From: Ross Jones Date: Thu, 25 Oct 2012 15:37:53 +0000 Subject: Human readable times X-Git-Url: https://maxious.lambdacomplex.org/git/?p=ckanext-ga-report.git&a=commitdiff&h=882c0822404ab7f9ffe0d4a3e45babbb35c40bad --- Human readable times --- --- a/README.rst +++ b/README.rst @@ -26,7 +26,7 @@ 1. Activate you CKAN python environment and install this extension's software:: $ pyenv/bin/activate - $ pip install -e git+https://github.com/okfn/ckanext-ga-report.git#egg=ckanext-ga-report + $ pip install -e git+https://github.com/datagovuk/ckanext-ga-report.git#egg=ckanext-ga-report 2. Ensure you development.ini (or similar) contains the info about your Google Analytics account and configuration:: --- a/ckanext/ga_report/command.py +++ b/ckanext/ga_report/command.py @@ -66,8 +66,7 @@ And where is: all - data for all time latest - (default) just the 'latest' data - YYYY-MM-DD - just data for all time periods going - back to (and including) this date + YYYY-MM - just data for the specific month """ summary = __doc__.split('\n')[0] usage = __doc__ @@ -96,6 +95,7 @@ elif time_period == 'latest': downloader.latest() else: - since_date = datetime.datetime.strptime(time_period, '%Y-%m-%d') - downloader.since_date(since_date) + # The month to use + for_date = datetime.datetime.strptime(time_period, '%Y-%m') + downloader.specific_month(for_date) --- a/ckanext/ga_report/controller.py +++ b/ckanext/ga_report/controller.py @@ -1,10 +1,158 @@ import logging -from ckan.lib.base import BaseController, c, render -import report_model +import operator +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, GA_Stat log = logging.getLogger('ckanext.ga-report') + +def _get_month_name(strdate): + import calendar + from time import strptime + d = strptime(strdate, '%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[0]))) + 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-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): - return render('index.html') + # 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).\ + order_by('ga_stat.key').all() + + c.global_totals = [] + for e in entries: + val = e.value + if e.key in ['Average time on site', 'Pages per visit', 'Percent new visits']: + val = "%.2f" % round(float(e.value), 2) + if e.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) + e.key = '%s *' % e.key + c.global_totals.append((e.key, val)) + + + 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') + + +class GaPublisherReport(BaseController): + """ + Displays the pageview and visit count for specific publishers based on + the datasets associated with the publisher. + """ + + 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 period_name=%s + group by department_id order by views desc limit 20; + """ + # Add this back (before and period_name =%s) if you want to ignore publisher + # homepage views + # and not url like '/publisher/%%' + + 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 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 = _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]) + + entry = model.Session.query(GA_Url).\ + filter(GA_Url.url=='/publisher/%s' % c.publisher.name).\ + filter(GA_Url.period_name==c.month).first() + c.publisher_page_views = entry.pageviews if entry else 0 + + 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::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/read.html') + --- a/ckanext/ga_report/download_analytics.py +++ b/ckanext/ga_report/download_analytics.py @@ -21,8 +21,17 @@ self.profile_id = profile_id - def all_(self): - self.since_date(datetime.datetime(2010, 1, 1)) + def specific_month(self, date): + import calendar + + first_of_this_month = datetime.datetime(date.year, date.month, 1) + _, last_day_of_month = calendar.monthrange(int(date.year), int(date.month)) + last_of_this_month = datetime.datetime(date.year, date.month, last_day_of_month) + periods = ((date.strftime(FORMAT_MONTH), + last_day_of_month, + first_of_this_month, last_of_this_month),) + self.download_and_store(periods) + def latest(self): if self.period == 'monthly': @@ -37,13 +46,13 @@ self.download_and_store(periods) - def since_date(self, since_date): + def for_date(self, for_date): assert isinstance(since_date, datetime.datetime) periods = [] # (period_name, period_complete_day, start_date, end_date) if self.period == 'monthly': first_of_the_months_until_now = [] - year = since_date.year - month = since_date.month + year = for_date.year + month = for_date.month now = datetime.datetime.now() first_of_this_month = datetime.datetime(now.year, now.month, 1) while True: @@ -85,7 +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)) @@ -95,7 +104,7 @@ log.info('Storing Publisher Analytics for period "%s"', self.get_full_period_name(period_name, period_complete_day)) self.store(period_name, period_complete_day, data,) - """ + ga_model.update_publisher_stats(period_name) # about 30 seconds. self.sitewide_stats( period_name ) --- a/ckanext/ga_report/plugin.py +++ b/ckanext/ga_report/plugin.py @@ -1,13 +1,14 @@ import logging import ckan.lib.helpers as h +import ckan.plugins as p from ckan.plugins import implements, toolkit -import gasnippet -import commands -import dbutil +#import gasnippet +#import commands +#import dbutil log = logging.getLogger('ckanext.ga-report') -class GoogleAnalyticsPlugin(p.SingletonPlugin): +class GAReportPlugin(p.SingletonPlugin): implements(p.IConfigurer, inherit=True) implements(p.IRoutes, inherit=True) @@ -17,9 +18,24 @@ def after_map(self, map): map.connect( - '/data/analytics/index', - controller='ckanext.ga-report.controller:GaReport', + '/data/analytics/publisher', + controller='ckanext.ga_report.controller:GaPublisherReport', action='index' + ) + map.connect( + '/data/analytics/publisher/{id}', + controller='ckanext.ga_report.controller:GaPublisherReport', + action='read' + ) + map.connect( + '/data/analytics', + controller='ckanext.ga_report.controller:GaReport', + action='index' + ) + map.connect( + '/data/analytics/data_{month}.csv', + controller='ckanext.ga_report.controller:GaReport', + action='csv' ) return map --- /dev/null +++ b/ckanext/ga_report/templates/ga_report/publisher/index.html @@ -1,1 +1,64 @@ + + Publisher Analytics for ${g.site_title} + + +
  • +

    Publishers

    +

    The table shows the top 20 publishers as recorded by page views of datasets owned by that publisher, and the number of visits to each publisher's home page.

    +
    • +     + +
    +

    Publisher Analytics

    +

    The top 20 publishers

    + +
    +
    + + +
    +
    + + + + + + + + + + + + + + +
    PublisherDataset ViewsVisits
    ${h.link_to(publisher.title, h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport', action='read', id=publisher.name))} + ${views}${visits}
    + + +
    + + + + + + + + + + + + --- /dev/null +++ b/ckanext/ga_report/templates/ga_report/publisher/read.html @@ -1,1 +1,64 @@ + + Analytics for ${g.site_title} + + +
  • +

    ${c.publisher.title}

    +

    + The table shows the top 20 most viewed datasets belonging to ${c.publisher.title}. +

    +

    + As well as showing the number of views within ${c.month_desc}, it will also show the + number of visitors that viewed each dataset. +

    +

    The dataset list page for ${c.publisher.title} was viewed ${c.publisher_page_views} times during ${c.month_desc}

    +

    View the publishers leaderboard

    +
    • +     + +
    +

    Analytics for ${c.publisher.title}

    + +

    Top 20 most viewed datasets

    +

    Note: this data does not include API calls

    + +
    +
    + + +
    +
    + + + + + + + + + + + + + + +
    DatasetViewsVisits
    ${h.link_to(package.title or package.name, h.url_for(controller='package', action='read', id=package.name))} + ${views}${visits}
    + + +
    + + + + + + + --- /dev/null +++ b/ckanext/ga_report/templates/ga_report/site/index.html @@ -1,1 +1,149 @@ + + Site analytics + + +
  • +

    Statistics

    +

    It is possible to export the analytics data as a CSV file, which contains all of the information for ${c.month_desc}

    + +
    • +     + +
    +

    Site statistics

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

    * Values are rounded up to 2 decimal places.

    +
    +
    + + + + + + + + + + + +
    NameValue
    ${name}${value}
    +
    +
    + + + + + + + + + + + +
    NameValue
    ${name}${value}
    +
    +
    + + + + + + + + + + + +
    NameValue
    ${name}${value}
    +
    +
    + + + + + + + + + + + +
    NameValue
    ${name}${value}
    +
    +
    + + + + + + + + + + + +
    NameValue
    ${name}${value}
    +
    + + +
    +
    + + + +
    + + + + + + + + + + + --- a/ckanext/ga_report/tests/test_api.py +++ b/ckanext/ga_report/tests/test_api.py @@ -32,7 +32,7 @@ svc = init_service("token.dat", "credentials.json") downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc)) try: - downloader.since_date(datetime.datetime.now() - datetime.timedelta(days=-30)) + downloader.for_date(datetime.datetime.now() - datetime.timedelta(days=-30)) except Exception as e: assert False, e --- a/setup.py +++ b/setup.py @@ -27,11 +27,12 @@ """ [ckan.plugins] # Add plugins here, eg - ga-report=ckanext.ga_report.plugin:GaReportPlugin + ga-report=ckanext.ga_report.plugin:GAReportPlugin [paste.paster_command] loadanalytics = ckanext.ga_report.command:LoadAnalytics initdb = ckanext.ga_report.command:InitDB + getauthtoken = ckanext.ga_report.command:GetAuthToken """, )