microformat_scraper 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 4b44795b4d645cb6953ae2fa501b646666d9829f
+  data.tar.gz: 8ad97e266b17e1ea523618802c400b6b3435c8ab
+SHA512:
+  metadata.gz: 4988fceee08731ff7f1953e68603b6882206454a72a09366efc5cd94a95fe330ec93bc122a3907111cb99b8fc3c94b51c2c338643341932d265be9210ada01d7
+  data.tar.gz: 86e5a16a5ac2b51eb35881ace2527d4373d9ec9702f60988081f9d7125575cd5f5776f66abbeaa07cc865d501d943d52f43db68d3d43190898ee4e8d319ae94e

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 +1,3 @@
+language: ruby
+rvm:
+  - 2.1.2

data/Gemfile

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

data/README.md

@@ -0,0 +1,39 @@
+# MicroformatScraper
+
+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/microformat_scraper`. 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 'microformat_scraper'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install microformat_scraper
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, 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` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/microformat_scraper/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

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 "microformat_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

data/bin/scrape_event

@@ -0,0 +1,19 @@
+#!/usr/bin/env ruby
+
+require 'microformat_scraper'
+
+url = ARGV.last
+puts "scraping events from #{url}"
+
+page = MicroformatScraper::Page.new(url)
+parser = MicroformatScraper::EventParser.new
+
+events = parser.parse(page.content)
+puts "found #{events.count} events"
+
+events.each do |event|
+  puts "START TIME: #{event.start_time}"
+  puts "END TIME: #{event.end_time}"
+  puts "DESCRIPTION: #{event.description}"
+  puts "SUMMARY: #{event.summary}"
+end

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/microformat_scraper.rb

@@ -0,0 +1,13 @@
+require "microformat_scraper/version"
+require "microformat_scraper/page"
+require "microformat_scraper/event_parser"
+
+module MicroformatScraper
+
+  def self.scheduled_events(url)
+    page = Page.new(url)
+    parser = EventParser.new
+    parser.parse(page.content)
+  end
+
+end

data/lib/microformat_scraper/event.rb

@@ -0,0 +1,14 @@
+require 'virtus'
+
+module MicroformatScraper
+
+  class Event
+    include Virtus.model
+
+    attribute :start_time, Time
+    attribute :end_time, Time
+    attribute :description, String
+    attribute :summary, String
+  end
+
+end

data/lib/microformat_scraper/event_parser.rb

@@ -0,0 +1,44 @@
+require 'microformat_scraper/event'
+require 'nokogiri'
+
+module MicroformatScraper
+
+  class EventParser
+
+    # This method is extremely fragile, but so far EOLclub.org has been sticking to
+    # the same format, so that may be okay.
+    def parse(content)
+      doc = Nokogiri::HTML.parse(content)
+      doc.css('.vevent').map{|elem| parse_event(elem)}
+    end
+
+    private
+
+    def parse_event(elem)
+      summary = mf_value(elem, '.summary')
+
+      description = elem.css('.description').map(&:to_html).join
+
+      start_time = mf_value(elem, '.dtstart')
+      end_time = mf_value(elem, '.dtend')
+
+      Event.new(
+        start_time: start_time,
+        end_time: end_time,
+        description: description,
+        summary: summary,
+      )
+    end
+
+    def mf_value(elem, css_path)
+      el = elem.css(css_path).first
+      if attr = el.attributes['title']
+        attr.value
+      else
+        el.text
+      end
+    end
+
+  end
+
+end

data/lib/microformat_scraper/page.rb

@@ -0,0 +1,15 @@
+require 'open-uri'
+
+module MicroformatScraper
+
+  class Page
+    def initialize(url)
+      @url = url
+    end
+
+    def content
+      open(@url).read
+    end
+  end
+
+end

data/lib/microformat_scraper/version.rb

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

data/microformat_scraper.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'microformat_scraper/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "microformat_scraper"
+  spec.version       = MicroformatScraper::VERSION
+  spec.authors       = ["Matt Gillooly"]
+  spec.email         = ["git@mattgillooly.com"]
+
+  spec.summary       = %q{Microformat event scraper}
+  spec.description   = %q{Scrape scheduled events from microformatted web pages}
+  spec.homepage      = "http://pvdtechevents.com/"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency 'nokogiri'
+  spec.add_dependency 'virtus', '~> 1.0'
+  spec.add_development_dependency "bundler", "~> 1.9"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency 'rspec'
+  spec.add_development_dependency 'vcr'
+  spec.add_development_dependency 'webmock'
+end

metadata

@@ -0,0 +1,156 @@
+--- !ruby/object:Gem::Specification
+name: microformat_scraper
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Matt Gillooly
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2015-09-21 00:00:00.000000000 Z
+dependencies:
+- !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: virtus
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+- !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: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: vcr
+  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: 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'
+description: Scrape scheduled events from microformatted web pages
+email:
+- git@mattgillooly.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/scrape_event
+- bin/setup
+- lib/microformat_scraper.rb
+- lib/microformat_scraper/event.rb
+- lib/microformat_scraper/event_parser.rb
+- lib/microformat_scraper/page.rb
+- lib/microformat_scraper/version.rb
+- microformat_scraper.gemspec
+homepage: http://pvdtechevents.com/
+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: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Microformat event scraper
+test_files: []