SELECT-- 成员iddistinct_idASmember_id,-- 浏览时长get_json_object(all_json,'$.properties.event_duration')ASbrow_duration,-- 浏览退出时间from_unixtime(CAST(get_json_object(all_json,'$.time')ASDOUBLE)/1000)ASout_time,-- 内容编号regexp_extract(get_json_object(all_json,'$.properties.$url_query'),'id=([^&]*)',1)ASnumberFROM{args['TABLE_NAME']}WHEREevent='$MPPageLeave'ANDLENGTH(distinct_id)<30ANDget_json_object(all_json,'$.time')isnotnullANDget_json_object(all_json,'$.properties.$url_query')isnotnullANDregexp_extract(get_json_object(all_json,'$.properties.$url_query'),'id=([^&]*)',1)isnotnullANDTRIM(regexp_extract(get_json_object(all_json,'$.properties.$url_query'),'id=([^&]*)',1))!=''ANDcreated_at>=unix_timestamp('2026-01-20 00:00:00')ANDcreated_at<unix_timestamp('2026-01-21 00:00:00');参考
- pyspark.sql.functions.unix_timestamp