Merge branch 'master' of git+ssh://maxious.lambdacomplex.org/git/ckanext-ga-report
--- a/ckanext/ga_report/controller.py
+++ b/ckanext/ga_report/controller.py
@@ -1,6 +1,7 @@
import re
import csv
import sys
+import json
import logging
import operator
import collections
@@ -21,6 +22,10 @@
d = strptime(strdate, '%Y-%m')
return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year)
+def _get_unix_epoch(strdate):
+ from time import strptime,mktime
+ d = strptime(strdate, '%Y-%m')
+ return int(mktime(d))
def _month_details(cls, stat_key=None):
'''
@@ -107,11 +112,26 @@
return key, val
+ # Query historic values for sparkline rendering
+ sparkline_query = model.Session.query(GA_Stat)\
+ .filter(GA_Stat.stat_name=='Totals')\
+ .order_by(GA_Stat.period_name)
+ sparkline_data = {}
+ for x in sparkline_query:
+ sparkline_data[x.key] = sparkline_data.get(x.key,[])
+ key, val = clean_key(x.key,float(x.value))
+ tooltip = '%s: %s' % (_get_month_name(x.period_name), val)
+ sparkline_data[x.key].append( (tooltip,x.value) )
+ # Trim the latest month, as it looks like a huge dropoff
+ for key in sparkline_data:
+ sparkline_data[key] = sparkline_data[key][:-1]
+
c.global_totals = []
if c.month:
for e in entries:
key, val = clean_key(e.key, e.value)
- c.global_totals.append((key, val))
+ sparkline = sparkline_data[e.key]
+ c.global_totals.append((key, val, sparkline))
else:
d = collections.defaultdict(list)
for e in entries:
@@ -121,10 +141,18 @@
v = sum(v)
else:
v = float(sum(v))/float(len(v))
+ sparkline = sparkline_data[k]
key, val = clean_key(k,v)
- c.global_totals.append((key, val))
- c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0))
+ c.global_totals.append((key, val, sparkline))
+ # Sort the global totals into a more pleasant order
+ def sort_func(x):
+ key = x[0]
+ total_order = ['Total page views','Total visits','Pages per visit']
+ if key in total_order:
+ return total_order.index(key)
+ return 999
+ c.global_totals = sorted(c.global_totals, key=sort_func)
keys = {
'Browser versions': 'browser_versions',
@@ -161,12 +189,13 @@
for k, v in keys.iteritems():
q = model.Session.query(GA_Stat).\
- filter(GA_Stat.stat_name==k)
+ filter(GA_Stat.stat_name==k).\
+ order_by(GA_Stat.period_name)
+ # Buffer the tabular data
if c.month:
entries = []
q = q.filter(GA_Stat.period_name==c.month).\
order_by('ga_stat.value::int desc')
-
d = collections.defaultdict(int)
for e in q.all():
d[e.key] += int(e.value)
@@ -175,10 +204,27 @@
entries.append((key,val,))
entries = sorted(entries, key=operator.itemgetter(1), reverse=True)
+ # Run a query on all months to gather graph data
+ graph_query = model.Session.query(GA_Stat).\
+ filter(GA_Stat.stat_name==k).\
+ order_by(GA_Stat.period_name)
+ graph_dict = {}
+ for stat in graph_query:
+ graph_dict[ stat.key ] = graph_dict.get(stat.key,{
+ 'name':stat.key,
+ 'raw': {}
+ })
+ graph_dict[ stat.key ]['raw'][stat.period_name] = float(stat.value)
+ stats_in_table = [x[0] for x in entries]
+ stats_not_in_table = set(graph_dict.keys()) - set(stats_in_table)
+ stats = stats_in_table + sorted(list(stats_not_in_table))
+ graph = [graph_dict[x] for x in stats]
+ setattr(c, v+'_graph', json.dumps( _to_rickshaw(graph,percentageMode=True) ))
+
# Get the total for each set of values and then set the value as
# a percentage of the total
if k == 'Social sources':
- total = sum([x for n,x in c.global_totals if n == 'Total visits'])
+ total = sum([x for n,x,graph in c.global_totals if n == 'Total visits'])
else:
total = sum([num for _,num in entries])
setattr(c, v, [(k,_percent(v,total)) for k,v in entries ])
@@ -203,7 +249,9 @@
writer = csv.writer(response)
writer.writerow(["Publisher Title", "Publisher Name", "Views", "Visits", "Period Name"])
- for publisher,view,visit in _get_top_publishers(None):
+ top_publishers = _get_top_publishers(limit=None)
+
+ for publisher,view,visit in top_publishers:
writer.writerow([publisher.title.encode('utf-8'),
publisher.name.encode('utf-8'),
view,
@@ -223,7 +271,7 @@
if not c.publisher:
abort(404, 'A publisher with that name could not be found')
- packages = self._get_packages(c.publisher)
+ packages = self._get_packages(publisher=c.publisher, month=c.month)
response.headers['Content-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = \
str('attachment; filename=datasets_%s_%s.csv' % (c.publisher_name, month,))
@@ -253,12 +301,17 @@
c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
c.top_publishers = _get_top_publishers()
- return render('ga_report/publisher/index.html')
-
- def _get_packages(self, publisher=None, count=-1):
+ graph_data = _get_top_publishers_graph()
+ c.top_publishers_graph = json.dumps( _to_rickshaw(graph_data) )
+
+ x = render('ga_report/publisher/index.html')
+
+ return x
+
+ def _get_packages(self, publisher=None, month='', count=-1):
'''Returns the datasets in order of views'''
have_download_data = True
- month = c.month or 'All'
+ month = month or 'All'
if month != 'All':
have_download_data = month >= DOWNLOADS_AVAILABLE_FROM
@@ -284,11 +337,13 @@
filter(GA_Stat.key==package.name)
if month != 'All': # Fetch everything unless the month is specific
dls = dls.filter(GA_Stat.period_name==month)
-
- downloads = sum(int(d.value) for d in dls.all())
+ downloads = 0
+ for x in dls:
+ downloads += int(x.value)
else:
downloads = 'No data'
- top_packages.append((package, entry.pageviews, entry.visits, downloads))
+ if package.private == False:
+ top_packages.append((package, entry.pageviews, entry.visits, downloads))
else:
log.warning('Could not find package associated package')
@@ -334,9 +389,73 @@
entry = q.filter(GA_Url.period_name==c.month).first()
c.publisher_page_views = entry.pageviews if entry else 0
- c.top_packages = self._get_packages(c.publisher, 20)
+ c.top_packages = self._get_packages(publisher=c.publisher, count=20, month=c.month)
+
+ # Graph query
+ top_packages_all_time = self._get_packages(publisher=c.publisher, count=20, month='All')
+ top_package_names = [ x[0].name for x in top_packages_all_time ]
+ graph_query = model.Session.query(GA_Url,model.Package)\
+ .filter(model.Package.name==GA_Url.package_id)\
+ .filter(GA_Url.url.like('/dataset/%'))\
+ .filter(GA_Url.package_id.in_(top_package_names))
+ all_series = {}
+ for entry,package in graph_query:
+ if not package: continue
+ if entry.period_name=='All': continue
+ all_series[package.name] = all_series.get(package.name,{
+ 'name':package.title,
+ 'raw': {}
+ })
+ all_series[package.name]['raw'][entry.period_name] = int(entry.pageviews)
+ graph = [ all_series[series_name] for series_name in top_package_names ]
+ c.graph_data = json.dumps( _to_rickshaw(graph) )
return render('ga_report/publisher/read.html')
+
+def _to_rickshaw(data, percentageMode=False):
+ if data==[]:
+ return data
+ # x-axis is every month in c.months. Note that data might not exist
+ # for entire history, eg. for recently-added datasets
+ x_axis = [x[0] for x in c.months]
+ x_axis.reverse() # Ascending order
+ x_axis = x_axis[:-1] # Remove latest month
+ totals = {}
+ for series in data:
+ series['data'] = []
+ for x_string in x_axis:
+ x = _get_unix_epoch( x_string )
+ y = series['raw'].get(x_string,0)
+ series['data'].append({'x':x,'y':y})
+ totals[x] = totals.get(x,0)+y
+ if not percentageMode:
+ return data
+ # Turn all data into percentages
+ # Roll insignificant series into a catch-all
+ THRESHOLD = 1
+ raw_data = data
+ data = []
+ for series in raw_data:
+ for point in series['data']:
+ percentage = (100*float(point['y'])) / totals[point['x']]
+ if not (series in data) and percentage>THRESHOLD:
+ data.append(series)
+ point['y'] = percentage
+ others = [ x for x in raw_data if not (x in data) ]
+ if len(others):
+ data_other = []
+ for i in range(len(x_axis)):
+ x = _get_unix_epoch(x_axis[i])
+ y = 0
+ for series in others:
+ y += series['data'][i]['y']
+ data_other.append({'x':x,'y':y})
+ data.append({
+ 'name':'Other',
+ 'data': data_other
+ })
+ return data
+
def _get_top_publishers(limit=20):
'''
@@ -366,6 +485,46 @@
return top_publishers
+def _get_top_publishers_graph(limit=20):
+ '''
+ Returns a list of the top 20 publishers by dataset visits.
+ (The number to show can be varied with 'limit')
+ '''
+ connection = model.Session.connection()
+ q = """
+ select department_id, sum(pageviews::int) views
+ from ga_url
+ where department_id <> ''
+ and package_id <> ''
+ and url like '/dataset/%%'
+ and period_name='All'
+ group by department_id order by views desc
+ """
+ if limit:
+ q = q + " limit %s;" % (limit)
+
+ res = connection.execute(q)
+ department_ids = [ row[0] for row in res ]
+
+ # Query for a history graph of these department ids
+ q = model.Session.query(
+ GA_Url.department_id,
+ GA_Url.period_name,
+ func.sum(cast(GA_Url.pageviews,sqlalchemy.types.INT)))\
+ .filter( GA_Url.department_id.in_(department_ids) )\
+ .filter( GA_Url.url.like('/dataset/%') )\
+ .filter( GA_Url.package_id!='' )\
+ .group_by( GA_Url.department_id, GA_Url.period_name )
+ graph_dict = {}
+ for dept_id,period_name,views in q:
+ graph_dict[dept_id] = graph_dict.get( dept_id, {
+ 'name' : model.Group.get(dept_id).title,
+ 'raw' : {}
+ })
+ graph_dict[dept_id]['raw'][period_name] = views
+ return [ graph_dict[id] for id in department_ids ]
+
+
def _get_publishers():
'''
Returns a list of all publishers. Each item is a tuple:
@@ -373,7 +532,7 @@
'''
publishers = []
for pub in model.Session.query(model.Group).\
- filter(model.Group.type=='publisher').\
+ filter(model.Group.type=='organization').\
filter(model.Group.state=='active').\
order_by(model.Group.name):
publishers.append((pub.name, pub.title))
--- a/ckanext/ga_report/download_analytics.py
+++ b/ckanext/ga_report/download_analytics.py
@@ -1,7 +1,12 @@
import os
import logging
import datetime
+import httplib
+import urllib
import collections
+import requests
+import json
+import re
from pylons import config
from ga_model import _normalize_url
import ga_model
@@ -18,13 +23,14 @@
class DownloadAnalytics(object):
'''Downloads and stores analytics info'''
- def __init__(self, service=None, profile_id=None, delete_first=False,
+ def __init__(self, service=None, token=None, profile_id=None, delete_first=False,
skip_url_stats=False):
self.period = config['ga-report.period']
self.service = service
self.profile_id = profile_id
self.delete_first = delete_first
self.skip_url_stats = skip_url_stats
+ self.token = token
def specific_month(self, date):
import calendar
@@ -32,6 +38,11 @@
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)
+ # if this is the latest month, note that it is only up until today
+ now = datetime.datetime.now()
+ if now.year == date.year and now.month == date.month:
+ last_day_of_month = now.day
+ last_of_this_month = now
periods = ((date.strftime(FORMAT_MONTH),
last_day_of_month,
first_of_this_month, last_of_this_month),)
@@ -112,13 +123,13 @@
accountName = config.get('googleanalytics.account')
log.info('Downloading analytics for dataset views')
- data = self.download(start_date, end_date, '~/%s/dataset/[a-z0-9-_]+' % accountName)
+ data = self.download(start_date, end_date, '~^/dataset/[a-z0-9-_]+')
log.info('Storing dataset views (%i rows)', len(data.get('url')))
self.store(period_name, period_complete_day, data, )
log.info('Downloading analytics for publisher views')
- data = self.download(start_date, end_date, '~/%s/publisher/[a-z0-9-_]+' % accountName)
+ data = self.download(start_date, end_date, '~^/organization/[a-z0-9-_]+')
log.info('Storing publisher views (%i rows)', len(data.get('url')))
self.store(period_name, period_complete_day, data,)
@@ -126,7 +137,7 @@
# Make sure the All records are correct.
ga_model.post_update_url_stats()
- log.info('Aggregating datasets by publisher')
+ log.info('Associating datasets with their publisher')
ga_model.update_publisher_stats(period_name) # about 30 seconds.
@@ -144,21 +155,31 @@
metrics = 'ga:entrances'
sort = '-ga:entrances'
- # 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,
- sort=sort,
- dimensions="ga:landingPagePath,ga:socialNetwork",
- max_results=10000,
- end_date=end_date).execute()
+ try:
+ # Because of issues of invalid responses, we are going to make these requests
+ # ourselves.
+ headers = {'authorization': 'Bearer ' + self.token}
+
+ args = dict(ids='ga:' + self.profile_id,
+ filters=query,
+ metrics=metrics,
+ sort=sort,
+ dimensions="ga:landingPagePath,ga:socialNetwork",
+ max_results=10000)
+
+ args['start-date'] = start_date
+ args['end-date'] = end_date
+
+ results = self._get_json(args)
+ except Exception, e:
+ log.exception(e)
+ results = dict(url=[])
+
+
data = collections.defaultdict(list)
rows = results.get('rows',[])
for row in rows:
- url = _normalize_url('http:/' + row[0])
+ url = row[0]
data[url].append( (row[1], int(row[2]),) )
ga_model.update_social(period_name, data)
@@ -173,23 +194,34 @@
# 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,
- sort=sort,
- dimensions="ga:pagePath",
- max_results=10000,
- end_date=end_date).execute()
+ # https://ga-dev-tools.appspot.com/explorer/
+ try:
+ args = {}
+ args["sort"] = "-ga:pageviews"
+ args["max-results"] = 100000
+ args["dimensions"] = "ga:pagePath"
+ args["start-date"] = start_date
+ args["end-date"] = end_date
+ args["metrics"] = metrics
+ args["ids"] = "ga:" + self.profile_id
+ args["filters"] = query
+ args["alt"] = "json"
+ print args
+ results = self._get_json(args)
+
+ except Exception, e:
+ log.exception(e)
+ return dict(url=[])
packages = []
log.info("There are %d results" % results['totalResults'])
- for entry in results.get('rows'):
+ if results['totalResults'] > 0:
+ for entry in results.get('rows'):
(loc,pageviews,visits) = entry
- url = _normalize_url('http:/' + loc) # strips off domain e.g. www.data.gov.uk or data.gov.uk
-
- if not url.startswith('/dataset/') and not url.startswith('/publisher/'):
+ #url = _normalize_url('http:/' + loc) # strips off domain e.g. www.data.gov.uk or data.gov.uk
+ url = loc
+ #print url
+ if not url.startswith('/dataset/') and not url.startswith('/organization/'):
# filter out strays like:
# /data/user/login?came_from=http://data.gov.uk/dataset/os-code-point-open
# /403.html?page=/about&from=http://data.gov.uk/publisher/planning-inspectorate
@@ -221,25 +253,78 @@
data[key] = data.get(key,0) + result[1]
return data
+ def _get_json(self, params, prev_fail=False):
+ 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
+
+ log.info("Trying to refresh our OAuth token")
+ try:
+ from ga_auth import init_service
+ self.token, svc = init_service(ga_token_filepath, None)
+ log.info("OAuth token refreshed")
+ except Exception, auth_exception:
+ log.error("Oauth refresh failed")
+ log.exception(auth_exception)
+ return
+
+ try:
+ headers = {'authorization': 'Bearer ' + self.token}
+ r = requests.get("https://www.googleapis.com/analytics/v3/data/ga", params=params, headers=headers)
+ if r.status_code != 200:
+ log.info("STATUS: %s" % (r.status_code,))
+ log.info("CONTENT: %s" % (r.content,))
+ raise Exception("Request with params: %s failed" % params)
+
+ return json.loads(r.content)
+ except Exception, e:
+ log.exception(e)
+
+ return dict(url=[])
+
def _totals_stats(self, start_date, end_date, period_name, period_complete_day):
""" Fetches distinct totals, total pageviews etc """
- results = self.service.data().ga().get(
- ids='ga:' + self.profile_id,
- start_date=start_date,
- metrics='ga:pageviews',
- sort='-ga:pageviews',
- max_results=10000,
- end_date=end_date).execute()
+ try:
+ args = {}
+ args["max-results"] = 100000
+ args["start-date"] = start_date
+ args["end-date"] = end_date
+ args["ids"] = "ga:" + self.profile_id
+
+ args["metrics"] = "ga:pageviews"
+ args["sort"] = "-ga:pageviews"
+ args["alt"] = "json"
+
+ results = self._get_json(args)
+ except Exception, e:
+ log.exception(e)
+ results = dict(url=[])
+
result_data = results.get('rows')
ga_model.update_sitewide_stats(period_name, "Totals", {'Total page views': result_data[0][0]},
period_complete_day)
- results = self.service.data().ga().get(
- ids='ga:' + self.profile_id,
- start_date=start_date,
- metrics='ga:pageviewsPerVisit,ga:avgTimeOnSite,ga:percentNewVisits,ga:visits',
- max_results=10000,
- end_date=end_date).execute()
+ try:
+ # Because of issues of invalid responses, we are going to make these requests
+ # ourselves.
+ headers = {'authorization': 'Bearer ' + self.token}
+
+ args = {}
+ args["max-results"] = 100000
+ args["start-date"] = start_date
+ args["end-date"] = end_date
+ args["ids"] = "ga:" + self.profile_id
+
+ args["metrics"] = "ga:pageviewsPerVisit,ga:avgTimeOnSite,ga:percentNewVisits,ga:visits"
+ args["alt"] = "json"
+
+ results = self._get_json(args)
+ except Exception, e:
+ log.exception(e)
+ results = dict(url=[])
+
result_data = results.get('rows')
data = {
'Pages per visit': result_data[0][0],
@@ -250,16 +335,29 @@
ga_model.update_sitewide_stats(period_name, "Totals", data, period_complete_day)
# Bounces from / or another configurable page.
- path = '/%s%s' % (config.get('googleanalytics.account'),
- config.get('ga-report.bounce_url', '/'))
- results = self.service.data().ga().get(
- ids='ga:' + self.profile_id,
- filters='ga:pagePath==%s' % (path,),
- start_date=start_date,
- metrics='ga:visitBounceRate',
- dimensions='ga:pagePath',
- max_results=10000,
- end_date=end_date).execute()
+ path = '/' #% (config.get('googleanalytics.account'), config.get('ga-report.bounce_url', '/'))
+
+ try:
+ # Because of issues of invalid responses, we are going to make these requests
+ # ourselves.
+ headers = {'authorization': 'Bearer ' + self.token}
+
+ args = {}
+ args["max-results"] = 100000
+ args["start-date"] = start_date
+ args["end-date"] = end_date
+ args["ids"] = "ga:" + self.profile_id
+
+ args["filters"] = 'ga:pagePath==%s' % (path,)
+ args["dimensions"] = 'ga:pagePath'
+ args["metrics"] = "ga:visitBounceRate"
+ args["alt"] = "json"
+
+ results = self._get_json(args)
+ except Exception, e:
+ log.exception(e)
+ results = dict(url=[])
+
result_data = results.get('rows')
if not result_data or len(result_data) != 1:
log.error('Could not pinpoint the bounces for path: %s. Got results: %r',
@@ -275,14 +373,28 @@
def _locale_stats(self, start_date, end_date, period_name, period_complete_day):
""" Fetches stats about language and country """
- results = self.service.data().ga().get(
- ids='ga:' + self.profile_id,
- start_date=start_date,
- metrics='ga:pageviews',
- sort='-ga:pageviews',
- dimensions="ga:language,ga:country",
- max_results=10000,
- end_date=end_date).execute()
+
+ try:
+ # Because of issues of invalid responses, we are going to make these requests
+ # ourselves.
+ headers = {'authorization': 'Bearer ' + self.token}
+
+ args = {}
+ args["max-results"] = 100000
+ args["start-date"] = start_date
+ args["end-date"] = end_date
+ args["ids"] = "ga:" + self.profile_id
+
+ args["dimensions"] = "ga:language,ga:country"
+ args["metrics"] = "ga:pageviews"
+ args["sort"] = "-ga:pageviews"
+ args["alt"] = "json"
+
+ results = self._get_json(args)
+ except Exception, e:
+ log.exception(e)
+ results = dict(url=[])
+
result_data = results.get('rows')
data = {}
for result in result_data:
@@ -298,20 +410,32 @@
def _download_stats(self, start_date, end_date, period_name, period_complete_day):
- """ Fetches stats about language and country """
+ """ Fetches stats about data downloads """
import ckan.model as model
data = {}
- results = self.service.data().ga().get(
- ids='ga:' + self.profile_id,
- start_date=start_date,
- filters='ga:eventAction==download',
- metrics='ga:totalEvents',
- sort='-ga:totalEvents',
- dimensions="ga:eventLabel",
- max_results=10000,
- end_date=end_date).execute()
+ try:
+ # Because of issues of invalid responses, we are going to make these requests
+ # ourselves.
+ headers = {'authorization': 'Bearer ' + self.token}
+
+ args = {}
+ args["max-results"] = 100000
+ args["start-date"] = start_date
+ args["end-date"] = end_date
+ args["ids"] = "ga:" + self.profile_id
+
+ args["filters"] = 'ga:eventAction==Download'
+ args["dimensions"] = "ga:eventLabel"
+ args["metrics"] = "ga:totalEvents"
+ args["alt"] = "json"
+
+ results = self._get_json(args)
+ except Exception, e:
+ log.exception(e)
+ results = dict(url=[])
+
result_data = results.get('rows')
if not result_data:
# We may not have data for this time period, so we need to bail
@@ -320,8 +444,15 @@
return
def process_result_data(result_data, cached=False):
+ progress_total = len(result_data)
+ progress_count = 0
+ resources_not_matched = []
for result in result_data:
- url = result[0].strip()
+ progress_count += 1
+ if progress_count % 100 == 0:
+ log.debug('.. %d/%d done so far', progress_count, progress_total)
+
+ url = urllib.unquote(result[0].strip())
# Get package id associated with the resource that has this URL.
q = model.Session.query(model.Resource)
@@ -329,40 +460,73 @@
r = q.filter(model.Resource.cache_url.like("%s%%" % url)).first()
else:
r = q.filter(model.Resource.url.like("%s%%" % url)).first()
+
+ # new style internal download links
+ if re.search('(?:/resource/)(.*)(?:/download/)',url):
+ resource_id = re.search('(?:/resource/)(.*)(?:/download/)',url)
+ r = q.filter(model.Resource.id.like("%s%%" % resource_id.group(1))).first()
package_name = r.resource_group.package.name if r else ""
+
+
if package_name:
data[package_name] = data.get(package_name, 0) + int(result[1])
else:
- log.warning(u"Could not find resource for URL: {url}".format(url=url))
+ resources_not_matched.append(url)
continue
-
+ if resources_not_matched:
+ log.debug('Could not match %i or %i resource URLs to datasets. e.g. %r',
+ len(resources_not_matched), progress_total, resources_not_matched[:3])
+
+ log.info('Associating downloads of resource URLs with their respective datasets')
process_result_data(results.get('rows'))
- results = self.service.data().ga().get(
- ids='ga:' + self.profile_id,
- start_date=start_date,
- filters='ga:eventAction==download-cache',
- metrics='ga:totalEvents',
- sort='-ga:totalEvents',
- dimensions="ga:eventLabel",
- max_results=10000,
- end_date=end_date).execute()
- process_result_data(results.get('rows'), cached=False)
+ '''try:
+ # Because of issues of invalid responses, we are going to make these requests
+ # ourselves.
+ headers = {'authorization': 'Bearer ' + self.token}
+
+ args = dict( ids='ga:' + self.profile_id,
+ filters='ga:eventAction==download-cache',
+ metrics='ga:totalEvents',
+ sort='-ga:totalEvents',
+ dimensions="ga:eventLabel",
+ max_results=10000)
+ args['start-date'] = start_date
+ args['end-date'] = end_date
+
+ results = self._get_json(args)
+ except Exception, e:
+ log.exception(e)
+ results = dict(url=[])
+
+ log.info('Associating downloads of cache resource URLs with their respective datasets')
+ process_result_data(results.get('rows'), cached=False)'''
self._filter_out_long_tail(data, MIN_DOWNLOADS)
ga_model.update_sitewide_stats(period_name, "Downloads", data, period_complete_day)
def _social_stats(self, start_date, end_date, period_name, period_complete_day):
""" Finds out which social sites people are referred from """
- results = self.service.data().ga().get(
- ids='ga:' + self.profile_id,
- start_date=start_date,
- metrics='ga:pageviews',
- sort='-ga:pageviews',
- dimensions="ga:socialNetwork,ga:referralPath",
- max_results=10000,
- end_date=end_date).execute()
+
+ try:
+ # Because of issues of invalid responses, we are going to make these requests
+