在PySpark成对RDD中搜索值，以查找来自另一个RDD的键

# 导入必要的模块
from pyspark import SparkContext

# 创建SparkContext对象
sc = SparkContext("local", "PySpark Example")

# 创建第一个RDD
rdd1 = sc.parallelize([(1, "apple"), (2, "banana"), (3, "orange")])

# 创建第二个RDD
rdd2 = sc.parallelize([(1, "fruit"), (2, "fruit"), (3, "fruit"), (4, "vegetable")])

# 将两个RDD进行join操作
joined_rdd = rdd1.join(rdd2)

# 过滤出满足条件的键值对
filtered_rdd = joined_rdd.filter(lambda x: x[1][1] == "fruit")

# 打印结果
print(filtered_rdd.collect())