FilesExpand file tree

 numpy

/

load_data_by_post.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

executable file

·

135 lines (113 loc) · 4.51 KB

 numpy

/

load_data_by_post.py

Copy path

Top

File metadata and controls

• Code
• Blame

executable file

·

135 lines (113 loc) · 4.51 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

#!/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 loads data into BigQuery via HTTP POST.

This sample is used on this page:

https://cloud.google.com/bigquery/loading-data-into-bigquery

For more information, see the README.md under /bigquery.

"""

import argparse

import json

import time

from googleapiclient import discovery

from googleapiclient.http import MediaFileUpload

from oauth2client.client import GoogleCredentials

# [START make_post]

def load_data(schema_path, data_path, project_id, dataset_id, table_id):

"""Loads the given data file into BigQuery.

Args:

schema_path: the path to a file containing a valid bigquery schema.

see https://cloud.google.com/bigquery/docs/reference/v2/tables

data_path: the name of the file to insert into the table.

project_id: The project id that the table exists under. This is also

assumed to be the project id this request is to be made under.

dataset_id: The dataset id of the destination table.

table_id: The table id to load data into.

"""

# Create a bigquery service object, using the application's default auth

credentials = GoogleCredentials.get_application_default()

bigquery = discovery.build('bigquery', 'v2', credentials=credentials)

# Infer the data format from the name of the data file.

source_format = 'CSV'

if data_path[-5:].lower() == '.json':

source_format = 'NEWLINE_DELIMITED_JSON'

# Post to the jobs resource using the client's media upload interface. See:

# http://developers.google.com/api-client-library/python/guide/media_upload

insert_request = bigquery.jobs().insert(

projectId=project_id,

# Provide a configuration object. See:

# https://cloud.google.com/bigquery/docs/reference/v2/jobs#resource

body={

'configuration': {

'load': {

'schema': {

'fields': json.load(open(schema_path, 'r'))

},

'destinationTable': {

'projectId': project_id,

'datasetId': dataset_id,

'tableId': table_id

},

'sourceFormat': source_format,

}

}

},

media_body=MediaFileUpload(

data_path,

mimetype='application/octet-stream'))

job = insert_request.execute()

print('Waiting for job to finish...')

status_request = bigquery.jobs().get(

projectId=job['jobReference']['projectId'],

jobId=job['jobReference']['jobId'])

# Poll the job until it finishes.

while True:

result = status_request.execute(num_retries=2)

if result['status']['state'] == 'DONE':

if result['status'].get('errors'):

raise RuntimeError('\n'.join(

e['message'] for e in result['status']['errors']))

print('Job complete.')

return

time.sleep(1)

# [END make_post]

# [START main]

def main(project_id, dataset_id, table_name, schema_path, data_path):

load_data(

schema_path,

data_path,

project_id,

dataset_id,

table_name)

# [END 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(

'schema_file',

help='Path to a schema file describing the table schema.')

parser.add_argument(

'data_file',

help='Path to the data file.')

args = parser.parse_args()

main(

args.project_id,

args.dataset_id,

args.table_name,

args.schema_file,

args.data_file)