forked from GoogleCloudPlatform/python-docs-samples
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathstreaming.py
More file actions
executable file
·106 lines (87 loc) · 3.27 KB
/
Copy pathstreaming.py
File metadata and controls
executable file
·106 lines (87 loc) · 3.27 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
#!/usr/bin/env python
# Copyright 2015, Google, Inc.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Command-line application that streams data into BigQuery.
This sample is used on this page:
https://cloud.google.com/bigquery/streaming-data-into-bigquery
For more information, see the README.md under /bigquery.
"""
import argparse
import ast
import json
import uuid
from googleapiclient import discovery
from oauth2client.client import GoogleCredentials
from six.moves import input
# [START stream_row_to_bigquery]
def stream_row_to_bigquery(bigquery, project_id, dataset_id, table_name, row,
num_retries=5):
insert_all_data = {
'rows': [{
'json': row,
# Generate a unique id for each row so retries don't accidentally
# duplicate insert
'insertId': str(uuid.uuid4()),
}]
}
return bigquery.tabledata().insertAll(
projectId=project_id,
datasetId=dataset_id,
tableId=table_name,
body=insert_all_data).execute(num_retries=num_retries)
# [END stream_row_to_bigquery]
# [START run]
def main(project_id, dataset_id, table_name, num_retries):
# [START build_service]
# Grab the application's default credentials from the environment.
credentials = GoogleCredentials.get_application_default()
# Construct the service object for interacting with the BigQuery API.
bigquery = discovery.build('bigquery', 'v2', credentials=credentials)
# [END build_service]
for row in get_rows():
response = stream_row_to_bigquery(
bigquery, project_id, dataset_id, table_name, row, num_retries)
print(json.dumps(response))
def get_rows():
line = input("Enter a row (python dict) into the table: ")
while line:
yield ast.literal_eval(line)
line = input("Enter another row into the table \n" +
"[hit enter to stop]: ")
# [END run]
# [START main]
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('project_id', help='Your Google Cloud project ID.')
parser.add_argument('dataset_id', help='A BigQuery dataset ID.')
parser.add_argument(
'table_name', help='Name of the table to load data into.')
parser.add_argument(
'-p', '--poll_interval',
help='How often to poll the query for completion (seconds).',
type=int,
default=1)
parser.add_argument(
'-r', '--num_retries',
help='Number of times to retry in case of 500 error.',
type=int,
default=5)
args = parser.parse_args()
main(
args.project_id,
args.dataset_id,
args.table_name,
args.num_retries)
# [END main]