google_sheet_reader 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.rspec +2 -0
- data/.travis.yml +4 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +83 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/google_sheet_reader.gemspec +28 -0
- data/lib/google_sheet_reader.rb +72 -0
- data/lib/google_sheet_reader/version.rb +3 -0
- data/mocks/spreadsheet_file.rb +36 -0
- metadata +143 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 5fddd75645c1a3b2ab59543f2b803bb176597392
|
4
|
+
data.tar.gz: 723e426884952c3d1aa67b7177dd3f9bfe1cf847
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 0416b7d595761e4c5236ad68889cce2ea4f7ba48b7bfb1c9fac152424e6d2f25dbb4e53f69ec522d0b017c2c8f6d9b6b0d27c3b4103faa7a186d770aa69a01b7
|
7
|
+
data.tar.gz: 09da21de9750c5ee53b31b6705a4e0dc55ed9a3c9f33ff5aee13bb73e1876bf0c494b428eb44a742810bb21faa7c8deaeb7b9f6bcac9e5c0792ef41a19a23be0
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 MJ Rossetti (@s2t2)
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,83 @@
|
|
1
|
+
# GoogleSheetReader
|
2
|
+
|
3
|
+
A ruby library
|
4
|
+
for extracting spreadsheet data from [Google Drive](https://www.google.com/drive/).
|
5
|
+
|
6
|
+
Performs a custom ETL procedure on each row.
|
7
|
+
|
8
|
+
## Installation
|
9
|
+
|
10
|
+
Add this line to your application's Gemfile:
|
11
|
+
|
12
|
+
```ruby
|
13
|
+
gem 'google_sheet_reader'
|
14
|
+
```
|
15
|
+
|
16
|
+
Or install yourself with `gem install google_sheet_reader`.
|
17
|
+
|
18
|
+
## Usage
|
19
|
+
|
20
|
+
```` rb
|
21
|
+
spreadsheet_id = "1a2B3C45_x0G44lk15Ff_M33ps"
|
22
|
+
# see Prerequisites section below for instructions on how to obtain most of these configuration option values ...
|
23
|
+
configuration_options = {
|
24
|
+
:app_name => "my-app",
|
25
|
+
:email_address => "abc-123@developer.gserviceaccount.com",
|
26
|
+
:key_file_path => File.expand_path("../key_file/my-app-abc123xy456z.p12", __FILE__),
|
27
|
+
:extraction_procedure => Proc.new do |row|
|
28
|
+
"PARSING A SPREADSHEET ROW HERE -- #{row.inspect}"
|
29
|
+
end
|
30
|
+
}
|
31
|
+
|
32
|
+
GoogleSheetReader.extract(spreadsheet_id, configuration_options)
|
33
|
+
````
|
34
|
+
|
35
|
+
### Prerequisites
|
36
|
+
|
37
|
+
#### Drive API-enabled App
|
38
|
+
|
39
|
+
Visit the [google developer console](https://console.developers.google.com), create a new application, and note its name.
|
40
|
+
|
41
|
+
Navigate to the **APIs & Auth > APIs** menu and enable the *Drive API* by searching for it.
|
42
|
+
|
43
|
+
#### Service Account
|
44
|
+
|
45
|
+
Navigate to the **APIs & Auth > Credentials** menu and add credentials for a service account.
|
46
|
+
|
47
|
+
Choose the .p12 key file option, download it, optionally move it somewhere else, and finally note its file path.
|
48
|
+
|
49
|
+
Back in the browser, also note the service account's email address.
|
50
|
+
|
51
|
+
#### Spreadsheet
|
52
|
+
|
53
|
+
Create a spreadsheet, and inspect its url to find its document identifier: *docs.google.com/spreadsheets/d/`spreadsheet_id`/edit*.
|
54
|
+
|
55
|
+
Share the spreadsheet with the service account's email address in a "can edit" role.
|
56
|
+
|
57
|
+
## Contributing
|
58
|
+
|
59
|
+
Browse existing [issues](https://github.com/data-creative/google-sheet-reader-ruby/issues) or create a new issue to communicate bugs, desired features, etc.
|
60
|
+
|
61
|
+
After forking the repo and pushing your changes, create a pull request referencing the applicable issue(s).
|
62
|
+
|
63
|
+
### Developing
|
64
|
+
|
65
|
+
After checking out the repo, run `bin/setup` to install dependencies.
|
66
|
+
|
67
|
+
### Testing
|
68
|
+
|
69
|
+
Store a real service account .p12 key file in the **spec/key_file/** directory, and add the following environment variables to your .bash_profile:
|
70
|
+
|
71
|
+
+ `GOOGLE_SHEET_READER_APP_NAME`
|
72
|
+
+ `GOOGLE_SHEET_READER_EMAIL`
|
73
|
+
+ `GOOGLE_SHEET_READER_KEY_FILE_NAME`
|
74
|
+
|
75
|
+
Run `rake rspec` or `bundle exec rspec spec/` to run the tests.
|
76
|
+
|
77
|
+
Optionally run `bin/console` for an interactive prompt that will allow you to experiment.
|
78
|
+
|
79
|
+
### Releasing
|
80
|
+
|
81
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
82
|
+
|
83
|
+
## [License](LICENSE.txt)
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "google_sheet_reader"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
require "pry"
|
11
|
+
Pry.start
|
12
|
+
|
13
|
+
# require "irb"
|
14
|
+
# IRB.start
|
data/bin/setup
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'google_sheet_reader/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "google_sheet_reader"
|
8
|
+
spec.version = GoogleSheetReader::VERSION
|
9
|
+
spec.authors = ["MJ Rossetti (@s2t2)"]
|
10
|
+
spec.email = ["s2t2mail+git@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{A ruby library for extracting spreadsheet data from Google Drive.}
|
13
|
+
spec.description = %q{A ruby library for extracting spreadsheet data from Google Drive. Performs a custom ETL procedure on each row.}
|
14
|
+
spec.homepage = "https://github.com/data-creative/google-sheet-reader-ruby"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
+
spec.bindir = "exe"
|
19
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_development_dependency "bundler", "~> 1.10"
|
23
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
24
|
+
spec.add_development_dependency "rspec"
|
25
|
+
spec.add_development_dependency "pry", "~> 0.10"
|
26
|
+
spec.add_development_dependency "yard"
|
27
|
+
spec.add_dependency 'google-api-client'
|
28
|
+
end
|
@@ -0,0 +1,72 @@
|
|
1
|
+
require 'google/api_client'
|
2
|
+
require 'csv'
|
3
|
+
|
4
|
+
require "google_sheet_reader/version"
|
5
|
+
|
6
|
+
module GoogleSheetReader
|
7
|
+
|
8
|
+
def self.client(options = {})
|
9
|
+
app_name = options[:app_name]
|
10
|
+
email_address = options[:email_address]
|
11
|
+
key_file_path = options[:key_file_path]
|
12
|
+
|
13
|
+
key = Google::APIClient::KeyUtils.load_from_pkcs12(key_file_path, 'notasecret')
|
14
|
+
asserter = Google::APIClient::JWTAsserter.new(email_address, 'https://www.googleapis.com/auth/drive', key)
|
15
|
+
google_api_client = Google::APIClient.new({:application_name => app_name, :application_version => "1.0"})
|
16
|
+
google_api_client.authorization = asserter.authorize()
|
17
|
+
return google_api_client
|
18
|
+
end
|
19
|
+
|
20
|
+
# Extract data from a Google Drive spreadsheet.
|
21
|
+
#
|
22
|
+
# @param [String] spreadsheet_id
|
23
|
+
# @param [Hash] options [String] app_name
|
24
|
+
# @param [Hash] options [String] email_address
|
25
|
+
# @param [Hash] options [String] key_file_path
|
26
|
+
# @param [Hash] options [Proc] extraction_procedure
|
27
|
+
#
|
28
|
+
# @example GoogleSheetReader.extract(file_id, opts)
|
29
|
+
#
|
30
|
+
def self.extract(spreadsheet_id, options = {})
|
31
|
+
app_name = options[:app_name]
|
32
|
+
email_address = options[:email_address]
|
33
|
+
key_file_path = options[:key_file_path]
|
34
|
+
extraction_procedure = options[:extraction_procedure]
|
35
|
+
|
36
|
+
puts "CONNECTING TO GOOGLE DRIVE ..."
|
37
|
+
|
38
|
+
google_api_client = self.client(options)
|
39
|
+
drive = google_api_client.discovered_api('drive', 'v2')
|
40
|
+
|
41
|
+
get_request_result = google_api_client.execute(
|
42
|
+
:api_method => drive.files.get,
|
43
|
+
:parameters => { 'fileId' => spreadsheet_id }
|
44
|
+
)
|
45
|
+
raise FileRetrievalError unless get_request_result.status == 200
|
46
|
+
|
47
|
+
file = get_request_result.data
|
48
|
+
download_url = file.exportLinks["text/csv"]
|
49
|
+
raise FileDownloadLinkError unless download_url
|
50
|
+
|
51
|
+
download_request_result = google_api_client.execute(:uri => download_url)
|
52
|
+
raise FileDownloadError unless download_request_result.status == 200
|
53
|
+
|
54
|
+
file_contents = download_request_result.body
|
55
|
+
csv_result = CSV.parse(file_contents, headers:true)
|
56
|
+
#headers = csv_result.headers
|
57
|
+
|
58
|
+
raise EmptyFileError.new("This spreadsheet has no data. Please add rows.") unless csv_result.any?
|
59
|
+
|
60
|
+
csv_result.each do |row|
|
61
|
+
extraction_procedure.call(row)
|
62
|
+
end
|
63
|
+
|
64
|
+
puts "PARSED #{csv_result.count} ROWS"
|
65
|
+
return {:status => "SUCCESS", :row_count => csv_result.count}
|
66
|
+
end
|
67
|
+
|
68
|
+
class FileRetrievalError < StandardError ; end
|
69
|
+
class FileDownloadLinkError < StandardError ; end
|
70
|
+
class FileDownloadError < StandardError ; end
|
71
|
+
class EmptyFileError < StandardError ; end
|
72
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
#<Google::APIClient::Schema::Drive::V2::File:0x3fc9526f4edc DATA:
|
2
|
+
{
|
3
|
+
"kind"=>"drive#file",
|
4
|
+
"id"=>"xyz_123",
|
5
|
+
"etag"=>"\"abcd\"",
|
6
|
+
"selfLink"=>"https://www.googleapis.com/drive/v2/files/xyz_123",
|
7
|
+
"alternateLink"=>"https://docs.google.com/spreadsheets/d/xyz_123/edit?usp=drivesdk",
|
8
|
+
"embedLink"=>"https://docs.google.com/spreadsheets/d/xyz_123/htmlembed",
|
9
|
+
"iconLink"=>"https://ssl.gstatic.com/docs/doclist/images/icon_11_spreadsheet_list.png",
|
10
|
+
"thumbnailLink"=>"https://docs.google.com/feeds/vt?gd=true&id=xyz_123&v=0&s=ggggg",
|
11
|
+
"title"=>"my-sheet",
|
12
|
+
"mimeType"=>"application/vnd.google-apps.spreadsheet",
|
13
|
+
"labels"=>{"starred"=>false, "hidden"=>false, "trashed"=>false, "restricted"=>false, "viewed"=>false}, "createdDate"=>"2015-09-18T23:40:45.972Z",
|
14
|
+
"modifiedDate"=>"2015-09-19T02:01:13.137Z",
|
15
|
+
"markedViewedByMeDate"=>"1970-01-01T00:00:00.000Z",
|
16
|
+
"sharedWithMeDate"=>"2015-09-19T02:01:13.144Z",
|
17
|
+
"version"=>"98647",
|
18
|
+
"sharingUser"=>{"kind"=>"drive#user",
|
19
|
+
"displayName"=>"Jim Jones",
|
20
|
+
"picture"=>{"url"=>"https://lh6.googleusercontent.com/photo.jpg"}, "isAuthenticatedUser"=>false, "permissionId"=>"1234567890987654321",
|
21
|
+
"emailAddress"=>"jim.Jones@gmail.com"}, "parents"=>[],"exportLinks"=>{"text/csv"=>"https://docs.google.com/spreadsheets/export?id=xyz_123&exportFormat=csv",
|
22
|
+
"application/pdf"=>"https://docs.google.com/spreadsheets/export?id=xyz_123&exportFormat=pdf",
|
23
|
+
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"=>"https://docs.google.com/spreadsheets/export?id=xyz_123&exportFormat=xlsx"}, "userPermission"=>{"kind"=>"drive#permission",
|
24
|
+
"etag"=>"\"tagggggggggg3434738473\"",
|
25
|
+
"id"=>"me",
|
26
|
+
"selfLink"=>"https://www.googleapis.com/drive/v2/files/xyz_123/permissions/me",
|
27
|
+
"role"=>"writer",
|
28
|
+
"type"=>"user"}, "quotaBytesUsed"=>"0",
|
29
|
+
"ownerNames"=>["Jim Jones"], "owners"=>[{"kind"=>"drive#user",
|
30
|
+
"displayName"=>"Jim Jones",
|
31
|
+
"picture"=>{"url"=>"https://lh6.googleusercontent.com/photo.jpg"}, "isAuthenticatedUser"=>false, "permissionId"=>"1234567890987654321",
|
32
|
+
"emailAddress"=>"jim.Jones@gmail.com"}], "lastModifyingUserName"=>"Jim Jones",
|
33
|
+
"lastModifyingUser"=>{"kind"=>"drive#user",
|
34
|
+
"displayName"=>"Jim Jones",
|
35
|
+
"picture"=>{"url"=>"https://lh6.googleusercontent.com/photo.jpg"}, "isAuthenticatedUser"=>false, "permissionId"=>"1234567890987654321",
|
36
|
+
"emailAddress"=>"jim.Jones@gmail.com"}, "editable"=>true, "copyable"=>true, "writersCanShare"=>true, "shared"=>true, "explicitlyTrashed"=>false, "appDataContents"=>false, "spaces"=>["drive"]} #>
|
metadata
ADDED
@@ -0,0 +1,143 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: google_sheet_reader
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- MJ Rossetti (@s2t2)
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-09-19 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.10'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.10'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pry
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0.10'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0.10'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: yard
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: google-api-client
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description: A ruby library for extracting spreadsheet data from Google Drive. Performs
|
98
|
+
a custom ETL procedure on each row.
|
99
|
+
email:
|
100
|
+
- s2t2mail+git@gmail.com
|
101
|
+
executables: []
|
102
|
+
extensions: []
|
103
|
+
extra_rdoc_files: []
|
104
|
+
files:
|
105
|
+
- ".gitignore"
|
106
|
+
- ".rspec"
|
107
|
+
- ".travis.yml"
|
108
|
+
- Gemfile
|
109
|
+
- LICENSE.txt
|
110
|
+
- README.md
|
111
|
+
- Rakefile
|
112
|
+
- bin/console
|
113
|
+
- bin/setup
|
114
|
+
- google_sheet_reader.gemspec
|
115
|
+
- lib/google_sheet_reader.rb
|
116
|
+
- lib/google_sheet_reader/version.rb
|
117
|
+
- mocks/spreadsheet_file.rb
|
118
|
+
homepage: https://github.com/data-creative/google-sheet-reader-ruby
|
119
|
+
licenses:
|
120
|
+
- MIT
|
121
|
+
metadata: {}
|
122
|
+
post_install_message:
|
123
|
+
rdoc_options: []
|
124
|
+
require_paths:
|
125
|
+
- lib
|
126
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - ">="
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '0'
|
131
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
132
|
+
requirements:
|
133
|
+
- - ">="
|
134
|
+
- !ruby/object:Gem::Version
|
135
|
+
version: '0'
|
136
|
+
requirements: []
|
137
|
+
rubyforge_project:
|
138
|
+
rubygems_version: 2.4.5
|
139
|
+
signing_key:
|
140
|
+
specification_version: 4
|
141
|
+
summary: A ruby library for extracting spreadsheet data from Google Drive.
|
142
|
+
test_files: []
|
143
|
+
has_rdoc:
|