tweet_words_counter 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +12 -0
- data/.rspec +3 -0
- data/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +6 -0
- data/LICENSE.txt +21 -0
- data/README.md +43 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/twitter_streaming_api.rb +73 -0
- data/lib/twitter_streaming_api/version.rb +3 -0
- data/twitter_streaming_api.gemspec +37 -0
- metadata +117 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 1f2755abc6f8384a468ae09f54b92b91a0edb14a
|
4
|
+
data.tar.gz: 468f6fcca2789c7bb78648ba1b266648c53f2e88
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 86da9c51c0b89ab76ab752c75c13b437f7c3c88d33b354a60394f7c9f9be8918196f99ed068db6596fa6114ca0269e580a0e1619eefdfb07c63a8f3eac525315
|
7
|
+
data.tar.gz: 6c4bfb10c6066dc431697283c7bb863907f0bd2271b04db4e0d7fb2f03e1b6be429b96868861e4bab60456080e4161deba29880a9f0e142dc6a9038b0400cf52
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at aashish.saini@3pillarglobal.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2018 Aashish Saini
|
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 +1,43 @@
|
|
1
|
+
# TwitterStreamingApi
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/twitter_streaming_api`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'twitter_streaming_api'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install twitter_streaming_api
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
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).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/twitter_streaming_api. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
36
|
+
|
37
|
+
## License
|
38
|
+
|
39
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
40
|
+
|
41
|
+
## Code of Conduct
|
42
|
+
|
43
|
+
Everyone interacting in the TwitterStreamingApi project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/twitter_streaming_api/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "twitter_streaming_api"
|
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(__FILE__)
|
data/bin/setup
ADDED
@@ -0,0 +1,73 @@
|
|
1
|
+
require_relative "twitter_streaming_api/version"
|
2
|
+
|
3
|
+
module TwitterStreamingApi
|
4
|
+
#!/usr/bin/env ruby
|
5
|
+
require 'twitter'
|
6
|
+
require 'optparse'
|
7
|
+
require 'yaml'
|
8
|
+
|
9
|
+
class FetchTweets
|
10
|
+
# will store the values of count so that in case the program restarts it initialize the count value
|
11
|
+
@@WORDS_COUNT = {}
|
12
|
+
def initialize(time: 300, word_counts: @@WORDS_COUNT)
|
13
|
+
|
14
|
+
# build option hash to load the config file and time to fetch the tweets
|
15
|
+
# default time is 5 minutes
|
16
|
+
options = {:config_file => 'config.yml', :time => time}
|
17
|
+
|
18
|
+
# Load in Twitter connection info from config.yaml file.
|
19
|
+
puts "Loading config from #{options[:config_file]} and running for #{options[:time]} seconds"
|
20
|
+
yaml_config = YAML.load_file(options[:config_file])
|
21
|
+
|
22
|
+
# establish connection with twitter end point
|
23
|
+
client = Twitter::Streaming::Client.new do |config|
|
24
|
+
config.consumer_key = yaml_config['consumer_key']
|
25
|
+
config.consumer_secret = yaml_config['consumer_secret']
|
26
|
+
config.access_token = yaml_config['access_token']
|
27
|
+
config.access_token_secret = yaml_config['access_token_secret']
|
28
|
+
end
|
29
|
+
|
30
|
+
# pick the ignore words from config yml as we will be excluding it from result list
|
31
|
+
ignore_list = yaml_config['ignore_words'].downcase.split(',')
|
32
|
+
|
33
|
+
# List when we're starting & ending collection of Tweets
|
34
|
+
start_time = Time.now
|
35
|
+
end_time = start_time + Integer(options[:time])
|
36
|
+
puts "Analysing Twitter tweets starting at #{start_time} ending at #{end_time}"
|
37
|
+
tweets = 0
|
38
|
+
|
39
|
+
# Sample Tweets from Twitter stream until time is up.
|
40
|
+
progress_show_at = Time.now
|
41
|
+
client.sample do |object|
|
42
|
+
current_time = Time.now
|
43
|
+
break if current_time >= end_time
|
44
|
+
if progress_show_at.sec != current_time.sec
|
45
|
+
print '*'
|
46
|
+
progress_show_at = current_time
|
47
|
+
end
|
48
|
+
|
49
|
+
# ignoring non-English tweets
|
50
|
+
# Unicode could still have some weird stuff show up like 💦 so ignoring them as well
|
51
|
+
if object.is_a?(Twitter::Tweet) && object.lang == 'en'
|
52
|
+
tweets += 1
|
53
|
+
words = object.text.split(' ')
|
54
|
+
words.each do |word|
|
55
|
+
# making case insensitive so that it will be easier to compare the values
|
56
|
+
word.downcase!
|
57
|
+
unless word_counts.has_key?(word)
|
58
|
+
next if ignore_list.include?(word)
|
59
|
+
word_counts[word] = 0
|
60
|
+
end
|
61
|
+
word_counts[word] += 1
|
62
|
+
end
|
63
|
+
end
|
64
|
+
# assigning word count to class variable so that if instance reinitialize then we will have
|
65
|
+
# previous count value
|
66
|
+
@@WORDS_COUNT = word_counts
|
67
|
+
end
|
68
|
+
|
69
|
+
# displaying result at console
|
70
|
+
puts "\nTop 10 words by count in #{tweets} Tweets: #{word_counts.sort_by{|word, count| count}.reverse.take(10)}"
|
71
|
+
end
|
72
|
+
end
|
73
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "twitter_streaming_api/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "tweet_words_counter"
|
8
|
+
spec.version = TwitterStreamingApi::VERSION
|
9
|
+
spec.authors = ["Aashish Saini"]
|
10
|
+
spec.email = ["aashish.saini@3pillarglobal.com"]
|
11
|
+
|
12
|
+
spec.summary = 'Twitter streaming API (statuses/sample) to collect 5 minutes of tweets.'
|
13
|
+
spec.description = 'Twitter streaming API (statuses/sample) to collect 5 minutes of tweets.Obtain a total word count, filter out "stop words" (words like "and", "the", "me", etc -- useless words), and present the 10 most frequent words in those 5 minutes of tweets.Implement it so that if you had to stop the program and restart, it will pick up from the total word counts that you started from.'
|
14
|
+
spec.homepage = "http://www.example.com"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
18
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
19
|
+
# if spec.respond_to?(:metadata)
|
20
|
+
# spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
|
21
|
+
# else
|
22
|
+
# raise "RubyGems 2.0 or newer is required to protect against " \
|
23
|
+
# "public gem pushes."
|
24
|
+
# end
|
25
|
+
|
26
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
27
|
+
f.match(%r{^(test|spec|features)/})
|
28
|
+
end
|
29
|
+
spec.bindir = "exe"
|
30
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
31
|
+
spec.require_paths = ["lib"]
|
32
|
+
|
33
|
+
spec.add_development_dependency "bundler", "~> 1.16"
|
34
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
35
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
36
|
+
spec.add_development_dependency "twitter", '~> 6.2'
|
37
|
+
end
|
metadata
ADDED
@@ -0,0 +1,117 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: tweet_words_counter
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Aashish Saini
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-06-26 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: '1.16'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.16'
|
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: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: twitter
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '6.2'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '6.2'
|
69
|
+
description: Twitter streaming API (statuses/sample) to collect 5 minutes of tweets.Obtain
|
70
|
+
a total word count, filter out "stop words" (words like "and", "the", "me", etc
|
71
|
+
-- useless words), and present the 10 most frequent words in those 5 minutes of
|
72
|
+
tweets.Implement it so that if you had to stop the program and restart, it will
|
73
|
+
pick up from the total word counts that you started from.
|
74
|
+
email:
|
75
|
+
- aashish.saini@3pillarglobal.com
|
76
|
+
executables: []
|
77
|
+
extensions: []
|
78
|
+
extra_rdoc_files: []
|
79
|
+
files:
|
80
|
+
- ".gitignore"
|
81
|
+
- ".rspec"
|
82
|
+
- ".travis.yml"
|
83
|
+
- CODE_OF_CONDUCT.md
|
84
|
+
- Gemfile
|
85
|
+
- LICENSE.txt
|
86
|
+
- README.md
|
87
|
+
- Rakefile
|
88
|
+
- bin/console
|
89
|
+
- bin/setup
|
90
|
+
- lib/twitter_streaming_api.rb
|
91
|
+
- lib/twitter_streaming_api/version.rb
|
92
|
+
- twitter_streaming_api.gemspec
|
93
|
+
homepage: http://www.example.com
|
94
|
+
licenses:
|
95
|
+
- MIT
|
96
|
+
metadata: {}
|
97
|
+
post_install_message:
|
98
|
+
rdoc_options: []
|
99
|
+
require_paths:
|
100
|
+
- lib
|
101
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- - ">="
|
104
|
+
- !ruby/object:Gem::Version
|
105
|
+
version: '0'
|
106
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
requirements: []
|
112
|
+
rubyforge_project:
|
113
|
+
rubygems_version: 2.6.13
|
114
|
+
signing_key:
|
115
|
+
specification_version: 4
|
116
|
+
summary: Twitter streaming API (statuses/sample) to collect 5 minutes of tweets.
|
117
|
+
test_files: []
|