews if entry else 0 | |
| return render('ga_report/publisher/index.html') | |
| entries = model.Session.query(GA_Url).\ | |
| filter(GA_Url.department_id==c.publisher.name).\ | def _get_packages(self, publisher=None, count=-1): |
| filter(GA_Url.period_name==c.month).\ | '''Returns the datasets in order of visits''' |
| order_by('ga_url.pageviews::int desc')[:20] | if count == -1: |
| for entry in entries: | count = sys.maxint |
| if entry.url.startswith('/dataset/'): | |
| p = model.Package.get(entry.url[len('/dataset/'):]) | q = model.Session.query(GA_Url)\ |
| c.top_packages.append((p,entry.pageviews,entry.visitors)) | .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.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.limit(count): | |
| 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) | |
| return top_packages | |
| def read(self): | |
| ''' | |
| Lists the most popular datasets across all publishers | |
| ''' | |
| return self.read_publisher(None) | |
| def read_publisher(self, id): | |
| ''' | |
| Lists the most popular datasets for a publisher (or across all publishers) | |
| ''' | |
| count = 20 | |
| c.publishers = _get_publishers() | |
| id = request.params.get('publisher', id) | |
| if id and id != 'all': | |
| c.publisher = model.Group.get(id) | |
| if not c.publisher: | |
| abort(404, 'A publisher with that name could not be found') | |
| c.publisher_name = c.publisher.name | |
| 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 months' | |
| 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') | return render('ga_report/publisher/read.html') |
| def _get_top_publishers(limit=20): | |
| ''' | |
| Returns a list of the top 20 publishers by dataset visits. | |
| (The number to show can be varied with 'limit') | |
| ''' | |
| 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 | |
| """ |