| ckanext-ga-report | ckanext-ga-report |
| ================= | ================= |
| **Status:** Development | **Status:** Development |
| **CKAN Version:** 1.7.1+ | **CKAN Version:** 1.7.1+ |
| Overview | Overview |
| -------- | -------- |
| For creating detailed reports of CKAN analytics, including totals per group. | For creating detailed reports of CKAN analytics, including totals per group. |
| Whereas ckanext-googleanalytics focusses on providing page view stats a recent period and for all time (aimed at end users), ckanext-ga-report is more interested in building regular periodic reports (more for site managers to monitor). | Whereas ckanext-googleanalytics focusses on providing page view stats a recent period and for all time (aimed at end users), ckanext-ga-report is more interested in building regular periodic reports (more for site managers to monitor). |
| Contents of this extension: | Contents of this extension: |
| * Use the CLI tool to download Google Analytics data for each time period into this extension's database tables | * Use the CLI tool to download Google Analytics data for each time period into this extension's database tables |
| * Users can view the data as web page reports | * Users can view the data as web page reports |
| Installation | Installation |
| ------------ | ------------ |
| 1. Activate you CKAN python environment and install this extension's software:: | 1. Activate you CKAN python environment and install this extension's software:: |
| $ pyenv/bin/activate | $ 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:: | 2. Ensure you development.ini (or similar) contains the info about your Google Analytics account and configuration:: |
| googleanalytics.id = UA-1010101-1 | googleanalytics.id = UA-1010101-1 |
| googleanalytics.username = googleaccount@gmail.com | googleanalytics.account = Account name (i.e. data.gov.uk, see top level item at https://www.google.com/analytics) |
| googleanalytics.password = googlepassword | |
| ga-report.period = monthly | 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):: | 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):: |
| $ paster initdb --config=../ckan/development.ini | $ paster initdb --config=../ckan/development.ini |
| 4. Enable the extension in your CKAN config file by adding it to ``ckan.plugins``:: | 4. Enable the extension in your CKAN config file by adding it to ``ckan.plugins``:: |
| ckan.plugins = ga-report | ckan.plugins = ga-report |
| Authorization | 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: | 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>`_ | 1. Visit the `Google APIs Console <https://code.google.com/apis/console>`_ |
| 2. Sign-in and create a project or use an existing project. | 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. | 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>`_ | 4. Go to the `API Access pane <https://code.google.com/apis/console/#:access>`_ |
| 5. Click Create an OAuth 2.0 client ID.... | 5. Click Create an OAuth 2.0 client ID.... |
| 6. Fill out the Branding Information fields and click Next. | 6. Fill out the Branding Information fields and click Next. |
| 7. In Client ID Settings, set Application type to Installed application. | 7. In Client ID Settings, set Application type to Installed application. |
| 8. Click Create client ID | 8. Click Create client ID |
| 9. The details you need below are Client ID, Client secret, and Redirect URIs | 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 | 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 | following command, which will store your oauth token in a file called token.dat once you have finished |
| giving permission in the browser. | giving permission in the browser:: |
| $ paster getauthtoken --config=../ckan/development.ini | $ paster getauthtoken --config=../ckan/development.ini |
| Tutorial | 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 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 token.dat 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 | Software Licence |
| ================ | ================ |
| This software is developed by Cabinet Office. It is Crown Copyright and opened up under the Open Government Licence (OGL) (which is compatible with Creative Commons Attibution License). | This software is developed by Cabinet Office. It is Crown Copyright and opened up under the Open Government Licence (OGL) (which is compatible with Creative Commons Attibution License). |
| OGL terms: http://www.nationalarchives.gov.uk/doc/open-government-licence/ | OGL terms: http://www.nationalarchives.gov.uk/doc/open-government-licence/ |
| import logging | import logging |
| import datetime | |
| from ckan.lib.cli import CkanCommand | 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): | class InitDB(CkanCommand): |
| """Initialise the extension's database tables | """Initialise the extension's database tables |
| """ | """ |
| summary = __doc__.split('\n')[0] | summary = __doc__.split('\n')[0] |
| usage = __doc__ | usage = __doc__ |
| max_args = 0 | max_args = 0 |
| min_args = 0 | min_args = 0 |
| def command(self): | def command(self): |
| self._load_config() | self._load_config() |
| import ckan.model as model | import ckan.model as model |
| model.Session.remove() | model.Session.remove() |
| model.Session.configure(bind=model.meta.engine) | model.Session.configure(bind=model.meta.engine) |
| log = logging.getLogger('ckanext.ga-report') | log = logging.getLogger('ckanext.ga-report') |
| import ga_model | import ga_model |
| ga_model.init_tables() | ga_model.init_tables() |
| log.info("DB tables are setup") | log.info("DB tables are setup") |
| class GetAuthToken(CkanCommand): | class GetAuthToken(CkanCommand): |
| """ Get's the Google auth token | """ 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] | summary = __doc__.split('\n')[0] |
| usage = __doc__ | usage = __doc__ |
| max_args = 0 | max_args = 0 |
| min_args = 0 | min_args = 0 |
| def command(self): | def command(self): |
| from ga_auth import initialize_service | """ |
| initialize_service('token.dat', | In this case we don't want a valid service, but rather just to |
| self.args[0] if self.args | force the user through the auth flow. We allow this to complete to |
| else 'credentials.json') | 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): | class LoadAnalytics(CkanCommand): |
| """Get data from Google Analytics API and save it | """Get data from Google Analytics API and save it |
| in the ga_model | in the ga_model |
| Usage: paster loadanalytics <tokenfile> <time-period> | Usage: paster loadanalytics <tokenfile> <time-period> |
| Where <tokenfile> is the name of the auth token file from | Where <tokenfile> is the name of the auth token file from |
| the getauthtoken step. | the getauthtoken step. |
| And where <time-period> is: | And where <time-period> is: |
| all - data for all time | all - data for all time |
| latest - (default) just the 'latest' data | latest - (default) just the 'latest' data |
| YYYY-MM-DD - just data for all time periods going | YYYY-MM-DD - just data for all time periods going |
| back to (and including) this date | back to (and including) this date |
| """ | """ |
| summary = __doc__.split('\n')[0] | summary = __doc__.split('\n')[0] |
| usage = __doc__ | usage = __doc__ |
| max_args = 2 | max_args = 2 |
| min_args = 1 | min_args = 1 |
| def command(self): | def command(self): |
| self._load_config() | self._load_config() |
| from ga_auth import initialize_service | from download_analytics import DownloadAnalytics |
| from ga_auth import (init_service, get_profile_id) | |
| try: | try: |
| svc = initialize_service(self.args[0], None) | svc = init_service(self.args[0], None) |
| except TypeError: | except TypeError: |
| print 'Have you correctly run the getauthtoken task and specified the correct file here' | print ('Have you correctly run the getauthtoken task and ' |
| 'specified the correct file here') | |
| return | return |
| from download_analytics import DownloadAnalytics | |
| from ga_auth import get_profile_id | |
| downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc)) | downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc)) |
| time_period = self.args[1] if self.args and len(self.args) > 1 else 'latest' | time_period = self.args[1] if self.args and len(self.args) > 1 \ |
| else 'latest' | |
| if time_period == 'all': | if time_period == 'all': |
| downloader.all_() | downloader.all_() |
| elif time_period == 'latest': | elif time_period == 'latest': |
| downloader.latest() | downloader.latest() |
| else: | else: |
| since_date = datetime.datetime.strptime(time_period, '%Y-%m-%d') | since_date = datetime.datetime.strptime(time_period, '%Y-%m-%d') |
| downloader.since_date(since_date) | downloader.since_date(since_date) |
| import logging | import logging |
| from ckan.lib.base import BaseController, c, render | import operator |
| import report_model | 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') | log = logging.getLogger('ckanext.ga-report') |
| def _get_month_name(str): | |
| import calendar | |
| from time import strptime | |
| d = strptime('2012-10', '%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))) | |
| return sorted(months, key=operator.itemgetter(0), reverse=True) | |
| class GaReport(BaseController): | 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-disposition'] = 'attachment; filename=dgu_analytics_%s.csv' % (month) | |
| 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): | 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).all() | |
| c.global_totals = [(s.key, s.value) for s in entries ] | |
| 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 not url like '/publisher/%%' | |
| and period_name=%s | |
| group by department_id order by views desc limit 20; | |
| """ | |
| 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') | |
| import os | |
| import logging | import logging |
| import datetime | import datetime |
| from pylons import config | from pylons import config |
| import ga_model | import ga_model |
| #from ga_client import GA | #from ga_client import GA |
| log = logging.getLogger('ckanext.ga-report') | log = logging.getLogger('ckanext.ga-report') |
| FORMAT_MONTH = '%Y-%m' | FORMAT_MONTH = '%Y-%m' |
| class DownloadAnalytics(object): | class DownloadAnalytics(object): |
| '''Downloads and stores analytics info''' | '''Downloads and stores analytics info''' |
| def __init__(self, service=None, profile_id=None): | def __init__(self, service=None, profile_id=None): |
| self.period = config['ga-report.period'] | self.period = config['ga-report.period'] |
| self.service = service | self.service = service |
| self.profile_id = profile_id | self.profile_id = profile_id |
| def all_(self): | def all_(self): |
| self.since_date(datetime.datetime(2010, 1, 1)) | self.since_date(datetime.datetime(2010, 1, 1)) |
| def latest(self): | def latest(self): |
| if self.period == 'monthly': | if self.period == 'monthly': |
| # from first of this month to today | # from first of this month to today |
| now = datetime.datetime.now() | now = datetime.datetime.now() |
| first_of_this_month = datetime.datetime(now.year, now.month, 1) | first_of_this_month = datetime.datetime(now.year, now.month, 1) |
| periods = ((now.strftime(FORMAT_MONTH), | periods = ((now.strftime(FORMAT_MONTH), |
| now.day, | now.day, |
| first_of_this_month, now),) | first_of_this_month, now),) |
| else: | else: |
| raise NotImplementedError | raise NotImplementedError |
| self.download_and_store(periods) | self.download_and_store(periods) |
| def since_date(self, since_date): | def since_date(self, since_date): |
| assert isinstance(since_date, datetime.datetime) | assert isinstance(since_date, datetime.datetime) |
| periods = [] # (period_name, period_complete_day, start_date, end_date) | periods = [] # (period_name, period_complete_day, start_date, end_date) |
| if self.period == 'monthly': | if self.period == 'monthly': |
| first_of_the_months_until_now = [] | first_of_the_months_until_now = [] |
| year = since_date.year | year = since_date.year |
| month = since_date.month | month = since_date.month |
| now = datetime.datetime.now() | now = datetime.datetime.now() |
| first_of_this_month = datetime.datetime(now.year, now.month, 1) | first_of_this_month = datetime.datetime(now.year, now.month, 1) |
| while True: | while True: |
| first_of_the_month = datetime.datetime(year, month, 1) | first_of_the_month = datetime.datetime(year, month, 1) |
| if first_of_the_month == first_of_this_month: | if first_of_the_month == first_of_this_month: |
| periods.append((now.strftime(FORMAT_MONTH), | periods.append((now.strftime(FORMAT_MONTH), |
| now.day, | now.day, |
| first_of_this_month, now)) | first_of_this_month, now)) |
| break | break |
| elif first_of_the_month < first_of_this_month: | elif first_of_the_month < first_of_this_month: |
| in_the_next_month = first_of_the_month + datetime.timedelta(40) | in_the_next_month = first_of_the_month + datetime.timedelta(40) |
| last_of_the_month = datetime.datetime(in_the_next_month.year, | last_of_the_month = datetime.datetime(in_the_next_month.year, |
| in_the_next_month.month, 1)\ | in_the_next_month.month, 1)\ |
| - datetime.timedelta(1) | - datetime.timedelta(1) |
| periods.append((now.strftime(FORMAT_MONTH), 0, | periods.append((now.strftime(FORMAT_MONTH), 0, |
| first_of_the_month, last_of_the_month)) | first_of_the_month, last_of_the_month)) |
| else: | else: |
| # first_of_the_month has got to the future somehow | # first_of_the_month has got to the future somehow |
| break | break |
| month += 1 | month += 1 |
| if month > 12: | if month > 12: |
| year += 1 | year += 1 |
| month = 1 | month = 1 |
| else: | else: |
| raise NotImplementedError | raise NotImplementedError |
| self.download_and_store(periods) | self.download_and_store(periods) |
| @staticmethod | @staticmethod |
| def get_full_period_name(period_name, period_complete_day): | def get_full_period_name(period_name, period_complete_day): |
| if period_complete_day: | if period_complete_day: |
| return period_name + ' (up to %ith)' % period_complete_day | return period_name + ' (up to %ith)' % period_complete_day |
| else: | else: |
| return period_name | return period_name |
| def download_and_store(self, periods): | def download_and_store(self, periods): |
| for period_name, period_complete_day, start_date, end_date in periods: | for period_name, period_complete_day, start_date, end_date in periods: |
| log.info('Downloading Analytics for period "%s" (%s - %s)', | log.info('Downloading Analytics for period "%s" (%s - %s)', |
| self.get_full_period_name(period_name, period_complete_day), | self.get_full_period_name(period_name, period_complete_day), |
| start_date.strftime('%Y %m %d'), | start_date.strftime('%Y %m %d'), |
| end_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.get_full_period_name(period_name, period_complete_day)) |
| self.store(period_name, period_complete_day, data) | self.store(period_name, period_complete_day, data, ) |
| data = self.download(start_date, end_date, '~/publisher/[a-z0-9-_]+') | |
| def download(self, start_date, end_date): | 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''' | '''Get data from GA for a given time period''' |
| start_date = start_date.strftime('%Y-%m-%d') | start_date = start_date.strftime('%Y-%m-%d') |
| end_date = end_date.strftime('%Y-%m-%d') | end_date = end_date.strftime('%Y-%m-%d') |
| # url | query = 'ga:pagePath=%s$' % path |
| #query = 'ga:pagePath=~^%s,ga:pagePath=~^%s' % \ | metrics = 'ga:uniquePageviews, ga:visitors' |
| # (PACKAGE_URL, self.resource_url_tag) | |
| query = 'ga:pagePath=~^/dataset/' | |
| #query = 'ga:pagePath=~^/User/' | |
| metrics = 'ga:uniquePageviews' | |
| sort = '-ga:uniquePageviews' | sort = '-ga:uniquePageviews' |
| # Supported query params at | # Supported query params at |
| # https://developers.google.com/analytics/devguides/reporting/core/v3/reference | # https://developers.google.com/analytics/devguides/reporting/core/v3/reference |
| results = self.service.data().ga().get( | results = self.service.data().ga().get( |
| ids='ga:' + self.profile_id, | ids='ga:' + self.profile_id, |
| filters=query, | filters=query, |
| start_date=start_date, | start_date=start_date, |
| metrics=metrics, | metrics=metrics, |
| sort=sort, | sort=sort, |
| end_date=end_date).execute() | dimensions="ga:pagePath", |
| self.print_results(results) | max_results=10000, |
| end_date=end_date).execute() | |
| # for entry in GA.ga_query(query_filter=query, | |
| # from_date=start_date, | if os.getenv('DEBUG'): |
| # metrics=metrics, | import pprint |
| # sort=sort, | pprint.pprint(results) |
| # to_date=end_date): | |
| # print entry, type(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 [] | |
| def print_results(self, results): | |
| import pprint | |
| pprint.pprint(results) | |
| if results: | |
| print 'Profile: %s' % results.get('profileInfo').get('profileName') | |
| print 'Total results: %s' % results.get('totalResults') | print 'Total results: %s' % results.get('totalResults') |
| print 'Total Visits: %s' % results.get('rows', [[-1]])[0][0] | |
| else: | packages = [] |
| print 'No results found' | 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): | def store(self, period_name, period_complete_day, data): |
| if 'url' in data: | if 'url' in data: |
| ga_model.update_url_stats(period_name, period_complete_day, data['url']) | 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) | |
| import os | |
| import httplib2 | import httplib2 |
| from apiclient.discovery import build | from apiclient.discovery import build |
| from oauth2client.client import flow_from_clientsecrets | from oauth2client.client import flow_from_clientsecrets |
| from oauth2client.file import Storage | from oauth2client.file import Storage |
| from oauth2client.tools import run | from oauth2client.tools import run |
| from pylons import config | from pylons import config |
| def _prepare_credentials( token_filename, credentials_filename ): | def _prepare_credentials(token_filename, credentials_filename): |
| storage = Storage( token_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() | credentials = storage.get() |
| if credentials is None or credentials.invalid: | if credentials is None or credentials.invalid: |
| flow = flow_from_clientsecrets(credentials_filename, | flow = flow_from_clientsecrets(credentials_filename, |
| scope='https://www.googleapis.com/auth/analytics.readonly', | scope='https://www.googleapis.com/auth/analytics.readonly', |
| message="Can't find the credentials file") | message="Can't find the credentials file") |
| credentials = run(flow, storage) | credentials = run(flow, storage) |
| return credentials | return credentials |
| def initialize_service( token_file, credentials_file ): | |
| 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() | http = httplib2.Http() |
| credentials = _prepare_credentials(token_file, credentials_file) | credentials = _prepare_credentials(token_file, credentials_file) |
| http = credentials.authorize(http) # authorize the http object | http = credentials.authorize(http) # authorize the http object |
| return build('analytics', 'v3', http=http) | return build('analytics', 'v3', http=http) |
| def get_profile_id(service): | def get_profile_id(service): |
| # Get a list of all Google Analytics accounts for this user | """ |
| 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() | accounts = service.management().accounts().list().execute() |
| if accounts.get('items'): | if not accounts.get('items'): |
| firstAccountId = accounts.get('items')[0].get('id') | return None |
| webPropertyId = config.get('googleanalytics.id') | |
| profiles = service.management().profiles().list( | |
| accountId=firstAccountId, | |
| webPropertyId=webPropertyId).execute() | |
| if profiles.get('items'): | accountName = config.get('googleanalytics.account') |
| # return the first Profile ID | webPropertyId = config.get('googleanalytics.id') |
| return profiles.get('items')[0].get('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 | return None |
| import re | import re |
| import uuid | import uuid |
| from sqlalchemy import Table, Column, MetaData | from sqlalchemy import Table, Column, MetaData |
| from sqlalchemy import types | from sqlalchemy import types |
| from sqlalchemy.sql import select, text | from sqlalchemy.sql import select |
| from sqlalchemy.orm import mapper | |
| from sqlalchemy import func | from sqlalchemy import func |
| import ckan.model as model | import ckan.model as model |
| from ckan.model.types import JsonType | |
| from ckan.lib.base import * | from ckan.lib.base import * |
| def make_uuid(): | def make_uuid(): |
| return unicode(uuid.uuid4()) | 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(): | 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) | metadata.create_all(model.meta.engine) |
| cached_tables = {} | cached_tables = {} |
| def get_table(name): | def get_table(name): |
| if name not in cached_tables: | if name not in cached_tables: |
| meta = MetaData() | meta = MetaData() |
| meta.reflect(bind=model.meta.engine) | meta.reflect(bind=model.meta.engine) |
| table = meta.tables[name] | table = meta.tables[name] |
| cached_tables[name] = table | cached_tables[name] = table |
| return cached_tables[name] | return cached_tables[name] |
| def _normalize_url(url): | def _normalize_url(url): |
| '''Strip off the hostname etc. Do this before storing it. | '''Strip off the hostname etc. Do this before storing it. |
| >>> normalize_url('http://data.gov.uk/dataset/weekly_fuel_prices') | >>> normalize_url('http://data.gov.uk/dataset/weekly_fuel_prices') |
| '/dataset/weekly_fuel_prices' | '/dataset/weekly_fuel_prices' |
| ''' | ''' |
| url = re.sub('https?://(www\.)?data.gov.uk', '', url) | url = re.sub('https?://(www\.)?data.gov.uk', '', url) |
| return url | return url |
| def _get_department_id_of_url(url): | def _get_department_id_of_url(url): |
| # e.g. /dataset/fuel_prices | # e.g. /dataset/fuel_prices |
| # e.g. /dataset/fuel_prices/resource/e63380d4 | # e.g. /dataset/fuel_prices/resource/e63380d4 |
| dataset_match = re.match('/dataset/([^/]+)(/.*)?', url) | dataset_match = re.match('/dataset/([^/]+)(/.*)?', url) |
| if dataset_match: | if dataset_match: |
| dataset_ref = dataset_match.groups()[0] | dataset_ref = dataset_match.groups()[0] |
| dataset = model.Package.get(dataset_ref) | dataset = model.Package.get(dataset_ref) |
| if dataset: | if dataset: |
| publisher_groups = dataset.get_groups('publisher') | publisher_groups = dataset.get_groups('publisher') |
| if publisher_groups: | 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): | def update_url_stats(period_name, period_complete_day, url_data): |
| table = get_table('ga_url') | for url, views, visitors in url_data: |
| connection = model.Session.connection() | |
| for url, views, next_page in url_data: | |
| url = _normalize_url(url) | url = _normalize_url(url) |
| department_id = _get_department_id_of_url(url) | department_id = _get_department_id_of_url(url) |
| # see if the row for this url & month is in the table already | # see if the row for this url & month is in the table already |
| s = select([func.count(id_col)], | item = model.Session.query(GA_Url).\ |
| table.c.period_name == period_name, | filter(GA_Url.period_name==period_name).\ |
| table.c.url == url) | filter(GA_Url.url==url).first() |
| count = connection.execute(s).fetchone() | if item: |
| if count and count[0]: | item.period_name = period_name |
| # update the row | item.pageviews = views |
| connection.execute(table.update()\ | item.visitors = visitors |
| .where(table.c.period_name == period_name, | item.department_id = department_id |
| table.c.url == url)\ | model.Session.add(item) |
| .values(period_complete_day=period_complete_day, | |
| views=views, | |
| department_id=department_id, | |
| next_page=next_page)) | |
| else: | else: |
| # create the row | # create the row |
| values = {'period_name': period_name, | values = {'id': make_uuid(), |
| 'period_name': period_name, | |
| 'period_complete_day': period_complete_day, | 'period_complete_day': period_complete_day, |
| 'url': url, | 'url': url, |
| 'views': views, | 'pageviews': views, |
| 'department_id': department_id, | 'visitors': visitors, |
| 'next_page': next_page} | 'department_id': department_id |
| connection.execute(stats.insert()\ | } |
| .values(**values)) | 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.''' | |
| return model.Session.query(model.Group).\ | |
| outerjoin(model.Member, model.Member.table_id == model.Group.id and \ | |
| model.Member.table_name == 'group' and \ | |
| model.Member.state == 'active').\ | |
| filter(model.Member.id==None).\ | |
| filter(model.Group.type=='publisher').\ | |
| order_by(model.Group.name).all() | |
| def get_children(publisher): | |
| '''Finds child publishers for the given publisher (object). (Not recursive)''' | |
| from ckan.model.group import HIERARCHY_CTE | |
| return model.Session.query(model.Group).\ | |
| from_statement(HIERARCHY_CTE).params(id=publisher.id, type='publisher').\ | |
| all() | |
| def go_down_tree(publisher): | |
| '''Provided with a publisher object, it walks down the hierarchy and yields each publisher, | |
| including the one you supply.''' | |
| yield publisher | |
| for child in get_children(publisher): | |
| for grandchild in go_down_tree(child): | |
| yield grandchild | |
| import logging | import logging |
| import ckan.lib.helpers as h | import ckan.lib.helpers as h |
| import ckan.plugins as p | |
| from ckan.plugins import implements, toolkit | from ckan.plugins import implements, toolkit |
| import gasnippet | #import gasnippet |
| import commands | #import commands |
| import dbutil | #import dbutil |
| log = logging.getLogger('ckanext.ga-report') | log = logging.getLogger('ckanext.ga-report') |
| class GoogleAnalyticsPlugin(p.SingletonPlugin): | class GAReportPlugin(p.SingletonPlugin): |
| implements(p.IConfigurer, inherit=True) | implements(p.IConfigurer, inherit=True) |
| implements(p.IRoutes, inherit=True) | implements(p.IRoutes, inherit=True) |
| def update_config(self, config): | def update_config(self, config): |
| toolkit.add_template_directory(config, 'templates') | toolkit.add_template_directory(config, 'templates') |
| toolkit.add_public_directory(config, 'public') | toolkit.add_public_directory(config, 'public') |
| def after_map(self, map): | def after_map(self, map): |
| map.connect( | map.connect( |
| '/data/analytics/index', | '/data/analytics', |
| controller='ckanext.ga-report.controller:GaReport', | controller='ckanext.ga_report.controller:GaReport', |
| action='index' | action='index' |
| ) | |
| map.connect( | |
| '/data/analytics_{month}.csv', | |
| controller='ckanext.ga_report.controller:GaReport', | |
| action='csv' | |
| ) | |
| map.connect( | |
| '/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' | |
| ) | ) |
| return map | return map |
| <html xmlns:py="http://genshi.edgewall.org/" | |
| xmlns:i18n="http://genshi.edgewall.org/i18n" | |
| xmlns:xi="http://www.w3.org/2001/XInclude" | |
| py:strip=""> | |
| <py:def function="page_title">Publisher Analytics for ${g.site_title}</py:def> | |
| <py:match path="primarysidebar"> | |
| <li class="widget-container boxed widget_text"> | |
| <h4>Publishers</h4> | |
| </li> | |
| </py:match> | |
| <div py:match="content"> | |
| <h1>Publisher Analytics</h1> | |
| <h2>The top 20 publishers</h2> | |
| <form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='index')}" method="get"> | |
| <div class="controls"> | |
| <select name="month"> | |
| <py:for each="val,desc in c.months"> | |
| <option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option> | |
| </py:for> | |
| </select> | |
| <input class="btn button" type='submit' value="Update"/> | |
| </div> | |
| </form> | |
| <table class="table table-condensed table-bordered table-striped"> | |
| <tr> | |
| <th>Publisher</th> | |
| <th>Dataset Views</th> | |
| <th>Visits</th> | |
| </tr> | |
| <py:for each="publisher, views, visits in c.top_publishers"> | |
| <tr> | |
| <td>${h.link_to(publisher.title, h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport', action='read', id=publisher.name))} | |
| </td> | |
| <td>${views}</td> | |
| <td>${visits}</td> | |
| </tr> | |
| </py:for> | |
| </table> | |
| </div> | |
| <xi:include href="../../layout.html" /> | |
| <py:def function="optional_footer"> | |
| <script type='text/javascript'> | |
| $('.nav-tabs li a').click(function (e) { | |
| e.preventDefault(); | |
| $(this).tab('show'); | |
| }) | |
| </script> | |
| </py:def> | |
| </html> | |
| <html xmlns:py="http://genshi.edgewall.org/" | |
| xmlns:i18n="http://genshi.edgewall.org/i18n" | |
| xmlns:xi="http://www.w3.org/2001/XInclude" | |
| py:strip=""> | |
| <py:def function="page_title">Analytics for ${g.site_title}</py:def> | |
| <py:match path="primarysidebar"> | |
| <li class="widget-container boxed widget_text"> | |
| <h4>${c.publisher.title}</h4> | |
| <p> | |
| The table shows the top 20 most viewed datasets belonging to ${c.publisher.title}. | |
| </p> | |
| <p> | |
| As well as showing the number of views within ${c.month_desc}, it will also show the | |
| number of visitors that viewed each dataset. | |
| </p> | |
| <p> | |
| <p>The dataset list page for <a href="${h.url_for(controller='ckanext.dgu.controllers.publisher:PublisherController', action='read', id=c.publisher.name)}">${c.publisher.title}</a> was viewed ${c.publisher_page_views} times during ${c.month_desc}</p> | |
| </p> | |
| </li> | |
| </py:match> | |
| <div py:match="content"> | |
| <h1>Analytics for ${c.publisher.title}</h1> | |
| <h2>Top 20 most viewed datasets</h2> | |
| <p><em>Note: this data does not include API calls</em></p> | |
| <form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='read',id=c.publisher.name)}" method="get"> | |
| <div class="controls"> | |
| <select name="month"> | |
| <py:for each="val,desc in c.months"> | |
| <option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option> | |
| </py:for> | |
| </select> | |
| <input class="btn button" type='submit' value="Update"/> | |
| </div> | |
| </form> | |
| <table class="table table-condensed table-bordered table-striped"> | |
| <tr> | |
| <th>Dataset</th> | |
| <th>Views</th> | |
| <th>Visits</th> | |
| </tr> | |
| <py:for each="package, views, visits in c.top_packages"> | |
| <tr> | |
| <td>${h.link_to(package.title or package.name, h.url_for(controller='package', action='read', id=package.name))} | |
| </td> | |
| <td>${views}</td> | |
| <td>${visits}</td> | |
| </tr> | |
| </py:for> | |
| </table> | |
| </div> | |
| <xi:include href="../../layout.html" /> | |
| </html> | |
| <html xmlns:py="http://genshi.edgewall.org/" | |
| xmlns:i18n="http://genshi.edgewall.org/i18n" | |
| xmlns:xi="http://www.w3.org/2001/XInclude" | |
| py:strip=""> | |
| <py:def function="page_title">Site analytics</py:def> | |
| <py:match path="primarysidebar"> | |
| <li class="widget-container boxed widget_text"> | |
| <h4>Statistics</h4> | |
| <p>It is possible to <a href="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='csv',month=c.month)}">export the analytics data</a> as a CSV file, which contains all of the information for ${c.month_desc}</p> | |
| </li> | |
| </py:match> | |
| <div py:match="content"> | |
| <h1>Site statistics</h1> | |
| <form class="form-inline" action="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='index')}" method="get"> | |
| <div class="controls"> | |
| <select name="month"> | |
| <py:for each="val,desc in c.months"> | |
| <option value='${val}' py:attrs="{'selected': 'selected' if c.month == val else None}">${desc}</option> | |
| </py:for> | |
| </select> | |
| <input class="btn button" type='submit' value="Update"/> | |
| </div> | |
| </form> | |
| <div class="tabbable"> | |
| <ul class="nav nav-tabs"> | |
| <li class="active"><a href="#totals" data-toggle="tab">Totals</a></li> | |
| <li><a href="#browsers" data-toggle="tab">Browsers</a></li> | |
| <li><a href="#os" data-toggle="tab">Operating Systems</a></li> | |
| <li><a href="#social_networks" data-toggle="tab">Social Networks</a></li> | |
| <li><a href="#languages" data-toggle="tab">Languages</a></li> | |
| <li><a href="#country" data-toggle="tab">Country</a></li> | |
| </ul> | |
| <div class="tab-content"> | |
| <div class="tab-pane active" id="totals"> | |
| <table class="table table-condensed table-bordered table-striped"> | |
| <tr> | |
| <th>Name</th> | |
| <th>Value</th> | |
| </tr> | |
| <py:for each="name, value in c.global_totals"> | |
| <tr> | |
| <td>${name}</td> | |
| <td>${value}</td> | |
| </tr> | |
| </py:for> | |
| </table> | |
| </div> | |
| <div class="tab-pane" id="browsers"> | |
| <table class="table table-condensed table-bordered table-striped"> | |
| <tr> | |
| <th>Name</th> | |
| <th>Value</th> | |
| </tr> | |
| <py:for each="name, value in c.browsers"> | |
| <tr> | |
| <td>${name}</td> | |
| <td>${value}</td> | |
| </tr> | |
| </py:for> | |
| </table> | |
| </div> | |
| <div class="tab-pane" id="os"> | |
| <table class="table table-condensed table-bordered table-striped"> | |
| <tr> | |
| <th>Name</th> | |
| <th>Value</th> | |
| </tr> | |
| <py:for each="name, value in c.os"> | |
| <tr> | |
| <td>${name}</td> | |
| <td>${value}</td> | |
| </tr> | |
| </py:for> | |
| </table> | |
| </div> | |
| <div class="tab-pane" id="social_networks"> | |
| <table class="table table-condensed table-bordered table-striped"> | |
| <tr> | |
| <th>Name</th> | |
| <th>Value</th> | |
| </tr> | |
| <py:for each="name, value in c.social_networks"> | |
| <tr> | |
| <td>${name}</td> | |
| <td>${value}</td> | |
| </tr> | |
| </py:for> | |
| </table> | |
| </div> | |
| <div class="tab-pane" id="languages"> | |
| <table class="table table-condensed table-bordered table-striped"> | |
| <tr> | |
| <th>Name</th> | |
| <th>Value</th> | |
| </tr> | |
| <py:for each="name, value in c.languages"> | |
| <tr> | |
| <td>${name}</td> | |
| <td>${value}</td> | |
| </tr> | |
| </py:for> | |
| </table> | |
| </div> | |
| <div class="tab-pane" id="country"> | |
| <table class="table table-condensed table-bordered table-striped"> | |
| <tr> | |
| <th>Name</th> | |
| <th>Value</th> | |
| </tr> | |
| <py:for each="name, value in c.country"> | |
| <tr> | |
| <td>${name}</td> | |
| <td>${value}</td> | |
| </tr> | |
| </py:for> | |
| </table> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| <xi:include href="../../layout.html" /> | |
| <py:def function="optional_footer"> | |
| <script type='text/javascript'> | |
| $('.nav-tabs li a').click(function (e) { | |
| e.preventDefault(); | |
| $(this).tab('show'); | |
| }) | |
| </script> | |
| </py:def> | |
| </html> | |
| import os | |
| import datetime | |
| from nose.tools import assert_equal | |
| from ckanext.ga_report.download_analytics import DownloadAnalytics | |
| from ckanext.ga_report.ga_auth import (init_service, get_profile_id) | |
| from ckanext.ga_report.ga_model import init_tables | |
| class TestAPI: | |
| @classmethod | |
| def setup_class(cls): | |
| if not os.path.exists("token.dat") or not os.path.exists("credentials.json"): | |
| print '*' * 60 | |
| print "Tests may not run without first having run the auth process" | |
| print '*' * 60 | |
| init_tables() | |
| @classmethod | |
| def teardown_class(cls): | |
| pass | |
| def test_latest(self): | |
| svc = init_service("token.dat", "credentials.json") | |
| try: | |
| downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc)) | |
| downloader.latest() | |
| except Exception as e: | |
| assert False, e | |
| def test_since(self): | |
| 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)) | |
| except Exception as e: | |
| assert False, e | |
| import os | |
| from nose.tools import assert_equal | |
| from ckanext.ga_report.ga_auth import (init_service, get_profile_id) | |
| class TestAuth: | |
| @classmethod | |
| def setup_class(cls): | |
| if not os.path.exists("token.dat") or not os.path.exists("credentials.json"): | |
| print '*' * 60 | |
| print "Tests may not run without first having run the auth process" | |
| print '*' * 60 | |
| @classmethod | |
| def teardown_class(cls): | |
| pass | |
| def test_init(self): | |
| try: | |
| res = init_service(None, None) | |
| assert False, "Init service worked without credentials or tokens" | |
| except TypeError: | |
| pass | |
| def test_init_with_token(self): | |
| res = init_service("token.dat", None) | |
| assert res is not None, "Init service worked without credentials" | |
| def test_init_with_token_and_credentials(self): | |
| res = init_service("token.dat", "credentials.json") | |
| assert res is not None, "Unable to create service with valid details" | |
| def test_init_with_redentials(self): | |
| #res = init_service("", "credentials.json") | |
| # Triggers the auth flow via the browser | |
| pass | |
| def test_get_profile(self): | |
| svc = init_service("token.dat", "credentials.json") | |
| profile = get_profile_id(svc) | |
| assert profile is not None, "Unable to find a profile given configured UA id and user details" |
| from setuptools import setup, find_packages | from setuptools import setup, find_packages |
| import sys, os | import sys, os |
| version = '0.1' | version = '0.1' |
| setup( | setup( |
| name='ckanext-ga-report', | name='ckanext-ga-report', |
| version=version, | version=version, |
| description="GA reporting for CKAN", | description="GA reporting for CKAN", |
| long_description="""\ | long_description="""\ |
| """, | """, |
| classifiers=[], # Get strings from http://pypi.python.org/pypi?%3Aaction=list_classifiers | classifiers=[], # Get strings from http://pypi.python.org/pypi?%3Aaction=list_classifiers |
| keywords='', | keywords='', |
| author='David Read', | author='David Read', |
| author_email='david.read@hackneyworkshop.com', | author_email='david.read@hackneyworkshop.com', |
| url='', | url='', |
| license='', | license='', |
| packages=find_packages(exclude=['ez_setup', 'examples', 'tests']), | packages=find_packages(exclude=['ez_setup', 'examples', 'tests']), |
| namespace_packages=['ckanext', 'ckanext.ga_report'], | namespace_packages=['ckanext', 'ckanext.ga_report'], |
| include_package_data=True, | include_package_data=True, |
| zip_safe=False, | zip_safe=False, |
| install_requires=[ | install_requires=[ |
| 'gdata', | 'gdata', |
| 'google-api-python-client' | 'google-api-python-client' |
| ], | ], |
| entry_points=\ | entry_points=\ |
| """ | """ |
| [ckan.plugins] | [ckan.plugins] |
| # Add plugins here, eg | # Add plugins here, eg |
| ga-report=ckanext.ga_report.plugin:GaReportPlugin | ga-report=ckanext.ga_report.plugin:GAReportPlugin |
| [paste.paster_command] | [paste.paster_command] |
| loadanalytics = ckanext.ga_report.command:LoadAnalytics | loadanalytics = ckanext.ga_report.command:LoadAnalytics |
| initdb = ckanext.ga_report.command:InitDB | initdb = ckanext.ga_report.command:InitDB |
| getauthtoken = ckanext.ga_report.command:GetAuthToken | |
| """, | """, |
| ) | ) |