BaseDataMaintenance/BaseDataMaintenance/maintenance/extract_uuid.py

import re
import pandas as pd

import pickle

def save(object_to_save, path):
    '''
    保存对象
    @Arugs:
        object_to_save: 需要保存的对象

    @Return:
        保存的路径
    '''
    with open(path, 'wb') as f:
        pickle.dump(object_to_save, f)

def extract_uuid_from_log():
    list_files = [
                  "/data/python/flow_init_log/flow_init_2022-06-02.log",
                  "/data/python/flow_init_log/flow_init_2022-06-03.log",
                  "/data/python/flow_init_log/flow_init_2022-06-04.log",
                  "/data/python/flow_init_log/flow_init_2022-06-05.log",
                  "/data/python/flow_init.log"
    ]
    list_uuid = []
    _regrex = "delete\s+(?P<tablename>bxkc[^\s]+)\s+.*ID='(?P<uuid>.+)'"
    for _file in list_files:
        with open(_file,"r",encoding="utf8") as f:
            while 1:
                _line = f.readline()
                if not _line:
                    break
                _match = re.search(_regrex,_line)
                if _match is not None:
                    _uuid = _match.groupdict().get("uuid")
                    tablename = _match.groupdict().get("tablename")
                    if _uuid is not None:
                        list_uuid.append({"uuid":_uuid,"tablename":tablename})
    df_data = {"uuid":[],
               "tablename":[]}
    for _data in list_uuid:
        for k,v in df_data.items():
            v.append(_data.get(k))
    save(df_data,"uuid.pk")

if __name__ == '__main__':
    extract_uuid_from_log()