如何使用csv.DictWriter跳过空单元格

Question

我正在尝试匿名CSV中的数据，但是，我只想对非空的单元格执行此操作。目前，我的程序将匿名数据添加到具有给定行的所有单元格。

如何跳过清空空单元格？下面是我的程序

import csv
from faker import Faker
from collections import defaultdict



def anonymize():
    "Anonymizes the given original data to anonymized form"
    faker = Faker()

    names = defaultdict(faker.name)
    emails = defaultdict(faker.email)

    with open(filename, "r") as f:
        with open(f"{filename}-anonymized_data.csv", "w") as o:
            reader = csv.DictReader(f)
            writer = csv.DictWriter(o, reader.fieldnames)
            writer.writeheader()
            for row in reader:
                    row["adult_First_Name"] = names[
                        row["adult_First_Name"]
                    ]
                    row["child_First_Name"] = names[
                        row["child_First_Name"]
                    ]
                    row["Adult - EMAIL ADDRESS"] = emails[row["Adult - EMAIL ADDRESS"]]
                    row["Parent - EMAIL ADDRESS"] = emails[row["Parent - EMAIL ADDRESS"]]
                    writer.writerow(row)


if __name__ == "__main__":
    anonymize()

Answer 1

您可以在应用假值之前测试每个字段。一种更简单的方法是将需要更改的字段存储在fields列表中，以及在需要时应用哪个伪造函数：

import csv
from faker import Faker

def anonymize():
    "Anonymizes the given original data to anonymized form"
    faker = Faker()

    fields = [
        ("adult_First_Name", faker.name),
        ("child_First_Name", faker.name),
        ("Adult - EMAIL ADDRESS", faker.email),
        ("Parent - EMAIL ADDRESS", faker.email),
    ]

    with open(filename, "r") as f:
        with open(f"{filename}-anonymized_data.csv", "w", newline="") as o:
            reader = csv.DictReader(f)
            writer = csv.DictWriter(o, reader.fieldnames)
            writer.writeheader()
            
            for row in reader:
                for field, fake in fields:
                    if row[field]:
                        row[field] = fake()
                
                writer.writerow(row)

    
if __name__ == "__main__":
    anonymize()

添加newline=''会在输出中停止多余的空行。