web_reptile 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 889d004908345db250a70bb98af7d316c5a78acb
+  data.tar.gz: 8ca6a65a23367a6e08b3b4311a690bdfecacbb09
+SHA512:
+  metadata.gz: 1d02c6e675541da068296120e4a0525de4bcbff6e93880d2aeefb615fd791f7df9e6ba7d3e59b3a4d5f7f1e8c315831b00a55a375c3220aa8b07bdbb5d49d7b6
+  data.tar.gz: 47bac14d750fae6712366afb419313214513ec368674836cadd255718b1c5837f8f2552ab0353a6d0d72fcc54a3bb3b181d3676ea943982c872e91c5f0a33c24

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.gem

data/.rspec

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

data/.travis.yml

@@ -0,0 +1,10 @@
+language: ruby
+rvm:
+  - 2.3.0
+before_install: gem install bundler -v 1.11.2
+script: bundle exec rspec spec
+deploy:
+  provider: rubygems
+  api_key: "0a83ba9104db0bc50ca2b67e3fc67406"
+  on:
+    tags: true

data/Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in reptile.gemspec
+gemspec
+
+gem "mechanize"

data/README.md

@@ -0,0 +1,48 @@
+# WebReptile
+
+[![Travis](https://img.shields.io/travis/DotHide/reptile.svg?maxAge=2592000)](https://travis-ci.org/DotHide/reptile) 
+
+WebReptile is a web spider framework using Ruby.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'web_reptile'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install web_reptile
+
+## Usage
+
+```ruby
+require('web_reptile')
+
+domain = WebReptile.url("http://www.jd.com/allSort.aspx")
+items = domain.grab(".category-items .category-item .items dt a")
+items.map do |item|
+    href = item.attr('href')
+    text = item.text
+    "[#{text}](#{href})"
+end
+
+# ["[电子书刊](//e.jd.com/ebook.html)", "[音像](//mvd.jd.com/)", "[英文原版](//channel.jd.com/1713-4855.html)", "[文艺](//channel.jd.com/p_wenxuezongheguan.html)", "[少儿](//book.jd.com/children.html)", "[人文社科](//book.jd.com/library/socialscience.html)", "[经管励志](//channel.jd.com/p_Comprehensive.html)", ...]
+```
+
+## 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/DotHide/web_reptile.
+

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 "reptile"
+
+# 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/web_reptile.rb

@@ -0,0 +1,30 @@
+require "web_reptile/version"
+require "mechanize"
+
+module WebReptile
+
+  def WebReptile.url(url, options = {}, &block)
+    Core.url(url, options, &block)
+  end
+
+  class Core
+    def initialize(url, opts = {})
+      @url = url.is_a?(URI) ? url : URI(url)
+      @opts = opts
+
+      agent = Mechanize.new
+      @page = agent.get(@url)
+    end
+
+    def self.url(url, opts = {})
+      self.new(url, opts) do |web|
+        yield web if block_given?
+        self
+      end
+    end
+
+    def grab(selector)
+       items = @page.search(selector)
+    end
+  end
+end

data/lib/web_reptile/version.rb

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

data/web_reptile.gemspec

@@ -0,0 +1,23 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'web_reptile/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "web_reptile"
+  spec.version       = WebReptile::VERSION
+  spec.authors       = ["Martin_nett"]
+  spec.email         = ["dothide@gmail.com"]
+
+  spec.summary       = %q{WebReptile is a web spider framework using Ruby.}
+  spec.homepage      = "https://github.com/DotHide/reptile"
+
+  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_development_dependency "bundler", "~> 1.11"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

metadata

@@ -0,0 +1,96 @@
+--- !ruby/object:Gem::Specification
+name: web_reptile
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Martin_nett
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-06-21 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'
+description: 
+email:
+- dothide@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/web_reptile.rb
+- lib/web_reptile/version.rb
+- web_reptile.gemspec
+homepage: https://github.com/DotHide/reptile
+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: 2.6.4
+signing_key: 
+specification_version: 4
+summary: WebReptile is a web spider framework using Ruby.
+test_files: []