fb_scrape 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1ab9e7be1ccd90aba528b2d6066ca78a88d52b2f
+  data.tar.gz: 3332a40809f0d331fc26442b4b9a89bb24a9facd
+SHA512:
+  metadata.gz: f25735dc3e5d82e38f70077f59a31bf55814e54378c1c8fb23472bfafe1ca76a7b6e5e74cfe6f77e569867fb9d08aaa7c37c679b2208a502b647cd7405acaafa
+  data.tar.gz: '08c38ed64d2007ddc243c58011ca8b2e74f0f1364076f0e828b37e647d3741084e3c5e278988863b6726e888e4cfe73be3212a0ef010674f9a39ec7835b6de5b'

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:
+  - 2.4.0
+before_install: gem install bundler -v 1.15.4

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in fb_scrape.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2017 Trevor Kimenye
+
+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 +1,102 @@
+# FB_Scrape
+
+This gem provides a utility for scraping facebook posts and comments. You will require a facebook app id
+to use this gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+  gem 'fb_scrape'
+```
+
+And then execute:
+```ruby
+    $ bundle
+```
+Or install it yourself as:
+```ruby
+    $ gem install fb_scrape
+```
+## Usage
+
+### Getting information about a Facebook page
+
+  ```ruby
+    require 'fb_scrape'
+
+    client = FBScrape::Client.new("page_name", "access_token")
+    puts client.id
+    puts client.name
+  ```
+
+### Loading all the posts for an Facebook account  
+
+  ```ruby
+    require 'fb_scrape'
+    client = FBScrape::Client.new("page_name", "access_token", "page_id")
+    client.load
+
+    puts client.posts.length
+  ```
+
+### Loading a post
+
+  ```ruby
+    require 'fb_scrape'
+
+    post = FBScrape::Post.load_from_id(id, access_token)    
+    puts post.has_more_comments?
+
+    post.load_all_comments
+    puts post.has_more_comments?
+  ```
+
+
+### Loading a comment and its replies
+
+  ```ruby
+    require 'fb_scrape'
+
+    comment = FBScrape::Comment.new(payload, access_token, page_id)
+    comment.load_replies
+
+    puts comment.comments.count
+    puts comment.has_more_replies?
+    comment.load_all_replies
+    puts comment.comments.count
+  ```
+
+### Using the CLI
+
+  You can use the CLI to get a dump in JSON of posts and comments
+
+  ```
+    gem install fb_scrape
+
+    fb_scrape help
+
+    # get the page id for a url
+    fb_scrape id --page_name theusername --token token
+
+    # load all the posts for an account
+    fb_scrape posts --page_name theusername --token token
+
+    # load all the comments for a post
+    fb_scrape comments --id post_id --token token --page_id page_id
+  ```
+
+## 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/ongair/ig_scrape.
+
+## 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 "fb_scrape"
+
+# 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(__FILE__)

data/bin/fb_scrape

@@ -0,0 +1,55 @@
+#!/usr/bin/env ruby
+
+require 'fb_scrape'
+require 'thor'
+require 'json'
+
+class FBScrape::CLI < Thor
+
+  desc "id", "Get the page_id for page"
+  option :page_name, :required => true
+  option :token, :required => true
+  def id
+    begin
+      client = FBScrape::Client.new(options[:page_name], options[:token])
+      client.init
+      puts client.id
+    rescue ArgumentError => e
+      puts e.message
+    end
+  end
+
+  desc "posts", "Get all the posts for the page"
+  option :page_id, :required => true
+  option :token, :required => true
+  def posts
+    begin
+      client = FBScrape::Client.new(nil, options[:token], options[:page_id])
+      client.load
+      posts = client.posts
+      puts JSON.pretty_generate(posts)
+    rescue ArgumentError => e
+      puts e.message
+    end
+  end
+
+  desc "comments", "Get all the comments for a post's shortcode"
+  option :id, :required => true
+  option :token, :required => true
+  option :page_id, :required => false
+  def comments
+    begin
+      # post = FBScrape::Post.load_from_shortcode(options[:shortcode])
+      post = FBScrape::Post.load_from_id(options[:id], options:[token])
+      post.load_all_comments
+
+      comments = post.comments
+      puts JSON.pretty_generate(comments)
+    rescue ArgumentError => e
+      puts e.message
+    end
+  end
+
+end
+
+IGScrape::CLI.start(ARGV)

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/fb_scrape.gemspec

@@ -0,0 +1,31 @@
+# coding: utf-8
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "fb_scrape/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "fb_scrape"
+  spec.version       = FBScrape::VERSION
+  spec.authors       = ["Trevor Kimenye"]
+  spec.email         = ["kimenye@gmail.com"]
+
+  spec.summary       = %q{A gem to scrape facebook posts and comments}
+  spec.description   = %q{A gem to scrape facebook posts and comments}
+  spec.homepage      = "https://github.com/ongair/fb_scrape"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.15"
+  spec.add_development_dependency "minitest-reporters"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "minitest", "~> 5.0"
+  spec.add_development_dependency "webmock"
+  spec.add_dependency "httparty"
+  spec.add_dependency "thor"
+end

data/lib/fb_scrape/client.rb

@@ -0,0 +1,78 @@
+require 'httparty'
+
+class FBScrape::Client
+
+  attr_accessor :page_name, :id, :name, :posts
+
+  def initialize(page_name, token_secret, id=nil)
+    @page_name = page_name
+    @token_secret = token_secret
+    @id = id
+    @posts = []
+    @loaded_initial = false
+    if @id
+      load_initial_posts
+    else
+      get_page_id
+    end
+  end
+
+  def load
+    load_initial_posts
+    while has_more_posts? do
+      # load more posts
+      load_more_posts
+    end
+  end
+
+  def has_more_posts?
+    @page_info && next_cursor
+  end
+
+  private
+
+    def load_initial_posts
+      if !@loaded_initial
+        url = "https://graph.facebook.com/v#{FBScrape::GRAPH_VERSION}/#{@id}/posts?access_token=#{@token_secret}"
+        load_posts_from_url url
+        @loaded_initial = true
+      end
+    end
+
+    def load_more_posts
+      url = "https://graph.facebook.com/v#{FBScrape::GRAPH_VERSION}/#{id}/posts?access_token=#{@token_secret}&limit=25&after=#{next_cursor}"
+      load_posts_from_url url
+    end
+
+    def load_posts_from_url url
+      resp = HTTParty.get(url)
+      case resp.code
+        when 200
+          response = JSON.parse(resp.body)
+          more_posts = response["data"].collect { |p| FBScrape::Post.new(p) }
+          @posts = @posts.concat(more_posts)
+          @page_info = response["paging"]
+      end
+    end
+
+    def next_cursor
+      @page_info["cursors"]["after"]
+    end
+
+    def get_page_id
+      url = "https://graph.facebook.com/#{@page_name}?access_token=#{@token_secret}"
+      resp = HTTParty.get(url)
+
+      case resp.code
+        when 200
+          response = JSON.parse(resp.body)
+          @name = response["name"]
+          @id = response["id"]
+        when 400
+          response = JSON.parse(resp.body)
+          error = response["error"]["message"]
+          raise ArgumentError.new(error)
+      end
+    end
+
+end

data/lib/fb_scrape/comment.rb

@@ -0,0 +1,69 @@
+require 'json'
+
+class FBScrape::Comment
+
+  attr_accessor :id, :created_at, :from_name, :from_id, :message, :comments
+
+  def initialize(payload, access_token=nil, page_id=nil)
+    @comments = []
+    @access_token = access_token
+    @page_id = page_id
+    load_from_payload payload
+  end
+
+  def is_page_response?
+    @page_id == @from_id
+  end
+
+  def load_replies access_token=nil
+    @access_token = access_token if access_token
+    url = "https://graph.facebook.com/v#{FBScrape::GRAPH_VERSION}/#{@id}/comments?access_token=#{@access_token}"
+    load_from_url url
+  end
+
+  def has_more_replies?
+    @page_info && next_cursor
+  end
+
+  def load_all_replies
+    while has_more_replies? do
+      load_more_replies
+    end
+  end
+
+  private
+
+    def next_cursor
+      @page_info["cursors"]["next"]
+    end
+
+    def load_more_replies
+      url = "https://graph.facebook.com/v#{FBScrape::GRAPH_VERSION}/#{@id}/comments?access_token=#{@access_token}&limit=25&after=next_cursor"
+      load_from_url url
+    end
+
+    def load_from_url url
+
+      resp = HTTParty.get(url)
+
+      case resp.code
+        when 200
+          response = JSON.parse(resp)
+          @comments = @comments.concat(response["data"].collect{ |c| FBScrape::Comment.new(c, @access_token, @page_id) })
+          @page_info = response["paging"]
+      end
+    end
+
+    def load_from_payload payload
+      if payload
+        @id =  payload['id']
+        @created_at = payload['created_at']
+        @message = payload['message']
+
+        if payload['from']
+          @from_name = payload['from']['name']
+          @from_id = payload['from']['id']
+        end
+      end
+    end
+end

data/lib/fb_scrape/post.rb

@@ -0,0 +1,65 @@
+require 'json'
+
+class FBScrape::Post
+
+  attr_accessor :id, :created_at, :message, :comments
+
+  def initialize payload
+    @comments = []
+
+    if payload
+      load_from_payload(payload)
+    end
+  end
+
+  def self.load_from_id id, access_token
+    post = FBScrape::Post.new({ 'id' => id })
+    post.load_comments(access_token)
+    post
+  end
+
+  def load_comments token
+    @token = token
+    url = "https://graph.facebook.com/v#{FBScrape::GRAPH_VERSION}/#{@id}/comments?access_token=#{@token}"
+    load_from_url url
+  end
+
+  def has_more_comments?
+    @page_info && next_cursor
+  end
+
+  def load_all_comments
+    while has_more_comments? do
+      load_more_comments
+    end
+  end
+
+  private
+
+    def load_from_url url
+      resp = HTTParty.get(url)
+
+      case resp.code
+        when 200
+          response = JSON.parse(resp.body)
+          @comments = @comments.concat(response["data"].collect{ |c| FBScrape::Comment.new(c) })
+          @page_info = response["paging"]
+      end
+    end
+
+    def load_more_comments
+      url = "https://graph.facebook.com/v#{FBScrape::GRAPH_VERSION}/#{@id}/comments?access_token=#{@token}&limit=15&after=#{next_cursor}"
+      load_from_url url
+    end
+
+
+    def next_cursor
+      @page_info["cursors"]["after"]
+    end
+
+    def load_from_payload payload
+      @id = payload["id"]
+      @created_at = payload["created_at"]
+      @message = payload["message"]
+    end
+end

data/lib/fb_scrape/version.rb

@@ -0,0 +1,3 @@
+module FBScrape
+  VERSION = "0.0.1"
+end

data/lib/fb_scrape.rb

@@ -0,0 +1,8 @@
+require "fb_scrape/version"
+require "fb_scrape/client"
+require "fb_scrape/post"
+require "fb_scrape/comment"
+
+module FBScrape
+  GRAPH_VERSION = "2.10"
+end

metadata

@@ -0,0 +1,157 @@
+--- !ruby/object:Gem::Specification
+name: fb_scrape
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Trevor Kimenye
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-10-09 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+- !ruby/object:Gem::Dependency
+  name: minitest-reporters
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: httparty
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: thor
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A gem to scrape facebook posts and comments
+email:
+- kimenye@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/fb_scrape
+- bin/setup
+- fb_scrape.gemspec
+- lib/fb_scrape.rb
+- lib/fb_scrape/client.rb
+- lib/fb_scrape/comment.rb
+- lib/fb_scrape/post.rb
+- lib/fb_scrape/version.rb
+homepage: https://github.com/ongair/fb_scrape
+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: 2.6.11
+signing_key: 
+specification_version: 4
+summary: A gem to scrape facebook posts and comments
+test_files: []