Fixed the publishr information (to enable leaderboard) to show the number
of children publishers and the total for all sub-publishers
--- a/.gitignore
+++ b/.gitignore
@@ -15,6 +15,10 @@
develop-eggs
.installed.cfg
+# Private info
+credentials.json
+token.dat
+
# Installer logs
pip-log.txt
--- a/README.rst
+++ b/README.rst
@@ -31,11 +31,10 @@
2. Ensure you development.ini (or similar) contains the info about your Google Analytics account and configuration::
googleanalytics.id = UA-1010101-1
- googleanalytics.username = googleaccount@gmail.com
- googleanalytics.password = googlepassword
+ googleanalytics.account = Account name (i.e. data.gov.uk, see top level item at https://www.google.com/analytics)
ga-report.period = monthly
- Note that your password 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.
+ 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)::
@@ -46,12 +45,52 @@
ckan.plugins = ga-report
+Authorization
+--------------
+
+Before you can access the data, you need to set up the OAUTH details which you can do by following the `instructions <https://developers.google.com/analytics/resources/tutorials/hello-analytics-api>`_ the outcome of which will be a file called credentials.json which should look like credentials.json.template with the relevant fields completed. These steps are below for convenience:
+
+1. Visit the `Google APIs Console <https://code.google.com/apis/console>`_
+
+2. Sign-in and create a project or use an existing project.
+
+3. In the `Services pane <https://code.google.com/apis/console#:services>`_ , activate Analytics API for your project. If prompted, read and accept the terms of service.
+
+4. Go to the `API Access pane <https://code.google.com/apis/console/#:access>`_
+
+5. Click Create an OAuth 2.0 client ID....
+
+6. Fill out the Branding Information fields and click Next.
+
+7. In Client ID Settings, set Application type to Installed application.
+
+8. Click Create client ID
+
+9. The details you need below are Client ID, Client secret, and Redirect URIs
+
+
+Once you have set up your credentials.json file you can generate an oauth token file by using the
+following command, which will store your oauth token in a file called token.dat once you have finished
+giving permission in the browser::
+
+ $ paster getauthtoken --config=../ckan/development.ini
+
+
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)::
+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::
- $ paster loadanalytics latest --config=../ckan/development.ini
+ $ paster loadanalytics token.dat latest --config=../ckan/development.ini
+
+The value after the token file is how much data you want to retrieve, this can be
+
+* **all** - data for all time (since 2010)
+
+* **latest** - (default) just the 'latest' data
+
+* **YYYY-MM-DD** - just data for all time periods going back to (and including) this date
+
Software Licence
--- a/ckanext/ga_report/command.py
+++ b/ckanext/ga_report/command.py
@@ -1,7 +1,10 @@
import logging
+import datetime
from ckan.lib.cli import CkanCommand
-# No other CKAN imports allowed until _load_config is run, or logging is disabled
+# No other CKAN imports allowed until _load_config is run,
+# or logging is disabled
+
class InitDB(CkanCommand):
"""Initialise the extension's database tables
@@ -23,13 +26,44 @@
ga_model.init_tables()
log.info("DB tables are setup")
+
+class GetAuthToken(CkanCommand):
+ """ Get's the Google auth token
+
+ Usage: paster getauthtoken <credentials_file>
+
+ Where <credentials_file> is the file name containing the details
+ for the service (obtained from https://code.google.com/apis/console).
+ By default this is set to credentials.json
+ """
+ summary = __doc__.split('\n')[0]
+ usage = __doc__
+ max_args = 0
+ min_args = 0
+
+ def command(self):
+ """
+ In this case we don't want a valid service, but rather just to
+ force the user through the auth flow. We allow this to complete to
+ act as a form of verification instead of just getting the token and
+ assuming it is correct.
+ """
+ from ga_auth import init_service
+ init_service('token.dat',
+ self.args[0] if self.args
+ else 'credentials.json')
+
+
class LoadAnalytics(CkanCommand):
"""Get data from Google Analytics API and save it
in the ga_model
- Usage: paster loadanalytics <time-period>
+ Usage: paster loadanalytics <tokenfile> <time-period>
- Where <time-period> is:
+ Where <tokenfile> is the name of the auth token file from
+ the getauthtoken step.
+
+ And where <time-period> is:
all - data for all time
latest - (default) just the 'latest' data
YYYY-MM-DD - just data for all time periods going
@@ -37,16 +71,26 @@
"""
summary = __doc__.split('\n')[0]
usage = __doc__
- max_args = 1
- min_args = 0
+ max_args = 2
+ min_args = 1
def command(self):
self._load_config()
from download_analytics import DownloadAnalytics
- downloader = DownloadAnalytics()
-
- time_period = self.args[0] if self.args else 'latest'
+ from ga_auth import (init_service, get_profile_id)
+
+ try:
+ svc = init_service(self.args[0], None)
+ except TypeError:
+ print ('Have you correctly run the getauthtoken task and '
+ 'specified the correct file here')
+ return
+
+ downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc))
+
+ time_period = self.args[1] if self.args and len(self.args) > 1 \
+ else 'latest'
if time_period == 'all':
downloader.all_()
elif time_period == 'latest':
@@ -55,4 +99,3 @@
since_date = datetime.datetime.strptime(time_period, '%Y-%m-%d')
downloader.since_date(since_date)
-
--- a/ckanext/ga_report/download_analytics.py
+++ b/ckanext/ga_report/download_analytics.py
@@ -1,10 +1,12 @@
+import os
import logging
import datetime
from pylons import config
import ga_model
-from ga_client import GA
+
+#from ga_client import GA
log = logging.getLogger('ckanext.ga-report')
@@ -12,12 +14,16 @@
class DownloadAnalytics(object):
'''Downloads and stores analytics info'''
- def __init__(self):
+
+ def __init__(self, service=None, profile_id=None):
self.period = config['ga-report.period']
-
+ self.service = service
+ self.profile_id = profile_id
+
+
def all_(self):
- pass
-
+ self.since_date(datetime.datetime(2010, 1, 1))
+
def latest(self):
if self.period == 'monthly':
# from first of this month to today
@@ -49,8 +55,8 @@
break
elif first_of_the_month < first_of_this_month:
in_the_next_month = first_of_the_month + datetime.timedelta(40)
- last_of_the_month == datetime.datetime(in_the_next_month.year,
- in_the_next_month.month, a)\
+ last_of_the_month = datetime.datetime(in_the_next_month.year,
+ in_the_next_month.month, 1)\
- datetime.timedelta(1)
periods.append((now.strftime(FORMAT_MONTH), 0,
first_of_the_month, last_of_the_month))
@@ -71,7 +77,7 @@
return period_name + ' (up to %ith)' % period_complete_day
else:
return period_name
-
+
def download_and_store(self, periods):
for period_name, period_complete_day, start_date, end_date in periods:
@@ -79,38 +85,215 @@
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)
- log.info('Storing Analytics for period "%s"',
+ """
+ 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))
- self.store(period_name, period_complete_day, data)
-
- @classmethod
- def download(cls, start_date, end_date):
+ self.store(period_name, period_complete_day, data, )
+
+ data = self.download(start_date, end_date, '~/publisher/[a-z0-9-_]+')
+ 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 )
+
+
+ def download(self, start_date, end_date, path='~/dataset/[a-z0-9-_]+'):
'''Get data from GA for a given time period'''
start_date = start_date.strftime('%Y-%m-%d')
end_date = end_date.strftime('%Y-%m-%d')
- # url
- #query = 'ga:pagePath=~^%s,ga:pagePath=~^%s' % \
- # (PACKAGE_URL, self.resource_url_tag)
- query = 'ga:pagePath=~^/dataset/'
- metrics = 'ga:uniquePageviews'
+ query = 'ga:pagePath=%s$' % path
+ metrics = 'ga:uniquePageviews, ga:visitors'
sort = '-ga:uniquePageviews'
- for entry in GA.ga_query(query_filter=query,
- from_date=start_date,
+
+ # 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,
- to_date=end_date):
- print entry
- import pdb; pdb.set_trace()
- for dim in entry.dimension:
- if dim.name == "ga:pagePath":
- package = dim.value
- count = entry.get_metric(
- 'ga:uniquePageviews').value or 0
- packages[package] = int(count)
- return packages
+ dimensions="ga:pagePath",
+ 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
+ packages.append( ('http:/' + loc, pageviews, visits,) ) # Temporary hack
+ return dict(url=packages)
def store(self, period_name, period_complete_day, data):
if 'url' in data:
ga_model.update_url_stats(period_name, period_complete_day, data['url'])
+ def sitewide_stats(self, period_name):
+ import calendar
+ year, month = period_name.split('-')
+ _, last_day_of_month = calendar.monthrange(int(year), int(month))
+
+ start_date = '%s-01' % period_name
+ end_date = '%s-%s' % (period_name, last_day_of_month)
+ print 'Sitewide_stats for %s (%s -> %s)' % (period_name, start_date, end_date)
+
+ funcs = ['_totals_stats', '_social_stats', '_os_stats',
+ '_locale_stats', '_browser_stats', '_mobile_stats']
+ for f in funcs:
+ print ' + Fetching %s stats' % f.split('_')[1]
+ getattr(self, f)(start_date, end_date, period_name)
+
+ def _get_results(result_data, f):
+ data = {}
+ for result in result_data:
+ key = f(result)
+ data[key] = data.get(key,0) + result[1]
+ return data
+
+ def _totals_stats(self, start_date, end_date, period_name):
+ """ Fetches distinct totals, total pageviews etc """
+ results = self.service.data().ga().get(
+ ids='ga:' + self.profile_id,
+ start_date=start_date,
+ metrics='ga:uniquePageviews',
+ sort='-ga:uniquePageviews',
+ 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',
+ max_results=10000,
+ end_date=end_date).execute()
+ result_data = results.get('rows')
+ data = {
+ '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],
+ }
+ ga_model.update_sitewide_stats(period_name, "Totals", data)
+
+
+ def _locale_stats(self, start_date, end_date, period_name):
+ """ Fetches stats about language and country """
+ results = self.service.data().ga().get(
+ ids='ga:' + self.profile_id,
+ start_date=start_date,
+ metrics='ga:uniquePageviews',
+ sort='-ga:uniquePageviews',
+ dimensions="ga:language,ga:country",
+ max_results=10000,
+ end_date=end_date).execute()
+ result_data = results.get('rows')
+ data = {}
+ for result in result_data:
+ data[result[0]] = data.get(result[0], 0) + int(result[2])
+ 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])
+ ga_model.update_sitewide_stats(period_name, "Country", data)
+
+
+ def _social_stats(self, start_date, end_date, period_name):
+ """ Finds out which social sites people are referred from """
+ results = self.service.data().ga().get(
+ ids='ga:' + self.profile_id,
+ start_date=start_date,
+ metrics='ga:uniquePageviews',
+ sort='-ga:uniquePageviews',
+ dimensions="ga:socialNetwork,ga:referralPath",
+ 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])
+ ga_model.update_sitewide_stats(period_name, "Social sources", data)
+
+
+ def _os_stats(self, start_date, end_date, period_name):
+ """ Operating system stats """
+ results = self.service.data().ga().get(
+ ids='ga:' + self.profile_id,
+ start_date=start_date,
+ metrics='ga:uniquePageviews',
+ sort='-ga:uniquePageviews',
+ dimensions="ga:operatingSystem,ga:operatingSystemVersion",
+ max_results=10000,
+ end_date=end_date).execute()
+ result_data = results.get('rows')
+ data = {}
+ for result in result_data:
+ data[result[0]] = data.get(result[0], 0) + int(result[2])
+ 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]
+ ga_model.update_sitewide_stats(period_name, "Operating Systems versions", data)
+
+
+ def _browser_stats(self, start_date, end_date, period_name):
+ """ Information about browsers and browser versions """
+ results = self.service.data().ga().get(
+ ids='ga:' + self.profile_id,
+ start_date=start_date,
+ metrics='ga:uniquePageviews',
+ sort='-ga:uniquePageviews',
+ dimensions="ga:browser,ga:browserVersion",
+ max_results=10000,
+ end_date=end_date).execute()
+ result_data = results.get('rows')
+ data = {}
+ for result in result_data:
+ data[result[0]] = data.get(result[0], 0) + int(result[2])
+ 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]
+ ga_model.update_sitewide_stats(period_name, "Browser versions", data)
+
+
+ def _mobile_stats(self, start_date, end_date, period_name):
+ """ Info about mobile devices """
+
+ results = self.service.data().ga().get(
+ ids='ga:' + self.profile_id,
+ start_date=start_date,
+ metrics='ga:uniquePageviews',
+ sort='-ga:uniquePageviews',
+ dimensions="ga:mobileDeviceBranding, ga:mobileDeviceInfo",
+ max_results=10000,
+ end_date=end_date).execute()
+
+ result_data = results.get('rows')
+ data = {}
+ for result in result_data:
+ data[result[0]] = data.get(result[0], 0) + int(result[2])
+ 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])
+ ga_model.update_sitewide_stats(period_name, "Mobile devices", data)
+
--- /dev/null
+++ b/ckanext/ga_report/ga_auth.py
@@ -1,1 +1,70 @@
+import os
+import httplib2
+from apiclient.discovery import build
+from oauth2client.client import flow_from_clientsecrets
+from oauth2client.file import Storage
+from oauth2client.tools import run
+from pylons import config
+
+
+def _prepare_credentials(token_filename, credentials_filename):
+ """
+ Either returns the user's oauth credentials or uses the credentials
+ file to generate a token (by forcing the user to login in the browser)
+ """
+ storage = Storage(token_filename)
+ credentials = storage.get()
+
+ if credentials is None or credentials.invalid:
+ flow = flow_from_clientsecrets(credentials_filename,
+ scope='https://www.googleapis.com/auth/analytics.readonly',
+ message="Can't find the credentials file")
+ credentials = run(flow, storage)
+
+ return credentials
+
+
+def init_service(token_file, credentials_file):
+ """
+ Given a file containing the user's oauth token (and another with
+ credentials in case we need to generate the token) will return a
+ service object representing the analytics API.
+ """
+ http = httplib2.Http()
+
+ credentials = _prepare_credentials(token_file, credentials_file)
+ http = credentials.authorize(http) # authorize the http object
+
+ return build('analytics', 'v3', http=http)
+
+
+def get_profile_id(service):
+ """
+ Get the profile ID for this user and the service specified by the
+ 'googleanalytics.id' configuration option. This function iterates
+ over all of the accounts available to the user who invoked the
+ service to find one where the account name matches (in case the
+ user has several).
+ """
+ accounts = service.management().accounts().list().execute()
+
+ if not accounts.get('items'):
+ return None
+
+ accountName = config.get('googleanalytics.account')
+ webPropertyId = config.get('googleanalytics.id')
+ for acc in accounts.get('items'):
+ if acc.get('name') == accountName:
+ accountId = acc.get('id')
+
+ webproperties = service.management().webproperties().list(accountId=accountId).execute()
+
+ profiles = service.management().profiles().list(
+ accountId=accountId, webPropertyId=webPropertyId).execute()
+
+ if profiles.get('items'):
+ return profiles.get('items')[0].get('id')
+
+ return None
+
--- a/ckanext/ga_report/ga_model.py
+++ b/ckanext/ga_report/ga_model.py
@@ -3,30 +3,80 @@
from sqlalchemy import Table, Column, MetaData
from sqlalchemy import types
-from sqlalchemy.sql import select, text
+from sqlalchemy.sql import select
+from sqlalchemy.orm import mapper
from sqlalchemy import func
import ckan.model as model
-from ckan.model.types import JsonType
from ckan.lib.base import *
def make_uuid():
return unicode(uuid.uuid4())
+
+
+class GA_Url(object):
+
+ def __init__(self, **kwargs):
+ 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),
+ Column('period_name', types.UnicodeText),
+ Column('period_complete_day', types.Integer),
+ Column('pageviews', types.UnicodeText),
+ Column('visitors', types.UnicodeText),
+ Column('url', types.UnicodeText),
+ Column('department_id', types.UnicodeText),
+ )
+mapper(GA_Url, url_table)
+
+stat_table = Table('ga_stat', metadata,
+ Column('id', types.UnicodeText, primary_key=True,
+ default=make_uuid),
+ Column('period_name', types.UnicodeText),
+ Column('stat_name', types.UnicodeText),
+ Column('key', types.UnicodeText),
+ Column('value', types.UnicodeText), )
+mapper(GA_Stat, stat_table)
+
+
+pub_table = Table('ga_publisher', metadata,
+ Column('id', types.UnicodeText, primary_key=True,
+ default=make_uuid),
+ Column('period_name', types.UnicodeText),
+ Column('publisher_name', types.UnicodeText),
+ Column('views', types.UnicodeText),
+ Column('visitors', types.UnicodeText),
+ Column('toplevel', types.Boolean, default=False),
+ Column('subpublishercount', types.Integer, default=0),
+ Column('parent', types.UnicodeText),
+)
+mapper(GA_Publisher, pub_table)
+
+
def init_tables():
- metadata = MetaData()
- package_stats = Table('ga_url', metadata,
- Column('id', types.UnicodeText, primary_key=True, default=make_uuid),
- Column('period_name', types.UnicodeText),
- Column('period_complete_day', types.Integer),
- Column('visits', types.Integer),
- Column('group_id', types.String(60)),
- Column('next_page', JsonType),
- )
metadata.create_all(model.meta.engine)
cached_tables = {}
+
def get_table(name):
if name not in cached_tables:
@@ -45,6 +95,7 @@
'''
url = re.sub('https?://(www\.)?data.gov.uk', '', url)
return url
+
def _get_department_id_of_url(url):
# e.g. /dataset/fuel_prices
@@ -56,36 +107,144 @@
if dataset:
publisher_groups = dataset.get_groups('publisher')
if publisher_groups:
- return publisher_groups[0].id
+ return publisher_groups[0].name
+ else:
+ publisher_match = re.match('/publisher/([^/]+)(/.*)?', url)
+ if publisher_match:
+ return publisher_match.groups()[0]
+
+
+def update_sitewide_stats(period_name, stat_name, data):
+ for k,v in data.iteritems():
+ item = model.Session.query(GA_Stat).\
+ filter(GA_Stat.period_name==period_name).\
+ filter(GA_Stat.key==k).\
+ filter(GA_Stat.stat_name==stat_name).first()
+ if item:
+ item.period_name = period_name
+ item.key = k
+ item.value = v
+ model.Session.add(item)
+ else:
+ # create the row
+ values = {'id': make_uuid(),
+ 'period_name': period_name,
+ 'key': k,
+ 'value': v,
+ 'stat_name': stat_name
+ }
+ model.Session.add(GA_Stat(**values))
+ model.Session.commit()
+
+
def update_url_stats(period_name, period_complete_day, url_data):
- table = get_table('ga_url')
- connection = model.Session.connection()
- for url, views, next_page in url_data:
+ for url, views, visitors in url_data:
url = _normalize_url(url)
department_id = _get_department_id_of_url(url)
+
# see if the row for this url & month is in the table already
- s = select([func.count(id_col)],
- table.c.period_name == period_name,
- table.c.url == url)
- count = connection.execute(s).fetchone()
- if count and count[0]:
- # update the row
- connection.execute(table.update()\
- .where(table.c.period_name == period_name,
- table.c.url == url)\
- .values(period_complete_day=period_complete_day,
- views=views,
- department_id=department_id,
- next_page=next_page))
+ item = model.Session.query(GA_Url).\
+ filter(GA_Url.period_name==period_name).\
+ filter(GA_Url.url==url).first()
+ if item:
+ item.period_name = period_name
+ item.pageviews = views
+ item.visitors = visitors
+ item.department_id = department_id
+ model.Session.add(item)
else:
# create the row
- values = {'period_name': period_name,
+ values = {'id': make_uuid(),
+ 'period_name': period_name,
'period_complete_day': period_complete_day,
'url': url,
- 'views': views,
- 'department_id': department_id,
- 'next_page': next_page}
- connection.execute(stats.insert()\
- .values(**values))
-
+ 'pageviews': views,
+ 'visitors': visitors,
+ 'department_id': department_id
+ }
+ model.Session.add(GA_Url(**values))
+ model.Session.commit()
+
+
+
+def update_publisher_stats(period_name):
+ """
+ Updates the publisher stats from the data retrieved for /dataset/*
+ and /publisher/*. Will run against each dataset and generates the
+ totals for the entire tree beneath each publisher.
+ """
+ toplevel = get_top_level()
+ publishers = model.Session.query(model.Group).\
+ filter(model.Group.type=='publisher').\
+ filter(model.Group.state=='active').all()
+ for publisher in publishers:
+ views, visitors, subpub = update_publisher(period_name, publisher, publisher.name)
+ parent, parents = '', publisher.get_groups('publisher')
+ if parents:
+ parent = parents[0].name
+ item = model.Session.query(GA_Publisher).\
+ filter(GA_Publisher.period_name==period_name).\
+ filter(GA_Publisher.publisher_name==publisher.name).first()
+ if item:
+ item.views = views
+ item.visitors = visitors
+ item.publisher_name = publisher.name
+ item.toplevel = publisher in toplevel
+ item.subpublishercount = subpub
+ item.parent = parent
+ model.Session.add(item)
+ else:
+ # create the row
+ values = {'id': make_uuid(),
+ 'period_name': period_name,
+ 'publisher_name': publisher.name,
+ 'views': views,
+ 'visitors': visitors,
+ 'toplevel': publisher in toplevel,
+ 'subpublishercount': subpub,
+ 'parent': parent
+ }
+ model.Session.add(GA_Publisher(**values))
+ model.Session.commit()
+
+
+def update_publisher(period_name, pub, part=''):
+ views,visitors,subpub = 0, 0, 0
+ for publisher in go_down_tree(pub):
+ subpub = subpub + 1
+ items = model.Session.query(GA_Url).\
+ filter(GA_Url.period_name==period_name).\
+ filter(GA_Url.department_id==publisher.name).all()
+ for item in items:
+ views = views + int(item.pageviews)
+ visitors = visitors + int(item.visitors)
+
+ return views, visitors, (subpub-1)
+
+
+def get_top_level():
+ '''Returns the top level publishers.'''