| 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): | |
| def __init__(self, service=None, profile_id=None): | |
| self.period = config['ga-report.period'] | self.period = config['ga-report.period'] |
| self.service = service | |
| self.profile_id = profile_id | |
| def all_(self): | def all_(self): |
| pass | 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, a)\ | 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) | data = self.download(start_date, end_date) |
| log.info('Storing Analytics for period "%s"', | log.info('Storing 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) |
| @classmethod | |
| def download(cls, start_date, end_date): | def download(self, start_date, end_date): |
| '''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=~/dataset/[a-z0-9-]+$' |
| #query = 'ga:pagePath=~^%s,ga:pagePath=~^%s' % \ | |
| # (PACKAGE_URL, self.resource_url_tag) | |
| query = 'ga:pagePath=~^/dataset/' | |
| metrics = 'ga:uniquePageviews' | metrics = 'ga:uniquePageviews' |
| sort = '-ga:uniquePageviews' | sort = '-ga:uniquePageviews' |
| for entry in GA.ga_query(query_filter=query, | |
| from_date=start_date, | # 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, | metrics=metrics, |
| sort=sort, | sort=sort, |
| to_date=end_date): | dimensions="ga:pagePath", |
| print entry | max_results=10000, |
| import pdb; pdb.set_trace() | end_date=end_date).execute() |
| for dim in entry.dimension: | |
| if dim.name == "ga:pagePath": | if os.getenv('DEBUG'): |
| package = dim.value | import pprint |
| count = entry.get_metric( | pprint.pprint(results) |
| 'ga:uniquePageviews').value or 0 | print 'Total results: %s' % results.get('totalResults') |
| packages[package] = int(count) | |
| return packages | packages = [] |
| for entry in results.get('rows'): | |
| (loc,size,) = entry | |
| packages.append( ('http:/' + loc,size, '',) ) # 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']) |