Read the smb file using pyspark:
for p in conn.listPath(share, path, pattern=pattern):
p: SharedFile = p
src = f'{share}{path}/{p.filename}'
filepath = f'{path}/{p.filename}'
src_temppath = tempfile.mktemp()
enter code here
with open(src_temppath, 'wb') as temp:
conn.retrieveFile(share, filepath, temp)
df = spark.read.format("binaryFile").load(f'file:///{src_temppath}')
df = df.withColumn('values', F.explode(load_xls('content')).alias('values'))
df = df.select('values.*')
rows_count = df.count()
error:
File file:///tmp/tmpzq27b61e does not exist
Is this a correct way to read the excel file from the SMB?