1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 | import re import csv import sys import logging import operator import collections from ckan.lib.base import (BaseController, c, g, render, request, response, abort) import sqlalchemy from sqlalchemy import func, cast, Integer import ckan.model as model from ga_model import GA_Url, GA_Stat, GA_ReferralStat, GA_Publisher log = logging.getLogger('ckanext.ga-report') def _get_month_name(strdate): import calendar from time import strptime d = strptime(strdate, '%Y-%m') return '%s %s' % (calendar.month_name[d.tm_mon], d.tm_year) def _month_details(cls): '''Returns a list of all the month names''' months = [] vals = model.Session.query(cls.period_name).filter(cls.period_name!='All').distinct().all() for m in vals: months.append( (m[0], _get_month_name(m[0]))) return sorted(months, key=operator.itemgetter(0), reverse=True) class GaReport(BaseController): def csv(self, month): import csv q = model.Session.query(GA_Stat) if month != 'all': q = q.filter(GA_Stat.period_name==month) 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-Disposition'] = str('attachment; filename=stats_%s.csv' % (month,)) writer = csv.writer(response) writer.writerow(["Period", "Statistic", "Key", "Value"]) for entry in entries: writer.writerow([entry.period_name.encode('utf-8'), entry.stat_name.encode('utf-8'), entry.key.encode('utf-8'), entry.value.encode('utf-8')]) def index(self): # Get the month details by fetching distinct values and determining the # month names from the values. c.months = _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]) q = model.Session.query(GA_Stat).\ filter(GA_Stat.stat_name=='Totals') if c.month: q = q.filter(GA_Stat.period_name==c.month) entries = q.order_by('ga_stat.key').all() def clean_key(key, val): if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounce rate (home page)']: val = "%.2f" % round(float(val), 2) if key == 'Average time on site': mins, secs = divmod(float(val), 60) hours, mins = divmod(mins, 60) val = '%02d:%02d:%02d (%s seconds) ' % (hours, mins, secs, val) if key in ['New visits','Bounce rate (home page)']: val = "%s%%" % val if key in ['Total page views', 'Total visits']: val = int(val) return key, val c.global_totals = [] if c.month: for e in entries: key, val = clean_key(e.key, e.value) c.global_totals.append((key, val)) else: d = collections.defaultdict(list) for e in entries: d[e.key].append(float(e.value)) for k, v in d.iteritems(): if k in ['Total page views', 'Total visits']: v = sum(v) else: v = float(sum(v))/len(v) key, val = clean_key(k,v) c.global_totals.append((key, val)) c.global_totals = sorted(c.global_totals, key=operator.itemgetter(0)) keys = { 'Browser versions': 'browser_versions', 'Browsers': 'browsers', 'Operating Systems versions': 'os_versions', 'Operating Systems': 'os', 'Social sources': 'social_networks', 'Languages': 'languages', 'Country': 'country' } 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(): q = model.Session.query(GA_Stat).\ filter(GA_Stat.stat_name==k) 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) entries = [] for key, val in d.iteritems(): entries.append((key,val,)) entries = sorted(entries, key=operator.itemgetter(1), reverse=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']) 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') class GaDatasetReport(BaseController): """ Displays the pageview and visit count for datasets with options to filter by publisher and time period. """ def publisher_csv(self, month): ''' 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-Disposition'] = str('attachment; filename=publishers_%s.csv' % (month,)) writer = csv.writer(response) writer.writerow(["Publisher Title", "Publisher Name", "Views", "Visits", "Period Name"]) for publisher,view,visit in _get_top_publishers(None): writer.writerow([publisher.title.encode('utf-8'), publisher.name.encode('utf-8'), view, visit, month]) def dataset_csv(self, id='all', month='all'): ''' Returns a CSV with the number of views & visits for each dataset. :param id: A Publisher ID or None if you want for all :param month: The time period, or 'all' ''' 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) response.headers['Content-Type'] = "text/csv; charset=utf-8" response.headers['Content-Disposition'] = \ str('attachment; filename=datasets_%s_%s.csv' % (c.publisher_name, month,)) writer = csv.writer(response) writer.writerow(["Dataset Title", "Dataset Name", "Views", "Visits", "Period Name"]) for package,view,visit in packages: writer.writerow([package.title.encode('utf-8'), package.name.encode('utf-8'), view, visit, month]) def publishers(self): '''A list of publishers and the number of views/visits for each''' # Get the month details by fetching distinct values and determining the # month names from the values. c.months = _month_details(GA_Url) # Work out which month to show, based on query params of the first item c.month = request.params.get('month', '') c.month_desc = 'all months' if c.month: 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): '''Returns the datasets in order of visits''' if count == -1: count = sys.maxint month = c.month or 'All' q = model.Session.query(GA_Url,model.Package)\ .filter(model.Package.name==GA_Url.package_id)\ .filter(GA_Url.url.like('/dataset/%')) if publisher: q = q.filter(GA_Url.department_id==publisher.name) q = q.filter(GA_Url.period_name==month) q = q.order_by('ga_url.visits::int desc') top_packages = [] for entry,package in q.limit(count): if package: top_packages.append((package, entry.pageviews, entry.visits)) else: log.warning('Could not find package associated package') return top_packages def read(self): ''' Lists the most popular datasets across all publishers ''' return self.read_publisher(None) def read_publisher(self, id): ''' Lists the most popular datasets for a publisher (or across all publishers) ''' count = 20 c.publishers = _get_publishers() id = request.params.get('publisher', id) if id and id != 'all': c.publisher = model.Group.get(id) if not c.publisher: abort(404, 'A publisher with that name could not be found') c.publisher_name = c.publisher.name c.top_packages = [] # package, dataset_views in c.top_packages # Get the month details by fetching distinct values and determining the # month names from the values. c.months = _month_details(GA_Url) # Work out which month to show, based on query params of the first item c.month = request.params.get('month', '') if not c.month: c.month_desc = 'all months' else: c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month]) month = c.month or 'All' c.publisher_page_views = 0 q = model.Session.query(GA_Url).\ filter(GA_Url.url=='/publisher/%s' % c.publisher_name) 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) return render('ga_report/publisher/read.html') def _get_top_publishers(limit=20): ''' Returns a list of the top 20 publishers by dataset visits. (The number to show can be varied with 'limit') ''' month = c.month or 'All' connection = model.Session.connection() q = """ select department_id, sum(pageviews::int) views, sum(visits::int) visits from ga_url where department_id <> '' and package_id <> '' and url like '/dataset/%%' and period_name=%s group by department_id order by views desc """ if limit: q = q + " limit %s;" % (limit) top_publishers = [] res = connection.execute(q, month) for row in res: g = model.Group.get(row[0]) if g: top_publishers.append((g, row[1], row[2])) return top_publishers def _get_publishers(): ''' Returns a list of all publishers. Each item is a tuple: (names, title) ''' publishers = [] for pub in model.Session.query(model.Group).\ filter(model.Group.type=='publisher').\ filter(model.Group.state=='active').\ order_by(model.Group.name): publishers.append((pub.name, pub.title)) return publishers def _percent(num, total): p = 100 * float(num)/float |