exquisite_corpus 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0746301260233dd47c8a66d37ce3eccb9808c12c
+  data.tar.gz: 158b58c581444b0d34d73bb2ea879adfc08d4ca6
+SHA512:
+  metadata.gz: af53c05a6da730fd32c3ee2107a681cba2a5931f36934b767ab25c3590b16969d3db04006600e388c6b6c292f01d4bb9499d1367820b713f20c4a5290a6febd3
+  data.tar.gz: 1ac765bfe2d8d798743de4aa9d1bb048ed7c64c73fb5e35ac82d01a669eb50d34cbafa90b475092d74f8a1768c624d8310dff0c2e08354793800c6aac8d8e777

data/.gitignore

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

data/.rspec

@@ -0,0 +1 @@
+--require spec_helper

data/.ruby-gemset

@@ -0,0 +1 @@
+exquisite_corpus

data/.ruby-version

@@ -0,0 +1 @@
+2.3.1

data/Gemfile

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

data/README.md

@@ -0,0 +1,67 @@
+# Exquisite Corpus
+
+Scrape sites, feeds, & files.
+Turn them to 'just text' so you can feed them to the AI gawd.  
+**You can parse any type of feed supported by [feedjira](http://feedjira.com/).**
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'exquisite_corpus'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install exquisite_corpus
+
+## Usage
+
+
+### Basic
+
+```ruby
+
+parser = ExquisiteCorpus.new(inputs: [
+    {source: 'http://example.com'},
+    {source: 'https://example.com/feed'},
+    {source: '/path/to/local/file.html'}
+])
+
+parser.parse!
+
+# A plain-text of example.com's markup
+parser.results.first.content
+
+# Want all the text?
+all_content = parser.results.map(&:content)
+
+# Export a directory of text files
+parser.export_to('/a/new/directory')
+```
+
+### Don't Scrape Dumb Stuff
+
+This library **refuses to scrape** `script`, `form`, `input`, `style` tags.
+Want to exclude more?:
+
+```ruby
+parser = ExquisiteCorpus.new(inputs: [
+    {source: 'http://example.com', except: ['array', 'of', 'cssSelectors']}
+])
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. 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/nodanaonlyzuul/exquisite_corpus.

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "exquisite_corpus"
+
+# 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/exquisite_corpus.gemspec

@@ -0,0 +1,39 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'exquisite_corpus/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "exquisite_corpus"
+  spec.version       = ExquisiteCorpus::VERSION
+  spec.authors       = ["nodanaonlyzuul"]
+  spec.email         = ["beholdthepanda@gmail.com"]
+
+  spec.summary       = %q{Scrape sites, feeds, and files. Feed them to the AI gawd.}
+  spec.homepage      = "https://github.com/nodanaonlyzuul/exquisite_corpus"
+
+  # # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # # to allow pushing to a single host or delete this section to allow pushing to any host.
+  # if spec.respond_to?(:metadata)
+  #   spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
+  # else
+  #   raise "RubyGems 2.0 or newer is required to protect against " \
+  #     "public gem pushes."
+  # end
+
+  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_dependency 'feedjira', '~> 2.0'
+  spec.add_dependency 'marky_markov', '~> 0.3.5'
+  spec.add_development_dependency 'webmock', '~> 3.0', '>= 3.0.1'
+  spec.add_development_dependency 'rspec',   '~> 3.6'
+  spec.add_development_dependency 'bundler', '~> 1.13'
+  spec.add_development_dependency 'rake',    '~> 10.0'
+  spec.add_development_dependency 'pry',     '~> 0.10.4'
+  spec.add_development_dependency 'vcr',     '~> 3.0', '>= 3.0.3'
+end

data/lib/exquisite_corpus.rb

@@ -0,0 +1,89 @@
+require 'rubygems'
+require 'open-uri'
+require 'feedjira'
+require 'nokogiri'
+require 'fileutils'
+
+require File.join(__dir__, 'result')
+
+class ExquisiteCorpus
+  attr_reader :results
+
+  REQUIRED_ARGS = [:inputs]
+  STRIPPED_TAGS = %w{script form input style}
+
+  def initialize(options = {})
+    check_for_required_args(options)
+    @inputs  = options[:inputs]
+    @results = []
+  end
+
+  def parse!
+    @inputs.each do |input|
+      response = open(input[:source]).read
+      parse_feed(input, response) || parse_html(input, response)
+    end
+  end
+
+  def export_to(path)
+    unless @results.empty?
+      path = File.expand_path(path)
+      FileUtils.mkdir_p(path)
+      @results.each do |result|
+        File.write(File.join(path, result.exported_as), result.content)
+      end
+    end
+  end
+
+private
+
+  def parse_feed(input, response)
+    begin
+      feed = Feedjira::Feed.parse(response)
+
+      feed.entries.each do |entry|
+        content = Nokogiri::HTML(entry.content).css('body')
+        @results << Result.new(
+          source:  input[:source],
+          content: content.text()
+        )
+      end
+    rescue
+      false
+    end
+  end
+
+  def parse_html(input, response)
+    begin
+      response = Nokogiri::HTML(response).css('body')
+      strip_tags!(response, input)
+
+      @results << Result.new(
+        source:  input[:source],
+        content: response.text()
+      )
+    rescue Exception => e
+      require 'pry'; binding.pry
+      false
+    end
+  end
+
+  def check_for_required_args(args)
+    REQUIRED_ARGS.each do |required_arg|
+      unless args[required_arg]
+        throw "#{required_arg} is required"
+      end
+    end
+  end
+
+  def strip_tags!(document, input)
+    strip_except_options(document, STRIPPED_TAGS.push(input[:except]).compact.flatten)
+  end
+
+  def strip_except_options(document, css_selectors)
+    css_selectors.each do |css_selector|
+      document.search(css_selector).remove
+    end
+  end
+
+end

data/lib/exquisite_corpus/version.rb

@@ -0,0 +1,3 @@
+class ExquisiteCorpus
+  VERSION = "0.1.0"
+end

data/lib/result.rb

@@ -0,0 +1,44 @@
+require 'uri'
+require 'digest'
+
+class Result
+
+  attr_reader :source, :content
+
+  def initialize(options = {})
+    @source = options[:source]
+    @content = options[:content]
+  end
+
+  def exported_as
+    if @source
+
+      if source_is_url?
+        file_basename = output_from_url(@source)
+      else
+        file_basename = "#{File.basename(@source, '.*')}"
+      end
+
+      "#{file_basename}-#{rand(900000)}.txt"
+    end
+  end
+
+private
+
+  def output_from_url(source)
+    uri = URI.parse(source)
+    output_file = uri.host
+
+    unless uri.path.empty?
+      output_file = "#{output_file}.#{File.basename(uri.path, '.*')}"
+    end
+
+    "#{output_file}.txt"
+  end
+
+  def source_is_url?
+    @uri = URI.parse(@source)
+    %w( http https ).include?(@uri.scheme)
+  end
+
+end

metadata

@@ -0,0 +1,180 @@
+--- !ruby/object:Gem::Specification
+name: exquisite_corpus
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- nodanaonlyzuul
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-06-26 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: feedjira
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: marky_markov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.5
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.5
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.0.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.0.1
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.6'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+- !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: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.4
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.4
+- !ruby/object:Gem::Dependency
+  name: vcr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.0.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.0.3
+description: 
+email:
+- beholdthepanda@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".ruby-gemset"
+- ".ruby-version"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- exquisite_corpus.gemspec
+- lib/exquisite_corpus.rb
+- lib/exquisite_corpus/version.rb
+- lib/result.rb
+homepage: https://github.com/nodanaonlyzuul/exquisite_corpus
+licenses: []
+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: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Scrape sites, feeds, and files. Feed them to the AI gawd.
+test_files: []