sport_headlines 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 72dad286df2f6d0b59bd5748e921c97fc578f109
+  data.tar.gz: b32b3d3d95b27ea4aa1ff639dd58e3f24099605f
+SHA512:
+  metadata.gz: 2b12256526bcc632458d6ceaa68af3b4141ffe2f3363c7bfa67e48967484ab4d23fc9963b1cfe2335edb26feb4ff4a54adac32c863ec24ad2416335e3607e015
+  data.tar.gz: 6a3b96c0f0621f9788a7a8d57b40d0e9ecc09e456e3b6a115311da1fe23e5c7fe06f938e1d0bd524cf40dce6b1cf1628c4a0de34f91547a75f4ef3a463a678f9

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 +1,4 @@
+language: ruby
+rvm:
+  - 2.2.3
+before_install: gem install bundler -v 1.11.2

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 cernanb@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 sport_headlines.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 cernanb
+
+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 +1,38 @@
+# SportHeadlines
+
+Welcome to my Sport Headlines Aggregator gem! This gem will scrape the top headlines for 4 separate sports websites and you will be able to choose the site and the article you would like to view the content for. I built this gem as a project for the Flatiron School's Learn Verified Full Stack Web Development online program. I hope you enjoy it!
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'sport_headlines'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install sport_headlines
+
+## 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]/sport_headlines. 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 "sport_headlines"
+
+# 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/sport_headlines

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "sport_headlines"
+
+SportHeadlines::CLI.new.call

data/lib/sport_headlines/article.rb

@@ -0,0 +1,9 @@
+class SportHeadlines::Article
+  attr_accessor :title, :content, :article_url, :site
+
+  def print_content
+    puts self.content
+    puts ""
+  end
+
+end

data/lib/sport_headlines/cli.rb

@@ -0,0 +1,43 @@
+class SportHeadlines::CLI
+  def call
+    puts "Welcome to the Sports Headlines Aggregator."
+    puts ""
+    SportHeadlines::Site.create_sites_from_hash
+    start
+  end
+
+  def start
+    # sites = SportHeadlines::Site.all
+    scraper = SportHeadlines::Scraper
+    puts ""
+    input = nil
+    while input != 'exit'
+      puts "Please select a site - by number you would like to view the top headlines from. Enter exit to end the program"
+      puts ""
+      list_sites
+      puts ""
+      input = gets.strip
+      if input.to_i.between?(1,sites.size)
+        site = SportHeadlines::Site.find(input)
+        site.scrape_headlines!
+        # scraper.scrape_site_headlines(sites[input.to_i-1])
+
+        puts "Select an article to read its content."
+        puts ""
+        site.list_articles
+        article_input = gets.strip
+        article = site.scrape_article(article_input) # preps the article, and returns the instance of the article
+        # scraper.scrape_article(sites[input.to_i-1].articles[article_input.to_i - 1])
+        article.print_content
+
+        # sites[input.to_i-1].articles[article_input.to_i - 1].print_content
+      end
+    end
+  end
+
+  def list_sites
+    SportHeadlines::Site.all.each_with_index do |site, index|
+      puts "#{index +1}. #{site.site_name}"
+    end
+  end
+end

data/lib/sport_headlines/scraper.rb

@@ -0,0 +1,55 @@
+module SportHeadlines::Scraper
+
+  def self.scrape_site_headlines(site)
+    binding.pry
+    doc = Nokogiri::HTML(open(site.site_url))
+    site.clear_articles
+    if site.site_name == "ESPN"
+      doc.search(".headlines li").each do |headline|
+        new_article ||= SportHeadlines::Article.new
+        new_article.title ||= headline.search("a").text
+        new_article.article_url ||= site.site_url + headline.search("a").attribute("href").value
+
+        # site.add_article(new_article)
+        new_article.site = site # has two jobs, first, association the site with the article, then inform the site of the new article
+      end
+    elsif site.site_name == "Bleacher Report"
+      doc.search(".headlineArticles li").each do |headline|
+        new_article = SportHeadlines::Article.new
+        new_article.title = headline.search("span.title").text
+        new_article.article_url = headline.search("a.title").attribute("href").value
+        site.add_article(new_article)
+        new_article.site = site
+      end
+    else
+      doc.search("#top-headlines li").each do |headline|
+        new_article = SportHeadlines::Article.new
+        new_article.title = headline.text
+        new_article.article_url = headline.search("a").attribute("href").value
+        site.add_article(new_article)
+        new_article.site = site
+      end
+    end
+  end
+
+  def self.scrape_article(article)
+    doc = Nokogiri::HTML(open(article.article_url))
+    p_text = ""
+
+    if article.site.site_name == "ESPN"
+      doc.search(".article-body p").each do |p|
+        p_text += "    " + p.text + "\n\n"
+      end
+    elsif article.site.site_name == "Bleacher Report"
+      doc.search(".article_body p").each do |p|
+        p_text += "    " + p.text + "\n"
+      end
+    elsif article.site.site_name == "Pro Football Talk"
+      doc.search(".post-body p").each do |p|
+        p_text += "    " + p.text + "\n\n"
+      end
+    end
+
+    article.content = p_text
+  end
+end

data/lib/sport_headlines/site.rb

@@ -0,0 +1,64 @@
+class SportHeadlines::Site
+  attr_accessor :site_name, :site_url, :articles
+
+  SITES = {
+        "ESPN" => "http://espn.go.com/",
+        "Bleacher Report" => "http://bleacherreport.com/",
+        "Pro Football Talk" => "http://profootballtalk.nbcsports.com/"
+  }
+ #
+  @@all = []
+
+  def initialize(site_name, site_url)
+    @site_name = site_name
+    @site_url = site_url
+    @articles = []
+    @@all << self
+  end
+
+  def self.all
+    @@all
+  end
+
+  def clear_articles
+    self.articles.clear
+  end
+
+  def self.create_sites_from_hash
+    SITES.each do |site, url|
+      self.new(site, url)
+    end
+  end
+
+  def add_article(article)
+    # self is the site, article is the article
+    self.articles << article
+    article.site = self # reciprocal relationship - when we add ana rticle to a site, we also inform the article of it's relationship to this site
+  end
+
+  def list_articles
+    self.articles.each_with_index do |article, index|
+      puts "#{index + 1}. #{article.title}"
+    end
+  end
+
+  def self.find(input)
+    self.all[input.to_i-1]
+  end
+
+  def scrape_headlines!
+    SportHeadlines::Scraper.scrape_site_headlines(self)
+  end
+
+  def find_article(input)
+    self.articles[input.to_i - 1]
+  end
+
+  def scrape_article(input)
+    # we want this method to both scrape the article and return it.
+    article = self.find_article(input)
+    SportHeadlines::Scraper.scrape_article(article)
+    article
+  end
+
+end

data/lib/sport_headlines/version.rb

@@ -0,0 +1,3 @@
+module SportHeadlines
+  VERSION = "0.1.0"
+end

data/lib/sport_headlines.rb

@@ -0,0 +1,15 @@
+require 'open-uri'
+require 'nokogiri'
+require 'pry'
+
+require 'sport_headlines/cli'
+
+require "sport_headlines/version"
+require "sport_headlines/article"
+require "sport_headlines/site"
+require "sport_headlines/cli"
+require "sport_headlines/scraper"
+
+module SportHeadlines
+
+end

data/notes.md

@@ -0,0 +1,38 @@
+#top sports headlines scraper
+#scrapes top headlines from espn, sportsillustrated, bleacher report, pro football talk
+
+How to Build a CLI Gem
+
+1. Plan your gem, imagine your interface
+2. Start with the project structure
+3. Start with the entry point - the file run
+4. Force that to build the CLI interface
+5. Stub out the interface
+6. start making things real
+7. discover objects
+8. program
+
+
+"Welcome to the Sports Headlines Aggregator."
+
+"Please select a site - by number you would like to view the top headlines from..."
+
+1. ESPN
+2. Sports Illustrated
+3. Bleacher Report
+4. Pro Football Talk
+
+=> 1. ESPN => list_articles[1-1 = 0]
+
+1. Article 1
+2. Article 2
+2. Article 3
+2. Article 4
+
+
+
+# doc = Nokogiri::HTML(open("http://espn.go.com/")) =>
+# doc = Nokogiri::HTML(open("http://bleacherreport.com/"))
+# doc = Nokogiri::HTML(open("http://www.si.com/"))
+# doc = Nokogiri::HTML(open("http://profootballtalk.nbcsports.com/"))
+# doc.search("div.headlines li").size => returns each headline li in the top headlines

data/sport_headlines.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'sport_headlines/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "sport_headlines"
+  spec.version       = SportHeadlines::VERSION
+  spec.authors       = ["cernanb"]
+  spec.email         = ["cernanb@gmail.com"]
+
+  spec.summary       = %q{A gem to collate top sport headlines.}
+  spec.description   = %q{This gem will scrape the current top headlines of popular sport sites.}
+  spec.homepage      = "https://github.com/cernanb/sport-headlines-cli-gem"
+  spec.license       = "MIT"
+
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  # spec.bindir        = "exe"
+  spec.executables   = ["sport_headlines"]
+  spec.require_paths = ["lib", "lib/sport_headlines"]
+
+  spec.add_development_dependency "bundler", "~> 1.11"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency 'nokogiri'
+  spec.add_development_dependency "pry"
+end

metadata

@@ -0,0 +1,135 @@
+--- !ruby/object:Gem::Specification
+name: sport_headlines
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- cernanb
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-06-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+- !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: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  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'
+description: This gem will scrape the current top headlines of popular sport sites.
+email:
+- cernanb@gmail.com
+executables:
+- sport_headlines
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- bin/sport_headlines
+- lib/sport_headlines.rb
+- lib/sport_headlines/article.rb
+- lib/sport_headlines/cli.rb
+- lib/sport_headlines/scraper.rb
+- lib/sport_headlines/site.rb
+- lib/sport_headlines/version.rb
+- notes.md
+- sport_headlines.gemspec
+homepage: https://github.com/cernanb/sport-headlines-cli-gem
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+- lib/sport_headlines
+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: 2.4.5.1
+signing_key: 
+specification_version: 4
+summary: A gem to collate top sport headlines.
+test_files: []