解析pyspark dataframe中的字符串json的udf

from pyspark.sql import SparkSession
from pyspark.sql.functions import udf
from pyspark.sql.types import StructType, StructField, StringType

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

# 创建示例DataFrame
data = [("{'name': 'John', 'age': 30}",),
        ("{'name': 'Alice', 'age': 25}",),
        ("{'name': 'Bob', 'age': 35}",)]
df = spark.createDataFrame(data, ["json_string"])

# 定义UDF来解析JSON字符串
def parse_json(json_string):
    import json
    return json.loads(json_string)

# 注册UDF
parse_json_udf = udf(parse_json, StructType([
    StructField("name", StringType(), True),
    StructField("age", StringType(), True)
]))

# 应用UDF并创建新列
df = df.withColumn("parsed_json", parse_json_udf(df["json_string"]))

# 显示结果
df.show(truncate=False)