如何使用pyspark从数据库中的ADLS Gen2 Datalake的“文件共享”中读取csv文件

from pyspark.sql import SparkSession

spark = SparkSession.builder \
    .appName("Read CSV from ADLS Gen2 Datalake") \
    .getOrCreate()

spark.conf.set("fs.azure.account.auth.type.<your-storage-account-name>.dfs.core.windows.net", "OAuth")
spark.conf.set("fs.azure.account.oauth.provider.type.<your-storage-account-name>.dfs.core.windows.net", "org.apache.hadoop.fs.azurebfs.oauth2.ClientCredsTokenProvider")
spark.conf.set("fs.azure.account.oauth2.client.id.<your-storage-account-name>.dfs.core.windows.net", "<your-client-id>")
spark.conf.set("fs.azure.account.oauth2.client.secret.<your-storage-account-name>.dfs.core.windows.net", "<your-client-secret>")
spark.conf.set("fs.azure.account.oauth2.client.endpoint.<your-storage-account-name>.dfs.core.windows.net", "https://login.microsoftonline.com/<your-directory-id>/oauth2/token")

df = spark.read.csv("abfss://<your-storage-account-name>.dfs.core.windows.net/<your-file-share>/<your-file-path>.csv", header=True, inferSchema=True)

df.show()
# 进行其他操作，如筛选、聚合等