如何列出另一个订阅中的另一个 Azure 数据湖 gen2 存储帐户中的所有文件和子目录

Question

我正在尝试从不同订阅的 Azure 存储帐户中的容器中获取所有文件及其子目录，并且业务要求是使用 abfss url。 abfss://@.dfs.core.windows.net//。 我尝试为订阅导入 spark 配置，并使用以下代码返回文件列表。 然而失败了。

import os
from fnmatch import fnmatch
root_list="abfss://staging@bdoibgedpsadlssandbox.dfs.core.windows.net/staging/"
files_list = []
pattern = "*.*"
print(pattern)
for path, subdirs, files in os.walk(root_list):
  for name in files:
    if fnmatch(name.upper(), pattern.upper()):
      files_list.append(path+"/"+name)

这将打印“[]”空列表。

Answer 1

您可以将以下代码用于此用例。

from pyspark.sql.functions import col
from azure.storage.blob import BlockBlobService
from datetime import datetime
import os.path

account_name='accountname'
container_name ='container_name'
second_conatainer_name ='data'
account_key = 'storage-account-key'
prefix_val = second_conatainer_name+'/'

block_blob_service = BlockBlobService(account_name='%s'%(account_name), account_key='%s'%(account_key))

#block_blob_service.create_container(container_name)
generator = block_blob_service.list_blobs(container_name,prefix="%s"%(prefix_val))
report_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')


Target_file = "/target2/%s.csv" % (container_name)
print(Target_file)

Target_file = open("%s"%(Target_file), 'w')

for blob in generator:
    length = BlockBlobService.get_blob_properties(block_blob_service,container_name,blob.name)
    last_modified = BlockBlobService.get_blob_properties(block_blob_service,container_name,blob.name).properties.last_modified
    file_size = BlockBlobService.get_blob_properties(block_blob_service,container_name,blob.name).properties.content_length
    blob_type = BlockBlobService.get_blob_properties(block_blob_service,container_name,blob.name).properties.blob_type
    creation_time = BlockBlobService.get_blob_properties(block_blob_service,container_name,blob.name).properties.blob_tier_change_time
    if file_size != 0:
       line = account_name+'|'+container_name+'|'+blob.name+'|'+ str(file_size) +'|'+str(last_modified)[:10]+'|'
       print(line)
       Target_file.write(line+'\n')