from pyspark.sql.functions import input_file_name
df = spark.read.text("hdfs://xxx/xxx").withColumn("file_name", input_file_name()).where("value like '%5ec36294%'")
df.show(10,False)
运行结果
from pyspark.sql.functions import input_file_name
df = spark.read.text("hdfs://xxx/xxx").withColumn("file_name", input_file_name()).where("value like '%5ec36294%'")
df.show(10,False)
运行结果