| import logging | import logging |
| import operator | import operator |
| import ckan.lib.base as base | import ckan.lib.base as base |
| import ckan.model as model | import ckan.model as model |
| from ckanext.ga_report.ga_model import GA_Url, GA_Publisher | |
| from ckanext.ga_report.controller import _get_publishers | |
| _log = logging.getLogger(__name__) | _log = logging.getLogger(__name__) |
| def popular_datasets(count=10): | |
| import random | |
| publisher = None | |
| publishers = _get_publishers(30) | |
| total = len(publishers) | |
| while not publisher or not datasets: | |
| rand = random.randrange(0, total) | |
| publisher = publishers[rand][0] | |
| if not publisher.state == 'active': | |
| publisher = None | |
| continue | |
| datasets = _datasets_for_publisher(publisher, 10)[:count] | |
| ctx = { | |
| 'datasets': datasets, | |
| 'publisher': publisher | |
| } | |
| return base.render_snippet('ga_report/ga_popular_datasets.html', **ctx) | |
| def most_popular_datasets(publisher, count=20): | def most_popular_datasets(publisher, count=20): |
| from ckanext.ga_report.ga_model import GA_Url | |
| if not publisher: | if not publisher: |
| _log.error("No valid publisher passed to 'most_popular_datasets'") | _log.error("No valid publisher passed to 'most_popular_datasets'") |
| return "" | return "" |
| results = _datasets_for_publisher(publisher, count) | |
| ctx = { | |
| 'dataset_count': len(datasets), | |
| 'datasets': results, | |
| 'publisher': publisher | |
| } | |
| return base.render_snippet('ga_report/publisher/popular.html', **ctx) | |
| def _datasets_for_publisher(publisher, count): | |
| datasets = {} | datasets = {} |
| entries = model.Session.query(GA_Url).\ | entries = model.Session.query(GA_Url).\ |
| filter(GA_Url.department_id==publisher.name).\ | filter(GA_Url.department_id==publisher.name).\ |
| filter(GA_Url.url.like('/dataset/%')).\ | filter(GA_Url.url.like('/dataset/%')).\ |
| order_by('ga_url.pageviews::int desc').all() | order_by('ga_url.pageviews::int desc').all() |
| for entry in entries: | for entry in entries: |
| if len(datasets) < count: | if len(datasets) < count: |
| p = model.Package.get(entry.url[len('/dataset/'):]) | p = model.Package.get(entry.url[len('/dataset/'):]) |
| if not p in datasets: | if not p in datasets: |
| datasets[p] = {'views':0, 'visits': 0} | datasets[p] = {'views':0, 'visits': 0} |
| datasets[p]['views'] = datasets[p]['views'] + int(entry.pageviews) | datasets[p]['views'] = datasets[p]['views'] + int(entry.pageviews) |
| datasets[p]['visits'] = datasets[p]['visits'] + int(entry.visitors) | datasets[p]['visits'] = datasets[p]['visits'] + int(entry.visitors) |
| results = [] | results = [] |
| for k, v in datasets.iteritems(): | for k, v in datasets.iteritems(): |
| results.append((k,v['views'],v['visits'])) | results.append((k,v['views'],v['visits'])) |
| results = sorted(results, key=operator.itemgetter(1), reverse=True) | return sorted(results, key=operator.itemgetter(1), reverse=True) |
| ctx = { | |
| 'dataset_count': len(datasets), | |
| 'datasets': results, | |
| 'publisher': publisher | |
| } | |
| return base.render_snippet('ga_report/publisher/popular.html', **ctx) | |