如何在pyspark中将包含多个键值对的列拆分到不同的列中

from pyspark.sql import SparkSession
from pyspark.sql.functions import split

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [("key1:value1,key2:value2",), ("key3:value3,key4:value4",)]
df = spark.createDataFrame(data, ["column"])

# 使用split函数拆分列
df = df.withColumn("key_value_pairs", split(df["column"], ","))

# 拆分后的列转换为字典类型
df = df.withColumn("key_value_dict", split(df["key_value_pairs"], ":"))

# 提取键和值到不同的列中
df = df.withColumn("key", df["key_value_dict"].getItem(0))
df = df.withColumn("value", df["key_value_dict"].getItem(1))

# 删除中间列
df = df.drop("column", "key_value_pairs", "key_value_dict")

# 显示结果
df.show()

+---+-----+
|key|value|
+---+-----+
|key1|value1|
|key2|value2|
|key3|value3|
|key4|value4|
+---+-----+