Implements downloads counts (for dataset resources) and fixes an issue with 'All' records.
[ckanext-ga-report.git] / ckanext / ga_report / command.py
blob:a/ckanext/ga_report/command.py -> blob:b/ckanext/ga_report/command.py
import logging import logging
import datetime import datetime
import os import os
   
from pylons import config 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', 'credentials.json')
self.args[0] if self.args  
else 'credentials.json')  
   
class FixTimePeriods(CkanCommand): class FixTimePeriods(CkanCommand):
""" """
Fixes the 'All' records for GA_Urls Fixes the 'All' records for GA_Urls
   
It is possible that older urls that haven't recently been visited It is possible that older urls that haven't recently been visited
do not have All records. This command will traverse through those do not have All records. This command will traverse through those
records and generate valid All records for them. records and generate valid All records for them.
""" """
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 __init__(self, name): def __init__(self, name):
super(FixTimePeriods, self).__init__(name) super(FixTimePeriods, self).__init__(name)
   
def command(self): def command(self):
import ckan.model as model import ckan.model as model
from ga_model import post_update_url_stats from ga_model import post_update_url_stats
self._load_config() self._load_config()
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')
   
log.info("Updating 'All' records for old URLs") log.info("Updating 'All' records for old URLs")
post_update_url_stats() post_update_url_stats()
log.info("Processing complete") log.info("Processing complete")
   
   
   
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 <time-period> Usage: paster loadanalytics <time-period>
   
Where <time-period> is: 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 - just data for the specific month YYYY-MM - just data for the specific month
""" """
summary = __doc__.split('\n')[0] summary = __doc__.split('\n')[0]
usage = __doc__ usage = __doc__
max_args = 1 max_args = 1
min_args = 0 min_args = 0
   
def __init__(self, name): def __init__(self, name):
super(LoadAnalytics, self).__init__(name) super(LoadAnalytics, self).__init__(name)
self.parser.add_option('-d', '--delete-first', self.parser.add_option('-d', '--delete-first',
action='store_true', action='store_true',
default=False, default=False,
dest='delete_first', dest='delete_first',
help='Delete data for the period first') help='Delete data for the period first')
self.parser.add_option('-s', '--skip_url_stats', self.parser.add_option('-s', '--skip_url_stats',
action='store_true', action='store_true',
default=False, default=False,
dest='skip_url_stats', dest='skip_url_stats',
help='Skip the download of URL data - just do site-wide stats') help='Skip the download of URL data - just do site-wide stats')
  self.token = ""
   
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', '')) ga_token_filepath = os.path.expanduser(config.get('googleanalytics.token.filepath', ''))
if not ga_token_filepath: if not ga_token_filepath:
print 'ERROR: In the CKAN config you need to specify the filepath of the ' \ print 'ERROR: In the CKAN config you need to specify the filepath of the ' \
'Google Analytics token file under key: googleanalytics.token.filepath' 'Google Analytics token file under key: googleanalytics.token.filepath'
return return
   
try: try:
svc = init_service(ga_token_filepath, None) self.token, 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 token file in the CKAN config under ' 'specified the correct token file in the CKAN config under '
'"googleanalytics.token.filepath"?') '"googleanalytics.token.filepath"?')
return return
   
downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc), downloader = DownloadAnalytics(svc, self.token, profile_id=get_profile_id(svc),
delete_first=self.options.delete_first, delete_first=self.options.delete_first,
skip_url_stats=self.options.skip_url_stats) skip_url_stats=self.options.skip_url_stats)
   
time_period = self.args[0] if self.args else 'latest' time_period = self.args[0] if self.args 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:
# The month to use # The month to use
for_date = datetime.datetime.strptime(time_period, '%Y-%m') for_date = datetime.datetime.strptime(time_period, '%Y-%m')
downloader.specific_month(for_date) downloader.specific_month(for_date)