insta_scraper 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 38215b1a3acd833f33afb46c2eed6ce9540f8c99
+  data.tar.gz: 2fa1a3112f193457316479b58ff3b2e08ccdbb94
+SHA512:
+  metadata.gz: a0dd314dd16c00601e15c8c2575861dd4ef10d1a933c159f460abd39196723205be9103aa9bbbe70d7ace64b5fc7ca5396f2c21ce18abc93588918a2523f1968
+  data.tar.gz: 94c355556e21a3223ce191828439db47d711e997adfd818f8c6bbb65f2597bf618b7fe9bc0d0842d38dc5b607128ddf6ff7a8faa1bde7567ca6b76f521b99207

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.2.1
+before_install: gem install bundler -v 1.12.5

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in insta_scraper.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 preciz
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,67 @@
+# InstaScraper
+
+Scrapes Instagram
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'insta_scraper'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install insta_scraper
+
+## Usage
+
+Subclasses of InstaScraper::HTML are scraping html endpoints.
+Subclasses of InstaScraper::JSON are scraping json endpoints.
+
+* InstaScraper::HTML::Account
+
+```ruby
+account = InstaScraper::HTML::Account.new('barna.kovacs.codes')
+
+account.json #=> #<Hashie::Mash...
+account.json.deep_find('followed_by').fetch('count') #=> 4
+```
+
+* InstaScraper::HTML::Media
+
+```ruby
+media = InstaScraper::HTML::Media.new('BGFVAPPIaBQ')
+
+media.json #=> #<Hashie::Mash...
+media.json.deep_find('comments').fetch('count') #=> 1892
+```
+
+* InstaScraper::JSON::AccountMedia
+
+```ruby
+account_media = InstaScraper::JSON::AccountMedia.new('barna.kovacs.codes')
+
+account_media.json #=> #<Hashie::Mash...
+account_media.json.fetch('items') #=> [...]
+```
+
+## Development
+
+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.
+
+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).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/preciz/insta_scraper.
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
+

data/Rakefile

@@ -0,0 +1,10 @@
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << 'test'
+  t.libs << 'lib'
+  t.test_files = FileList['test/**/*_test.rb']
+end
+
+task default: :test

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require 'insta_scraper'
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require 'irb'
+IRB.start

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/insta_scraper.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'insta_scraper/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'insta_scraper'
+  spec.version       = InstaScraper::VERSION
+  spec.authors       = ['preciz']
+
+  spec.summary       = 'Scrapes Instagram accounts'
+  spec.description   = 'Scrapes Instagram accounts public data'
+  # spec.homepage      = "TODO: Put your gem's website or public repo URL here."
+  spec.license       = 'MIT'
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'hashie', '3.4.4'
+
+  spec.add_development_dependency 'bundler', '~> 1.12'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'minitest', '~> 5.0'
+end

data/lib/insta_scraper/html/account.rb

@@ -0,0 +1,23 @@
+module InstaScraper
+  class HTML::Account < InstaScraper::HTML
+    attr_reader :username
+
+    def initialize(username = nil, html = nil)
+      raise ArgumentError, 'Provide a username or html string' if !username && !html
+
+      @username = username
+      @html = html
+    end
+
+    def url
+      "https://www.instagram.com/#{username}/"
+    end
+
+    def json
+      @json ||=
+        Hashie::Mash.new(::JSON.parse(shared_data))
+                    .extend(Hashie::Extensions::DeepFetch)
+                    .extend(Hashie::Extensions::DeepFind)
+    end
+  end
+end

data/lib/insta_scraper/html/media.rb

@@ -0,0 +1,23 @@
+module InstaScraper
+  class HTML::Media < InstaScraper::HTML
+    attr_reader :code
+
+    def initialize(code = nil, html = nil)
+      raise ArgumentError, 'Provide a code or html string' if !code && !html
+
+      @code = code
+      @html = html
+    end
+
+    def url
+      "https://www.instagram.com/p/#{code}/"
+    end
+
+    def json
+      @json ||=
+        Hashie::Mash.new(::JSON.parse(shared_data))
+                    .extend(Hashie::Extensions::DeepFetch)
+                    .extend(Hashie::Extensions::DeepFind)
+    end
+  end
+end

data/lib/insta_scraper/html.rb

@@ -0,0 +1,31 @@
+module InstaScraper
+  class HTML
+    def html
+      @html ||= get_html
+    end
+
+    private
+
+    def get_html
+      open(url).read
+    end
+
+    private
+
+    def line_with_data
+      html.each_line.detect { |l| l[/sharedData/] }
+    end
+
+    def shared_data
+      line_with_data[shared_data_start..shared_data_end]
+    end
+
+    def shared_data_start
+      (line_with_data =~ /sharedData/) + 13
+    end
+
+    def shared_data_end
+      line_with_data =~ /\};</
+    end
+  end
+end

data/lib/insta_scraper/json/account_media.rb

@@ -0,0 +1,20 @@
+module InstaScraper
+  class JSON::AccountMedia < InstaScraper::JSON
+    attr_reader :username
+
+    def initialize(username)
+      @username = username
+    end
+
+    def url
+      "https://www.instagram.com/#{username}/media/"
+    end
+
+    def json
+      @json ||=
+        Hashie::Mash.new(::JSON.parse(raw_json))
+                    .extend(Hashie::Extensions::DeepFetch)
+                    .extend(Hashie::Extensions::DeepFind)
+    end
+  end
+end

data/lib/insta_scraper/json.rb

@@ -0,0 +1,13 @@
+module InstaScraper
+  class JSON
+    def raw_json
+      @raw_json ||= get_json
+    end
+
+    private
+
+    def get_json
+      open(url).read
+    end
+  end
+end

data/lib/insta_scraper/version.rb

@@ -0,0 +1,3 @@
+module InstaScraper
+  VERSION = '0.1.0'.freeze
+end

data/lib/insta_scraper.rb

@@ -0,0 +1,13 @@
+require 'insta_scraper/version'
+
+require 'open-uri'
+require 'json'
+
+require 'hashie'
+
+require 'insta_scraper/html'
+require 'insta_scraper/html/account'
+require 'insta_scraper/html/media'
+
+require 'insta_scraper/json'
+require 'insta_scraper/json/account_media'

metadata

@@ -0,0 +1,115 @@
+--- !ruby/object:Gem::Specification
+name: insta_scraper
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- preciz
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-06-05 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: hashie
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 3.4.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 3.4.4
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+description: Scrapes Instagram accounts public data
+email: 
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- insta_scraper.gemspec
+- lib/insta_scraper.rb
+- lib/insta_scraper/html.rb
+- lib/insta_scraper/html/account.rb
+- lib/insta_scraper/html/media.rb
+- lib/insta_scraper/json.rb
+- lib/insta_scraper/json/account_media.rb
+- lib/insta_scraper/version.rb
+homepage: 
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.6
+signing_key: 
+specification_version: 4
+summary: Scrapes Instagram accounts
+test_files: []