lrd_twimage 0.1.1

data/.gitignore

@@ -0,0 +1,6 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*
+.rvmrc
+*.swp

data/Gemfile

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

data/README.md

@@ -0,0 +1,50 @@
+# Twimage
+
+This is LRD's fork of twimage by Rob Cameron.   Our fork adds support for lockerz.com image service, and fixes a
+problem we ran into on some twitpic images.
+
+Twimage provides an easy way to pull raw images from the various Twitter photo image services (twitpic, yfrog, etc.)
+
+## Usage
+
+Add twimage to your Gemfile:
+
+    gem 'lrd_twimage'
+    
+Of without bundler:
+
+    gem install lrd_twimage
+    
+Now simply take the standard URL that is posted to Twitter and tell Twimage to go get it:
+
+    result = Twimage.get('http://instagr.am/p/EHqLG/')
+    
+Twimage will create a Ruby tempfile with the image. To get the tempfile:
+
+    result.tempfile
+    
+Save the image to your local system, upload to S3, etc. As soon as there are no more references to the
+tempfile in your code it will be unlinked (deleted). There are a couple additional instance variables
+you have access to...try `result.inspect` to take a look.
+
+Twimage will follow any redirects that eventually get you to any of the included services. So, if you
+have a Instagram image behind a Bitly shortened URL, just give the Bitly link to Twimage and he'll
+(she'll?) take care of the rest.
+
+Enjoy!
+
+## Support
+
+LRDTwimage currently supports the following services:
+
+* twitpic - http://twitpic.com
+* yfrog - http://yfrog.com
+* instagram - http://instagr.am
+* lockerz - http://lockerz.com
+
+## Contributing
+
+To add a parser, fork this repo and then send me a pull request. You should attempt to get the highest resolution
+version of the image possible, which isn't always available at the link posted to Twitter. Check out the `SERVICES`
+constant in `twimage.rb` for examples of `lambda`s used to modify the original `service_url` to get to the full res
+version's URL.

data/Rakefile

@@ -0,0 +1,2 @@
+require 'bundler'
+Bundler::GemHelper.install_tasks

data/lib/twimage.rb

@@ -0,0 +1,101 @@
+require 'nokogiri'
+require 'open-uri'
+require 'httparty'
+require 'tempfile'
+
+$:.unshift(File.dirname(__FILE__)) unless $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+require 'twimage/version'
+require 'twimage/image'
+
+module Twimage
+  
+  class ServiceURLInvalid < StandardError; end  # thrown if the service_url returns a 404
+  class ImageNotFound < StandardError; end      # thrown if the service_url doesn't contain an expected image tag
+  class ImageURLInvalid < StandardError; end    # thrown if the image_url found in the service_url returns a 404
+  
+  USER_AGENT = "Twimage #{Twimage::VERSION} http://github.com/cannikin/twimage"
+  SERVICES = [{ :name => :twitpic,
+                :service_match => /twitpic\.com/,
+                :full_url_modifier => lambda { |url| url + '/full' },
+                :image_css_match => 'body > img' },
+              { :name => :yfrog,
+                :service_match => /yfrog\.com/,
+                :full_url_modifier => lambda { |url| url.gsub(/\.com/, '.com/z') },
+                :image_css_match => '#the-image img' },
+              { :name => :instagram,
+                :service_match => [/instagr\.am/, /instagram\.com/],
+                :image_css_match => '.photo'},
+              { :name => :lockerz,
+                :service_match => /lockerz\.com/,
+                :image_css_match => '#photo' }
+  ]
+                  
+  def self.get(url)
+    service_url = HTTParty.get(url, :headers => { 'User-Agent' => USER_AGENT }).request.path.to_s                                                                 # first point HTTParty at this URL and follow any redirects to get to the final page
+    service = find_service(service_url)                                                                               # check the resulting service_url for which service we're hitting
+    full_res_service_url = service[:full_url_modifier] ? service[:full_url_modifier].call(service_url) : service_url  # get the full res version of the service_url
+    #debugger
+    image_url = get_image_url(service, full_res_service_url)                                                          # get the URL to the image
+    #debugger
+    image = get_image(image_url)                                                                                      # get the image itself
+    #debugger
+    p({
+      :url => url,
+      :image_url => image_url,
+      :service_url => service_url      
+    })
+
+
+    return Image.new(:service => service[:name], :service_url => service_url, :image_url => image_url, :image => image)
+  end
+  
+  
+  # figure out which service this is by matching against regexes
+  def self.find_service(url)
+    return SERVICES.find do |service|
+      [service[:service_match]].flatten.find do |regex|
+        url.match(regex)
+      end
+    end
+  end
+  
+  
+  # tear apart the HTML on the returned service page and find the source of the image
+  def self.get_image_url(service, url)
+    # get the content of the image page
+    begin
+      image_tag = Nokogiri::HTML(open(url, 'User-Agent' => USER_AGENT)).css(service[:image_css_match]).first
+    rescue OpenURI::HTTPError
+      raise ServiceURLInvalid, "The service URL #{url} was not found (returned a 404)"
+    end
+    
+    # get the URL to the actual image file
+    if image_tag
+      return enforce_protocol(image_tag['src'])
+    else
+      raise ImageNotFound, "The service URL #{url} did not contain an identifiable image"
+    end
+  end
+
+  def self.enforce_protocol(url)
+    if url =~ /^http/
+      url
+    elsif url =~ /^\/\//
+      "http:" + url 
+    end
+  end
+  
+
+  # download the actual image and put into a tempfile
+  def self.get_image(url)
+    #debugger
+    # get the image itself
+    response = HTTParty.get(url, :headers => { 'User-Agent' => USER_AGENT })
+    if response.code == 200
+      return response.body.force_encoding('utf-8')
+    else
+      raise ImageURLInvalid, "The image_url #{url} was not found (returned a 404)"
+    end
+  end
+  
+end

data/lib/twimage/image.rb

@@ -0,0 +1,21 @@
+module Twimage
+  class Image
+    
+    attr_reader :service, :service_url, :image_url, :tempfile
+    
+    def initialize(options)
+      @service      = options[:service]
+      @service_url  = options[:service_url]
+      @image_url    = options[:image_url]
+      
+      begin
+        extension = @image_url.match(/(\.\w+)(\?|$)/)[1]
+      rescue NoMethodError
+        extension = '.jpg'    # Lockerz does not put extensions or mime types on their images.
+      end
+      @tempfile = Tempfile.new(['twimage', extension])
+      @tempfile << options[:image]
+    end
+    
+  end
+end

data/lib/twimage/version.rb

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

data/twimage.gemspec

@@ -0,0 +1,24 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "twimage/version"
+
+Gem::Specification.new do |s|
+  s.name        = "lrd_twimage"
+  s.version     = Twimage::VERSION
+  s.platform    = Gem::Platform::RUBY
+  s.authors     = ["Evan Dorn", "Rob Cameron"]
+  s.email       = ["evan@lrdesign.com"]
+  s.homepage    = ""
+  s.summary     = %q{A gem for pulling images from various Twitter image services}
+  s.description = %q{This gem will programatically grab images from a bunch of the most used Twitter image services.}
+
+  s.rubyforge_project = "twimage"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+  
+  s.add_dependency 'nokogiri'
+  s.add_dependency 'httparty'
+end

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification 
+name: lrd_twimage
+version: !ruby/object:Gem::Version 
+  hash: 25
+  prerelease: 
+  segments: 
+  - 0
+  - 1
+  - 1
+  version: 0.1.1
+platform: ruby
+authors: 
+- Evan Dorn
+- Rob Cameron
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-10-19 00:00:00 -07:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: httparty
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id002
+description: This gem will programatically grab images from a bunch of the most used Twitter image services.
+email: 
+- evan@lrdesign.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .gitignore
+- Gemfile
+- README.md
+- Rakefile
+- lib/twimage.rb
+- lib/twimage/image.rb
+- lib/twimage/version.rb
+- twimage.gemspec
+has_rdoc: true
+homepage: ""
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: twimage
+rubygems_version: 1.4.2
+signing_key: 
+specification_version: 3
+summary: A gem for pulling images from various Twitter image services
+test_files: []
+