pyspark:返回所有单元格都与regex匹配的列

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, regexp_extract

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

# 创建示例DataFrame
data = [("John", "john@example.com"),
        ("Mike", "mike@example.com"),
        ("Anna", "anna@example.com")]

df = spark.createDataFrame(data, ["Name", "Email"])

# 使用正则表达式函数进行匹配
regex = ".*@example.com"
matched_columns = [col(column) for column in df.columns if regexp_extract(col(column), regex, 0) != ""]
result = df.select(*matched_columns)

# 打印结果
result.show()