python - 我的代码只循环到某个点并忽略之后的 Python、字典

Question

数据

slot : acu:1/1                         plannedtype : ngfcf                       actualtype : ngfcf                           operstatus : enabled              
errorstatus : noerror                                                                       availability : available            
alarmprofile : none                                                                          capabprofile : not_applicable       

slot : acu:1/2                         plannedtype : ngfcf                       actualtype : ngfcf                           operstatus : enabled              
errorstatus : noerror                                                                       availability : available            
alarmprofile : none                                                                          capabprofile : not_applicable   

slot : acu:1/3                       plannedtype : ngfcf                       actualtype : ngfcf                           operstatus : enabled              
errorstatus : noerror                                                                       availability : available            
alarmprofile : none                                                                          capabprofile : not_applicable   

As we can see the slot and other items are repeated, my loop is only inserting the first items in csv file i want to iterate through the repeated lines and add those values after":" to the next row of my csv file.

#reading a text file

import re
from collections import defaultdict
import pandas as pd

result = defaultdict(list)

with open('gthamelslot.txt') as f:
    for line in f:
        match = re.findall(r"\s+(\S+)\s+:\s+(\S+)", line)
        for k,v in match:
            if k in ["slot",
                     "errorstatus",
                     "alarmprofile",
                     "manufacturer",
                     "mnemonic",
                     "pbacode",
                     "fpbacode",
                     "fpbaics",
                     "cleicode",
                     "serialno",
                     "failedtest",
                     "ltrestarttime",
                     "plannedtype",
                     "ltrestartcause"]:
                result[k].append(v)

df = pd.DataFrame(result)
writetocsv = df.to_csv("test.csv")
print(df)

Output i got

slot     plannedtype  actualtype  errorstatus
acu:1/1  ngfcf         ngfcf        noerror

output required

slot     plannedtype  actualtype  errorstatus
acu:1/1  ngfcf         ngfcf        noerror
acu:1/2  ngfcf         ngfcf        noerror
acu:1/3  ngfcf         ngfcf        noerror

Answer 1

以下更改:

将正则表达式更改为 r"\b(\S+)\s+:\s+(\S+)"以允许在行开头匹配(更改以查找字边界)

比较列表中的某些项目(例如“计划类型”)在文件中没有的情况下带有“-”(因此请删除所需字段中的“-”，例如计划类型、实际类型、错误状态)。

import re
from collections import defaultdict
import pandas as pd

result = defaultdict(list)

with open('gthamelslot.txt') as f:
    for line in f:
        match = re.findall(r"\b(\S+)\s+:\s+(\S+)", line)
        for k,v in match:
            if k in ["slot",
              "actualtype",
              "errorstatus",
              "alarm-profile",
              "manufacturer",
              "mnemonic",
              "pbacode",
              "fpbacode",
              "fpbaics",
              "cleicode",
              "serialno",
              "failedtest",
              "ltrestarttime",
              "plannedtype",
              "ltrestartcause"]:
                result[k].append(v)

df = pd.DataFrame(result)
writetocsv = df.to_csv("test.csv")
print(df)

输出

slot plannedtype actualtype errorstatus
0  acu:1/1       ngfcf      ngfcf     noerror
1  acu:1/2       ngfcf      ngfcf     noerror
2  acu:1/3       ngfcf      ngfcf     noerror