pagedump 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0d237dc01548838acdbf7913b9b5fac0300b1e61
+  data.tar.gz: eb81b3546ee1a91f1f330dec98ddfb02224cb7b7
+SHA512:
+  metadata.gz: ce9df7137158f4df8629ef06e9e3159f72953db34c7844a9121d86c8d238f56b8dd30a88e1e8bd8f706638db9e6733ee72d81cf9bd8d39f186c39a91e5adf5fe
+  data.tar.gz: 3a58f23282572bacf3208f93b3f2509f53c80398968a128fcbdc6492ab28f91f1af004387e01c26f98aa4843aa79be72dd058297669bfedf62ee10960ccfe505

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 +1,12 @@
+language: ruby
+rvm:
+- 2.3.0
+before_install: gem install bundler -v 1.11.2
+deploy:
+  provider: rubygems
+  api_key:
+    secure: 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
+  gem: pagedump
+  on:
+    tags: true
+    repo: pompadour/pagedump

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Damien Cram
+
+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 +1,65 @@
+# Pagedump
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'pagedump'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install pagedump
+
+## Usage
+
+Create a page driver:
+
+``` ruby
+require "pagedump"
+
+class LeMonde < Pagedump::Driver
+  URL = "http://www.lemonde.fr/"
+
+  def headlines page
+    head 3, page.css(".titre_une a")[0]['href']
+
+    page.css(".titres_hauts article").each do |e|
+      head 1, e.css('a')[0]["href"]
+    end
+  end
+end
+```
+
+And scrap its links:
+
+``` ruby
+require "pagedump"
+
+healines = @driver.scrap
+healines.each do |headline, w|
+  puts "%3d\t%-s" % [w, headline]
+end
+
+```
+
+
+## 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/pompadour/pagedump.
+
+
+## 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 "pagedump"
+
+# 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/lib/pagedump.rb

@@ -0,0 +1,30 @@
+require 'logging'
+require 'mechanize'
+require "pagedump/version"
+require "pagedump/driver"
+
+module Pagedump
+  class << self
+    def logger
+      Logging.logger[Pagedump]
+    end
+    def load_drivers path
+      Dir[File.join(path, "**/*.rb")].each do |p|
+        require p
+      end
+    end
+    def register_driver driver_cls
+      drivers[driver_cls.name] = driver_cls
+    end
+    def drivers
+      @drivers ||= {}
+    end
+    def driver driver_name
+      if (cls = drivers[driver_name]).nil?
+        raise("No such driver class: #{driver_name}")
+      else
+        cls.new
+      end
+    end
+  end
+end

data/lib/pagedump/driver.rb

@@ -0,0 +1,38 @@
+module Pagedump
+  # WRANING !!
+  # No Thread-Safe
+  class Driver
+    attr_reader :headlines
+
+    def self.inherited(subclass)
+      Pagedump.register_driver subclass
+      puts "New driver: #{subclass}"
+    end
+
+    def initialize
+      @wlinks = {}
+    end
+
+    def link weight, href
+      abs_link = URI.parse(url).merge(URI.parse(href)).to_s
+      @wlinks[abs_link] = weight
+    end
+
+    def scrap
+      @wlinks = {}
+      Pagedump.logger.info "Getting headlines for url #{url}"
+      agent = Mechanize.new
+      page = agent.get(url)
+      self.links page
+      @wlinks
+    end
+
+    def url
+      self.class::URL
+    end
+
+    def name
+      self.class.name
+    end
+  end
+end

data/lib/pagedump/version.rb

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

data/pagedump.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'pagedump/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "pagedump"
+  spec.version       = Pagedump::VERSION
+  spec.authors       = ["Damien Cram"]
+  spec.email         = ["damien.cram@laposte.net"]
+
+  spec.summary       = %q{An API to scrap pages on the web and to extract selected links from it.}
+  spec.description   = %q{An API to scrap pages on the web and to extract selected links from it.}
+  spec.homepage      = "http://github.com/pompadour/pagedump/"
+  spec.license       = "MIT"
+
+  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 "mechanize", "~> 2.7"
+  spec.add_dependency "logging", "~> 2.1"
+
+  spec.add_development_dependency "bundler", "~> 1.11"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

metadata

@@ -0,0 +1,127 @@
+--- !ruby/object:Gem::Specification
+name: pagedump
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Damien Cram
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-05-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+- !ruby/object:Gem::Dependency
+  name: logging
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+- !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'
+description: An API to scrap pages on the web and to extract selected links from it.
+email:
+- damien.cram@laposte.net
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/pagedump.rb
+- lib/pagedump/driver.rb
+- lib/pagedump/version.rb
+- pagedump.gemspec
+homepage: http://github.com/pompadour/pagedump/
+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: An API to scrap pages on the web and to extract selected links from it.
+test_files: []