import logging | import logging |
import datetime | |
from ckan.lib.cli import CkanCommand | 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): | 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 |
initialize_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-DD - just data for all time periods going |
back to (and including) this date | 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 ga_auth import init_service | from download_analytics import DownloadAnalytics |
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 specified the correct file here' | print ('Have you correctly run the getauthtoken task and ' |
'specified the correct file here') | |
return | return |
from download_analytics import DownloadAnalytics | |
from ga_auth import get_profile_id | |
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 else 'latest' | time_period = self.args[1] if self.args and len(self.args) > 1 \ |
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') | since_date = datetime.datetime.strptime(time_period, '%Y-%m-%d') |
downloader.since_date(since_date) | downloader.since_date(since_date) |
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): |
""" | """ |
Get the profile ID for this user and the service specified by the | Get the profile ID for this user and the service specified by the |
'googleanalytics.id' configuration option. | 'googleanalytics.id' configuration option. |
""" | """ |
accounts = service.management().accounts().list().execute() | accounts = service.management().accounts().list().execute() |
if not accounts.get('items'): | if not accounts.get('items'): |
return None | return None |
accountId = accounts.get('items')[0].get('id') | accountId = accounts.get('items')[0].get('id') |
webPropertyId = config.get('googleanalytics.id') | webPropertyId = config.get('googleanalytics.id') |
profiles = service.management().profiles().list( | profiles = service.management().profiles().list( |
accountId=accountId, webPropertyId=webPropertyId).execute() | accountId=accountId, webPropertyId=webPropertyId).execute() |
if profiles.get('items'): | if profiles.get('items'): |
return profiles.get('items')[0].get('id') | return profiles.get('items')[0].get('id') |
return None | return None |
import re | import re |
import uuid | import uuid |
from sqlalchemy import Table, Column, MetaData | from sqlalchemy import Table, Column, MetaData |
from sqlalchemy import types | from sqlalchemy import types |
from sqlalchemy.sql import select, text | from sqlalchemy.sql import select |
from sqlalchemy import func | from sqlalchemy import func |
import ckan.model as model | import ckan.model as model |
from ckan.model.types import JsonType | from ckan.model.types import JsonType |
from ckan.lib.base import * | from ckan.lib.base import * |
def make_uuid(): | def make_uuid(): |
return unicode(uuid.uuid4()) | return unicode(uuid.uuid4()) |
def init_tables(): | def init_tables(): |
metadata = MetaData() | metadata = MetaData() |
package_stats = Table('ga_url', metadata, | package_stats = Table('ga_url', metadata, |
Column('id', types.UnicodeText, primary_key=True, default=make_uuid), | Column('id', types.UnicodeText, primary_key=True, |
default=make_uuid), | |
Column('period_name', types.UnicodeText), | Column('period_name', types.UnicodeText), |
Column('period_complete_day', types.Integer), | Column('period_complete_day', types.Integer), |
Column('visits', types.Integer), | Column('visits', types.Integer), |
Column('group_id', types.String(60)), | Column('group_id', types.String(60)), |
Column('next_page', JsonType), | Column('next_page', JsonType), |
) | ) |
metadata.create_all(model.meta.engine) | metadata.create_all(model.meta.engine) |
cached_tables = {} | cached_tables = {} |
def get_table(name): | def get_table(name): |
if name not in cached_tables: | if name not in cached_tables: |
meta = MetaData() | meta = MetaData() |
meta.reflect(bind=model.meta.engine) | meta.reflect(bind=model.meta.engine) |
table = meta.tables[name] | table = meta.tables[name] |
cached_tables[name] = table | cached_tables[name] = table |
return cached_tables[name] | return cached_tables[name] |
def _normalize_url(url): | def _normalize_url(url): |
'''Strip off the hostname etc. Do this before storing it. | '''Strip off the hostname etc. Do this before storing it. |
>>> normalize_url('http://data.gov.uk/dataset/weekly_fuel_prices') | >>> normalize_url('http://data.gov.uk/dataset/weekly_fuel_prices') |
'/dataset/weekly_fuel_prices' | '/dataset/weekly_fuel_prices' |
''' | ''' |
url = re.sub('https?://(www\.)?data.gov.uk', '', url) | url = re.sub('https?://(www\.)?data.gov.uk', '', url) |
return url | return url |
def _get_department_id_of_url(url): | def _get_department_id_of_url(url): |
# e.g. /dataset/fuel_prices | # e.g. /dataset/fuel_prices |
# e.g. /dataset/fuel_prices/resource/e63380d4 | # e.g. /dataset/fuel_prices/resource/e63380d4 |
dataset_match = re.match('/dataset/([^/]+)(/.*)?', url) | dataset_match = re.match('/dataset/([^/]+)(/.*)?', url) |
if dataset_match: | if dataset_match: |
dataset_ref = dataset_match.groups()[0] | dataset_ref = dataset_match.groups()[0] |
dataset = model.Package.get(dataset_ref) | dataset = model.Package.get(dataset_ref) |
if dataset: | if dataset: |
publisher_groups = dataset.get_groups('publisher') | publisher_groups = dataset.get_groups('publisher') |
if publisher_groups: | if publisher_groups: |
return publisher_groups[0].id | return publisher_groups[0].id |
def update_url_stats(period_name, period_complete_day, url_data): | def update_url_stats(period_name, period_complete_day, url_data): |
table = get_table('ga_url') | table = get_table('ga_url') |
connection = model.Session.connection() | connection = model.Session.connection() |
for url, views, next_page in url_data: | for url, views, next_page in url_data: |
url = _normalize_url(url) | url = _normalize_url(url) |
department_id = _get_department_id_of_url(url) | department_id = _get_department_id_of_url(url) |
# see if the row for this url & month is in the table already | # see if the row for this url & month is in the table already |
s = select([func.count(id_col)], | s = select([func.count(id_col)], |
table.c.period_name == period_name, | table.c.period_name == period_name, |
table.c.url == url) | table.c.url == url) |
count = connection.execute(s).fetchone() | count = connection.execute(s).fetchone() |
if count and count[0]: | if count and count[0]: |
# update the row | # update the row |
connection.execute(table.update()\ | connection.execute(table.update() |
.where(table.c.period_name == period_name, | .where(table.c.period_name == period_name, |
table.c.url == url)\ | table.c.url == url) |
.values(period_complete_day=period_complete_day, | .values(period_complete_day=period_complete_day, |
views=views, | views=views, |
department_id=department_id, | department_id=department_id, |
next_page=next_page)) | next_page=next_page)) |
else: | else: |
# create the row | # create the row |
values = {'period_name': period_name, | values = {'period_name': period_name, |
'period_complete_day': period_complete_day, | 'period_complete_day': period_complete_day, |
'url': url, | 'url': url, |
'views': views, | 'views': views, |
'department_id': department_id, | 'department_id': department_id, |
'next_page': next_page} | 'next_page': next_page} |
connection.execute(stats.insert()\ | connection.execute(stats.insert(). |
.values(**values)) | values(**values)) |