tag_crawler 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 471605481b6267a0dc6fabbdd9311f155d2aa408
+  data.tar.gz: bc97eda4a64a8c63ef55b2746e9c5aa3385dcf11
+SHA512:
+  metadata.gz: cb9f2043347d6e5640c3d820d925bd51ac1c6ad00f3585226cfbf8dee9fd4a4daccca436322554635dc4ca6d1858611d309b8d0aeac655f4cbb360f687ca4517
+  data.tar.gz: 9ce1eb65b8b52037543e62efac736da67c3acde1003355fa7bbeb7206abd2f820d1be7229dbdf3bf7d92c70e2403b34b790f97335a03f9622e991ff1f8d72fc7

data/.gitignore

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

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.3.1
+before_install: gem install bundler -v 1.12.5

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,49 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, and in the interest of
+fostering an open and welcoming community, we pledge to respect all people who
+contribute through reporting issues, posting feature requests, updating
+documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free
+experience for everyone, regardless of level of experience, gender, gender
+identity and expression, sexual orientation, disability, personal appearance,
+body size, race, ethnicity, age, religion, or nationality.
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery
+* Personal attacks
+* Trolling or insulting/derogatory comments
+* Public or private harassment
+* Publishing other's private information, such as physical or electronic
+  addresses, without explicit permission
+* Other unethical or unprofessional conduct
+
+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.
+
+By adopting this Code of Conduct, project maintainers commit themselves to
+fairly and consistently applying these principles to every aspect of managing
+this project. Project maintainers who do not follow or enforce the Code of
+Conduct may be permanently removed from the project team.
+
+This code of conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting a project maintainer at davidjgrey@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. Maintainers are
+obligated to maintain confidentiality with regard to the reporter of an
+incident.
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 1.3.0, available at
+[http://contributor-covenant.org/version/1/3/0/][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/3/0/

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2017 David Jiang
+
+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 +1,41 @@
+# TagCrawler
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/tag_crawler`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'tag_crawler'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install tag_crawler
+
+## Usage
+
+TODO: Write usage instructions here
+
+## 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]/tag_crawler. 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](http://opensource.org/licenses/MIT).
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

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

@@ -0,0 +1,5 @@
+#!/usr/bin/env ruby
+
+require 'tag_crawler'
+
+TagCrawler::Main.new.run

data/lib/file_writer.rb

@@ -0,0 +1,31 @@
+module TagCrawler
+
+	class FileWriter
+		def initialize(filename)
+			@filename = filename
+		end
+
+		def write(links, tags, sequences)
+			t = Time.now
+			#unique timestamp for output file
+			file = t.strftime("%Y%m%d%H%M%S") + "_" + @filename
+			open("./output/#{file}", 'w') do |f|
+				f.puts "Links"
+				f.puts "......."
+				links.each do |link|
+					f.puts link
+				end
+				f.puts "Tags"
+				f.puts "......."
+				f.puts tags.join("")
+				f.puts "Sequences"
+				f.puts "......."
+				sequences.each do |seq|
+					f.puts seq
+				end
+				puts "output/#{file} created"
+			end
+		end
+	end
+
+end

data/lib/tag_crawler/version.rb

@@ -0,0 +1,3 @@
+module TagCrawler
+  VERSION = "0.1.1"
+end

data/lib/tag_crawler.rb

@@ -0,0 +1,48 @@
+require "tag_crawler/version"
+require_relative "web_scraper"
+require_relative "file_writer"
+
+module TagCrawler
+
+PROTOCOL = /:\/\//
+VALID_PROTOCOLS = ["http", "https"]
+
+class Main
+	def run
+		validate_args
+		scraper = TagCrawler::WebScraper.new(@url)
+		puts "getting links..."
+		links = scraper.get_links
+		puts "getting tags..."
+		tags = scraper.get_tags
+		puts "getting sequences..."
+		sequences = scraper.get_sequences
+		puts "creating file..."
+		file_writer = TagCrawler::FileWriter.new(ARGV[1])
+		file_writer.write(links, tags, sequences)
+	end
+
+	def validate_args
+		if ARGV.length != 2
+			puts "Error: You must provide 2 arguments: a url and a filename."
+			exit
+		end
+		validate_url(ARGV[0])
+	end
+
+	def validate_url(url)
+		@url = url
+		url_protocol = @url.match(PROTOCOL)
+		# if no protocol, add http://
+		if(url_protocol.nil?)
+			@url = "http://" + @url
+		# print error if not valid protocol
+		elsif(!VALID_PROTOCOLS.include?(url_protocol.pre_match))
+			puts "Error: URL must have http or https protocol"
+			exit
+		end
+	end
+
+end
+
+end

data/lib/web_scraper.rb

@@ -0,0 +1,94 @@
+require 'nokogiri'
+require 'httparty'
+
+module TagCrawler
+
+	class WebScraper
+		TAG = /\<[^<>]+\>/
+		OPENING_TAG = /\<(\w+)(\>|\s([^\/]+)\>)/
+		CLOSING_TAG = /<\/(\w+)>/
+		SELF_CLOSING_TAG = /\<(\w+)(\/\>|\s*(.*)\/\>)/
+
+		def initialize(url)
+			begin
+				response = HTTParty.get(url)
+			rescue
+				puts "Error: Failed to connect to #{url}"
+				exit
+			end
+			@html_string = response.body
+			@html_doc = Nokogiri::HTML(@html_string)
+		end
+
+		def get_links()
+			links = []
+			@html_doc.xpath("//a").each do |link|
+				links << link.attributes["href"].value
+			end
+			links
+		end
+
+		def get_tags()
+			tags = []
+			tag_strings = @html_string.scan(TAG)
+			tag_strings.each do |tag|
+				if(tag_is_opener?(tag))
+					tags.push("<#{OPENING_TAG.match(tag)[1]}>")
+				elsif(tag_is_closer?(tag))
+					tags.push("</#{CLOSING_TAG.match(tag)[1]}>")
+				elsif(tag_is_self_closing?(tag))
+					tags.push("<#{SELF_CLOSING_TAG.match(tag)[1]}>")
+					tags.push("</#{SELF_CLOSING_TAG.match(tag)[1]}>")
+				end
+			end
+			tags
+		end
+
+		def get_sequences
+			nodes = get_text_nodes(@html_doc)
+			find_sequences(nodes)
+		end
+
+		private
+
+		def get_text_nodes(page)
+			page.xpath("//html/descendant::text()").map{|node| node.text}
+		end
+
+		def find_sequences(nodes)
+			sequences = []
+			nodes.each do |node|
+				words = node.split(" ")
+				current_sequence = []
+				words.each_with_index do |word, idx|
+					if(word[0] == word[0].upcase)
+						current_sequence << word
+					elsif(current_sequence.length >= 2)
+						sequences << current_sequence.join(" ")
+						current_sequence = []
+					else
+						current_sequence = []
+					end
+					if(idx == words.length-1 && current_sequence.length >= 2)
+						sequences << current_sequence.join(" ")
+					end
+				end
+			end
+			sequences
+		end
+
+		def tag_is_opener?(tag)
+			(OPENING_TAG =~ tag) == 0
+		end
+
+		def tag_is_closer?(tag)
+			(CLOSING_TAG =~ tag) == 0
+		end
+
+		def tag_is_self_closing?(tag)
+			(SELF_CLOSING_TAG =~ tag) == 0
+		end
+		
+	end
+
+end

data/tag_crawler.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'tag_crawler/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "tag_crawler"
+  spec.version       = TagCrawler::VERSION
+  spec.authors       = ["David Jiang"]
+  spec.email         = ["davidjgrey@gmail.com"]
+
+  spec.summary       = "Extracts features from an HTMl document"
+  spec.description   = "The application crawls a URL and extracts links, tags and sequences. These features are written to an output file"
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "bin"
+  spec.executables   = ["tag_crawler"]
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.12"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_runtime_dependency "nokogiri"
+  spec.add_runtime_dependency "httparty"
+end

metadata

@@ -0,0 +1,132 @@
+--- !ruby/object:Gem::Specification
+name: tag_crawler
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- David Jiang
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-03-18 00:00:00.000000000 Z
+dependencies:
+- !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: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  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: 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'
+description: The application crawls a URL and extracts links, tags and sequences.
+  These features are written to an output file
+email:
+- davidjgrey@gmail.com
+executables:
+- tag_crawler
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- bin/tag_crawler
+- lib/file_writer.rb
+- lib/tag_crawler.rb
+- lib/tag_crawler/version.rb
+- lib/web_scraper.rb
+- tag_crawler.gemspec
+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: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Extracts features from an HTMl document
+test_files: []