import logging | import logging |
import datetime | import datetime |
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 <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 - 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 = 2 |
min_args = 1 | min_args = 1 |
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) |
try: | try: |
svc = init_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 ' | print ('Have you correctly run the getauthtoken task and ' |
'specified the correct file here') | 'specified the correct file here') |
return | return |
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 \ | time_period = self.args[1] if self.args and len(self.args) > 1 \ |
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 logging | import logging |
import operator | import operator |
from ckan.lib.base import BaseController, c, render, request, response | from ckan.lib.base import BaseController, c, render, request, response |
import sqlalchemy | import sqlalchemy |
from sqlalchemy import func, cast, Integer | from sqlalchemy import func, cast, Integer |
import ckan.model as model | import ckan.model as model |
from ga_model import GA_Url, GA_Stat | 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): | def _get_month_name(strdate): |
import calendar | import calendar |
from time import strptime | from time import strptime |
d = strptime('2012-10', '%Y-%m') | d = strptime(strdate, '%Y-%m') |
return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) | return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) |
def _month_details(cls): | def _month_details(cls): |
months = [] | months = [] |
vals = model.Session.query(cls.period_name).distinct().all() | vals = model.Session.query(cls.period_name).distinct().all() |
for m in vals: | for m in vals: |
months.append( (m[0], _get_month_name(m))) | months.append( (m[0], _get_month_name(m[0]))) |
return sorted(months, key=operator.itemgetter(0), reverse=True) | return sorted(months, key=operator.itemgetter(0), reverse=True) |
class GaReport(BaseController): | class GaReport(BaseController): |
def csv(self, month): | def csv(self, month): |
import csv | import csv |
entries = model.Session.query(GA_Stat).\ | entries = model.Session.query(GA_Stat).\ |
filter(GA_Stat.period_name==month).\ | filter(GA_Stat.period_name==month).\ |
order_by('GA_Stat.stat_name, GA_Stat.key').all() | 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" | response.headers['Content-Type'] = "text/csv; charset=utf-8" |
writer = csv.writer(response) | writer = csv.writer(response) |
writer.writerow(["Period", "Statistic", "Key", "Value"]) | writer.writerow(["Period", "Statistic", "Key", "Value"]) |
for entry in entries: | for entry in entries: |
writer.writerow([entry.period_name.encode('utf-8'), | writer.writerow([entry.period_name.encode('utf-8'), |
entry.stat_name.encode('utf-8'), | entry.stat_name.encode('utf-8'), |
entry.key.encode('utf-8'), | entry.key.encode('utf-8'), |
entry.value.encode('utf-8')]) | entry.value.encode('utf-8')]) |
def index(self): | def index(self): |
# Get the month details by fetching distinct values and determining the | # Get the month details by fetching distinct values and determining the |
# month names from the values. | # month names from the values. |
c.months = _month_details(GA_Stat) | c.months = _month_details(GA_Stat) |
# Work out which month to show, based on query params of the first item | # 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 = 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]) | c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) |
entries = model.Session.query(GA_Stat).\ | entries = model.Session.query(GA_Stat).\ |
filter(GA_Stat.stat_name=='Totals').\ | filter(GA_Stat.stat_name=='Totals').\ |
filter(GA_Stat.period_name==c.month).all() | filter(GA_Stat.period_name==c.month).\ |
c.global_totals = [(s.key, s.value) for s in entries ] | order_by('ga_stat.key').all() |
c.global_totals = [] | |
for e in entries: | |
val = e.value | |
if e.key in ['Average time on site', 'Pages per visit', 'Percent new visits']: | |
val = "%.2f" % round(float(e.value), 2) | |
e.key = '%s *' % e.key | |
c.global_totals.append((e.key, val)) | |
keys = { | keys = { |
'Browser versions': 'browsers', | 'Browser versions': 'browsers', |
'Operating Systems versions': 'os', | 'Operating Systems versions': 'os', |
'Social sources': 'social_networks', | 'Social sources': 'social_networks', |
'Languages': 'languages', | 'Languages': 'languages', |
'Country': 'country' | 'Country': 'country' |
} | } |
for k, v in keys.iteritems(): | for k, v in keys.iteritems(): |
entries = model.Session.query(GA_Stat).\ | entries = model.Session.query(GA_Stat).\ |
filter(GA_Stat.stat_name==k).\ | filter(GA_Stat.stat_name==k).\ |
filter(GA_Stat.period_name==c.month).\ | filter(GA_Stat.period_name==c.month).\ |
order_by('ga_stat.value::int desc').all() | order_by('ga_stat.value::int desc').all() |
setattr(c, v, [(s.key, s.value) for s in entries ]) | setattr(c, v, [(s.key, s.value) for s in entries ]) |
return render('ga_report/site/index.html') | return render('ga_report/site/index.html') |
class GaPublisherReport(BaseController): | class GaPublisherReport(BaseController): |
""" | """ |
Displays the pageview and visit count for specific publishers based on | Displays the pageview and visit count for specific publishers based on |
the datasets associated with the publisher. | the datasets associated with the publisher. |
""" | """ |
def index(self): | def index(self): |
# Get the month details by fetching distinct values and determining the | # Get the month details by fetching distinct values and determining the |
# month names from the values. | # month names from the values. |
c.months = _month_details(GA_Url) | c.months = _month_details(GA_Url) |
# Work out which month to show, based on query params of the first item | # 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 = 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]) | c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) |
connection = model.Session.connection() | connection = model.Session.connection() |
q = """ | q = """ |
select department_id, sum(pageviews::int) views, sum(visitors::int) visits | select department_id, sum(pageviews::int) views, sum(visitors::int) visits |
from ga_url | from ga_url |
where department_id <> '' | where department_id <> '' |
and not url like '/publisher/%%' | |
and period_name=%s | and period_name=%s |
group by department_id order by views desc limit 20; | group by department_id order by views desc limit 20; |
""" | """ |
# Add this back (before and period_name =%s) if you want to ignore publisher | |
# homepage views | |
# and not url like '/publisher/%%' | |
c.top_publishers = [] | c.top_publishers = [] |
res = connection.execute(q, c.month) | res = connection.execute(q, c.month) |
for row in res: | for row in res: |
c.top_publishers.append((model.Group.get(row[0]), row[1], row[2])) | c.top_publishers.append((model.Group.get(row[0]), row[1], row[2])) |
return render('ga_report/publisher/index.html') | return render('ga_report/publisher/index.html') |
def read(self, id): | def read(self, id): |
c.publisher = model.Group.get(id) | c.publisher = model.Group.get(id) |
c.top_packages = [] # package, dataset_views in c.top_packages | c.top_packages = [] # package, dataset_views in c.top_packages |
# Get the month details by fetching distinct values and determining the | # Get the month details by fetching distinct values and determining the |
# month names from the values. | # month names from the values. |
c.months = _month_details(GA_Url) | c.months = _month_details(GA_Url) |
# Work out which month to show, based on query params of the first item | # 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 = 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]) | c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) |
entry = model.Session.query(GA_Url).\ | entry = model.Session.query(GA_Url).\ |
filter(GA_Url.url=='/publisher/%s' % c.publisher.name).\ | filter(GA_Url.url=='/publisher/%s' % c.publisher.name).\ |
filter(GA_Url.period_name==c.month).first() | filter(GA_Url.period_name==c.month).first() |
c.publisher_page_views = entry.pageviews if entry else 0 | c.publisher_page_views = entry.pageviews if entry else 0 |
entries = model.Session.query(GA_Url).\ | entries = model.Session.query(GA_Url).\ |
filter(GA_Url.department_id==c.publisher.name).\ | filter(GA_Url.department_id==c.publisher.name).\ |
filter(GA_Url.period_name==c.month).\ | filter(GA_Url.period_name==c.month).\ |
order_by('ga_url.pageviews::int desc')[:20] | order_by('ga_url.pageviews::int desc')[:20] |
for entry in entries: | for entry in entries: |
if entry.url.startswith('/dataset/'): | if entry.url.startswith('/dataset/'): |
p = model.Package.get(entry.url[len('/dataset/'):]) | p = model.Package.get(entry.url[len('/dataset/'):]) |
c.top_packages.append((p,entry.pageviews,entry.visitors)) | c.top_packages.append((p,entry.pageviews,entry.visitors)) |
return render('ga_report/publisher/read.html') | return render('ga_report/publisher/read.html') |
import os | 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 specific_month(self, date): |
self.since_date(datetime.datetime(2010, 1, 1)) | 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_th |