1 files changed, 43 insertions, 3 deletions
diff --git a/admin/stats/dump.py b/admin/stats/dump.py
index d0bdda3..ac412c9 100755
--- a/admin/stats/dump.py
+++ b/admin/stats/dump.py
@@ -10,7 +10,7 @@ from pathlib import Path
 import re
 from statistics import mean, median, stdev
 from sys import argv
-from urllib.parse import urlparse
+from urllib.parse import unquote, urlparse
 from typing import Dict, List, Tuple
 
 import user_agents
@@ -41,7 +41,7 @@ DOMAINS = {
 def normalize_path(p):
     if p == '/':
         return '/index.html'
-    return p
+    return unquote(p)
 
 
 @dataclass
@@ -165,6 +165,16 @@ def find_days(visits):
     }
 
 
+def find_pages(visitors):
+    return sorted({
+        access.resource
+        for v in visitors
+        for visit in v.visits
+        for access in visit
+        if v.useragent.is_human()
+    })
+
+
 def daily_visitors(visitors, output_path):
     days: Dict[datetime, Counter] = defaultdict(Counter)
     columns = ('mobile', 'tablet', 'pc', 'bot', 'n/a')
@@ -248,12 +258,42 @@ def daily_pages_per_visit(visitors, output_path):
             print(*values[:4], *(f'{v:.2f}' for v in values[4:]), sep='\t')
 
 
+def daily_page_hits(visitors, output_path):
+    days: Dict[datetime, Counter] = defaultdict(Counter)
+    columns = find_pages(visitors.values())
+
+    print('Page hits:')
+
+    for v in visitors.values():
+        if not v.useragent.is_human():
+            continue
+
+        for visit in v.visits:
+            day = datetime_day(visit[0].time)
+            for access in visit:
+                days[day][access.resource] += 1
+
+    with open(output_path, 'w') as f:
+        out = csv.writer(f)
+        out.writerow(('day', *columns))
+
+        for day in sorted(days):
+            page_hits = days[day]
+            values = (day.strftime('%F'),
+                      *(page_hits[page] for page in columns))
+            out.writerow(values)
+
+            print(day.strftime('%F'))
+            for page, hits in page_hits.most_common(5):
+                print(hits, page, sep='\t')
+
+
 def daily_stats(visitors, output_dir):
     output_dir = Path(output_dir)
     daily_visitors(visitors, output_dir.joinpath('dailyvisitors.csv'))
     daily_visits(visitors, output_dir.joinpath('dailyvisits.csv'))
     daily_pages_per_visit(visitors, output_dir.joinpath('dailypagespervisit.csv'))
-    # daily_page_hits(visitors, output_dir.joinpath('dailypagehits.csv'))
+    daily_page_hits(visitors, output_dir.joinpath('dailypagehits.csv'))
     # daily_referrers(visitors, output_dir.joinpath('dailyreferrers.csv'))