Remove port info from host names in CrUX crawler

InternetHealthReport · Feb 8, 2025 · a3f0959 · a3f0959
1 parent c6335c2
commit a3f0959
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/iyp/crawlers/google/crux_top1m_country.py b/iyp/crawlers/google/crux_top1m_country.py
@@ -88,8 +88,9 @@ def run(self):
                 # timeframe.
                 continue
 
-            # Extract hostname from "URLs"
-            df['hostname'] = df['origin'].str.partition('://')[2]
+            # Extract hostname from "URLs".
+            # Some origins contain ports information as well.
+            df['hostname'] = df['origin'].str.partition('://')[2].str.partition(':')[0]
 
             ranking_name = f'CrUX top 1M ({country_code})'