link_scraper 1.01

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 763fe1b9044fc08f804e6949a2d3f996876d4720554238315d190853e246f8e1
+  data.tar.gz: 8686914221781dac64b47a71a0269d220f6f64470c0495bc77c8916e2af4b913
+SHA512:
+  metadata.gz: 9107b027d965d5fdc610313504299752cc33e0726ef8041c69b8d4c4a5d291c836e30f9ebfd4cb87dfac8ee6eca82d9b7b79134ae8fde8ffe58afa5fc704ece9
+  data.tar.gz: 63e57e717fed2a090d42c6ad2bdc8983d9db5dc3f106b59483f1c3a96d57cc8ffc1dba8019ecde92d35bd2611ec7dd5d4be97b169aa7b0f7b4037dd5c698b759

data/.gitignore

@@ -0,0 +1,16 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/pkg/
+/spec/reports/
+/tmp/
+
+link_scraper-*.gem
+.DS_Store
+.idea/
+.xlsx
+.txt
+.gemspec
+!seed.csv

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.5.1
+before_install: gem install bundler -v 1.16.2

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at 4rlm@protonmail.ch. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

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 link_scraper.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2018 Adam Booth
+
+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 +1,47 @@
+# LinkScraper
+
+[![Gem Version](https://badge.fury.io/rb/link_scraper.svg)](https://badge.fury.io/rb/link_scraper)
+[![MIT License](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+#### Scrape website links' text and href with built-in scrubbing filter.  
+
+Designed to rapidly visit and scrape links from list of several URLs, then filters them based on your criteria.  For example, to only grab the links for inventory, staff, or contact us, etc.
+
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'link_scraper'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install link_scraper
+
+## Usage
+
+### COMING SOON - GEM IS CURRENTLY BEING DEVELOPED.
+
+## Development
+
+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.
+
+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/[USERNAME]/link_scraper. 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.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the LinkScraper project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/link_scraper/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,49 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+require 'link_scraper'
+require 'webs_criteria'
+
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec
+task :test => :spec
+
+###################
+task :console do
+  require 'irb'
+  require 'irb/completion'
+  require 'link_scraper'
+  require "active_support/all"
+  ARGV.clear
+
+  scraped_links = run_link_scraper
+  # binding.pry
+
+  IRB.start
+end
+
+
+def run_link_scraper
+  urls = %w[
+    austinchevrolet.not.real
+    smith_acura.com/staff
+    abcrepair.ca
+    hertzrentals.com/review
+    londonhyundai.uk/fleet
+    http://www.townbuick.net/staff
+    http://youtube.com/download
+    www.madridinfiniti.es/collision
+    www.mitsubishideals.sofake
+    www.dallassubaru.com.sofake
+    www.quickeats.net/contact_us
+    www.school.edu/teachers
+    www.www.nissancars/inventory
+    www.www.toyotatown.net/staff/management
+    www.www.yellowpages.com/business
+  ]
+
+  binding.pry
+  scraper_obj = LinkScraper::Scrape.new(WebsCriteria.all_scrub_web_criteria)
+  scraped_links = scraper_obj.scrub_urls(urls)
+end

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "link_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(__FILE__)

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/lib/link_scraper.rb

@@ -0,0 +1,7 @@
+require "link_scraper/version"
+# require 'crm_formatter'
+# require 'pry'
+
+module LinkScraper
+  # Your code goes here...
+end

data/lib/link_scraper/version.rb

@@ -0,0 +1,3 @@
+module LinkScraper
+  VERSION = "1.01"
+end

data/lib/webs_criteria.rb

@@ -0,0 +1,55 @@
+# WebsCriteria.new.all_scrub_web_criteria
+
+class WebsCriteria
+
+  def self.all_scrub_web_criteria
+    {
+      neg_urls: seed_neg_urls,
+      pos_urls: seed_pos_urls,
+      neg_paths: seed_neg_paths,
+      pos_paths: seed_pos_paths,
+      neg_exts: seed_neg_exts,
+      pos_exts: seed_pos_exts
+    }
+  end
+
+  def self.seed_neg_urls
+    %w(approv avis budget collis eat enterprise facebook financ food google gourmet hertz hotel hyatt insur invest loan lube mobility motel motorola parts quick rent repair restaur rv ryder service softwar travel twitter webhost yellowpages yelp youtube)
+  end
+
+  def self.seed_pos_urls
+    ["acura", "alfa romeo", "aston martin", "audi", "bmw", "bentley", "bugatti", "buick", "cdjr", "cadillac", "chevrolet", "chrysler", "dodge", "ferrari", "fiat", "ford", "gmc", "group", "group", "honda", "hummer", "hyundai", "infiniti", "isuzu", "jaguar", "jeep", "kia", "lamborghini", "lexus", "lincoln", "lotus", "mini", "maserati", "mazda", "mclaren", "mercedes-benz", "mitsubishi", "nissan", "porsche", "ram", "rolls-royce", "saab", "scion", "smart", "subaru", "suzuki", "toyota", "volkswagen", "volvo"]
+  end
+
+  def self.seed_neg_paths
+    %w(: .biz .co .edu .gov .jpg .net // afri anounc book business buy bye call cash cheap click collis cont distrib download drop event face feature feed financ find fleet form gas generat graphic hello home hospi hour hours http info insta inventory item join login mail mailto mobile movie museu music news none offer part phone policy priva pump rate regist review schedul school service shop site test ticket tire tv twitter watch www yelp youth)
+  end
+
+  def self.seed_pos_paths
+    %w(team staff management)
+  end
+
+  def self.seed_neg_exts
+     %w(au ca edu es gov in ru uk us)
+  end
+
+  def self.seed_pos_exts
+     %w(com net)
+  end
+
+  # def self.seed_neg_hrefs
+  #   %w(? .com .jpg @ * afri after anounc apply approved blog book business buy call care career cash charit cheap check click collis commerc cont contrib deal distrib download employ event face feature feed financ find fleet form gas generat golf here holiday hospi hour info insta inventory join later light login mail mobile movie museu music news none now oil part pay phone policy priva pump quick quote rate regist review saving schedul service shop sign site speci ticket tire today transla travel truck tv twitter watch youth)
+  # end
+  #
+  # def self.seed_pos_hrefs
+  #   %w(team staff management)
+  # end
+
+
+  # ##Rails C: StartCrm.run_scrub_webs
+  # def self.get_urls
+  #   urls = %w(approvedautosales.org autosmartfinance.com leessummitautorepair.net melodytoyota.com northeastacura.com gemmazda.com)
+  #   urls += %w(Scrubwebsite.com Scrubwebsite.business.site Scrubwebsite Scrubwebsite.fake Scrubwebsite.fake.com Scrubwebsite.com.fake)
+  # end
+
+end

data/link_scraper.gemspec

@@ -0,0 +1,78 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "link_scraper/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "link_scraper"
+  spec.version       = LinkScraper::VERSION
+  spec.authors       = ["Adam Booth"]
+  spec.email         = ["4rlm@protonmail.ch"]
+  spec.homepage      = 'https://github.com/4rlm/scrub_db'
+  spec.license       = "MIT"
+
+  spec.summary       = %q{Scrape website links' text and href with built-in scrubbing filter.}
+  spec.description   = %q{Scrape website links' text and href with built-in scrubbing filter.  Designed to rapidly visit and scrape links from list of several URLs, then filters them based on your criteria.  For example, to only grab the links for inventory, staff, or contact us, etc.}
+
+
+  if spec.respond_to?(:metadata)
+    spec.metadata['allowed_push_host'] = 'https://rubygems.org'
+  else
+    raise 'RubyGems 2.0 or newer is required to protect against ' \
+      'public gem pushes.'
+  end
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  # spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+  #   `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  # 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.required_ruby_version = '~> 2.5.1'
+  spec.add_dependency 'activesupport', '~> 5.2'
+  spec.add_dependency 'utf8_sanitizer', '~> 2.16'
+  spec.add_dependency 'crm_formatter', '~> 2.61'
+  spec.add_dependency 'mechanizer', '~> 1.11'
+  spec.add_dependency 'scrub_db', '~> 2.22'
+  spec.add_dependency 'url_verifier', '~> 2.12'
+
+  # spec.add_dependency "activesupport-inflector", ['~> 0.1.0']
+  spec.add_development_dependency 'bundler', '~> 1.16', '>= 1.16.2'
+  spec.add_development_dependency 'pry', '~> 0.11.3'
+  spec.add_development_dependency 'rake', '~> 12.3', '>= 12.3.1'
+  spec.add_development_dependency 'rspec', '~> 3.7'
+  # spec.add_development_dependency 'byebug', '~> 10.0', '>= 10.0.2'
+  # spec.add_development_dependency 'class_indexer', '~> 0.3.0'
+  # spec.add_development_dependency 'irbtools', '~> 2.2', '>= 2.2.1'
+  # spec.add_development_dependency 'rubocop', '~> 0.56.0'
+  # spec.add_development_dependency 'ruby-beautify', '~> 0.97.4'
+  # spec.add_runtime_dependency 'library', '~> 2.2'
+  # spec.add_dependency 'activerecord', '>= 3.0'
+  # spec.add_dependency 'actionpack', '>= 3.0'
+  # spec.add_dependency 'polyamorous', '~> 1.3.2'
+  # spec.add_development_dependency 'machinist', '~> 1.0.6'
+  # spec.add_development_dependency 'faker', '~> 0.9.5'
+  # spec.add_development_dependency 'sqlite3', '~> 1.3.3'
+  # spec.add_development_dependency 'pg', '~> 0.21'
+  # spec.add_development_dependency 'mysql2', '0.3.20'
+
+  # spec.requirements << 'libmagick, v6.0'
+  # spec.requirements << 'A good graphics card'
+  # # This gem will work with 1.8.6 or greater...
+  # spec.required_ruby_version = '>= 1.8.6'
+  #
+  # # Only with ruby 2.0.x
+  # spec.required_ruby_version = '~> 2.0'
+  #
+  # # Only with ruby between 2.2.0 and 2.2.2
+  # spec.required_ruby_version = ['>= 2.2.0', '< 2.2.3']
+
+end

metadata

@@ -0,0 +1,214 @@
+--- !ruby/object:Gem::Specification
+name: link_scraper
+version: !ruby/object:Gem::Version
+  version: '1.01'
+platform: ruby
+authors:
+- Adam Booth
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-07-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.2'
+- !ruby/object:Gem::Dependency
+  name: utf8_sanitizer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.16'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.16'
+- !ruby/object:Gem::Dependency
+  name: crm_formatter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.61'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.61'
+- !ruby/object:Gem::Dependency
+  name: mechanizer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+- !ruby/object:Gem::Dependency
+  name: scrub_db
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.22'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.22'
+- !ruby/object:Gem::Dependency
+  name: url_verifier
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.12'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.12'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.16.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.16.2
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.11.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.11.3
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '12.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 12.3.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '12.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 12.3.1
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.7'
+description: Scrape website links' text and href with built-in scrubbing filter.  Designed
+  to rapidly visit and scrape links from list of several URLs, then filters them based
+  on your criteria.  For example, to only grab the links for inventory, staff, or
+  contact us, etc.
+email:
+- 4rlm@protonmail.ch
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/link_scraper.rb
+- lib/link_scraper/version.rb
+- lib/webs_criteria.rb
+- link_scraper.gemspec
+homepage: https://github.com/4rlm/scrub_db
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - "~>"
+    - !ruby/object:Gem::Version
+      version: 2.5.1
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.7.6
+signing_key: 
+specification_version: 4
+summary: Scrape website links' text and href with built-in scrubbing filter.
+test_files: []