--- a/ckanext/ga_report/command.py +++ b/ckanext/ga_report/command.py @@ -1,7 +1,13 @@ import logging +import datetime +import os + +from pylons import config from ckan.lib.cli import CkanCommand -# No other CKAN imports allowed until _load_config is run, or logging is disabled +# No other CKAN imports allowed until _load_config is run, +# or logging is disabled + class InitDB(CkanCommand): """Initialise the extension's database tables @@ -17,7 +23,7 @@ import ckan.model as model model.Session.remove() model.Session.configure(bind=model.meta.engine) - log = logging.getLogger('ckanext.ga-report') + log = logging.getLogger('ckanext.ga_report') import ga_model ga_model.init_tables() @@ -46,51 +52,100 @@ assuming it is correct. """ from ga_auth import init_service - initialize_service('token.dat', - self.args[0] if self.args - else 'credentials.json') + init_service('token.dat', 'credentials.json') + +class FixTimePeriods(CkanCommand): + """ + Fixes the 'All' records for GA_Urls + + It is possible that older urls that haven't recently been visited + do not have All records. This command will traverse through those + records and generate valid All records for them. + """ + summary = __doc__.split('\n')[0] + usage = __doc__ + max_args = 0 + min_args = 0 + + def __init__(self, name): + super(FixTimePeriods, self).__init__(name) + + def command(self): + import ckan.model as model + from ga_model import post_update_url_stats + self._load_config() + model.Session.remove() + model.Session.configure(bind=model.meta.engine) + + log = logging.getLogger('ckanext.ga_report') + + log.info("Updating 'All' records for old URLs") + post_update_url_stats() + log.info("Processing complete") + + class LoadAnalytics(CkanCommand): """Get data from Google Analytics API and save it in the ga_model - Usage: paster loadanalytics + Usage: paster loadanalytics - Where is the name of the auth token file from - the getauthtoken step. - - And where is: + Where is: all - data for all time latest - (default) just the 'latest' data - YYYY-MM-DD - just data for all time periods going - back to (and including) this date + YYYY-MM - just data for the specific month """ summary = __doc__.split('\n')[0] usage = __doc__ - max_args = 2 - min_args = 1 + max_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') + self.token = "" def command(self): self._load_config() - from ga_auth import init_service - try: - svc = init_service(self.args[0], None) - except TypeError: - print 'Have you correctly run the getauthtoken task and specified the correct file here' + from download_analytics import DownloadAnalytics + 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 - from download_analytics import DownloadAnalytics - from ga_auth import get_profile_id - downloader = DownloadAnalytics(svc, profile_id=get_profile_id(svc)) + try: + self.token, svc = init_service(ga_token_filepath, None) + except TypeError: + print ('Have you correctly run the getauthtoken task and ' + 'specified the correct token file in the CKAN config under ' + '"googleanalytics.token.filepath"?') + return - time_period = self.args[1] if self.args and len(self.args) > 1 else 'latest' + downloader = DownloadAnalytics(svc, self.token, profile_id=get_profile_id(svc), + delete_first=self.options.delete_first, + skip_url_stats=self.options.skip_url_stats) + + time_period = self.args[0] if self.args else 'latest' if time_period == 'all': downloader.all_() elif time_period == 'latest': downloader.latest() else: - since_date = datetime.datetime.strptime(time_period, '%Y-%m-%d') - downloader.since_date(since_date) + # The month to use + for_date = datetime.datetime.strptime(time_period, '%Y-%m') + downloader.specific_month(for_date) -