Created
June 6, 2017 08:04
-
-
Save nikparmar/1d88ca4d01cd41517c014fc33f70105f to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from google.cloud import bigquery | |
# from google.cloud.storage import Blob, Client as storage_client | |
from google.cloud import storage | |
import uuid | |
import time | |
class BigQueryToGCS(object): | |
def __init__(self, load_config_from_json=True): | |
self.config_from_file = load_config_from_json | |
def wait_for_job(self, job): | |
while True: | |
job.reload() | |
if job.state == 'DONE': | |
if job.error_result: | |
raise RuntimeError(job.errors) | |
return | |
time.sleep(1) | |
def export_data_to_gcs(self, dataset_name, table_name, bucket_name): | |
""" | |
:param dataset_name: This means the 54190935 account number for ACM | |
this corresponds to the dataset in BigQuery | |
:param table_name: The table name stored in BigQuery are of the format | |
"ga_sessions_YYYYMMDD" | |
:param bucket_name: Name of the bucket where the data needs to be | |
exported | |
:return: | |
""" | |
table_name = 'ga_sessions_{0}'.format(table_name) | |
destination = 'gs://{0}/{1}.json'.format(bucket_name, table_name) | |
# if self.config_from_file is True: | |
bigquery_client = bigquery.Client() | |
dataset = bigquery_client.dataset(dataset_name) | |
table = dataset.table(table_name) | |
job_name = str(uuid.uuid4()) | |
job = bigquery_client.extract_table_to_storage( | |
job_name, table, destination) | |
job.destination_format = "NEWLINE_DELIMITED_JSON" | |
job.begin() | |
self.wait_for_job(job) | |
print 'Exported {}:{} to {}'.format( | |
dataset_name, table_name, destination) | |
def download_to_local_from_gcs(self): | |
client = storage.Client() | |
print client.SCOPE | |
a = client.list_buckets() | |
# print a | |
# for i in a: | |
# print i | |
bucket = client.get_bucket('astro-big-data-project.appspot.com') | |
print bucket.acl | |
# blob = Blob('bqoutput/ga_sessions_20170604.json', bucket=bucket) | |
# with open('my-secure-file.json', 'wb') as file_obj: | |
# blob.download_to_file(file_obj) | |
_obj = BigQueryToGCS(True) | |
# _obj.export_data_to_gcs(54190935, 20170604, | |
# 'astro-big-data-project.appspot.com/bqoutput') | |
_obj.download_to_local_from_gcs() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment