Skip to content

Commit 12c22ca

Browse files
jcmpagelchristianliebel
authored andcommitted
Add SQL query for .ai domain ranking analysis
1 parent 79ebcc2 commit 12c22ca

1 file changed

Lines changed: 45 additions & 0 deletions

File tree

sql/2025/generative-ai/ai_tld.sql

Lines changed: 45 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
#standardSQL
2+
# .ai domains per exclusive rank bucket, 2022 vs 2025
3+
4+
WITH base AS (
5+
SELECT
6+
date,
7+
client,
8+
rank,
9+
NET.HOST(page) AS host
10+
FROM
11+
`httparchive.crawl.pages`
12+
WHERE
13+
is_root_page
14+
AND client IN ('desktop', 'mobile')
15+
AND date IN ('2022-06-01', '2025-07-01')
16+
AND rank <= 10000000
17+
AND ENDS_WITH(NET.HOST(page), '.ai')
18+
),
19+
20+
bucketed AS (
21+
SELECT
22+
date,
23+
client,
24+
CASE
25+
WHEN rank <= 1000 THEN 1000
26+
WHEN rank <= 10000 THEN 10000
27+
WHEN rank <= 100000 THEN 100000
28+
WHEN rank <= 1000000 THEN 1000000
29+
WHEN rank <= 10000000 THEN 10000000
30+
END AS rank_bucket,
31+
host
32+
FROM base
33+
)
34+
35+
SELECT
36+
date,
37+
client,
38+
rank_bucket,
39+
COUNT(DISTINCT host) AS ai_domains
40+
FROM
41+
bucketed
42+
GROUP BY
43+
date, client, rank_bucket
44+
ORDER BY
45+
date, client, rank_bucket;

0 commit comments

Comments
 (0)