ig_scrape 0.0.2

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 ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: a2d0a888ba09af0188257b8924cbaa83f85b15b0
4
+ data.tar.gz: 3d17f54b10d168c4aedc8eeadb40c280ffbb3fbc
5
+ SHA512:
6
+ metadata.gz: 74804b533c38dfd21e4b49aa63380ce652f91700873f2a4916c6a3e591194d5027aa56520d9b7194c756be5016650e70234084537e239a1d76a166eb0c5f7cf3
7
+ data.tar.gz: 624898bb60e1a872e409d843947e214cb0c2691cc8fb6f1d3408d883dcdf9f5c61d86c2faf87182b9120e6cefc170b15442e6d60afa8b76fc485aef177795593
data/.gitignore ADDED
@@ -0,0 +1,9 @@
1
+ /.bundle/
2
+ /.yardoc
3
+ /Gemfile.lock
4
+ /_yardoc/
5
+ /coverage/
6
+ /doc/
7
+ /pkg/
8
+ /spec/reports/
9
+ /tmp/
data/.travis.yml ADDED
@@ -0,0 +1,5 @@
1
+ sudo: false
2
+ language: ruby
3
+ rvm:
4
+ - 2.4.0
5
+ before_install: gem install bundler -v 1.15.4
data/Gemfile ADDED
@@ -0,0 +1,6 @@
1
+ source "https://rubygems.org"
2
+
3
+ git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
4
+
5
+ # Specify your gem's dependencies in ig_scrape.gemspec
6
+ gemspec
data/LICENSE.txt ADDED
@@ -0,0 +1,21 @@
1
+ The MIT License (MIT)
2
+
3
+ Copyright (c) 2017 Trevor Kimenye
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 +1,69 @@
1
+ # IG_Scrape
2
+
3
+ This gem provides a utility for scraping instagram posts and comments
4
+
5
+ ## Installation
6
+
7
+ Add this line to your application's Gemfile:
8
+
9
+ ```ruby
10
+ gem 'ig_scrape'
11
+ ```
12
+
13
+ And then execute:
14
+
15
+ $ bundle
16
+
17
+ Or install it yourself as:
18
+
19
+ $ gem install ig_scrape
20
+
21
+ ## Usage
22
+
23
+ ### Getting information about an Instagram account
24
+
25
+ ```ruby
26
+ require 'ig_scrape'
27
+
28
+ client = IGScrape::Client.new("username")
29
+ puts client.follower_count
30
+ puts client.follows_count
31
+ puts client.post_count
32
+ ```
33
+
34
+ ### Loading all the posts for an instagram account
35
+
36
+ ```ruby
37
+ require 'ig_scrape'
38
+ client = IGScrape::Client.new("username")
39
+ client.load
40
+
41
+ puts client.posts.length == client.post_count
42
+ ```
43
+
44
+ ### Loading a post
45
+
46
+ ```ruby
47
+ require 'ig_scrape'
48
+ code = "KVHudYDs"
49
+ post = IGScrape::Post.load_from_shortcode(code)
50
+ puts post.comment_count
51
+ puts post.has_more_comments?
52
+
53
+ post.load_more_comments
54
+ puts post.has_more_comments?
55
+ ```
56
+
57
+ ## Development
58
+
59
+ After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
60
+
61
+ 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).
62
+
63
+ ## Contributing
64
+
65
+ Bug reports and pull requests are welcome on GitHub at https://github.com/ongair/ig_scrape.
66
+
67
+ ## License
68
+
69
+ The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
data/Rakefile ADDED
@@ -0,0 +1,10 @@
1
+ require "bundler/gem_tasks"
2
+ require "rake/testtask"
3
+
4
+ Rake::TestTask.new(:test) do |t|
5
+ t.libs << "test"
6
+ t.libs << "lib"
7
+ t.test_files = FileList["test/**/*_test.rb"]
8
+ end
9
+
10
+ task :default => :test
data/bin/console ADDED
@@ -0,0 +1,14 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "bundler/setup"
4
+ require "ig_scrape"
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 +1,8 @@
1
+ #!/usr/bin/env bash
2
+ set -euo pipefail
3
+ IFS=$'\n\t'
4
+ set -vx
5
+
6
+ bundle install
7
+
8
+ # Do any other automated setup that you need to do here
data/ig_scrape.gemspec ADDED
@@ -0,0 +1,31 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path("../lib", __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require "ig_scrape/version"
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = "ig_scrape"
8
+ spec.version = IGScrape::VERSION
9
+ spec.authors = ["Trevor Kimenye"]
10
+ spec.email = ["kimenye@gmail.com"]
11
+
12
+ spec.summary = %q{A gem to scrape instagram posts and comments}
13
+ spec.description = %q{A gem to scrape instagram posts and comments.}
14
+ spec.homepage = "https://github.com/ongair/ig_scrape"
15
+ spec.license = "MIT"
16
+
17
+ spec.files = `git ls-files -z`.split("\x0").reject do |f|
18
+ f.match(%r{^(test|spec|features)/})
19
+ end
20
+ spec.bindir = "exe"
21
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
22
+ spec.require_paths = ["lib"]
23
+
24
+ spec.add_development_dependency "bundler", "~> 1.15"
25
+ spec.add_development_dependency "rake", "~> 10.0"
26
+ spec.add_development_dependency "minitest", "~> 5.0"
27
+ spec.add_development_dependency "mocha"
28
+ spec.add_development_dependency "webmock"
29
+ spec.add_development_dependency "minitest-reporters"
30
+ spec.add_dependency "httparty"
31
+ end
@@ -0,0 +1,68 @@
1
+ require 'httparty'
2
+
3
+ class IGScrape::Client
4
+
5
+ attr_accessor :username, :full_name, :follower_count, :follows_count, :id ,:post_count, :profile_pic_url, :posts
6
+
7
+ def initialize(username)
8
+ @username = username
9
+ @posts = []
10
+ load_profile
11
+ end
12
+
13
+ def load
14
+ while has_more_posts? do
15
+ load_more_posts
16
+ end
17
+ end
18
+
19
+ def has_more_posts?
20
+ @posts.length < @post_count
21
+ end
22
+
23
+ def loaded_post_count
24
+ @posts.length
25
+ end
26
+
27
+ private
28
+
29
+ def load_profile
30
+ url = "https://www.instagram.com/#{@username}/?__a=1"
31
+ resp = HTTParty.get(url)
32
+
33
+ response = JSON.parse(resp.body)
34
+ user = response["user"]
35
+ @full_name = user["full_name"]
36
+ @follower_count = user["followed_by"]["count"]
37
+ @follows_count = user["follows"]["count"]
38
+ @id = user["id"]
39
+ @post_count = user["media"]["count"]
40
+ @page_info = user["media"]["page_info"]
41
+ @profile_pic_url = user["profile_pic_url"]
42
+
43
+ media = user["media"]["nodes"]
44
+ if media
45
+ @posts = media.collect do |node|
46
+ IGScrape::Post.new(node)
47
+ end
48
+ end
49
+ end
50
+
51
+ def load_more_posts
52
+ cursor = @page_info["end_cursor"]
53
+
54
+ variables = URI.encode_www_form_component("{\"id\":\"#{@id}\",\"first\":12,\"after\":\"#{cursor}\"}")
55
+ url = "https://www.instagram.com/graphql/query/?query_id=17888483320059182&variables=#{variables}"
56
+
57
+ resp = HTTParty.get(url)
58
+ response = JSON.parse(resp.body)
59
+ timeline = response["data"]["user"]["edge_owner_to_timeline_media"]
60
+ @page_info = timeline["page_info"]
61
+ new_posts = timeline["edges"].collect do |edge|
62
+ IGScrape::Post.new(IGScrape::Post.edge_timeline_to_payload(edge["node"]))
63
+ end
64
+
65
+ @posts = @posts.concat(new_posts)
66
+ end
67
+
68
+ end
@@ -0,0 +1,19 @@
1
+ class IGScrape::Comment
2
+
3
+ attr_accessor :id, :text, :created_at, :author_id, :author_name, :author_profile_pic
4
+
5
+ def initialize(payload)
6
+ load_from_payload(payload)
7
+ end
8
+
9
+ private
10
+
11
+ def load_from_payload payload
12
+ @id = payload["id"]
13
+ @text = payload["text"]
14
+ @created_at = payload["created_at"]
15
+ @author_id = payload["owner"]["id"]
16
+ @author_profile_pic = payload["owner"]["profile_pic_url"]
17
+ @author_name = payload["owner"]["username"]
18
+ end
19
+ end
@@ -0,0 +1,81 @@
1
+ class IGScrape::Post
2
+
3
+ attr_accessor :id, :comment_count, :likes, :is_video, :code, :display_src, :caption, :created_at, :type, :comments
4
+
5
+ def initialize payload
6
+ @comments = []
7
+ load_from_payload(payload)
8
+ end
9
+
10
+ def self.load_from_shortcode code
11
+ url = "https://www.instagram.com/p/#{code}/?__a=1"
12
+ resp = HTTParty.get(url)
13
+ response = JSON.parse(resp.body)
14
+ payload = response["graphql"]["shortcode_media"]
15
+
16
+ post = IGScrape::Post.new(self.edge_timeline_to_payload(payload))
17
+ end
18
+
19
+ def has_more_comments?
20
+ @comments.length < @comment_count
21
+ end
22
+
23
+ def load_comments
24
+ while has_more_comments? do
25
+ load_more_comments
26
+ end
27
+ end
28
+
29
+ def self.edge_timeline_to_payload node
30
+ {
31
+ "id" => node["id"],
32
+ "__typename" => node["__typename"],
33
+ "is_video" => node["is_video"],
34
+ "code" => node["shortcode"],
35
+ "display_src" => node["display_url"],
36
+ "caption" => (node["edge_media_to_caption"]["edges"].length > 0 ? node["edge_media_to_caption"]["edges"].first["node"]["text"] : ""),
37
+ "date" => node["taken_at_timestamp"],
38
+ "comments" => node["edge_media_to_comment"],
39
+ "likes" => node["edge_media_preview_like"]
40
+ }
41
+ end
42
+
43
+ private
44
+
45
+ def load_more_comments
46
+ cursor = @comment_page_info["end_cursor"]
47
+ variables = URI.encode_www_form_component("{\"shortcode\":\"#{@code}\",\"first\":20,\"after\":\"#{cursor}\"}")
48
+
49
+ url = "https://www.instagram.com/graphql/query/?query_id=17852405266163336&variables=#{variables}"
50
+ resp = HTTParty.get(url)
51
+ response = JSON.parse(resp.body)
52
+
53
+ edges = response["data"]["shortcode_media"]["edge_media_to_comment"]["edges"]
54
+ new_comments = edges.collect do |edge|
55
+ IGScrape::Comment.new(edge["node"])
56
+ end
57
+
58
+ @comment_page_info = response["data"]["shortcode_media"]["edge_media_to_comment"]["page_info"]
59
+ @comments = @comments.concat(new_comments)
60
+ end
61
+
62
+ def load_from_payload payload
63
+ @id = payload["id"]
64
+ @is_video = payload["is_video"]
65
+ @type = payload["__typename"]
66
+ @caption = payload["caption"]
67
+ @created_at = payload["date"]
68
+ @display_src = payload["display_src"]
69
+ @code = payload["code"]
70
+ @likes = payload["likes"]["count"]
71
+ @comment_count = payload["comments"]["count"]
72
+ @comment_page_info = payload["comments"]["page_info"]
73
+
74
+ # load comments
75
+ if payload["comments"]["edges"]
76
+ @comments = payload["comments"]["edges"].collect do |edge|
77
+ IGScrape::Comment.new(edge["node"])
78
+ end
79
+ end
80
+ end
81
+ end
@@ -0,0 +1,3 @@
1
+ module IGScrape
2
+ VERSION = "0.0.2"
3
+ end
data/lib/ig_scrape.rb ADDED
@@ -0,0 +1,4 @@
1
+ require "ig_scrape/version"
2
+ require "ig_scrape/client"
3
+ require "ig_scrape/post"
4
+ require "ig_scrape/comment"
metadata ADDED
@@ -0,0 +1,156 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: ig_scrape
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.2
5
+ platform: ruby
6
+ authors:
7
+ - Trevor Kimenye
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2017-09-25 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: '1.15'
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '1.15'
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: minitest
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: '5.0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - "~>"
53
+ - !ruby/object:Gem::Version
54
+ version: '5.0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: mocha
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: webmock
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: minitest-reporters
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - ">="
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: httparty
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :runtime
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ description: A gem to scrape instagram posts and comments.
112
+ email:
113
+ - kimenye@gmail.com
114
+ executables: []
115
+ extensions: []
116
+ extra_rdoc_files: []
117
+ files:
118
+ - ".gitignore"
119
+ - ".travis.yml"
120
+ - Gemfile
121
+ - LICENSE.txt
122
+ - README.md
123
+ - Rakefile
124
+ - bin/console
125
+ - bin/setup
126
+ - ig_scrape.gemspec
127
+ - lib/ig_scrape.rb
128
+ - lib/ig_scrape/client.rb
129
+ - lib/ig_scrape/comment.rb
130
+ - lib/ig_scrape/post.rb
131
+ - lib/ig_scrape/version.rb
132
+ homepage: https://github.com/ongair/ig_scrape
133
+ licenses:
134
+ - MIT
135
+ metadata: {}
136
+ post_install_message:
137
+ rdoc_options: []
138
+ require_paths:
139
+ - lib
140
+ required_ruby_version: !ruby/object:Gem::Requirement
141
+ requirements:
142
+ - - ">="
143
+ - !ruby/object:Gem::Version
144
+ version: '0'
145
+ required_rubygems_version: !ruby/object:Gem::Requirement
146
+ requirements:
147
+ - - ">="
148
+ - !ruby/object:Gem::Version
149
+ version: '0'
150
+ requirements: []
151
+ rubyforge_project:
152
+ rubygems_version: 2.6.11
153
+ signing_key:
154
+ specification_version: 4
155
+ summary: A gem to scrape instagram posts and comments
156
+ test_files: []