38 lines
1.0 KiB
SQL
38 lines
1.0 KiB
SQL
-- 统计等待爬取的数据条数 2023.12.25
|
|
SELECT 'comment' as wait_fetch, count(*) as `count` FROM `comment_progress` where current_status = 0
|
|
UNION ALL
|
|
SELECT 'album', count(*) FROM `wait_fetch_album`
|
|
UNION ALL
|
|
SELECT 'artist', count(*) FROM `wait_fetch_artist`
|
|
UNION ALL
|
|
SELECT 'lyric', count(*) FROM `wait_fetch_lyric`
|
|
|
|
-- 查看需要爬取的 comment 的分布
|
|
SELECT cast( FLOOR( song_id / 10000000 ) * 10000000 as UNSIGNED ) as s, count(*) as count
|
|
FROM comment_progress
|
|
WHERE current_status != 2
|
|
GROUP BY s
|
|
ORDER BY s DESC;
|
|
|
|
-- 查看需要爬取的 lyric 的分布
|
|
SELECT cast( FLOOR( id / 10000000 ) * 10000000 as UNSIGNED ) as s, count(*) as count
|
|
FROM wait_fetch_lyric
|
|
GROUP BY s
|
|
ORDER BY s DESC;
|
|
|
|
-- 查看需要爬取的 album 的分布
|
|
SELECT cast( FLOOR( id / 1000000 ) * 1000000 as UNSIGNED ) as s, count(*) as count
|
|
FROM wait_fetch_album
|
|
GROUP BY s
|
|
ORDER BY s DESC;
|
|
|
|
-- 查看需要爬取的 artist 的分布
|
|
SELECT cast( FLOOR(id / 1000000 ) * 1000000 as UNSIGNED ) as s, count(*) as count
|
|
FROM wait_fetch_artist
|
|
GROUP BY s
|
|
ORDER BY s DESC;
|
|
|
|
|
|
|
|
|