Script to parse page-requests.txt

humitos · humitos · commit 4c7d446375cb · 2020-06-19T12:10:07.000+02:00
diff --git a/scripts/pageviews.py b/scripts/pageviews.py
@@ -0,0 +1,18 @@
+from pprint import pprint
+
+results = {}
+
+# page-requests-20200504-20200510.txt
+# is a file containing stats from pageviews on the official Python documentation
+# (including different versions and languages)
+# grep -E '\.html$' page-requests-20200504-20200510.txt | grep -v tutorial | sed 's/3\..\///g' | sed 's/3\///g' | sed 's/2\///g' > pageviews.txt
+pages = open('pageviews.txt').readlines()[:-1]
+for p in pages:
+    count, key = int(p.split()[0]), p.split()[-1].strip()
+    if key in results:
+        results[key] += count
+    else:
+        results[key] = count
+
+for p in sorted(list(results.items()), key=lambda x: x[1], reverse=True)[50:100]:
+    print(p[1], p[0][1:])
