coder-xiaomo/tools
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity GitHub Gitee

netease_music 临时脚本暂存

Browse Source
This commit is contained in:
小墨
2023-12-30 01:10:07 +08:00
parent e2a092be3c
commit f72dad74c3
5 changed files with 290 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
netease_music/manual-script/# 统计SQL(临时).sql Normal file
View File

@@ -0,0 +1,37 @@
-- 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;