| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133 |
- #!/usr/bin/env python3
- # coding=utf-8
- """单用户实时行为时间线:当前可用实时/5分钟日志。"""
- import argparse
- from datetime import datetime
- from pathlib import Path
- import pandas as pd
- from odps_module import ODPSClient
- from user_timeline import EXCLUDED_BUSINESSTYPES, add_device_info, behavior_definition, build_apptype_filter, safe_name, sql_text
- SQL_REALTIME = """
- WITH v AS (
- SELECT CAST(clienttimestamp AS BIGINT) AS ts, apptype AS 产品apptype, 'video' AS 来源,
- businesstype, CAST(NULL AS STRING) AS eventid, machineinfo_system AS 系统, pagesource, CAST(NULL AS STRING) AS endRoutePath, CAST(NULL AS STRING) AS objecttype, videoid AS 视频id,
- CAST(NULL AS STRING) AS topic, CAST(NULL AS STRING) AS shareid, CAST(NULL AS STRING) AS creativeCode,
- CAST(NULL AS STRING) AS rootPageSource, CAST(NULL AS STRING) AS objectId, CAST(NULL AS STRING) AS targetUid,
- CAST(NULL AS STRING) AS networkType, CAST(NULL AS STRING) AS operationOptions, CAST(NULL AS STRING) AS operationExtParams,
- CAST(NULL AS STRING) AS hotsencetype, CAST(NULL AS STRING) AS path, subsessionid, sessionid
- FROM loghubods.video_action_log_per5min
- WHERE dt >= '{dt_start}' AND dt <= '{dt_end}'{apptype_filter} AND mid='{mc}'
- AND businesstype <> 'videoPreView' AND clienttimestamp IS NOT NULL AND clienttimestamp<>''
- ),
- a AS (
- SELECT CAST(clienttimestamp AS BIGINT) AS ts, apptype AS 产品apptype, 'ad' AS 来源,
- businesstype, eventid, GET_JSON_OBJECT(machineinfo, '$.system') AS 系统, pagesource, CAST(NULL AS STRING) AS endRoutePath, CAST(NULL AS STRING) AS objecttype, headvideoid AS 视频id,
- CAST(NULL AS STRING) AS topic, CAST(NULL AS STRING) AS shareid, creativecode AS creativeCode,
- CAST(NULL AS STRING) AS rootPageSource, CAST(NULL AS STRING) AS objectId, CAST(NULL AS STRING) AS targetUid,
- CAST(NULL AS STRING) AS networkType, CAST(NULL AS STRING) AS operationOptions, CAST(NULL AS STRING) AS operationExtParams,
- hotsencetype, CAST(NULL AS STRING) AS path, subsessionid, sessionid
- FROM loghubods.ad_action_log_own_per5min
- WHERE dt >= '{dt_start}' AND dt <= '{dt_end}'{apptype_filter} AND machinecode='{mc}'
- AND clienttimestamp IS NOT NULL AND clienttimestamp<>''
- ),
- p AS (
- SELECT CAST(clienttimestamp AS BIGINT) AS ts, apptype AS 产品apptype, 'play' AS 来源,
- businesstype, eventid, machineinfo_system AS 系统, pagesource, CAST(NULL AS STRING) AS endRoutePath, CAST(NULL AS STRING) AS objecttype, videoid AS 视频id,
- CAST(NULL AS STRING) AS topic, CAST(NULL AS STRING) AS shareid, CAST(NULL AS STRING) AS creativeCode,
- CAST(NULL AS STRING) AS rootPageSource, CAST(NULL AS STRING) AS objectId, CAST(NULL AS STRING) AS targetUid,
- CAST(NULL AS STRING) AS networkType, CAST(NULL AS STRING) AS operationOptions, CAST(NULL AS STRING) AS operationExtParams,
- CAST(NULL AS STRING) AS hotsencetype, CAST(NULL AS STRING) AS path, subsessionid, sessionid
- FROM loghubods.video_play_log_per5min
- WHERE dt >= '{dt_start}' AND dt <= '{dt_end}'{apptype_filter} AND mid='{mc}'
- AND clienttimestamp IS NOT NULL AND clienttimestamp<>''
- ),
- s AS (
- SELECT CAST(clienttimestamp AS BIGINT) AS ts, apptype AS 产品apptype, 'simpleevent' AS 来源,
- businesstype, eventid, system AS 系统, pagesource, CAST(NULL AS STRING) AS endRoutePath, objecttype, videoid AS 视频id,
- CAST(NULL AS STRING) AS topic, CAST(NULL AS STRING) AS shareid, CAST(NULL AS STRING) AS creativeCode,
- CAST(NULL AS STRING) AS rootPageSource, CAST(NULL AS STRING) AS objectId, CAST(NULL AS STRING) AS targetUid,
- CAST(NULL AS STRING) AS networkType, CAST(NULL AS STRING) AS operationOptions, CAST(NULL AS STRING) AS operationExtParams,
- CAST(NULL AS STRING) AS hotsencetype, CAST(NULL AS STRING) AS path, subsessionid, sessionid
- FROM loghubods.simpleevent_log_flow
- WHERE year='{year}' AND month='{month}' AND day='{day_of_month}'{apptype_filter} AND machinecode='{mc}'
- AND (businesstype IS NULL OR businesstype <> 'openGIdError') AND clienttimestamp IS NOT NULL AND clienttimestamp<>''
- ),
- u AS (
- SELECT CAST(clienttimestamp AS BIGINT) AS ts, apptype AS 产品apptype, 'useractive' AS 来源,
- businesstype, eventid, system AS 系统, pagesource, CAST(NULL AS STRING) AS endRoutePath, CAST(NULL AS STRING) AS objecttype, CAST(NULL AS STRING) AS 视频id,
- CAST(NULL AS STRING) AS topic, CAST(NULL AS STRING) AS shareid, CAST(NULL AS STRING) AS creativeCode,
- CAST(NULL AS STRING) AS rootPageSource, CAST(NULL AS STRING) AS objectId, CAST(NULL AS STRING) AS targetUid,
- CAST(NULL AS STRING) AS networkType, CAST(NULL AS STRING) AS operationOptions, CAST(NULL AS STRING) AS operationExtParams,
- CAST(NULL AS STRING) AS hotsencetype, path, subsessionid, sessionid
- FROM loghubods.useractive_log_per5min
- WHERE dt >= '{dt_start}' AND dt <= '{dt_end}'{apptype_filter} AND machinecode='{mc}'
- AND clienttimestamp IS NOT NULL AND clienttimestamp<>''
- ),
- r AS (
- SELECT CAST(clienttimestamp AS BIGINT) AS ts, apptype AS 产品apptype, 'share' AS 来源,
- type AS businesstype, eventid, CAST(NULL AS STRING) AS 系统, pagesource, CAST(NULL AS STRING) AS endRoutePath, CAST(NULL AS STRING) AS objecttype, CAST(NULL AS STRING) AS 视频id,
- topic, shareid, CAST(NULL AS STRING) AS creativeCode,
- rootpagesource AS rootPageSource, shareobjectid AS objectId, CAST(NULL AS STRING) AS targetUid,
- CAST(NULL AS STRING) AS networkType, CAST(NULL AS STRING) AS operationOptions, CAST(NULL AS STRING) AS operationExtParams,
- CAST(NULL AS STRING) AS hotsencetype, CAST(NULL AS STRING) AS path, subsessionid, sessionid
- FROM loghubods.user_share_log_per5min
- WHERE dt >= '{dt_start}' AND dt <= '{dt_end}'{apptype_filter} AND machinecode='{mc}'
- AND clienttimestamp IS NOT NULL AND clienttimestamp<>''
- ),
- o AS (
- SELECT CAST(clienttimestamp AS BIGINT) AS ts, apptype AS 产品apptype, 'operation' AS 来源,
- CAST(NULL AS STRING) AS businesstype, eventid, machineinfo_system AS 系统, pagesource, CAST(NULL AS STRING) AS endRoutePath, CAST(NULL AS STRING) AS objecttype, CAST(NULL AS STRING) AS 视频id,
- CAST(NULL AS STRING) AS topic, CAST(NULL AS STRING) AS shareid, CAST(NULL AS STRING) AS creativeCode,
- rootpagesource AS rootPageSource, objectid AS objectId, targetuid AS targetUid,
- networktype AS networkType, options AS operationOptions, extparams AS operationExtParams,
- CAST(NULL AS STRING) AS hotsencetype, CAST(NULL AS STRING) AS path, subsessionid, sessionid
- FROM loghubods.operation_log_per5min
- WHERE dt >= '{dt_start}' AND dt <= '{dt_end}'{apptype_filter} AND machinecode='{mc}'
- AND clienttimestamp IS NOT NULL AND clienttimestamp<>''
- ),
- t AS (
- SELECT * FROM v UNION ALL SELECT * FROM a UNION ALL SELECT * FROM p UNION ALL SELECT * FROM s
- UNION ALL SELECT * FROM u UNION ALL SELECT * FROM r UNION ALL SELECT * FROM o
- )
- SELECT t.ts, t.产品apptype, t.来源, t.businesstype, t.eventid, t.系统, t.endRoutePath, t.objecttype, t.pagesource, t.topic, t.shareid, t.creativeCode, t.视频id, b.title AS 视频标题,
- t.rootPageSource, t.objectId, t.targetUid, t.networkType, t.operationOptions, t.operationExtParams,
- t.hotsencetype, t.path, t.subsessionid, t.sessionid
- FROM t LEFT JOIN videoods.dim_video b ON t.视频id=b.videoid
- ORDER BY t.ts
- """
- def main():
- parser = argparse.ArgumentParser(description="查询单用户实时行为时间线")
- parser.add_argument("user_id", help="machinecode/mid")
- parser.add_argument("date", nargs="?", default=datetime.now().strftime("%Y%m%d"), help="yyyyMMdd")
- parser.add_argument("apptype", nargs="?", default=None, help="可选;不传则查询全部产品")
- parser.add_argument("--output-dir", type=Path, default=Path("."))
- args = parser.parse_args()
- query_date = datetime.strptime(args.date, "%Y%m%d")
- sql_args = {"mc": sql_text(args.user_id), "apptype_filter": build_apptype_filter(args.apptype), "dt_start": f"{args.date}000000", "dt_end": f"{args.date}235959", "year": query_date.strftime("%Y"), "month": query_date.strftime("%m"), "day_of_month": query_date.strftime("%d")}
- df = ODPSClient().execute_sql(SQL_REALTIME.format(**sql_args))
- df = df[~df["businesstype"].isin(EXCLUDED_BUSINESSTYPES)].sort_values("ts", kind="stable").reset_index(drop=True)
- df = df.rename(columns={"creativecode": "creativeCode", "endroutepath": "endRoutePath", "rootpagesource": "rootPageSource", "objectid": "objectId", "targetuid": "targetUid", "networktype": "networkType", "operationoptions": "operationOptions", "operationextparams": "operationExtParams"})
- df.insert(0, "北京时间", pd.to_datetime(df["ts"], unit="ms", utc=True).dt.tz_convert("Asia/Shanghai").dt.tz_localize(None))
- df = add_device_info(df.drop(columns="ts"))
- df.insert(df.columns.get_loc("businesstype") + 1, "行为", df.apply(behavior_definition, axis=1))
- df = df.rename(columns={"businesstype": "事件类型", "eventid": "事件ID"})
- df.insert(0, "用户ID", args.user_id)
- df.insert(0, "产品apptype", df.pop("产品apptype"))
- args.output_dir.mkdir(parents=True, exist_ok=True)
- out = args.output_dir / f"timeline_realtime_{safe_name(args.user_id[-12:])}_{args.date}.xlsx"
- with pd.ExcelWriter(out, engine="openpyxl", datetime_format="yyyy/mm/dd hh:mm:ss") as writer:
- df.to_excel(writer, sheet_name="实时行为路径", index=False)
- for cell in writer.sheets["实时行为路径"]["C"][1:]:
- cell.number_format = "yyyy/mm/dd hh:mm:ss"
- print("注意:simpleevent_log_flow 仅保留当前短实时窗口。")
- print(f"[XLSX] 日期={args.date} 事件数={len(df)} -> {out.resolve()}", flush=True)
- if __name__ == "__main__":
- main()
|