Remove unnecessary footnote marker (*)
[ckanext-ga-report.git] / ckanext / ga_report / controller.py
blob:a/ckanext/ga_report/controller.py -> blob:b/ckanext/ga_report/controller.py
import re import re
import csv import csv
import sys import sys
import logging import logging
import operator import operator
import collections import collections
from ckan.lib.base import BaseController, c, render, request, response, abort from ckan.lib.base import (BaseController, c, g, render, request, response, abort)
   
import sqlalchemy import sqlalchemy
from sqlalchemy import func, cast, Integer from sqlalchemy import func, cast, Integer
import ckan.model as model import ckan.model as model
from ga_model import GA_Url, GA_Stat from ga_model import GA_Url, GA_Stat, GA_ReferralStat, GA_Publisher
   
log = logging.getLogger('ckanext.ga-report') log = logging.getLogger('ckanext.ga-report')
   
   
def _get_month_name(strdate): def _get_month_name(strdate):
import calendar import calendar
from time import strptime from time import strptime
d = strptime(strdate, '%Y-%m') d = strptime(strdate, '%Y-%m')
return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year)
   
   
def _month_details(cls): def _month_details(cls):
  '''
  Returns a list of all the periods for which we have data, unfortunately
  knows too much about the type of the cls being passed as GA_Url has a
  more complex query
   
  This may need extending if we add a period_name to the stats
  '''
months = [] months = []
vals = model.Session.query(cls.period_name).distinct().all() day = None
   
  vals = model.Session.query(cls.period_name,cls.period_complete_day)\
  .filter(cls.period_name!='All').distinct(cls.period_name)\
  .order_by("period_name desc").all()
  if vals and vals[0][1]:
  day = int(vals[0][1])
  ordinal = 'th' if 11 <= day <= 13 \
  else {1:'st',2:'nd',3:'rd'}.get(day % 10, 'th')
  day = "{day}{ordinal}".format(day=day, ordinal=ordinal)
   
for m in vals: for m in vals:
months.append( (m[0], _get_month_name(m[0]))) months.append( (m[0], _get_month_name(m[0])))
return sorted(months, key=operator.itemgetter(0), reverse=True)  
  return months, day
   
   
class GaReport(BaseController): class GaReport(BaseController):
   
def csv(self, month): def csv(self, month):
import csv import csv
   
q = model.Session.query(GA_Stat) q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name!='Downloads')
if month != 'all': if month != 'all':
q = q.filter(GA_Stat.period_name==month) q = q.filter(GA_Stat.period_name==month)
entries = q.order_by('GA_Stat.period_name, GA_Stat.stat_name, GA_Stat.key').all() entries = q.order_by('GA_Stat.period_name, GA_Stat.stat_name, GA_Stat.key').all()
   
response.headers['Content-Type'] = "text/csv; charset=utf-8" response.headers['Content-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = str('attachment; filename=stats_%s.csv' % (month,)) response.headers['Content-Disposition'] = str('attachment; filename=stats_%s.csv' % (month,))
   
writer = csv.writer(response) writer = csv.writer(response)
writer.writerow(["Period", "Statistic", "Key", "Value"]) writer.writerow(["Period", "Statistic", "Key", "Value"])
   
for entry in entries: for entry in entries:
writer.writerow([entry.period_name.encode('utf-8'), writer.writerow([entry.period_name.encode('utf-8'),
entry.stat_name.encode('utf-8'), entry.stat_name.encode('utf-8'),
entry.key.encode('utf-8'), entry.key.encode('utf-8'),
entry.value.encode('utf-8')]) entry.value.encode('utf-8')])
   
  def csv_downloads(self, month):
  import csv
   
  q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name=='Downloads')
  if month != 'all':
  q = q.filter(GA_Stat.period_name==month)
  entries = q.order_by('GA_Stat.period_name, GA_Stat.key').all()
   
  response.headers['Content-Type'] = "text/csv; charset=utf-8"
  response.headers['Content-Disposition'] = str('attachment; filename=downloads_%s.csv' % (month,))
   
  writer = csv.writer(response)
  writer.writerow(["Period", "Resource URL", "Count"])
   
  for entry in entries:
  writer.writerow([entry.period_name.encode('utf-8'),
  entry.key.encode('utf-8'),
  entry.value.encode('utf-8')])
   
   
def index(self): def index(self):
   
# Get the month details by fetching distinct values and determining the # Get the month details by fetching distinct values and determining the
# month names from the values. # month names from the values.
c.months = _month_details(GA_Stat) c.months, c.day = _month_details(GA_Stat)
   
# Work out which month to show, based on query params of the first item # Work out which month to show, based on query params of the first item
c.month_desc = 'all time' c.month_desc = 'all months'
c.month = request.params.get('month', '') c.month = request.params.get('month', '')
if c.month: if c.month:
c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
   
q = model.Session.query(GA_Stat).\ q = model.Session.query(GA_Stat).\
filter(GA_Stat.stat_name=='Totals') filter(GA_Stat.stat_name=='Totals')
if c.month: if c.month:
q = q.filter(GA_Stat.period_name==c.month) q = q.filter(GA_Stat.period_name==c.month)
entries = q.order_by('ga_stat.key').all() entries = q.order_by('ga_stat.key').all()
   
def clean_key(key, val): def clean_key(key, val):
if key in ['Average time on site', 'Pages per visit', 'Percent new visits']: if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounce rate (home page)']:
val = "%.2f" % round(float(val), 2) val = "%.2f" % round(float(val), 2)
if key == 'Average time on site': if key == 'Average time on site':
mins, secs = divmod(float(val), 60) mins, secs = divmod(float(val), 60)
hours, mins = divmod(mins, 60) hours, mins = divmod(mins, 60)
val = '%02d:%02d:%02d (%s seconds) ' % (hours, mins, secs, val) val = '%02d:%02d:%02d (%s seconds) ' % (hours, mins, secs, val)
if key in ['Bounces', 'Total pageviews']: if key in ['New visits','Bounce rate (home page)']:
  val = "%s%%" % val
  if key in ['Total page views', 'Total visits']:
val = int(val) val = int(val)
   
return key, val return key, val
   
c.global_totals = [] c.global_totals = []
if c.month: if c.month:
for e in entries: for e in entries:
key, val = clean_key(e.key, e.value) key, val = clean_key(e.key, e.value)
c.global_totals.append((key, val)) c.global_totals.append((key, val))
else: else:
d = collections.defaultdict(list) d = collections.defaultdict(list)
for e in entries: for e in entries:
d[e.key].append(float(e.value)) d[e.key].append(float(e.value))
for k, v in d.iteritems(): for k, v in d.iteritems():
if k in ['Bounces', 'Total pageviews']: if k in ['Total page views', 'Total visits']:
v = sum(v) v = sum(v)
else: else:
v = float(sum(v))/len(v) v = float(sum(v))/float(len(v))
key, val = clean_key(k,v) key, val = clean_key(k,v)
   
c.global_totals.append((key, val)) c.global_totals.append((key, val))
c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0)) c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0))
   
keys = { keys = {
'Browser versions': 'browsers', 'Browser versions': 'browser_versions',
'Operating Systems versions': 'os', 'Browsers': 'browsers',
  'Operating Systems versions': 'os_versions',
  'Operating Systems': 'os',
'Social sources': 'social_networks', 'Social sources': 'social_networks',
'Languages': 'languages', 'Languages': 'languages',
'Country': 'country' 'Country': 'country'
} }
   
browser_version_re = re.compile("(.*)\((.*)\)") def shorten_name(name, length=60):
  return (name[:length] + '..') if len(name) > 60 else name
   
  def fill_out_url(url):
  import urlparse
  return urlparse.urljoin(g.site_url, url)
   
  c.social_referrer_totals, c.social_referrers = [], []
  q = model.Session.query(GA_ReferralStat)
  q = q.filter(GA_ReferralStat.period_name==c.month) if c.month else q
  q = q.order_by('ga_referrer.count::int desc')
  for entry in q.all():
  c.social_referrers.append((shorten_name(entry.url), fill_out_url(entry.url),
  entry.source,entry.count))
   
  q = model.Session.query(GA_ReferralStat.url,
  func.sum(GA_ReferralStat.count).label('count'))
  q = q.filter(GA_ReferralStat.period_name==c.month) if c.month else q
  q = q.order_by('count desc').group_by(GA_ReferralStat.url)
  for entry in q.all():
  c.social_referrer_totals.append((shorten_name(entry[0]), fill_out_url(entry[0]),'',
  entry[1]))
   
for k, v in keys.iteritems(): for k, v in keys.iteritems():
   
def clean_field(key):  
if k != 'Browser versions':  
return key  
m = browser_version_re.match(key)  
browser = m.groups()[0].strip()  
ver = m.groups()[1]  
parts = ver.split('.')  
if len(parts) > 1:  
if parts[1][0] == '0':  
ver = parts[0]  
else:  
ver = "%s.%s" % (parts[0],parts[1])  
if browser in ['Safari','Android Browser']: # Special case complex version nums  
ver = parts[0]  
if len(ver) > 2:  
ver = "%s%sX" % (ver[0], ver[1])  
   
return "%s (%s)" % (browser, ver,)  
   
q = model.Session.query(GA_Stat).\ q = model.Session.query(GA_Stat).\
filter(GA_Stat.stat_name==k) filter(GA_Stat.stat_name==k)
if c.month: if c.month:
entries = [] entries = []
q = q.filter(GA_Stat.period_name==c.month).\ q = q.filter(GA_Stat.period_name==c.month).\
order_by('ga_stat.value::int desc') order_by('ga_stat.value::int desc')
   
d = collections.defaultdict(int) d = collections.defaultdict(int)
for e in q.all(): for e in q.all():
d[clean_field(e.key)] += int(e.value) d[e.key] += int(e.value)
entries = [] entries = []
for key, val in d.iteritems(): for key, val in d.iteritems():
entries.append((key,val,)) entries.append((key,val,))
entries = sorted(entries, key=operator.itemgetter(1), reverse=True) entries = sorted(entries, key=operator.itemgetter(1), reverse=True)
   
setattr(c, v, [(k,v) for k,v in entries ]) # 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'])
  else:
  total = sum([num for _,num in entries])
  setattr(c, v, [(k,_percent(v,total)) for k,v in entries ])
   
return render('ga_report/site/index.html') return render('ga_report/site/index.html')
   
  def downloads(self):
class GaPublisherReport(BaseController):  
  # Get the month details by fetching distinct values and determining the
  # month names from the values.
  c.months, c.day = _month_details(GA_Stat)
   
  # Work out which month to show, based on query params of the first item
  c.month_desc = 'all months'
  c.month = request.params.get('month', '')
  if c.month:
  c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
   
  c.downloads = []
  q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name=='Downloads')
  q = q.filter(GA_Stat.period_name==c.month) if c.month else q
  q = q.order_by("ga_stat.value::int desc")
   
  for entry in q.all():
  print entry.key
  r = model.Session.query(model.Resource).filter(model.Resource.url==entry.key).first()
  if r:
  c.downloads.append((r,entry.value))
  else:
  log.info("Failed to find resource for %s" % entry.key)
   
  return render('ga_report/site/downloads.html')
   
   
  class GaDatasetReport(BaseController):
""" """
Displays the pageview and visit count for specific publishers based on Displays the pageview and visit count for datasets
the datasets associated with the publisher. with options to filter by publisher and time period.
""" """
def csv(self, month): def publisher_csv(self, month):
  '''
c.month = month if not month =='all' else '' Returns a CSV of each publisher with the total number of dataset
  views & visits.
  '''
  c.month = month if not month == 'all' else ''
response.headers['Content-Type'] = "text/csv; charset=utf-8" response.headers['Content-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = str('attachment; filename=publishers_%s.csv' % (month,)) response.headers['Content-Disposition'] = str('attachment; filename=publishers_%s.csv' % (month,))
   
writer = csv.writer(response) writer = csv.writer(response)
writer.writerow(["Publisher", "Views", "Visits", "Period Name"]) writer.writerow(["Publisher Title", "Publisher Name", "Views", "Visits", "Period Name"])
   
for publisher,view,visit in self._get_publishers(None): for publisher,view,visit in _get_top_publishers(None):
writer.writerow([publisher.title.encode('utf-8'), writer.writerow([publisher.title.encode('utf-8'),
  publisher.name.encode('utf-8'),
view, view,
visit, visit,
month]) month])
   
  def dataset_csv(self, id='all', month='all'):
  '''
def publisher_csv(self, id, month): Returns a CSV with the number of views & visits for each dataset.
   
c.month = month if not month =='all' else '' :param id: A Publisher ID or None if you want for all
c.publisher = model.Group.get(id) :param month: The time period, or 'all'
if not c.publisher: '''
abort(404, 'A publisher with that name could not be found') c.month = month if not month == 'all' else ''
  if id != 'all':
  c.publisher = model.Group.get(id)
  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(c.publisher)
response.headers['Content-Type'] = "text/csv; charset=utf-8" response.headers['Content-Type'] = "text/csv; charset=utf-8"
response.headers['Content-Disposition'] = \ response.headers['Content-Disposition'] = \
str('attachment; filename=%s_%s.csv' % (c.publisher.name, month,)) str('attachment; filename=datasets_%s_%s.csv' % (c.publisher_name, month,))
   
writer = csv.writer(response) writer = csv.writer(response)
writer.writerow(["Publisher", "Views", "Visits", "Period Name"]) writer.writerow(["Dataset Title", "Dataset Name", "Views", "Visits", "Period Name"])
   
for package,view,visit in packages: for package,view,visit in packages:
writer.writerow([package.title.encode('utf-8'), writer.writerow([package.title.encode('utf-8'),
  package.name.encode('utf-8'),
view, view,
visit, visit,
month]) month])
   
  def publishers(self):
  '''A list of publishers and the number of views/visits for each'''
def index(self):  
   
# Get the month details by fetching distinct values and determining the # Get the month details by fetching distinct values and determining the
# month names from the values. # month names from the values.
c.months = _month_details(GA_Url) c.months, c.day = _month_details(GA_Url)
   
# Work out which month to show, based on query params of the first item # Work out which month to show, based on query params of the first item
c.month = request.params.get('month', '') c.month = request.params.get('month', '')
c.month_desc = 'all time' c.month_desc = 'all months'
if c.month: if c.month:
c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
   
c.top_publishers = self._get_publishers() c.top_publishers = _get_top_publishers()
   
return render('ga_report/publisher/index.html') return render('ga_report/publisher/index.html')
   
def _get_publishers(self, limit=20): def _get_packages(self, publisher=None, count=-1):
connection = model.Session.connection() '''Returns the datasets in order of views'''
q = """  
select department_id, sum(pageviews::int) views, sum(visitors::int) visits  
from ga_url  
where department_id <> ''"""  
if c.month:  
q = q + """  
and period_name=%s  
"""  
q = q + """  
group by department_id order by views desc  
"""  
if limit:  
q = q + " limit %s;" % (limit)  
   
# Add this back (before and period_name =%s) if you want to ignore publisher