Show top datasets cross-publisher. Drop-down for the publisher. Browser version numbers filtered on download, so you get this version in the CSV too - for privacy. single_popular_dataset now copes when not much data, and can return the figures so DGU can reskin it in its own repo. Notes about usage stats centralised to notes.html.
--- a/README.rst
+++ b/README.rst
@@ -31,14 +31,8 @@
2. Ensure you development.ini (or similar) contains the info about your Google Analytics account and configuration::
googleanalytics.id = UA-1010101-1
- googleanalytics.account = Account name (i.e. data.gov.uk, see top level item at https://www.google.com/analytics)
+ googleanalytics.account = Account name (e.g. 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.
3. Set up this extension's database tables using a paster command. (Ensure your CKAN pyenv is still activated, run the command from ``src/ckanext-ga-report``, alter the ``--config`` option to point to your site config file)::
@@ -47,6 +41,12 @@
4. Enable the extension in your CKAN config file by adding it to ``ckan.plugins``::
ckan.plugins = ga-report
+
+Problem shooting
+----------------
+
+* ``(ProgrammingError) relation "ga_url" does not exist``
+ This means that the ``paster initdb`` step has not been run successfully. Refer to the installation instructions for this extension.
Authorization
@@ -83,7 +83,7 @@
Tutorial
--------
-Download some GA data and store it in CKAN's db. (Ensure your CKAN pyenv is still activated, run the command from ``src/ckanext-ga-report``, alter the ``--config`` option to point to your site config file) and specifying the name of your auth file (token.dat by default) from the previous step::
+Download some GA data and store it in CKAN's database. (Ensure your CKAN pyenv is still activated, run the command from ``src/ckanext-ga-report``, alter the ``--config`` option to point to your site config file) and specifying the name of your auth file (token.dat by default) from the previous step::
$ paster loadanalytics token.dat latest --config=../ckan/development.ini
--- a/ckanext/ga_report/command.py
+++ b/ckanext/ga_report/command.py
@@ -73,6 +73,14 @@
max_args = 2
min_args = 1
+ def __init__(self, name):
+ super(LoadAnalytics, self).__init__(name)
+ self.parser.add_option('-d', '--delete-first',
+ action='store_true',
+ default=False,
+ dest='delete_first',
+ help='Delete data for the period first')
+
def command(self):
self._load_config()
@@ -83,10 +91,11 @@
svc = init_service(self.args[0], None)
except TypeError:
print ('Have you correctly run the getauthtoken task and '
- 'specified the correct file here')
+ 'specified the correct token file?')
return
- downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc))
+ downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc),
+ delete_first=self.options.delete_first)
time_period = self.args[1] if self.args and len(self.args) > 1 \
else 'latest'
--- 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', 'Bounces']:
+ 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 in ['New visits','Bounces']:
+ if key == 'New visits':
val = "%s%%" % val
- if key in ['Total page views', 'Total visits']:
+ if key in ['Bounces', 'Total page views', 'Total visits']:
val = int(val)
return key, val
@@ -93,12 +93,11 @@
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']:
+ if k in ['Bounces', '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))
@@ -167,11 +166,15 @@
d = collections.defaultdict(int)
for e in q.all():
- d[clean_field(e.key)] += int(e.value)
+ 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)
+
+ 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
@@ -179,57 +182,65 @@
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')
-class GaPublisherReport(BaseController):
+class GaDatasetReport(BaseController):
"""
- Displays the pageview and visit count for specific publishers based on
- the datasets associated with the publisher.
+ Displays the pageview and visit count for datasets
+ with options to filter by publisher and time period.
"""
- def csv(self, month):
-
- c.month = month if not month =='all' else ''
+ def publisher_csv(self, month):
+ '''
+ Returns a CSV of each publisher with the total number of dataset
+ views & visits.
+ '''
+ c.month = month if not month == 'all' else ''
response.headers['Content-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = str('attachment; filename=publishers_%s.csv' % (month,))
writer = csv.writer(response)
- writer.writerow(["Publisher", "Views", "Visits", "Period Name"])
-
- for publisher,view,visit in _get_publishers(None):
+ writer.writerow(["Publisher Title", "Publisher Name", "Views", "Visits", "Period Name"])
+
+ for publisher,view,visit in _get_top_publishers(None):
writer.writerow([publisher.title.encode('utf-8'),
+ publisher.name.encode('utf-8'),
view,
visit,
month])
-
-
- def publisher_csv(self, id, month):
-
- c.month = month if not month =='all' else ''
- c.publisher = model.Group.get(id)
- if not c.publisher:
- abort(404, 'A publisher with that name could not be found')
+ def dataset_csv(self, id='all', month='all'):
+ '''
+ Returns a CSV with the number of views & visits for each dataset.
+
+ :param id: A Publisher ID or None if you want for all
+ :param month: The time period, or 'all'
+ '''
+ c.month = month if not month == 'all' else ''
+ if id != 'all':
+ c.publisher = model.Group.get(id)
+ if not c.publisher:
+ abort(404, 'A publisher with that name could not be found')
packages = self._get_packages(c.publisher)
response.headers['Content-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = \
- str('attachment; filename=%s_%s.csv' % (c.publisher.name, month,))
+ str('attachment; filename=datasets_%s_%s.csv' % (c.publisher_name, month,))
writer = csv.writer(response)
- writer.writerow(["Publisher", "Views", "Visits", "Period Name"])
+ 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 index(self):
+ 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
# month names from the values.
@@ -241,37 +252,46 @@
if c.month:
c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
- c.top_publishers = _get_publishers()
+ c.top_publishers = _get_top_publishers()
return render('ga_report/publisher/index.html')
-
- def _get_packages(self, publisher, count=-1):
+ def _get_packages(self, publisher=None, count=-1):
+ '''Returns the datasets in order of visits'''
if count == -1:
count = sys.maxint
- top_packages = []
- q = model.Session.query(GA_Url).\
- filter(GA_Url.department_id==publisher.name).\
- filter(GA_Url.url.like('/dataset/%'))
+ q = model.Session.query(GA_Url)\
+ .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.pageviews::int desc')
-
- if c.month:
- for entry in q[:count]:
- p = model.Package.get(entry.url[len('/dataset/'):])
- top_packages.append((p,entry.pageviews,entry.visitors))
+ 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.all():
+ for entry in q:
if len(ds) >= count:
break
- p = model.Package.get(entry.url[len('/dataset/'):])
- 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)
+ 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():
@@ -280,13 +300,26 @@
top_packages = sorted(results, key=operator.itemgetter(1), reverse=True)
return top_packages
-
- def read(self, id):
+ 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.publisher = model.Group.get(id)
- if not c.publisher:
- abort(404, 'A publisher with that name could not be found')
+ 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
@@ -302,7 +335,7 @@
c.publisher_page_views = 0
q = model.Session.query(GA_Url).\
- filter(GA_Url.url=='/publisher/%s' % c.publisher.name)
+ 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
@@ -314,7 +347,11 @@
return render('ga_report/publisher/read.html')
-def _get_publishers(limit=20):
+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
@@ -325,7 +362,7 @@
and period_name=%s
"""
q = q + """
- group by department_id order by views desc
+ group by department_id order by visits desc
"""
if limit:
q = q + " limit %s;" % (limit)
@@ -343,8 +380,16 @@
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)
-
+def _get_publishers():
+ '''
+ Returns a list of all publishers. Each item is a tuple:
+ (names, title)
+ '''
+ publishers = []
+ for pub in model.Session.query(model.Group).\
+ filter(model.Group.type=='publisher').\
+ filter(model.Group.state=='active').\
+ order_by(model.Group.name):
+ publishers.append((pub.name, pub.title))
+ return publishers
+
--- a/ckanext/ga_report/download_analytics.py
+++ b/ckanext/ga_report/download_analytics.py
@@ -11,15 +11,17 @@
log = logging.getLogger('ckanext.ga-report')
FORMAT_MONTH = '%Y-%m'
+MIN_VIEWS = 50
+MIN_VISITS = 20
class DownloadAnalytics(object):
'''Downloads and stores analytics info'''
- def __init__(self, service=None, profile_id=None):
+ def __init__(self, service=None, profile_id=None, delete_first=False):
self.period = config['ga-report.period']
self.service = service
self.profile_id = profile_id
-
+ self.delete_first = delete_first
def specific_month(self, date):
import calendar
@@ -90,11 +92,14 @@
def download_and_store(self, periods):
for period_name, period_complete_day, start_date, end_date in periods:
+ if self.delete_first:
+ log.info('Deleting existing Analytics for period "%s"',
+ period_name)
+ ga_model.delete(period_name)
log.info('Downloading Analytics for period "%s" (%s - %s)',
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))
@@ -156,6 +161,11 @@
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
@@ -203,38 +213,19 @@
results = self.service.data().ga().get(
ids='ga:' + self.profile_id,
start_date=start_date,
- metrics='ga:pageviewsPerVisit,ga:avgTimeOnSite,ga:percentNewVisits,ga:visitors',
+ metrics='ga:pageviewsPerVisit,ga:bounces,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],
- 'Average time on site': result_data[0][1],
- 'New visits': result_data[0][2],
- 'Total visits': result_data[0][3],
+ '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],
}
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):
""" Fetches stats about language and country """
@@ -250,11 +241,13 @@
data = {}
for result in result_data:
data[result[0]] = data.get(result[0], 0) + int(result[2])
+ self._filter_out_long_tail(data, MIN_VIEWS)
ga_model.update_sitewide_stats(period_name, "Languages", data)
data = {}
for result in result_data:
data[result[1]] = data.get(result[1], 0) + int(result[2])
+ self._filter_out_long_tail(data, MIN_VIEWS)
ga_model.update_sitewide_stats(period_name, "Country", data)
@@ -269,13 +262,11 @@
max_results=10000,
end_date=end_date).execute()
result_data = results.get('rows')
- twitter_links = []
data = {}
for result in result_data:
if not result[0] == '(not set)':
data[result[0]] = data.get(result[0], 0) + int(result[2])
- if result[0] == 'Twitter':
- twitter_links.append(result[1])
+ self._filter_out_long_tail(data, 3)
ga_model.update_sitewide_stats(period_name, "Social sources", data)
@@ -293,12 +284,14 @@
data = {}
for result in result_data:
data[result[0]] = data.get(result[0], 0) + int(result[2])
+ self._filter_out_long_tail(data, MIN_VIEWS)
ga_model.update_sitewide_stats(period_name, "Operating Systems", data)
data = {}
for result in result_data:
- key = "%s (%s)" % (result[0],result[1])
- data[key] = result[2]
+ if int(result[2]) >= MIN_VIEWS:
+ key = "%s %s" % (result[0],result[1])
+ data[key] = result[2]
ga_model.update_sitewide_stats(period_name, "Operating Systems versions", data)
@@ -313,17 +306,42 @@
max_results=10000,
end_date=end_date).execute()
result_data = results.get('rows')
+ # e.g. [u'Firefox', u'19.0', u'20']
+
data = {}
for result in result_data:
data[result[0]] = data.get(result[0], 0) + int(result[2])
+ self._filter_out_long_tail(data, MIN_VIEWS)
ga_model.update_sitewide_stats(period_name, "Browsers", data)
data = {}
for result in result_data:
- key = "%s (%s)" % (result[0], result[1])
- data[key] = result[2]
+ key = "%s %s" % (result[0], self._filter_browser_version(result[0], result[1]))
+ data[key] = data.get(key, 0) + int(result[2])
+ self._filter_out_long_tail(data, MIN_VIEWS)
ga_model.update_sitewide_stats(period_name, "Browser versions", data)
+ @classmethod
+ def _filter_browser_version(cls, browser, version_str):
+ '''
+ Simplifies a browser version string if it is detailed.
+ i.e. groups together Firefox 3.5.1 and 3.5.2 to be just 3.
+ This is helpful when viewing stats and good to protect privacy.
+ '''
+ ver = version_str
+ parts = ver.split('.')
+ if len(parts) > 1:
+ if parts[1][0] == '0':
+ ver = parts[0]
+ else:
+ ver = "%s" % (parts[0])
+ # Special case complex version nums
+ if browser in ['Safari', 'Android Browser']:
+ ver = parts[0]
+ if len(ver) > 2:
+ num_hidden_digits = len(ver) - 2
+ ver = ver[0] + ver[1] + 'X' * num_hidden_digits
+ return ver
def _mobile_stats(self, start_date, end_date, period_name):
""" Info about mobile devices """
@@ -341,10 +359,23 @@
data = {}
for result in result_data:
data[result[0]] = data.get(result[0], 0) + int(result[2])
+ self._filter_out_long_tail(data, MIN_VIEWS)
ga_model.update_sitewide_stats(period_name, "Mobile brands", data)
data = {}
for result in result_data:
data[result[1]] = data.get(result[1], 0) + int(result[2])
+ self._filter_out_long_tail(data, MIN_VIEWS)
ga_model.update_sitewide_stats(period_name, "Mobile devices", data)
+ @classmethod
+ def _filter_out_long_tail(cls, data, threshold=10):
+ '''
+ Given data which is a frequency distribution, filter out
+ results which are below a threshold count. This is good to protect
+ privacy.
+ '''
+ for key, value in data.items():
+ if value < threshold:
+ del data[key]
+
--- a/ckanext/ga_report/ga_auth.py
+++ b/ckanext/ga_report/ga_auth.py
@@ -53,7 +53,11 @@
return None
accountName = config.get('googleanalytics.account')
+ if not accountName:
+ raise Exception('googleanalytics.account needs to be configured')
webPropertyId = config.get('googleanalytics.id')
+ if not webPropertyId:
+ raise Exception('googleanalytics.id needs to be configured')
for acc in accounts.get('items'):
if acc.get('name') == accountName:
accountId = acc.get('id')
--- a/ckanext/ga_report/ga_model.py
+++ b/ckanext/ga_report/ga_model.py
@@ -295,3 +295,15 @@
for grandchild in go_down_tree(child):
yield grandchild
+def delete(period_name):
+ '''
+ Deletes table data for the specified period, or specify 'all'
+ for all periods.
+ '''
+ for object_type in (GA_Url, GA_Stat, GA_Publisher, GA_ReferralStat):
+ q = model.Session.query(object_type)
+ if period_name != 'all':
+ q = q.filter_by(period_name=period_name)
+ q.delete()
+ model.Session.commit()
+
--- a/ckanext/ga_report/helpers.py
+++ b/ckanext/ga_report/helpers.py
@@ -28,28 +28,37 @@
return base.render_snippet('ga_report/ga_popular_datasets.html', **ctx)
def single_popular_dataset(top=20):
+ '''Returns a random dataset from the most popular ones.
+
+ :param top: the number of top datasets to select from
+ '''
import random
- datasets = {}
- rand = random.randrange(0, top)
- entry = model.Session.query(GA_Url).\
- filter(GA_Url.url.like('/dataset/%')).\
- order_by('ga_url.pageviews::int desc')[rand]
+ top_datasets = model.Session.query(GA_Url).\
+ filter(GA_Url.url.like('/dataset/%')).\
+ order_by('ga_url.pageviews::int desc')
+ num_top_datasets = top_datasets.count()
-
- dataset = None
- while not dataset:
- dataset = model.Package.get(entry.url[len('/dataset/'):])
- if dataset and not dataset.state == 'active':
- dataset = None
- else:
- publisher = model.Group.get(entry.department_id)
-
- ctx = {
+ if num_top_datasets:
+ dataset = None
+ while not dataset:
+ rand = random.randrange(0, min(top, num_top_datasets))
+ ga_url = top_datasets[rand]
+ dataset = model.Package.get(ga_url.url[len('/dataset/'):])
+ if dataset and not dataset.state == 'active':
+ dataset = None
+ else:
+ dataset = model.Session.query(model.Package)\
+ .filter_by(state='active').first()
+ publisher = dataset.get_groups('publisher')[0]
+ return {
'dataset': dataset,
'publisher': publisher
}
- return base.render_snippet('ga_report/ga_popular_single.html', **ctx)
+
+def single_popular_dataset_html(top=20):
+ context = single_popular_dataset(top)
+ return base.render_snippet('ga_report/ga_popular_single.html', **context)
def most_popular_datasets(publisher, count=20):
@@ -61,7 +70,7 @@
results = _datasets_for_publisher(publisher, count)
ctx = {
- 'dataset_count': len(datasets),
+ 'dataset_count': len(results),
'datasets': results,
'publisher': publisher
--- a/ckanext/ga_report/plugin.py
+++ b/ckanext/ga_report/plugin.py
@@ -31,26 +31,7 @@
}
def after_map(self, map):
- map.connect(
- '/data/site-usage/publisher',
- controller='ckanext.ga_report.controller:GaPublisherReport',
- action='index'
- )
- map.connect(
- '/data/site-usage/publisher_{month}.csv',
- controller='ckanext.ga_report.controller:GaPublisherReport',
- action='csv'
- )
- map.connect(
- '/data/site-usage/publisher/{id}_{month}.csv',
- controller='ckanext.ga_report.controller:GaPublisherReport',
- action='publisher_csv'
- )
- map.connect(
- '/data/site-usage/publisher/{id}',
- controller='ckanext.ga_report.controller:GaPublisherReport',
- action='read'
- )
+ # GaReport
map.connect(
'/data/site-usage',
controller='ckanext.ga_report.controller:GaReport',
@@ -61,6 +42,33 @@
controller='ckanext.ga_report.controller:GaReport',
action='csv'
)
+
+ # GaDatasetReport
+ map.connect(
+ '/data/site-usage/publisher',
+ controller='ckanext.ga_report.controller:GaDatasetReport',
+ action='publishers'
+ )
+ map.connect(
+ '/data/site-usage/publishers_{month}.csv',
+ controller='ckanext.ga_report.controller:GaDatasetReport',
+ action='publisher_csv'
+ )
+ map.connect(
+ '/data/site-usage/dataset/datasets_{id}_{month}.csv',
+ controller='ckanext.ga_report.controller:GaDatasetReport',
+ action='dataset_csv'
+ )
+ map.connect(
+ '/data/site-usage/dataset',
+ controller='ckanext.ga_report.controller:GaDatasetReport',
+ action='read'
+ )
+ map.connect(
+ '/data/site-usage/dataset/{id}',
+ controller='ckanext.ga_report.controller:GaDatasetReport',
+ action='read_publisher'
+ )
return map
--- a/ckanext/ga_report/templates/ga_report/ga_popular_datasets.html
+++ b/ckanext/ga_report/templates/ga_report/ga_popular_datasets.html
@@ -5,7 +5,7 @@
<div class="popular_datasets">
<div class="pull-right">
- <a href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='index')}" class="btn btn-primary">More popular datasets »</a>
+ <a href="${h.url_for(controller='ckanext.ga_report.controller:GaDatasetReport',action='read')}" class="btn btn-primary">More popular datasets »</a>
</div>
<h2>Popular datasets</h2>
<h4>${publisher.title}</h4>
--- a/ckanext/ga_report/templates/ga_report/ga_popular_single.html
+++ b/ckanext/ga_report/templates/ga_report/ga_popular_single.html
@@ -7,11 +7,19 @@
<div class="popular_datasets">
<h2>Featured dataset</h2>
- <h3>${h.link_to(dataset.title, h.url_for(controller='package', action='read', id=dataset.name))}</h3> <div>${h.truncate(dataset.notes, length=200, whole_word=True)}</div>
- <p></p>
+ <div class="dataset-summary boxed">
+ <a class="dataset-header" href="${h.url_for(controller='package', action='read', id=dataset.name)}">
+ <h3>${dataset.title}</h3>
+ </a>
+ <h4>
+ <strong>Publisher</strong> :
+ <a href="/publisher/${publisher.name}">${publisher.title}</a>
+ </h4>