Python 如何根据日期筛选csv文件中的行？

我有一个名为

aa_20200907.txt的文件，它看起来像这样：

#DATA:DD,CARS_INTERNATIONAL:VERSION01.1
2020-09-07T00:00:00.285+02:00,New-York,XX,Audi
2020-09-07T00:01:00.385+02:00,London,100,Mercedes
2020-09-07T00:02:00.255+02:00,New-York,90,Ford
2020-09-07T00:03:00.523+02:00,New-York,91,BMW
2020-09-08T00:00:58.444+02:00,New-York,12,BMW
2020-09-08T00:01:55.336+02:00,New-York,11,Mercedes

我有一个基于2个条件过滤行的代码

条件\u 1:
我只想要
索引[2]
是数字的行
Condition_2
：如果
索引[1]
（日期）与处理文件名中提到的日期相同，我只需要这些行。文件名的日期被分配到名为
missing\u dates
的列表中
现在下面的代码在
条件_1
上完美工作，问题是
条件_2
没有按我希望的方式工作。请注意，我通常在多个文件上运行此代码，这意味着
缺少\u日期
包含更多值

这是我的代码：

import csv
import datetime 
from pathlib import Path

root=Path(r'c:\data\PPE\Desktop\test_folder')

def filter_row(r, date):  
    condition_1 = r[2].isdigit()  #<-- select only the rows if index 2 is numbers. 
    condition_2 = date != missing_date #<-- select only the rows of that specific day.
    
    return condition_1 and condition_2

missing_dates = ['20200907']

output_list = []
for missing_date in missing_dates:
    # print(f"processing {missing_date}")
    files=[fn for fn in (e for e in root.glob(f"**/*_{missing_date}.txt") if e.is_file())]
    for file in files:      
        with open(file, 'r') as log_file:
            reader = csv.reader(log_file, delimiter = ',')
            next(reader) # skip header
            for row in reader:
                if filter_row(row, missing_date):
                    output_list.append(row)
                    
print(output_list) 

[]

['2020-09-07T00:01:00.385+02:00', 'London', '100', 'Mercedes']
['2020-09-07T00:02:00.255+02:00', 'New-York', '90', 'Ford']
['2020-09-07T00:03:00.523+02:00', 'New-York', '91', 'BMW']

import os
import re
import csv
import datetime

with open(filePath) as infile:
    filename = os.path.basename(filePath)
    print(filename)  # -> aa_20200907.txt
    dateToCheck = datetime.datetime.strptime(re.sub(r"[^\d]", "", filename), "%Y%m%d").strftime("%Y-%m-%d")  # Get Date
    reader = csv.reader(infile)
    for line in reader:
        if line[0].startswith(dateToCheck) and  line[2].isdigit(): # Conditions
            print(line)

['2020-09-07T00:01:00.385+02:00', 'London', '100', 'Mercedes']
['2020-09-07T00:02:00.255+02:00', 'New-York', '90', 'Ford']
['2020-09-07T00:03:00.523+02:00', 'New-York', '91', 'BMW']

这是所需的输出：

import csv
import datetime 
from pathlib import Path

root=Path(r'c:\data\PPE\Desktop\test_folder')

def filter_row(r, date):  
    condition_1 = r[2].isdigit()  #<-- select only the rows if index 2 is numbers. 
    condition_2 = date != missing_date #<-- select only the rows of that specific day.
    
    return condition_1 and condition_2

missing_dates = ['20200907']

output_list = []
for missing_date in missing_dates:
    # print(f"processing {missing_date}")
    files=[fn for fn in (e for e in root.glob(f"**/*_{missing_date}.txt") if e.is_file())]
    for file in files:      
        with open(file, 'r') as log_file:
            reader = csv.reader(log_file, delimiter = ',')
            next(reader) # skip header
            for row in reader:
                if filter_row(row, missing_date):
                    output_list.append(row)
                    
print(output_list) 

[]

['2020-09-07T00:01:00.385+02:00', 'London', '100', 'Mercedes']
['2020-09-07T00:02:00.255+02:00', 'New-York', '90', 'Ford']
['2020-09-07T00:03:00.523+02:00', 'New-York', '91', 'BMW']

import os
import re
import csv
import datetime

with open(filePath) as infile:
    filename = os.path.basename(filePath)
    print(filename)  # -> aa_20200907.txt
    dateToCheck = datetime.datetime.strptime(re.sub(r"[^\d]", "", filename), "%Y%m%d").strftime("%Y-%m-%d")  # Get Date
    reader = csv.reader(infile)
    for line in reader:
        if line[0].startswith(dateToCheck) and  line[2].isdigit(): # Conditions
            print(line)

['2020-09-07T00:01:00.385+02:00', 'London', '100', 'Mercedes']
['2020-09-07T00:02:00.255+02:00', 'New-York', '90', 'Ford']
['2020-09-07T00:03:00.523+02:00', 'New-York', '91', 'BMW']

*请注意，我不想写一个全新的代码。我只想修复
条件2
，并保留当前代码，因为我对它感到满意。
这是一种方法

Ex:

import csv
import datetime 
from pathlib import Path

root=Path(r'c:\data\PPE\Desktop\test_folder')

def filter_row(r, date):  
    condition_1 = r[2].isdigit()  #<-- select only the rows if index 2 is numbers. 
    condition_2 = date != missing_date #<-- select only the rows of that specific day.
    
    return condition_1 and condition_2

missing_dates = ['20200907']

output_list = []
for missing_date in missing_dates:
    # print(f"processing {missing_date}")
    files=[fn for fn in (e for e in root.glob(f"**/*_{missing_date}.txt") if e.is_file())]
    for file in files:      
        with open(file, 'r') as log_file:
            reader = csv.reader(log_file, delimiter = ',')
            next(reader) # skip header
            for row in reader:
                if filter_row(row, missing_date):
                    output_list.append(row)
                    
print(output_list) 

[]

['2020-09-07T00:01:00.385+02:00', 'London', '100', 'Mercedes']
['2020-09-07T00:02:00.255+02:00', 'New-York', '90', 'Ford']
['2020-09-07T00:03:00.523+02:00', 'New-York', '91', 'BMW']

import os
import re
import csv
import datetime

with open(filePath) as infile:
    filename = os.path.basename(filePath)
    print(filename)  # -> aa_20200907.txt
    dateToCheck = datetime.datetime.strptime(re.sub(r"[^\d]", "", filename), "%Y%m%d").strftime("%Y-%m-%d")  # Get Date
    reader = csv.reader(infile)
    for line in reader:
        if line[0].startswith(dateToCheck) and  line[2].isdigit(): # Conditions
            print(line)

['2020-09-07T00:01:00.385+02:00', 'London', '100', 'Mercedes']
['2020-09-07T00:02:00.255+02:00', 'New-York', '90', 'Ford']
['2020-09-07T00:03:00.523+02:00', 'New-York', '91', 'BMW']

输出：

import csv
import datetime 
from pathlib import Path

root=Path(r'c:\data\PPE\Desktop\test_folder')

def filter_row(r, date):  
    condition_1 = r[2].isdigit()  #<-- select only the rows if index 2 is numbers. 
    condition_2 = date != missing_date #<-- select only the rows of that specific day.
    
    return condition_1 and condition_2

missing_dates = ['20200907']

output_list = []
for missing_date in missing_dates:
    # print(f"processing {missing_date}")
    files=[fn for fn in (e for e in root.glob(f"**/*_{missing_date}.txt") if e.is_file())]
    for file in files:      
        with open(file, 'r') as log_file:
            reader = csv.reader(log_file, delimiter = ',')
            next(reader) # skip header
            for row in reader:
                if filter_row(row, missing_date):
                    output_list.append(row)
                    
print(output_list) 

[]

['2020-09-07T00:01:00.385+02:00', 'London', '100', 'Mercedes']
['2020-09-07T00:02:00.255+02:00', 'New-York', '90', 'Ford']
['2020-09-07T00:03:00.523+02:00', 'New-York', '91', 'BMW']

import os
import re
import csv
import datetime

with open(filePath) as infile:
    filename = os.path.basename(filePath)
    print(filename)  # -> aa_20200907.txt
    dateToCheck = datetime.datetime.strptime(re.sub(r"[^\d]", "", filename), "%Y%m%d").strftime("%Y-%m-%d")  # Get Date
    reader = csv.reader(infile)
    for line in reader:
        if line[0].startswith(dateToCheck) and  line[2].isdigit(): # Conditions
            print(line)

['2020-09-07T00:01:00.385+02:00', 'London', '100', 'Mercedes']
['2020-09-07T00:02:00.255+02:00', 'New-York', '90', 'Ford']
['2020-09-07T00:03:00.523+02:00', 'New-York', '91', 'BMW']

给你，伙计：

输入：


#DATA:DD,CARS_INTERNATIONAL:VERSION01.1
2020-09-07T00:00:00.285+02:00,New-York,XX,Audi
2020-09-07T00:01:00.385+02:00,London,100,Mercedes
2020-09-07T00:02:00.255+02:00,New-York,90,Ford
2020-09-07T00:03:00.523+02:00,New-York,91,BMW
2020-09-08T00:00:58.444+02:00,New-York,12,BMW
2020-09-08T00:01:55.336+02:00,New-York,11,Mercedes


代码：

您的代码在条件_2和代码行下方存在问题，在代码段下方运行时，没有文件

    files=[fn for fn in (e for e in root.glob(f"**/*_{missing_date}.txt") if e.is_file())]



不使用熊猫有什么好的理由吗？Pandas使这些任务变得更简单。@quest这段代码是更大脚本的一部分。将所有内容重写为pandas将花费大量时间。您正在执行此操作
if filter_row（row，'20200907'）
这将始终返回false，因为'20200907'将始终等于其自身20200907。你的条件2没有意义。@ChandanMalla这就是为什么我试图重新定义我的条件2，但我不知道如何…谢谢你，但我不想重写一个全新的代码。我想保留我现在的剧本。我只想在
过滤器行
@TangerCity中修复
条件2
。您不需要重写整个代码。将
如果筛选行（行，缺少日期）
替换为
如果行[0]。开始使用（日期检查）和行[2]。isdigit（）：
我想保留函数
筛选行
。我只想调整
条件_2
您可以使用代码将'20200907'更改为'2020-09-07'。另外，如果文件的最后一行有日期为2020-09-07的记录，它还将添加一些垃圾字符，请确保修复它。谢谢，但您已将我代码的第二部分更改得太多了。这是为什么？`files=[fn for fn in（e for e in root.glob（f“*/{missing_date}.txt”）如果e.is_file（））]`这会产生空结果，因此我使用了不同的解决方案从目录中获取文件