| *.py[co] | *.py[co] |
| *.py~ | *.py~ |
| .gitignore | .gitignore |
| ckan.log | |
| # Packages | # Packages |
| *.egg | *.egg |
| *.egg-info | *.egg-info |
| dist | dist |
| build | build |
| eggs | eggs |
| parts | parts |
| bin | bin |
| var | var |
| sdist | sdist |
| develop-eggs | develop-eggs |
| .installed.cfg | .installed.cfg |
| # Private info | # Private info |
| credentials.json | credentials.json |
| token.dat | token.dat |
| # Installer logs | # Installer logs |
| pip-log.txt | pip-log.txt |
| # Unit test / coverage reports | # Unit test / coverage reports |
| .coverage | .coverage |
| .tox | .tox |
| #Translations | #Translations |
| *.mo | *.mo |
| #Mr Developer | #Mr Developer |
| .mr.developer.cfg | .mr.developer.cfg |
| 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.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) |
| googleanalytics.token.filepath = ~/pyenv/token.dat | |
| ga-report.period = monthly | ga-report.period = monthly |
| ga-report.bounce_url = / | |
| 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. | The ga-report.bounce_url specifies a particular path to record the bounce rate for. Typically it is / (the home page). |
| 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 |
| 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 | 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 |
| Now ensure you reference the correct path to your token.dat in your CKAN config file (e.g. development.ini):: | |
| googleanalytics.token.filepath = ~/pyenv/token.dat | |
| 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 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 | $ paster loadanalytics latest --config=../ckan/development.ini |
| The value after the token file is how much data you want to retrieve, this can be | The value after the token file is how much data you want to retrieve, this can be |
| * **all** - data for all time (since 2010) | * **all** - data for all time (since 2010) |
| * **latest** - (default) just the 'latest' data | * **latest** - (default) just the 'latest' data |
| * **YYYY-MM-DD** - just data for all time periods going back to (and including) this date | * **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 | import datetime |
| import os | |
| from pylons import config | |
| from ckan.lib.cli import CkanCommand | from ckan.lib.cli import CkanCommand |
| # No other CKAN imports allowed until _load_config is run, | # No other CKAN imports allowed until _load_config is run, |
| # or logging is disabled | # 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> | Usage: paster getauthtoken <credentials_file> |
| Where <credentials_file> is the file name containing the details | Where <credentials_file> is the file name containing the details |
| for the service (obtained from https://code.google.com/apis/console). | for the service (obtained from https://code.google.com/apis/console). |
| By default this is set to credentials.json | 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): |
| """ | """ |
| In this case we don't want a valid service, but rather just to | 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 | 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 | act as a form of verification instead of just getting the token and |
| assuming it is correct. | assuming it is correct. |
| """ | """ |
| from ga_auth import init_service | from ga_auth import init_service |
| init_service('token.dat', | init_service('token.dat', |
| self.args[0] if self.args | self.args[0] if self.args |
| else 'credentials.json') | 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 <time-period> |
| Where <tokenfile> is the name of the auth token file from | Where <time-period> is: |
| the getauthtoken step. | |
| 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 - just data for the specific month |
| 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 = 1 |
| min_args = 1 | min_args = 0 |
| 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') | |
| self.parser.add_option('-s', '--skip_url_stats', | |
| action='store_true', | |
| default=False, | |
| dest='skip_url_stats', | |
| help='Skip the download of URL data - just do site-wide stats') | |
| def command(self): | def command(self): |
| self._load_config() | self._load_config() |
| from download_analytics import DownloadAnalytics | from download_analytics import DownloadAnalytics |
| from ga_auth import (init_service, get_profile_id) | from ga_auth import (init_service, get_profile_id) |
| ga_token_filepath = os.path.expanduser(config.get('googleanalytics.token.filepath', '')) | |
| if not ga_token_filepath: | |
| print 'ERROR: In the CKAN config you need to specify the filepath of the ' \ | |
| 'Google Analytics token file under key: googleanalytics.token.filepath' | |
| return | |
| try: | try: |
| svc = init_service(self.args[0], None) | svc = init_service(ga_token_filepath, None) |
| except TypeError: | except TypeError: |
| print ('Have you correctly run the getauthtoken task and ' | print ('Have you correctly run the getauthtoken task and ' |
| 'specified the correct file here') | 'specified the correct token file in the CKAN config under ' |
| '"googleanalytics.token.filepath"?') | |
| return | 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, | |
| skip_url_stats=self.options.skip_url_stats) | |
| time_period = self.args[1] if self.args and len(self.args) > 1 \ | time_period = self.args[0] if self.args else 'latest' |
| 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') | # The month to use |
| downloader.since_date(since_date) | for_date = datetime.datetime.strptime(time_period, '%Y-%m') |
| downloader.specific_month(for_date) | |
| import re | |
| import csv | |
| import sys | |
| import logging | import logging |
| from ckan.lib.base import BaseController, c, render | import operator |
| import report_model | import collections |
| from ckan.lib.base import (BaseController, c, g, render, request, response, abort) | |
| import sqlalchemy | |
| from sqlalchemy import func, cast, Integer | |
| import ckan.model as model | |
| from ga_model import GA_Url, GA_Stat, GA_ReferralStat, GA_Publisher | |
| log = logging.getLogger('ckanext.ga-report') | log = logging.getLogger('ckanext.ga-report') |
| def _get_month_name(strdate): | |
| import calendar | |
| from time import strptime | |
| d = strptime(strdate, '%Y-%m') | |
| return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) | |
| def _month_details(cls, stat_key=None): | |
| ''' | |
| Returns a list of all the periods for which we have data, unfortunately | |
| knows too much about the type of the cls being passed as GA_Url has a | |
| more complex query | |
| This may need extending if we add a period_name to the stats | |
| ''' | |
| months = [] | |
| day = None | |
| q = model.Session.query(cls.period_name,cls.period_complete_day)\ | |
| .filter(cls.period_name!='All').distinct(cls.period_name) | |
| if stat_key: | |
| q= q.filter(cls.stat_name==stat_key) | |
| vals = q.order_by("period_name desc").all() | |
| if vals and vals[0][1]: | |
| day = int(vals[0][1]) | |
| ordinal = 'th' if 11 <= day <= 13 \ | |
| else {1:'st',2:'nd',3:'rd'}.get(day % 10, 'th') | |
| day = "{day}{ordinal}".format(day=day, ordinal=ordinal) | |
| for m in vals: | |
| months.append( (m[0], _get_month_name(m[0]))) | |
| return months, day | |
| class GaReport(BaseController): | class GaReport(BaseController): |
| def csv(self, month): | |
| import csv | |
| q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name!='Downloads') | |
| if month != 'all': | |
| q = q.filter(GA_Stat.period_name==month) | |
| entries = q.order_by('GA_Stat.period_name, GA_Stat.stat_name, GA_Stat.key').all() | |
| response.headers['Content-Type'] = "text/csv; charset=utf-8" | |
| response.headers['Content-Disposition'] = str('attachment; filename=stats_%s.csv' % (month,)) | |
| 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 csv_downloads(self, month): | |
| import csv | |
| q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name=='Downloads') | |
| if month != 'all': | |
| q = q.filter(GA_Stat.period_name==month) | |
| entries = q.order_by('GA_Stat.period_name, GA_Stat.key').all() | |
| response.headers['Content-Type'] = "text/csv; charset=utf-8" | |
| response.headers['Content-Disposition'] = str('attachment; filename=downloads_%s.csv' % (month,)) | |
| writer = csv.writer(response) | |
| writer.writerow(["Period", "Resource URL", "Count"]) | |
| for entry in entries: | |
| writer.writerow([entry.period_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, c.day = _month_details(GA_Stat) | |
| # Work out which month to show, based on query params of the first item | |
| c.month_desc = 'all months' | |
| c.month = request.params.get('month', '') | |
| if c.month: | |
| c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) | |
| q = model.Session.query(GA_Stat).\ | |
| filter(GA_Stat.stat_name=='Totals') | |
| if c.month: | |
| q = q.filter(GA_Stat.period_name==c.month) | |
| entries = q.order_by('ga_stat.key').all() | |
| def clean_key(key, val): | |
| if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounce rate (home page)']: | |
| 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','Bounce rate (home page)']: | |
| val = "%s%%" % val | |
| if key in ['Total page views', 'Total visits']: | |
| val = int(val) | |
| return key, val | |
| c.global_totals = [] | |
| if c.month: | |
| for e in entries: | |
| key, val = clean_key(e.key, e.value) | |
| c.global_totals.append((key, val)) | |
| else: | |
| d = collections.defaultdict(list) | |
| for e in entries: | |
| d[e.key].append(float(e.value)) | |
| for k, v in d.iteritems(): | |
| if k in ['Total page views', 'Total visits']: | |
| v = sum(v) | |
| else: | |
| v = float(sum(v))/float(len(v)) | |
| key, val = clean_key(k,v) | |
| c.global_totals.append((key, val)) | |
| c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0)) | |
| keys = { | |
| 'Browser versions': 'browser_versions', | |
| 'Browsers': 'browsers', | |
| 'Operating Systems versions': 'os_versions', | |
| 'Operating Systems': 'os', | |
| 'Social sources': 'social_networks', | |
| 'Languages': 'languages', | |
| 'Country': 'country' | |
| } | |
| def shorten_name(name, length=60): | |
| return (name[:length] + '..') if len(name) > 60 else name | |
| def fill_out_url(url): | |
| import urlparse | |
| return urlparse.urljoin(g.site_url, url) | |
| c.social_referrer_totals, c.social_referrers = [], [] | |
| q = model.Session.query(GA_ReferralStat) | |
| q = q.filter(GA_ReferralStat.period_name==c.month) if c.month else q | |
| q = q.order_by('ga_referrer.count::int desc') | |
| for entry in q.all(): | |
| c.social_referrers.append((shorten_name(entry.url), fill_out_url(entry.url), | |
| entry.source,entry.count)) | |
| q = model.Session.query(GA_ReferralStat.url, | |
| func.sum(GA_ReferralStat.count).label('count')) | |
| q = q.filter(GA_ReferralStat.period_name==c.month) if c.month else q | |
| q = q.order_by('count desc').group_by(GA_ReferralStat.url) | |
| for entry in q.all(): | |
| c.social_referrer_totals.append((shorten_name(entry[0]), fill_out_url(entry[0]),'', | |
| entry[1])) | |
| for k, v in keys.iteritems(): | |
| q = model.Session.query(GA_Stat).\ | |
| filter(GA_Stat.stat_name==k) | |
| if c.month: | |
| entries = [] | |
| q = q.filter(GA_Stat.period_name==c.month).\ | |
| order_by('ga_stat.value::int desc') | |
| d = collections.defaultdict(int) | |
| for e in q.all(): | |
| d[e.key] += int(e.value) | |
| entries = [] | |
| for key, val in d.iteritems(): | |
| entries.append((key,val,)) | |
| entries = sorted(entries, key=operator.itemgetter(1), reverse=True) | |
| # Get the total for each set of values and then set the value as | |
| # a percentage of the total | |
| if k == 'Social sources': | |
| total = sum([x for n,x in c.global_totals if n == 'Total visits']) | |
| else: | |
| total = sum([num for _,num in entries]) | |
| setattr(c, v, [(k,_percent(v,total)) for k,v in entries ]) | |
| return render('ga_report/site/index.html') | |
| def downloads(self): | |
| # Get the month details by fetching distinct values and determining the | |
| # month names from the values. | |
| c.months, c.day = _month_details(GA_Stat, "Downloads") | |
| # Work out which month to show, based on query params of the first item | |
| c.month_desc = 'all months' | |
| c.month = request.params.get('month', '') | |
| if c.month: | |
| c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) | |
| c.downloads = [] | |
| q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name=='Downloads') | |
| q = q.filter(GA_Stat.period_name==c.month) if c.month else q | |
| q = q.order_by("ga_stat.value::int desc") | |
| data = collections.defaultdict(int) | |
| for entry in q.all(): | |
| r = model.Session.query(model.Resource).filter(model.Resource.url==entry.key).first() | |
| if not r: | |
| continue | |
| data[r] += int(entry.value) | |
| c.downloads = [(k,v,) for k,v in data.iteritems()] | |
| c.downloads = sorted(c.downloads, key=operator.itemgetter(1), reverse=True) | |
| return render('ga_report/site/downloads.html') | |
| class GaDatasetReport(BaseController): | |
| """ | |
| Displays the pageview and visit count for datasets | |
| with options to filter by publisher and time period. | |
| """ | |
| 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 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 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=datasets_%s_%s.csv' % (c.publisher_name, month,)) | |
| writer = csv.writer(response) | |
| writer.writerow(["Dataset Title", "Dataset Name", "Views", "Visits", "Period Name"]) | |
| for package,view,visit in packages: | |
| writer.writerow([package.title.encode('utf-8'), | |
| package.name.encode('utf-8'), | |
| view, | |
| visit, | |
| month]) | |
| def publishers(self): | |
| '''A list of publishers and the number of views/visits for each''' | |
| # Get the month details by fetching distinct values and determining the | |
| # month names from the values. | |
| c.months, c.day = _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.month_desc = 'all months' | |
| if c.month: | |
| c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) | |
| c.top_publishers = _get_top_publishers() | |
| return render('ga_report/publisher/index.html') | |
| def _get_packages(self, publisher=None, count=-1): | |
| '''Returns the datasets in order of views''' | |
| if count == -1: | |
| count = sys.maxint | |
| month = c.month or 'All' | |
| q = model.Session.query(GA_Url,model.Package)\ | |
| .filter(model.Package.name==GA_Url.package_id)\ | |
| .filter(GA_Url.url.like('/dataset/%')) | |
| if publisher: | |
| q = q.filter(GA_Url.department_id==publisher.name) | |
| q = q.filter(GA_Url.period_name==month) | |
| q = q.order_by('ga_url.pageviews::int desc') | |
| top_packages = [] | |
| for entry,package in q.limit(count): | |
| if package: | |
| top_packages.append((package, entry.pageviews, entry.visits)) | |
| else: | |
| log.warning('Could not find package associated package') | |
| return top_packages | |
| def read(self): | |
| ''' | |
| Lists the most popular datasets across all publishers | |
| ''' | |
| return self.read_publisher(None) | |
| def read_publisher(self, id): | |
| ''' | |
| Lists the most popular datasets for a publisher (or across all publishers) | |
| ''' | |
| count = 20 | |
| c.publishers = _get_publishers() | |
| id = request.params.get('publisher', id) | |
| if id and id != 'all': | |
| c.publisher = model.Group.get(id) | |
| if not c.publisher: | |
| abort(404, 'A publisher with that name could not be found') | |
| c.publisher_name = c.publisher.name | |
| c.top_packages = [] # package, dataset_views in c.top_packages | |
| # Get the month details by fetching distinct values and determining the | |
| # month names from the values. | |
| c.months, c.day = _month_details(GA_Url) | |
| # Work out which month to show, based on query params of the first item | |
| c.month = request.params.get('month', '') | |
| if not c.month: | |
| c.month_desc = 'all months' | |
| else: | |
| c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) | |
| month = c.month or 'All' | |
| c.publisher_page_views = 0 | |
| q = model.Session.query(GA_Url).\ | |
| filter(GA_Url.url=='/publisher/%s' % c.publisher_name) | |
| entry = q.filter(GA_Url.period_name==c.month).first() | |
| c.publisher_page_views = entry.pageviews if entry else 0 | |
| c.top_packages = self._get_packages(c.publisher, 20) | |
| return render('ga_report/publisher/read.html') | |
| def _get_top_publishers(limit=20): | |
| ''' | |
| Returns a list of the top 20 publishers by dataset visits. | |
| (The number to show can be varied with 'limit') | |
| ''' | |
| month = c.month or 'All' | |
| connection = model.Session.connection() | |
| q = """ | |
| select department_id, sum(pageviews::int) views, sum(visits::int) visits | |
| from ga_url | |
| where department_id <> '' | |
| and package_id <> '' | |
| and url like '/dataset/%%' | |
| and period_name=%s | |
| group by department_id order by views desc | |
| """ | |
| if limit: | |
| q = q + " limit %s;" % (limit) | |
| top_publishers = [] | |
| res = connection.execute(q, month) | |
| for row in res: | |
| g = model.Group.get(row[0]) | |
| if g: | |
| top_publishers.append((g, row[1], row[2])) | |
| return top_publishers | |
| def _get_publishers(): | |
| ''' | |
| Returns a list of all publishers. Each item is a tuple: | |
| (name, 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 | |
| def _percent(num, total): | |
| p = 100 * float(num)/float(total) | |
| return "%.2f%%" % round(p, 2) | |
| import os | import os |
| import logging | import logging |
| import datetime | import datetime |
| import collections | |
| from pylons import config | from pylons import config |
| from ga_model import _normalize_url | |
| 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' |
| MIN_VIEWS = 50 | |
| MIN_VISITS = 20 | |
| MIN_DOWNLOADS = 10 | |
| 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, delete_first=False, |
| skip_url_stats=False): | |
| 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 |
| self.delete_first = delete_first | |
| self.skip_url_stats = skip_url_stats | |
| def all_(self): | |
| self.since_date(datetime.datetime(2010, 1, 1)) | def specific_month(self, date): |
| import calendar | |
| first_of_this_month = datetime.datetime(date.year, date.month, 1) | |
| _, last_day_of_month = calendar.monthrange(int(date.year), int(date.month)) | |
| last_of_this_month = datetime.datetime(date.year, date.month, last_day_of_month) | |
| periods = ((date.strftime(FORMAT_MONTH), | |
| last_day_of_month, | |
| first_of_this_month, last_of_this_month),) | |
| self.download_and_store(periods) | |
| def latest(self): | 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 for_date(self, for_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 = for_date.year |
| month = since_date.month | month = for_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('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"', | if self.delete_first: |
| self.get_full_period_name(period_name, period_complete_day)) | log.info('Deleting existing Analytics for this period "%s"', |
| self.store(period_name, period_complete_day, data) | period_name) |
| ga_model.delete(period_name) | |
| def download(self, start_date, end_date): | if not self.skip_url_stats: |
| # Clean out old url data before storing the new | |
| ga_model.pre_update_url_stats(period_name) | |
| accountName = config.get('googleanalytics.account') | |
| log.info('Downloading analytics for dataset views') | |
| data = self.download(start_date, end_date, '~/%s/dataset/[a-z0-9-_]+' % accountName) | |
| log.info('Storing dataset views (%i rows)', len(data.get('url'))) | |
| self.store(period_name, period_complete_day, data, ) | |
| log.info('Downloading analytics for publisher views') | |
| data = self.download(start_date, end_date, '~/%s/publisher/[a-z0-9-_]+' % accountName) | |
| log.info('Storing publisher views (%i rows)', len(data.get('url'))) | |
| self.store(period_name, period_complete_day, data,) | |
| log.info('Aggregating datasets by publisher') | |
| ga_model.update_publisher_stats(period_name) # about 30 seconds. | |
| log.info('Downloading and storing analytics for site-wide stats') | |
| self.sitewide_stats( period_name, period_complete_day ) | |
| log.info('Downloading and storing analytics for social networks') | |
| self.update_social_info(period_name, start_date, end_date) | |
| def update_social_info(self, period_name, start_date, end_date): | |
| start_date = start_date.strftime('%Y-%m-%d') | |
| end_date = end_date.strftime('%Y-%m-%d') | |
| query = 'ga:hasSocialSourceReferral=~Yes$' | |
| metrics = 'ga:entrances' | |
| sort = '-ga:entrances' | |
| # Supported query params at | |
| # https://developers.google.com/analytics/devguides/reporting/core/v3/reference | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| filters=query, | |
| start_date=start_date, | |
| metrics=metrics, | |
| sort=sort, | |
| dimensions="ga:landingPagePath,ga:socialNetwork", | |
| max_results=10000, | |
| end_date=end_date).execute() | |
| data = collections.defaultdict(list) | |
| rows = results.get('rows',[]) | |
| for row in rows: | |
| url = _normalize_url('http:/' + row[0]) | |
| data[url].append( (row[1], int(row[2]),) ) | |
| ga_model.update_social(period_name, data) | |
| def download(self, start_date, end_date, path=None): | |
| '''Get data from GA for a given time period''' | '''Get data from GA for a given time period''' |
| start_date = start_date.strftime('%Y-%m-%d') | start_date = start_date.strftime('%Y-%m-%d') |
| end_date = end_date.strftime('%Y-%m-%d') | end_date = end_date.strftime('%Y-%m-%d') |
| query = 'ga:pagePath=~/dataset/[a-z0-9-]+$' | query = 'ga:pagePath=%s$' % path |
| metrics = 'ga:uniquePageviews' | metrics = 'ga:pageviews, ga:visits' |
| sort = '-ga:uniquePageviews' | sort = '-ga:pageviews' |
| # 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, |
| dimensions="ga:pagePath", | dimensions="ga:pagePath", |
| max_results=10000, | max_results=10000, |
| end_date=end_date).execute() | end_date=end_date).execute() |
| if os.getenv('DEBUG'): | |
| import pprint | |
| pprint.pprint(results) | |
| print 'Total results: %s' % results.get('totalResults') | |
| packages = [] | packages = [] |
| for entry in results.get('rows'): | for entry in results.get('rows'): |
| (loc,size,) = entry | (loc,pageviews,visits) = entry |
| packages.append( ('http:/' + loc,size, '',) ) # Temporary hack | url = _normalize_url('http:/' + loc) # strips off domain e.g. www.data.gov.uk or data.gov.uk |
| if not url.startswith('/dataset/') and not url.startswith('/publisher/'): | |
| # filter out strays like: | |
| # /data/user/login?came_from=http://data.gov.uk/dataset/os-code-point-open | |
| # /403.html?page=/about&from=http://data.gov.uk/publisher/planning-inspectorate | |
| continue | |
| packages.append( (url, pageviews, visits,) ) # Temporary hack | |
| return dict(url=packages) | 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, period_complete_day): | |
| 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) | |
| funcs = ['_totals_stats', '_social_stats', '_os_stats', | |
| '_locale_stats', '_browser_stats', '_mobile_stats', '_download_stats'] | |
| for f in funcs: | |
| log.info('Downloading analytics for %s' % f.split('_')[1]) | |
| getattr(self, f)(start_date, end_date, period_name, period_complete_day) | |
| 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, period_complete_day): | |
| """ Fetches distinct totals, total pageviews etc """ | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| start_date=start_date, | |
| metrics='ga:pageviews', | |
| sort='-ga:pageviews', | |
| max_results=10000, | |
| end_date=end_date).execute() | |
| result_data = results.get('rows') | |
| ga_model.update_sitewide_stats(period_name, "Totals", {'Total page views': result_data[0][0]}, | |
| period_complete_day) | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| start_date=start_date, | |
| metrics='ga:pageviewsPerVisit,ga:avgTimeOnSite,ga:percentNewVisits,ga:visits', | |
| 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], | |
| } | |
| ga_model.update_sitewide_stats(period_name, "Totals", data, period_complete_day) | |
| # Bounces from / or another configurable page. | |
| path = '/%s%s' % (config.get('googleanalytics.account'), | |
| config.get('ga-report.bounce_url', '/')) | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| filters='ga:pagePath==%s' % (path,), | |
| start_date=start_date, | |
| metrics='ga:visitBounceRate', | |
| dimensions='ga:pagePath', | |
| max_results=10000, | |
| end_date=end_date).execute() | |
| result_data = results.get('rows') | |
| if not result_data or len(result_data) != 1: | |
| log.error('Could not pinpoint the bounces for path: %s. Got results: %r', | |
| path, result_data) | |
| return | |
| results = result_data[0] | |
| bounces = float(results[1]) | |
| # visitBounceRate is already a % | |
| log.info('Google reports visitBounceRate as %s', bounces) | |
| ga_model.update_sitewide_stats(period_name, "Totals", {'Bounce rate (home page)': float(bounces)}, | |
| period_complete_day) | |
| def _locale_stats(self, start_date, end_date, period_name, period_complete_day): | |
| """ Fetches stats about language and country """ | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| start_date=start_date, | |
| metrics='ga:pageviews', | |
| sort='-ga:pageviews', | |
| 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]) | |
| self._filter_out_long_tail(data, MIN_VIEWS) | |
| ga_model.update_sitewide_stats(period_name, "Languages", data, period_complete_day) | |
| 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, period_complete_day) | |
| def _download_stats(self, start_date, end_date, period_name, period_complete_day): | |
| """ Fetches stats about language and country """ | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| start_date=start_date, | |
| filters='ga:eventAction==download', | |
| metrics='ga:totalEvents', | |
| sort='-ga:totalEvents', | |
| dimensions="ga:eventLabel", | |
| max_results=10000, | |
| end_date=end_date).execute() | |
| result_data = results.get('rows') | |
| if not result_data: | |
| # We may not have data for this time period, so we need to bail | |
| # early. | |
| log.info("There is no download data for this time period") | |
| return | |
| # [[url, count], [url],count] | |
| data = {} | |
| for result in result_data: | |
| data[result[0]] = data.get(result[0], 0) + int(result[1]) | |
| self._filter_out_long_tail(data, MIN_DOWNLOADS) | |
| ga_model.update_sitewide_stats(period_name, "Downloads", data, period_complete_day) | |
| def _social_stats(self, start_date, end_date, period_name, period_complete_day): | |
| """ 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:pageviews', | |
| sort='-ga:pageviews', | |
| dimensions="ga:socialNetwork,ga:referralPath", | |
| max_results=10000, | |
| end_date=end_date).execute() | |
| result_data = results.get('rows') | |
| data = {} | |
| for result in result_data: | |
| if not result[0] == '(not set)': | |
| data[result[0]] = data.get(result[0], 0) + int(result[2]) | |
| self._filter_out_long_tail(data, 3) | |
| ga_model.update_sitewide_stats(period_name, "Social sources", data, period_complete_day) | |
| def _os_stats(self, start_date, end_date, period_name, period_complete_day): | |
| """ Operating system stats """ | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| start_date=start_date, | |
| metrics='ga:pageviews', | |
| sort='-ga:pageviews', | |
| 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]) | |
| self._filter_out_long_tail(data, MIN_VIEWS) | |
| ga_model.update_sitewide_stats(period_name, "Operating Systems", data, period_complete_day) | |
| data = {} | |
| for result in result_data: | |
| 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, period_complete_day) | |
| def _browser_stats(self, start_date, end_date, period_name, period_complete_day): | |
| """ Information about browsers and browser versions """ | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| start_date=start_date, | |
| metrics='ga:pageviews', | |
| sort='-ga:pageviews', | |
| dimensions="ga:browser,ga:browserVersion", | |
| 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, period_complete_day) | |
| data = {} | |
| for result in result_data: | |
| 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, period_complete_day) | |
| @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, period_complete_day): | |
| """ Info about mobile devices """ | |
| results = self.service.data().ga().get( | |
| ids='ga:' + self.profile_id, | |
| start_date=start_date, | |
| metrics='ga:pageviews', | |
| sort='-ga:pageviews', | |
| 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]) | |
| self._filter_out_long_tail(data, MIN_VIEWS) | |
| ga_model.update_sitewide_stats(period_name, "Mobile brands", data, period_complete_day) | |
| 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, period_complete_day) | |
| @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] | |
| import os | 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): |
| """ | """ |
| Either returns the user's oauth credentials or uses the credentials | 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) | file to generate a token (by forcing the user to login in the browser) |
| """ | """ |
| storage = Storage(token_filename) | 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 init_service(token_file, credentials_file): | def init_service(token_file, credentials_file): |
| """ | """ |
| Given a file containing the user's oauth token (and another with | Given a file containing the user's oauth token (and another with |
| credentials in case we need to generate the token) will return a | credentials in case we need to generate the token) will return a |
| service object representing the analytics API. | 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): |
| """ | """ |