from pyspark.sql import SparkSession
import boto3
import os
import pandas as pd
spark = SparkSession.builder.getOrCreate()
hadoop_conf = spark.sparkContext._jsc.hadoopConfiguration()
hadoop_conf.set("fs.s3.impl", "org.apache.hadoop.fs.s3a.S3AFileSystem")
hadoop_conf.set("fs.s3a.access.key", "myaccesskey")
hadoop_conf.set("fs.s3a.secret.key", "mysecretkey")
hadoop_conf.set("fs.s3a.endpoint", "s3.amazonaws.com")
hadoop_conf.set("fs.s3a.aws.credentials.provider", "org.apache.hadoop.fs.s3a.BasicAWSCredentialsProvider")
hadoop_conf.set("fs.s3a.connection.ssl.enabled", "true")
conn = boto3.resource("s3", region_name="us-east-1")
df = spark.read.csv("s3a://mani-test-1206/test/test.csv", header=True)
df.show()
spark.stop()
when running above code I had below error:
java.io.IOException: From option fs.s3a.aws.credentials.provider java.lang.ClassNotFoundException: Class org.apache.hadoop.fs.s3a.BasicAWSCredentialsProvider not found
Hadoop and aws jars program is using:
spark-hadoop-distribution: spark-3.2.0-bin-hadoop3.2
hadoop jars:
hadoop-annotations-3.2.0.jar
hadoop-auth-3.2.0.jar
hadoop-aws-3.2.0.jar
hadoop-client-api-3.3.1.jar
hadoop-client-runtime-3.3.1.jar
hadoop-common-3.2.0.jar
hadoop-hdfs-3.2.0.jar
aws jars:
aws-java-sdk-1.11.624.jar
aws-java-sdk-core-1.11.624.jar
aws-java-sdk-dynamodb-1.11.624.jar
aws-java-sdk-s3-1.11.624.jar
Any help will be highly appreciated, Thanks.