Athena 使用
资源
资源名称
作用




image-20230422235016151 
image-20230423111834746 
image-20230423112002481 
image-20230423112428019
参考
Last updated







Last updated
create database s3_access_logs_dbCREATE EXTERNAL TABLE IF NOT EXISTS s3_access_logs_db.mybucket_logs(
BucketOwner STRING,
Bucket STRING,
RequestDateTime STRING,
RemoteIP STRING,
Requester STRING,
RequestID STRING,
Operation STRING,
Key STRING,
RequestURI_operation STRING,
RequestURI_key STRING,
RequestURI_httpProtoversion STRING,
HTTPstatus STRING,
ErrorCode STRING,
BytesSent BIGINT,
ObjectSize BIGINT,
TotalTime STRING,
TurnAroundTime STRING,
Referrer STRING,
UserAgent STRING,
VersionId STRING,
HostId STRING,
SigV STRING,
CipherSuite STRING,
AuthType STRING,
EndPoint STRING,
TLSVersion STRING
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
'serialization.format' = '1', 'input.regex' = '([^ ]*) ([^ ]*) \\[(.*?)\\] ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) \\\"([^ ]*) ([^ ]*) (- |[^ ]*)\\\" (-|[0-9]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) (\"[^\"]*\") ([^ ]*)(?: ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*) ([^ ]*))?.*$' )
LOCATION 's3://s3-service-access-loging/';SELECT requesturi_operation, httpstatus, count(*)
FROM "s3_access_logs_db"."mybucket_logs"
GROUP BY requesturi_operation, httpstatus;SELECT * FROM "s3_access_logs_db"."mybucket_logs"
where httpstatus='403';