tweetlr 0.1.17 → 0.1.18

data/README.md

@@ -40,9 +40,11 @@ search_term: 'cat+dog+unicorn' #find tweets containing any of these terms
 start_at_tweet_id: 61847783463854082 # the tweet id to start searching at
 api_endpoint_twitter: 'http://search.twitter.com/search.json'
 api_endpoint_tumblr: 'http://www.tumblr.com'
-tumblr_username: YOUR_TUMBLR_EMAIL
-tumblr_password: YOUR_TUMBLR_PW
-group: TUMBLR_GROUP_TO_POST_TO #e.g. mysubblog.tumblr.com
+tumblr_oauth_api_key: YOUR APPS TUMBLR API TOKEN
+tumblr_oauth_api_secret: YOUR APPS TUMBLR API SECRET
+tumblr_oauth_access_token_key: YOUR BLOGS OAUTH ACCESS TOKEN KEY
+tumblr_oauth_access_token_secret: YOUR BLOGS OAUTH ACCESS TOKEN SECRE
+tumblr_blog_hostname: YOUR BLOGS HOSTNAME #e.g. myblog.tumblr.com
 embedly_key: '' #tweetlr uses http://embedly.com for link processing. a free plan containing an api key is available & recommended to use in order to ensure full support
 update_period: 300 #check for updates every 300 secs = 5 minutes
 shouts: 'says' # will be concatenated after the username, before the message: @mr_x says: awesome things on a photo!

data/bin/tweetlr

@@ -22,25 +22,7 @@ begin
    
   UPDATE_PERIOD = CONFIG['update_period']  
 
-  @tweetlr_config = {
-    :tumblr_blog_hostname => CONFIG['tumblr_blog_hostname'] || CONFIG['group'],
-    :tumblr_oauth_api_key => CONFIG['tumblr_oauth_api_key'],
-    :tumblr_oauth_api_secret => CONFIG['tumblr_oauth_api_secret'],
-    :tumblr_blog_hostname => CONFIG['tumblr_blog_hostname'],
-    :tumblr_oauth_access_token_key => CONFIG['tumblr_oauth_access_token_key'],
-    :tumblr_oauth_access_token_secret => CONFIG['tumblr_oauth_access_token_secret'],
-    :whitelist => CONFIG['whitelist'], 
-    :shouts => CONFIG['shouts'], 
-    :since_id => CONFIG['start_at_tweet_id'] , 
-    :terms => CONFIG['search_term'], 
-    :loglevel => CONFIG['loglevel'],
-    :update_period => UPDATE_PERIOD,
-    :api_endpoint_tumblr => CONFIG['api_endpoint_tumblr'],
-    :api_endpoint_twitter => CONFIG['api_endpoint_twitter'],
-    :results_per_page => CONFIG['results_per_page'],
-    :result_type => CONFIG['result_type'],
-    :embedly_key => CONFIG['embedly_key']
-    }
+  @tweetlr_config = prepare_tweetlr_config CONFIG
 rescue SystemCallError
   $stderr.puts "Ooops - looks like there is no ./config/tweetlr.yml found. I'm affraid tweetlr won't work properly until you introduced that configuration file."
   exit(1)
@@ -52,9 +34,31 @@ Daemons.run_proc('tweetlr', :dir_mode => :script, :dir => './', :backtrace => tr
   @log.info "creating a new tweetlr instance using this config: #{@tweetlr_config.inspect}"   
   EventMachine::run do 
     EventMachine::add_periodic_timer( UPDATE_PERIOD ) do
-      response = Tweetlr.crawl(@tweetlr_config)
+      response = Tweetlr::Core.crawl(@tweetlr_config)
       File.open(tid_file, "w+") { |io| io.write(response[:since_id]) }
       @tweetlr_config.merge! response
      end
    end
+end
+
+def prepare_tweetlr_config(config)
+  {
+    :tumblr_blog_hostname => config['tumblr_blog_hostname'] || config['group'],
+    :tumblr_oauth_api_key => config['tumblr_oauth_api_key'],
+    :tumblr_oauth_api_secret => config['tumblr_oauth_api_secret'],
+    :tumblr_blog_hostname => config['tumblr_blog_hostname'],
+    :tumblr_oauth_access_token_key => config['tumblr_oauth_access_token_key'],
+    :tumblr_oauth_access_token_secret => config['tumblr_oauth_access_token_secret'],
+    :whitelist => config['whitelist'], 
+    :shouts => config['shouts'], 
+    :since_id => config['start_at_tweet_id'] , 
+    :terms => config['search_term'], 
+    :loglevel => config['loglevel'],
+    :update_period => UPDATE_PERIOD,
+    :api_endpoint_tumblr => config['api_endpoint_tumblr'],
+    :api_endpoint_twitter => config['api_endpoint_twitter'],
+    :results_per_page => config['results_per_page'],
+    :result_type => config['result_type'],
+    :embedly_key => config['embedly_key']
+    }
 end

data/config/tweetlr.yml

@@ -1,18 +1,18 @@
 results_per_page: 100
 result_type: recent
-search_term: 'cat+dog+unicorn' #find tweets containing any of these terms
+search_term: 'coffeediary' #find tweets containing any of these terms
 start_at_tweet_id: 61847783463854082 # the tweet id to start searching at
 api_endpoint_twitter: 'http://search.twitter.com/search.json'
 api_endpoint_tumblr: 'http://www.tumblr.com'
-tumblr_oauth_api_key: YOUR APPS TUMBLR API TOKEN
-tumblr_oauth_api_secret: YOUR APPS TUMBLR API SECRET
-tumblr_oauth_access_token_key: YOUR BLOGS OAUTH ACCESS TOKEN KEY
-tumblr_oauth_access_token_secret: YOUR BLOGS OAUTH ACCESS TOKEN SECRE
-group: TUMBLR_GROUP_TO_POST_TO #e.g. mysubblog.tumblr.com
-embedly_key: '' #tweetlr uses http://embedly.com for link processing. a free plan containing an api key is available & recommended to use in order to ensure full support
-update_period: 300 #check for updates every 300 secs = 5 minutes
+tumblr_oauth_api_key: 'Buq8j3koYLqrZEMmTM4GL32S0guZU2Qvoz8xSvFRumaWuaxAnG'
+tumblr_oauth_api_secret: 'EnjBUAjUHo4Qi4d3BPUL5xsdc8qClDqRTLssz8Jzd2sKC7KZaq'
+tumblr_oauth_access_token_key: 'MQES8SEqr3JogLyUYzcV68RFfQ0b3ClxbnUihChh8p9UMH3tkM'
+tumblr_oauth_access_token_secret: 'FBnrEFW1p9RG7Zh1kztPjPDCbeE229fMPX5VwuzgZqUdD2hXSS'
+tumblr_blog_hostname: 'tweetlr-testlr.tumblr.com' #e.g. mysubblog.tumblr.com
+embedly_key: '9e6c2bb8372e11e1a92e4040d3dc5c07' #tweetlr uses http://embedly.com for link processing. a free plan containing an api key is available & recommended to use in order to ensure full support
+update_period: 10 #check for updates every 300 secs = 5 minutes
 shouts: 'says' # will be concatenated after the username, before the message: @mr_x says: awesome things on a photo!
 loglevel: 1 # 0: debug, 1: info (default), 2: warn, 3: error, 5: fatal
 whitelist: #twitter accounts in that list will have their tweets published immediately. post from others will be saved as drafts. blank list will publish all tweets immediately
   - whitey_mc_whitelist
-  - sven_kr
+  - sven_kr

data/lib/{combinators → tweetlr/combinators}/twitter_tumblr.rb

@@ -1,23 +1,23 @@
-require 'processors/twitter'
-require 'processors/tumblr'
-require 'processors/photo_service'
+local_path=File.dirname(__FILE__)
+require "#{local_path}/../processors/twitter"
+require "#{local_path}/../processors/tumblr"
+require "#{local_path}/../processors/photo_service"
+require "#{local_path}/../log_aware"
 
-require 'log_aware'
-
-module Combinators
+module Tweetlr::Combinators
   module TwitterTumblr
-    include LogAware
+    include Tweetlr::LogAware
     def self.log
-      LogAware.log #TODO why doesn't the include make the log method accessible?
+      Tweetlr::LogAware.log #TODO why doesn't the include make the log method accessible?
     end
     #extract a linked image file's url from a tweet. first found image will be used.
     def self.extract_image_url(tweet, embedly_key=nil)
-      links = Processors::Twitter::extract_links tweet
+      links = Tweetlr::Processors::Twitter::extract_links tweet
       image_url = nil
       if links
         links.each do |link|
-          image_url = Processors::PhotoService::find_image_url(link, embedly_key)
-          return image_url if Processors::PhotoService::photo? image_url
+          image_url = Tweetlr::Processors::PhotoService::find_image_url(link, embedly_key)
+          return image_url if Tweetlr::Processors::PhotoService::photo? image_url
         end
       end
       image_url
@@ -29,7 +29,7 @@ module Combinators
       message = tweet['text']
       whitelist = options[:whitelist]
       whitelist.each {|entry| entry.downcase!} if (whitelist && whitelist.size != 0)
-      if !Processors::Twitter::retweet? message
+      if !Tweetlr::Processors::Twitter::retweet? message
         log.debug "tweet: #{tweet}"
         tumblr_post = {}
         tumblr_post[:tumblr_blog_hostname] = options[:tumblr_blog_hostname] || options[:group]

data/lib/tweetlr/core.rb

@@ -0,0 +1,93 @@
+# encode: UTF-8
+local_path=File.dirname(__FILE__)
+require "#{local_path}/processors/twitter"
+require "#{local_path}/processors/http"
+require "#{local_path}/processors/photo_service"
+require "#{local_path}/processors/tumblr"
+require "#{local_path}/combinators/twitter_tumblr"
+require "#{local_path}/log_aware"
+require 'uri'
+
+class Tweetlr::Core  
+  include Tweetlr::LogAware
+  def self.log
+    Tweetlr::LogAware.log #TODO why doesn't the include make the log method accessible?
+  end
+  
+  def initialize(args)
+    log = Logger.new(STDOUT)
+    if (Logger::DEBUG..Logger::UNKNOWN).to_a.index(args[:loglevel])
+      log.level = args[:loglevel] 
+    else
+      log.level = Logger::INFO
+    end
+    log.debug "log level set to #{log.level}"
+    Tweetlr::LogAware.log=log
+    
+    @email = args[:tumblr_email]
+    @password = args[:tumblr_password]
+    @cookie = args[:cookie]
+    @api_endpoint_twitter = args[:api_endpoint_twitter] || Tweetlr::API_ENDPOINT_TWITTER
+    @api_endpoint_tumblr = args[:api_endpoint_tumblr] || Tweetlr::API_ENDPOINT_TUMBLR
+    @whitelist = args[:whitelist]
+    @shouts = args[:shouts]
+    @update_period = args[:update_period] || Tweetlr::UPDATE_PERIOD
+    @whitelist.each {|entry| entry.downcase!} if @whitelist
+    log.info "Tweetlr #{Tweetlr::VERSION} initialized. Ready to roll."
+  end
+  
+  def self.crawl(config)
+    log.debug "#{self}.crawl() using config: #{config.inspect}"
+    twitter_config = prepare_twitter_config config
+    tumblr_config = prepare_tumblr_config config
+    twitter_config[:search_term] = URI::escape(twitter_config[:search_term]) if twitter_config[:search_term]
+    log.info "starting tweetlr crawl..."
+    response = {}
+    response = Tweetlr::Processors::Twitter::lazy_search(twitter_config)
+    if response
+      tweets = response['results']
+      if tweets
+      tweets.each do |tweet|
+        tumblr_post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet(tweet, {:whitelist => config[:whitelist], :embedly_key => config[:embedly_key], :group => config[:group]}) 
+        if tumblr_post.nil? ||  tumblr_post[:source].nil?
+          log.warn "could not get image source: tweet: #{tweet} --- tumblr post: #{tumblr_post.inspect}"
+        else
+          log.debug "tumblr post: #{tumblr_post}"
+          res = Tweetlr::Processors::Tumblr.post tumblr_post.merge(tumblr_config)
+          log.debug "tumblr response: #{res}"
+          if res.code == "201"
+            log.info "tumblr post created (tumblr response: #{res.header} #{res.body}"
+          else
+            log.warn "tumblr response: #{res.header} #{res.body}"
+          end
+        end
+       end
+        # store the highest tweet id
+        config[:since_id] = response['max_id']
+      end
+    else
+      log.error "twitter search returned no response. hail the failwhale!"
+    end
+    log.info "finished tweetlr crawl."
+    return config
+  end
+private
+  def self.prepare_twitter_config(config)
+    {
+      :since_id => config[:since_id] || config[:start_at_tweet_id],
+      :search_term => config[:terms] || config[:search_term] ,
+      :results_per_page => config[:results_per_page] || Tweetlr::TWITTER_RESULTS_PER_PAGE,
+      :result_type => config[:result_type] || Tweetlr::TWITTER_RESULTS_TYPE,  
+      :api_endpoint_twitter => config[:api_endpoint_twitter] || Tweetlr::API_ENDPOINT_TWITTER
+    }
+  end
+  def self.prepare_tumblr_config(config)
+    { 
+      :tumblr_oauth_access_token_key => config[:tumblr_oauth_access_token_key],
+      :tumblr_oauth_access_token_secret => config[:tumblr_oauth_access_token_secret],
+      :tumblr_oauth_api_key => config[:tumblr_oauth_api_key],
+      :tumblr_oauth_api_secret => config[:tumblr_oauth_api_secret],
+      :tumblr_blog_hostname => config[:tumblr_blog_hostname] || config[:group]
+    }
+  end
+end

data/lib/{log_aware.rb → tweetlr/log_aware.rb}

@@ -1,9 +1,11 @@
 #use centralized logging
-module LogAware
+module Tweetlr
+  module LogAware
     def self.log=(log)
       @log = log
     end
     def self.log()
       @log || Logger.new(STDOUT)
     end
+  end
 end

data/lib/{processors → tweetlr/processors}/http.rb

@@ -1,16 +1,16 @@
 require 'curb'
 require 'json'
-require 'log_aware'
+require "#{File.dirname(__FILE__)}/../log_aware"
 
-module Processors
+module Tweetlr::Processors
   #utilities for handling http
   module Http
-    include LogAware
+    include Tweetlr::LogAware
   
     USER_AGENT = %{Mozilla/5.0 (compatible; tweetlr; +http://tweetlr.5v3n.com)}
     
     def self.log
-      LogAware.log #TODO why doesn't the include make the log method accessible?
+      Tweetlr::LogAware.log #TODO why doesn't the include make the log method accessible?
     end
     #convenience method for curl http get calls
     def self.http_get(request)

data/lib/{processors → tweetlr/processors}/photo_service.rb

@@ -1,8 +1,9 @@
-require 'processors/http'
+local_path=File.dirname(__FILE__)
+require "#{local_path}/http"
+require "#{local_path}/../log_aware"
 require 'nokogiri'
-require 'log_aware'
 
-module Processors
+module Tweetlr::Processors
   #utilities for dealing with photo services
   module PhotoService
   
@@ -10,10 +11,10 @@ module Processors
     LOCATION_STOP_INDICATOR  = "\r\n"
     PIC_REGEXP = /(.*?)\.(jpg|jpeg|png|gif)/i 
   
-    include LogAware
+    include Tweetlr::LogAware
     
     def self.log
-      LogAware.log #TODO why doesn't the include make the log method accessible?
+      Tweetlr::LogAware.log #TODO why doesn't the include make the log method accessible?
     end
   
     def self.find_image_url(link, embedly_key=nil)
@@ -41,40 +42,24 @@ module Processors
       link =~ PIC_REGEXP
     end
     def self.image_url_twimg(link_url)
-      service_url = link_url_redirect link_url #follow possible redirects
-      link_url = service_url if service_url #if there's no redirect, service_url will be nil
-      response = Processors::Http::http_get(link_url)
-      image_url = parse_html_for '.twimg img', Nokogiri::HTML.parse(response.body_str)
-      return image_url
+      retrieve_image_url_by_css link_url, '.twimg img'
     end
     #extract the image of an eyeem.com pic
     def self.image_url_eyeem(link_url)
-      service_url = link_url_redirect link_url #follow possible redirects
-      link_url = service_url if service_url #if there's no redirect, service_url will be nil
-      response = Processors::Http::http_get link_url
-      image_url = parse_html_for '.viewport-pic img', Nokogiri::HTML.parse(response.body_str)
-      return image_url
+      retrieve_image_url_by_css link_url, '.viewport-pic img'
     end
     #extract the image of a foursquare.com pic
     def self.image_url_foursqaure(link_url)
-      service_url = link_url_redirect link_url #follow possible redirects
-      link_url = service_url if service_url #if there's no redirect, service_url will be nil
-      response = Processors::Http::http_get link_url
-      image_url = parse_html_for '.commentPhoto img', Nokogiri::HTML.parse(response.body_str)
-      return image_url
+      retrieve_image_url_by_css link_url, '.commentPhoto img'
     end
     #extract the image of a path.com pic
     def self.image_url_path(link_url)
-      service_url = link_url_redirect link_url #follow possible redirects
-      link_url = service_url if service_url #if there's no redirect, service_url will be nil
-      response = Processors::Http::http_get link_url
-      image_url = parse_html_for 'img.photo-image', Nokogiri::HTML.parse(response.body_str)
-      return image_url
+      retrieve_image_url_by_css link_url, 'img.photo-image'
     end
   
     #find the image's url via embed.ly
     def self.image_url_embedly(link_url, key)
-      response = Processors::Http::http_get_json "http://api.embed.ly/1/oembed?key=#{key}&url=#{link_url}"
+      response = Tweetlr::Processors::Http::http_get_json "http://api.embed.ly/1/oembed?key=#{key}&url=#{link_url}"
       log.debug "embedly call: http://api.embed.ly/1/oembed?key=#{key}&url=#{link_url}"
       if response && response['type'] == 'photo'
         image_url = response['url'] 
@@ -83,7 +68,7 @@ module Processors
     end
     #find the image's url for a lockerz link
     def self.image_url_lockerz(link_url)
-      response = Processors::Http::http_get_json "http://api.plixi.com/api/tpapi.svc/json/metadatafromurl?details=false&url=#{link_url}"
+      response = Tweetlr::Processors::Http::http_get_json "http://api.plixi.com/api/tpapi.svc/json/metadatafromurl?details=false&url=#{link_url}"
       response["BigImageUrl"] if response
     end
     #find the image's url for an twitter shortened link
@@ -94,7 +79,7 @@ module Processors
     #find the image's url for an instagram link
     def self.image_url_instagram(link_url)
       link_url['instagram.com'] = 'instagr.am' if link_url.index 'instagram.com' #instagram's oembed does not work for .com links
-      response = Processors::Http::http_get_json "http://api.instagram.com/oembed?url=#{link_url}"
+      response = Tweetlr::Processors::Http::http_get_json "http://api.instagram.com/oembed?url=#{link_url}"
       response['url'] if response
     end
 
@@ -102,7 +87,7 @@ module Processors
     def self.image_url_picplz(link_url)
       id = extract_id link_url
       #try short url
-      response = Processors::Http::http_get_json "http://picplz.com/api/v2/pic.json?shorturl_ids=#{id}"
+      response = Tweetlr::Processors::Http::http_get_json "http://picplz.com/api/v2/pic.json?shorturl_ids=#{id}"
       #if short url fails, try long url
       #response = HTTParty.get "http://picplz.com/api/v2/pic.json?longurl_ids=#{id}"
       #extract url
@@ -118,7 +103,7 @@ module Processors
     end
     #find the image'S url for a yfrog link
     def self.image_url_yfrog(link_url)
-      response = Processors::Http::http_get_json("http://www.yfrog.com/api/oembed?url=#{link_url}")
+      response = Tweetlr::Processors::Http::http_get_json("http://www.yfrog.com/api/oembed?url=#{link_url}")
       response['url'] if response
     end
     #find the image's url for a img.ly link
@@ -169,5 +154,12 @@ module Processors
       end
       image_url
     end
+    def self.retrieve_image_url_by_css link_url, css_path
+      service_url = link_url_redirect link_url #follow possible redirects
+        link_url = service_url if service_url #if there's no redirect, service_url will be nil
+        response = Tweetlr::Processors::Http::http_get link_url
+        image_url = parse_html_for css_path, Nokogiri::HTML.parse(response.body_str)
+        return image_url
+    end
   end
 end

data/lib/tweetlr/processors/tumblr.rb

@@ -0,0 +1,55 @@
+require "#{File.dirname(__FILE__)}/../log_aware"
+require 'oauth'
+
+module Tweetlr::Processors
+  #utilities for handling tumblr
+  module Tumblr
+    GENERATOR = %{tweetlr - http://tweetlr.5v3n.com}
+    API_ENDPOINT_TUMBLR = 'http://www.tumblr.com'
+    include Tweetlr::LogAware
+    def self.log
+      Tweetlr::LogAware.log #TODO why doesn't the include make the log method accessible?
+    end
+    #post a tumblr photo entry. 
+    #
+    #required arguments are :tumblr_blog_hostname, :tumblr_blog_hostname, :tumblr_oauth_api_secret, :tumblr_oauth_access_token_secret, :source, :caption, :state
+    #
+    #optional arguments: :tags, :type (default: 'photo') 
+    #
+    def self.post(options={})
+      base_hostname       = options[:tumblr_blog_hostname] || options[:group]
+      tumblr_oauth_api_key= options[:tumblr_oauth_api_key] 
+      tumblr_oauth_api_secret= options[:tumblr_oauth_api_secret] 
+      access_token_key    = options[:tumblr_oauth_access_token_key]
+      access_token_secret = options[:tumblr_oauth_access_token_secret]
+      type                = options[:type] || 'photo'
+      tags                = options[:tags] || ''
+      post_response = nil
+
+      if base_hostname && access_token_key && access_token_secret
+
+        consumer = OAuth::Consumer.new(tumblr_oauth_api_key, tumblr_oauth_api_secret,
+                                       { :site => 'http://www.tumblr.com',
+                                         :request_token_path => '/oauth/request_token',
+                                         :authorize_path => '/oauth/authorize',
+                                         :access_token_path => '/oauth/access_token',
+                                         :http_method => :post } )
+
+        access_token = OAuth::AccessToken.new(consumer, access_token_key, access_token_secret)
+
+        post_response = access_token.post(
+          "http://api.tumblr.com/v2/blog/#{base_hostname}/post", { 
+            :type => type, 
+            :source => options[:source], 
+            :caption => options[:caption],
+            :date => options[:date],
+            :tags => tags,
+            :state => options[:state],
+            :generator => GENERATOR
+             }
+            )
+      end
+      post_response
+    end
+  end
+end

data/lib/{processors → tweetlr/processors}/twitter.rb

@@ -1,12 +1,13 @@
-require 'processors/http'
-require 'log_aware'
+local_path=File.dirname(__FILE__)
+require "#{local_path}/http"
+require "#{local_path}/../log_aware"
 
-module Processors
+module Tweetlr::Processors
   #utilities for dealing with twitter
   module Twitter
-    include LogAware
+    include Tweetlr::LogAware
     def self.log
-      LogAware.log #TODO why doesn't the include make the log method accessible?
+      Tweetlr::LogAware.log #TODO why doesn't the include make the log method accessible?
     end
     
     #checks if the message is a retweet
@@ -25,7 +26,7 @@ module Processors
     #fire a new search
     def self.search(config)
       search_call = "#{config[:api_endpoint_twitter]}?ors=#{config[:search_term]}&result_type=#{config[:result_type]}&rpp=#{config[:results_per_page]}"
-      Processors::Http::http_get_json search_call
+      Tweetlr::Processors::Http::http_get_json search_call
     end
 
     # lazy update - search for a term or refresh the search if a response is available already
@@ -34,7 +35,7 @@ module Processors
       if config
         search_url = "#{config[:api_endpoint_twitter]}?since_id=#{config[:since_id]}&ors=#{config[:search_term]}&result_type=#{config[:result_type]}&rpp=#{config[:results_per_page]}"
         log.info "lazy search using '#{search_url}'"
-        response = Processors::Http::http_get_json search_url
+        response = Tweetlr::Processors::Http::http_get_json search_url
       else
         log.error "#{self}.lazy_search: no config given!"
       end

data/lib/tweetlr.rb

@@ -1,89 +1,12 @@
-# encode: UTF-8
-require 'processors/twitter'
-require 'processors/http'
-require 'processors/photo_service'
-require 'processors/tumblr'
-require 'combinators/twitter_tumblr'
-require 'log_aware'
-require 'uri'
+require 'tweetlr/log_aware'
+require 'tweetlr/core'
 
-class Tweetlr
-
-  VERSION = '0.1.17'
-  
+module Tweetlr
+  VERSION = '0.1.18'
+    
   API_ENDPOINT_TWITTER = 'http://search.twitter.com/search.json'
   API_ENDPOINT_TUMBLR = 'http://www.tumblr.com'
   TWITTER_RESULTS_PER_PAGE = 100
   TWITTER_RESULTS_TYPE = 'recent'
   UPDATE_PERIOD = 600 #10 minutes
-  
-  include LogAware
-  def self.log
-    LogAware.log #TODO why doesn't the include make the log method accessible?
-  end
-  
-  def initialize(args)
-    log = Logger.new(STDOUT)
-    if (Logger::DEBUG..Logger::UNKNOWN).to_a.index(args[:loglevel])
-      log.level = args[:loglevel] 
-    else
-      log.level = Logger::INFO
-    end
-    log.debug "log level set to #{log.level}"
-    LogAware.log=log
-    
-    @email = args[:tumblr_email]
-    @password = args[:tumblr_password]
-    @cookie = args[:cookie]
-    @api_endpoint_twitter = args[:api_endpoint_twitter] || API_ENDPOINT_TWITTER
-    @api_endpoint_tumblr = args[:api_endpoint_tumblr] || API_ENDPOINT_TUMBLR
-    @whitelist = args[:whitelist]
-    @shouts = args[:shouts]
-    @update_period = args[:update_period] || UPDATE_PERIOD
-    @whitelist.each {|entry| entry.downcase!} if @whitelist
-    log.info "Tweetlr #{Tweetlr::VERSION} initialized. Ready to roll."
-  end
-  
-  def self.crawl(config)
-    log.debug "#{self}.crawl() using config: #{config.inspect}"
-    twitter_config = {
-      :since_id => config[:since_id] || config[:start_at_tweet_id],
-      :search_term => config[:terms] || config[:search_term] ,
-      :results_per_page => config[:results_per_page] || TWITTER_RESULTS_PER_PAGE,
-      :result_type => config[:result_type] || TWITTER_RESULTS_TYPE,  
-      :api_endpoint_twitter => config[:api_endpoint_twitter] || API_ENDPOINT_TWITTER
-    }
-    tumblr_config = { :tumblr_oauth_access_token_key => config[:tumblr_oauth_access_token_key],
-                      :tumblr_oauth_access_token_secret => config[:tumblr_oauth_access_token_secret],
-                      :tumblr_oauth_api_key => config[:tumblr_oauth_api_key],
-                      :tumblr_oauth_api_secret => config[:tumblr_oauth_api_secret],
-                      :tumblr_blog_hostname => config[:tumblr_blog_hostname] || config[:group]
-                    }
-      
-    twitter_config[:search_term] = URI::escape(twitter_config[:search_term]) if twitter_config[:search_term]
-    log.info "starting tweetlr crawl..."
-    response = {}
-    response = Processors::Twitter::lazy_search(twitter_config)
-    if response
-      tweets = response['results']
-      if tweets
-      tweets.each do |tweet|
-        tumblr_post = Combinators::TwitterTumblr::generate_photo_post_from_tweet(tweet, {:whitelist => config[:whitelist], :embedly_key => config[:embedly_key], :group => config[:group]}) 
-        if tumblr_post.nil? ||  tumblr_post[:source].nil?
-           log.warn "could not get image source: tweet: #{tweet} --- tumblr post: #{tumblr_post.inspect}"
-        else
-          log.debug "tumblr post: #{tumblr_post}"
-          res = Processors::Tumblr.post tumblr_post.merge(tumblr_config)
-          log.warn "tumblr response: #{res.header} #{res.body}" unless res.code == "201"
-        end
-       end
-        # store the highest tweet id
-        config[:since_id] = response['max_id']
-      end
-    else
-      log.error "twitter search returned no response. hail the failwhale!"
-    end
-    log.info "finished tweetlr crawl."
-    return config
-  end  
 end

data/spec/combinators/twitter_tumblr_combinator_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-describe Combinators::TwitterTumblr do
+describe Tweetlr::Combinators::TwitterTumblr do
   before :each do
     @first_link = "http://url.com"
     @second_link = "http://instagr.am/p/DzCWn/"
@@ -38,60 +38,60 @@ describe Combinators::TwitterTumblr do
     it "extracting their corresponding links" do
       @tweets.each do |key,value|
         send "stub_#{key}"
-        url = Combinators::TwitterTumblr.extract_image_url value
+        url = Tweetlr::Combinators::TwitterTumblr.extract_image_url value
         url.should be, "service #{key} not working!"
         check_pic_url_extraction key if [:instagram,:picplz,:yfrog,:imgly,:not_listed].index key
       end
     end
     it "using the first image link found in a tweet with multiple links" do
       stub_instagram
-      link = Combinators::TwitterTumblr.extract_image_url @twitter_response
+      link = Tweetlr::Combinators::TwitterTumblr.extract_image_url @twitter_response
       link.should == 'http://distillery.s3.amazonaws.com/media/2011/05/02/d25df62b9cec4a138967a3ad027d055b_7.jpg'
     end
     it "not returning links that do not belong to images" do
       stub_no_image_link
-      link = Combinators::TwitterTumblr.extract_image_url @twitter_response
+      link = Tweetlr::Combinators::TwitterTumblr.extract_image_url @twitter_response
       link.should_not be
     end
   end
   context "given a user whitelist" do
     it "should mark whitelist users' tweets as published" do
       stub_instagram
-      post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @twitter_response, :whitelist => @whitelist
+      post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @twitter_response, :whitelist => @whitelist
       post[:state].should == 'published' 
     end
     it "should mark non whitelist users' tweets as drafts" do
       stub_instagram
-      post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @non_whitelist_tweet, :whitelist => @whitelist
+      post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @non_whitelist_tweet, :whitelist => @whitelist
       post[:state].should == 'draft' 
     end
   end
   context "without a user whitelist (whitelist nil or empty)" do
     it "should mark every users' posts as published" do
       stub_instagram
-      post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @twitter_response, :whitelist => nil
+      post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @twitter_response, :whitelist => nil
       post[:state].should == 'published'
       stub_instagram
-      post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @non_whitelist_tweet, :whitelist => nil
+      post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @non_whitelist_tweet, :whitelist => nil
       post[:state].should == 'published'
-      post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @twitter_response, :whitelist => ""
+      post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @twitter_response, :whitelist => ""
       post[:state].should == 'published'
       stub_instagram
-      post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @non_whitelist_tweet, :whitelist => ""
+      post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @non_whitelist_tweet, :whitelist => ""
       post[:state].should == 'published'
     end
   end
   it "should not use retweets which would produce double blog posts" do
-    post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @retweet, :whitelist => @whitelist
+    post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @retweet, :whitelist => @whitelist
     post.should_not be
   end
   context "should not use new style retweets which would produce double blog posts" do
     it "for quotes in context" do
-      post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @new_style_retweet, :whitelist => @whitelist
+      post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @new_style_retweet, :whitelist => @whitelist
       post.should_not be
     end
     it "for quotes without further text addition" do
-      post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @new_style_retweet_no_addition, :whitelist => @whitelist
+      post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @new_style_retweet_no_addition, :whitelist => @whitelist
       post.should_not be
     end
   end
@@ -99,13 +99,13 @@ describe Combinators::TwitterTumblr do
     it "uses a given blog via group option to post to" do
       stub_instagram
       desired_group = 'mygroup.tumblr.com'
-      tumblr_post = Combinators::TwitterTumblr.generate_photo_post_from_tweet @twitter_response, {:whitelist => @whitelist, :group => desired_group}
+      tumblr_post = Tweetlr::Combinators::TwitterTumblr.generate_photo_post_from_tweet @twitter_response, {:whitelist => @whitelist, :group => desired_group}
       tumblr_post[:tumblr_blog_hostname].should eq desired_group
     end
     it "uses a given blog via tumblr_blog_hostname to post to" do
       stub_instagram
       desired_group = 'mygroup.tumblr.com'
-      tumblr_post = Combinators::TwitterTumblr.generate_photo_post_from_tweet @twitter_response, {:whitelist => @whitelist, :tumblr_blog_hostname => desired_group}
+      tumblr_post = Tweetlr::Combinators::TwitterTumblr.generate_photo_post_from_tweet @twitter_response, {:whitelist => @whitelist, :tumblr_blog_hostname => desired_group}
       tumblr_post[:tumblr_blog_hostname].should eq desired_group
     end
   end

data/spec/core_spec.rb

@@ -0,0 +1,60 @@
+require 'spec_helper'
+
+describe Tweetlr::Core do
+
+  config_file = File.join( Dir.pwd, 'config', 'tweetlr.yml')
+  config = YAML.load_file(config_file)
+  TIMESTAMP = config['twitter_timestamp']
+  WHITELIST = config['whitelist']
+
+  before :each do
+    @first_link = "http://url.com"
+    @second_link = "http://instagr.am/p/DzCWn/"
+    @third_link = "https://imageurl.com"
+    @twitter_response = {"from_user_id_str"=>"1915714", "profile_image_url"=>"http://a0.twimg.com/profile_images/386000279/2_normal.jpg", "created_at"=>"Sun, 17 Apr 2011 16:48:42 +0000", "from_user"=>"whitey_Mc_whIteLIst", "id_str"=>"59659561224765440", "metadata"=>{"result_type"=>"recent"}, "to_user_id"=>nil, "text"=>"Rigaer #wirsounterwegs #{@first_link}  @ Augenarzt Dr. Lierow #{@second_link} #{@third_link}", "id"=>59659561224765440, "from_user_id"=>1915714, "geo"=>{"type"=>"Point", "coordinates"=>[52.5182, 13.454]}, "iso_language_code"=>"de", "place"=>{"id"=>"3078869807f9dd36", "type"=>"city", "full_name"=>"Berlin, Berlin"}, "to_user_id_str"=>nil, "source"=>"<a href="http://instagr.am" rel="nofollow">instagram</a>"}
+    @tweetlr_config =  {
+      :since_id => 0,
+      :results_per_page => 3,
+      :search_term => 'coffeediary',
+      :result_type => 'recent',  
+      :api_endpoint_twitter => Tweetlr::API_ENDPOINT_TWITTER,
+      :loglevel=>1,
+      :tumblr_oauth_access_token_key => config['tumblr_oauth_access_token_key'],
+      :tumblr_oauth_access_token_secret => config['tumblr_oauth_access_token_secret'],
+      :tumblr_oauth_api_secret => config['tumblr_oauth_api_secret'],
+      :tumblr_oauth_api_key => config['tumblr_oauth_api_key'],
+      :tumblr_blog_hostname => config['tumblr_blog_hostname']
+    }
+    stub_tumblr
+    stub_twitter
+    stub_oauth
+  end
+  it "crawls twitter and posts to tumblr" do 
+    since_id_before = @tweetlr_config[:since_id]
+    result = Tweetlr::Core.crawl(@tweetlr_config)
+    since_id_before.should_not == result[:since_id]
+  end
+  it "copes with legacy config that use tumblr v1 api (basic auth)" do
+    legacy_config = {
+      :id=>16, 
+      :search_term=>"booga", 
+      :tumblr_email=>"wooga@booga.de", 
+      :tumblr_password=>"boogawooga", 
+      :since_id=>"246543935663661057", 
+      :results_per_page=>3, 
+      :result_type=>nil, 
+      :api_endpoint_twitter=>nil, 
+      :api_endpoint_tumblr=>nil, 
+      :update_period=>900, 
+      :shouts=>nil, 
+      :loglevel=>1, 
+      :whitelist=>["user1", "user2"],
+      :last_crawl=>"Fri, 14 Sep 2012 09:43:10 UTC +00:00",
+      :active=>true,
+      :tumblr_oauth_access_token_key=>nil, 
+      :tumblr_oauth_access_token_secret=>nil}
+    since_id_before = legacy_config[:since_id]
+    result = Tweetlr::Core.crawl(legacy_config)
+    since_id_before.should_not == result[:since_id]
+  end
+end

data/spec/processors/photo_services_processor_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-describe Processors::PhotoService do
+describe Tweetlr::Processors::PhotoService do
   before :each do
     @links = {
       :twimg => 'http://twitter.com/KSilbereisen/status/228035435237097472',
@@ -20,44 +20,44 @@ describe Processors::PhotoService do
   end
   it "extracts images from eye em" do
     stub_eyeem
-    link = Processors::PhotoService::find_image_url @links[:eyeem]
+    link = Tweetlr::Processors::PhotoService::find_image_url @links[:eyeem]
     link.should be
     link.should == "http://www.eyeem.com/thumb/h/1024/e35db836c5d3f02498ef60fc3d53837fbe621561-1334126483"
   end
   it "doesnt find images in embedly results that are not explicitly marked as 'Photo' via the response's 'thumbnail_url' attribute" do
     stub_embedly_no_photo
-    link = Processors::PhotoService::find_image_url 'http://makersand.co/'
+    link = Tweetlr::Processors::PhotoService::find_image_url 'http://makersand.co/'
     link.should be_nil
   end
   it "does find an image for foursquare that is not he profile pic" do
     stub_foursquare
-    link = Processors::PhotoService::find_image_url @links[:foursquare]
+    link = Tweetlr::Processors::PhotoService::find_image_url @links[:foursquare]
     link.index('userpix_thumbs').should_not be
   end
   it "should find a picture's url from the supported services" do
     @links.each do |service,link|
       send "stub_#{service}"
-      url = Processors::PhotoService::find_image_url link
+      url = Tweetlr::Processors::PhotoService::find_image_url link
       url.should be, "service #{service} not working!"
       check_pic_url_extraction service if [:twimg, :instagram,:picplz,:yfrog,:imgly,:foursqaure,:not_listed].index service
     end
   end
   it "finds path images for redirected moments as well" do
     stub_path_redirected
-    url = Processors::PhotoService::find_image_url @links[:path]
+    url = Tweetlr::Processors::PhotoService::find_image_url @links[:path]
     url.should == 'https://s3-us-west-1.amazonaws.com/images.path.com/photos2/f90fd831-43c3-48fd-84cb-5c3bae52957a/2x.jpg'
   end
   it "should not crash if embedly fallback won't find a link" do
     stub_bad_request
-    url = Processors::PhotoService::find_image_url "http://mopskopf"     
+    url = Tweetlr::Processors::PhotoService::find_image_url "http://mopskopf"     
   end
   it "should not crash with an encoding error when response is non-us-ascii" do
     stub_utf8_response
-    url = Processors::PhotoService::find_image_url "http://api.instagram.com/oembed?url=http://instagr.am/p/Gx%E2%80%946/"
+    url = Tweetlr::Processors::PhotoService::find_image_url "http://api.instagram.com/oembed?url=http://instagr.am/p/Gx%E2%80%946/"
   end
   it "follows redirects" do
     stub_imgly
-    link = Processors::PhotoService::link_url_redirect 'im mocked anyways'
+    link = Tweetlr::Processors::PhotoService::link_url_redirect 'im mocked anyways'
     link.should == 'http://s3.amazonaws.com/imgly_production/899582/full.jpg'
   end
 end

data/spec/processors/tumblr_processor_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-describe Processors::Tumblr do
+describe Tweetlr::Processors::Tumblr do
   before :all do
     config_file = File.join( Dir.pwd, 'config', 'tweetlr.yml')
     config = YAML.load_file(config_file)
@@ -21,10 +21,10 @@ describe Processors::Tumblr do
   it "posts to tumblr" do
     stub_tumblr
     stub_oauth
-    tumblr_post = Combinators::TwitterTumblr::generate_photo_post_from_tweet @twitter_response, @tweetlr_config
+    tumblr_post = Tweetlr::Combinators::TwitterTumblr::generate_photo_post_from_tweet @twitter_response, @tweetlr_config
     tumblr_post[:date] = Time.now.to_s
     tumblr_post[:source] = 'http://distilleryimage6.instagram.com/db72627effde11e1b3f322000a1e8899_7.jpg'
-    response = Processors::Tumblr::post @tweetlr_config.merge(tumblr_post)
+    response = Tweetlr::Processors::Tumblr::post @tweetlr_config.merge(tumblr_post)
     response.should be
     response.code.should == "201"
   end

data/spec/processors/twitter_processor_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-describe Processors::Twitter do
+describe Tweetlr::Processors::Twitter do
   before :each do
     @first_link = "http://url.com"
     @second_link = "http://instagr.am/p/DzCWn/"
@@ -16,15 +16,15 @@ describe Processors::Twitter do
   end
   it "should search twitter for a given term" do
     stub_twitter
-    response = Processors::Twitter::lazy_search @twitter_config
+    response = Tweetlr::Processors::Twitter::lazy_search @twitter_config
     tweets = response['results']
     tweets.should be
     tweets.should_not be_empty
   end
   it "extracts links" do
-    links = Processors::Twitter::extract_links ''
+    links = Tweetlr::Processors::Twitter::extract_links ''
     links.should be_nil
-    links = Processors::Twitter::extract_links @twitter_response
+    links = Tweetlr::Processors::Twitter::extract_links @twitter_response
     links[0].should == @first_link
     links[1].should == @second_link
     links[2].should == @third_link

data/spec/spec_helper.rb

@@ -1,15 +1,17 @@
 #encoding: utf-8
 require "bundler"
 require "logger"
+require "#{File.dirname(__FILE__)}/../lib/tweetlr"
+
 Bundler.require :default, :development, :test
 
 logger = Logger.new(STDOUT)
 logger.level = Logger::FATAL
-LogAware.log = logger
+Tweetlr::LogAware.log = logger
 
 def check_pic_url_extraction(service)
-  image_url = Processors::PhotoService::send "image_url_#{service}".to_sym, @links[service]
-  image_url.should =~ Processors::PhotoService::PIC_REGEXP
+  image_url = Tweetlr::Processors::PhotoService::send "image_url_#{service}".to_sym, @links[service]
+  image_url.should =~ Tweetlr::Processors::PhotoService::PIC_REGEXP
 end
 
 def stub_oauth

data/tweetlr.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name        = "tweetlr"
-  s.version     = "0.1.17"
+  s.version     = "0.1.18"
   s.author      = "Sven Kraeuter"
   s.email       = "sven.kraeuter@gmail.com"
   s.homepage    = "http://tweetlr.5v3n.com"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: tweetlr
 version: !ruby/object:Gem::Version
-  version: 0.1.17
+  version: 0.1.18
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-09-16 00:00:00.000000000 Z
+date: 2012-09-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
-  requirement: &2160430840 !ruby/object:Gem::Requirement
+  requirement: &2160420980 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2160430840
+  version_requirements: *2160420980
 - !ruby/object:Gem::Dependency
   name: eventmachine
-  requirement: &2160430180 !ruby/object:Gem::Requirement
+  requirement: &2160420140 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2160430180
+  version_requirements: *2160420140
 - !ruby/object:Gem::Dependency
   name: curb
-  requirement: &2160429480 !ruby/object:Gem::Requirement
+  requirement: &2160419680 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +43,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2160429480
+  version_requirements: *2160419680
 - !ruby/object:Gem::Dependency
   name: json
-  requirement: &2160429020 !ruby/object:Gem::Requirement
+  requirement: &2160419220 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,10 +54,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2160429020
+  version_requirements: *2160419220
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &2160428580 !ruby/object:Gem::Requirement
+  requirement: &2160418520 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -65,10 +65,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2160428580
+  version_requirements: *2160418520
 - !ruby/object:Gem::Dependency
   name: oauth
-  requirement: &2160428140 !ruby/object:Gem::Requirement
+  requirement: &2160417840 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -76,10 +76,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2160428140
+  version_requirements: *2160417840
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2160427720 !ruby/object:Gem::Requirement
+  requirement: &2160417320 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -87,10 +87,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2160427720
+  version_requirements: *2160417320
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2160427240 !ruby/object:Gem::Requirement
+  requirement: &2160416900 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -98,10 +98,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2160427240
+  version_requirements: *2160416900
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &2160426820 !ruby/object:Gem::Requirement
+  requirement: &2160416480 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -109,7 +109,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2160426820
+  version_requirements: *2160416480
 description: tweetlr crawls twitter for a given term, extracts photos out of the collected
   tweets' short urls and posts the images to tumblr.
 email: sven.kraeuter@gmail.com
@@ -130,19 +130,20 @@ files:
 - Rakefile
 - bin/tweetlr
 - config/tweetlr.yml
-- lib/combinators/twitter_tumblr.rb
-- lib/log_aware.rb
-- lib/processors/http.rb
-- lib/processors/photo_service.rb
-- lib/processors/tumblr.rb
-- lib/processors/twitter.rb
 - lib/tweetlr.rb
+- lib/tweetlr/combinators/twitter_tumblr.rb
+- lib/tweetlr/core.rb
+- lib/tweetlr/log_aware.rb
+- lib/tweetlr/processors/http.rb
+- lib/tweetlr/processors/photo_service.rb
+- lib/tweetlr/processors/tumblr.rb
+- lib/tweetlr/processors/twitter.rb
 - spec/combinators/twitter_tumblr_combinator_spec.rb
+- spec/core_spec.rb
 - spec/processors/photo_services_processor_spec.rb
 - spec/processors/tumblr_processor_spec.rb
 - spec/processors/twitter_processor_spec.rb
 - spec/spec_helper.rb
-- spec/tweetlr_spec.rb
 - tweetlr.gemspec
 homepage: http://tweetlr.5v3n.com
 licenses: []
@@ -171,8 +172,8 @@ summary: tweetlr crawls twitter for a given term, extracts photos out of the col
   tweets' short urls and posts the images to tumblr.
 test_files:
 - spec/combinators/twitter_tumblr_combinator_spec.rb
+- spec/core_spec.rb
 - spec/processors/photo_services_processor_spec.rb
 - spec/processors/tumblr_processor_spec.rb
 - spec/processors/twitter_processor_spec.rb
 - spec/spec_helper.rb
-- spec/tweetlr_spec.rb

data/lib/processors/tumblr.rb

@@ -1,51 +0,0 @@
-require 'log_aware'
-require 'oauth'
-
-module Processors
-  #utilities for handling tumblr
-  module Tumblr
-    GENERATOR = %{tweetlr - http://tweetlr.5v3n.com}
-    API_ENDPOINT_TUMBLR = 'http://www.tumblr.com'
-    include LogAware
-    def self.log
-      LogAware.log #TODO why doesn't the include make the log method accessible?
-    end
-    #post a tumblr photo entry. 
-    #
-    #required arguments are :tumblr_blog_hostname, :tumblr_blog_hostname, :tumblr_oauth_api_secret, :tumblr_oauth_access_token_secret, :source, :caption, :state
-    #
-    #optional arguments: :tags, :type (default: 'photo') 
-    #
-    def self.post(options={})
-      base_hostname       = options[:tumblr_blog_hostname] || options[:group]
-      tumblr_oauth_api_key= options[:tumblr_oauth_api_key] 
-      tumblr_oauth_api_secret= options[:tumblr_oauth_api_secret] 
-      access_token_key    = options[:tumblr_oauth_access_token_key]
-      access_token_secret = options[:tumblr_oauth_access_token_secret]
-      type                = options[:type] || 'photo'
-      tags                = options[:tags] || ''
-
-      consumer = OAuth::Consumer.new(tumblr_oauth_api_key, tumblr_oauth_api_secret,
-                                     { :site => 'http://www.tumblr.com',
-                                       :request_token_path => '/oauth/request_token',
-                                       :authorize_path => '/oauth/authorize',
-                                       :access_token_path => '/oauth/access_token',
-                                       :http_method => :post } )
-
-      access_token = OAuth::AccessToken.new(consumer, access_token_key, access_token_secret)
-
-      post_response = access_token.post(
-        "http://api.tumblr.com/v2/blog/#{base_hostname}/post", { 
-          :type => type, 
-          :source => options[:source], 
-          :caption => options[:caption],
-          :date => options[:date],
-          :tags => tags,
-          :state => options[:state],
-          :generator => GENERATOR
-           }
-          )
-      post_response
-    end
-  end
-end

data/spec/tweetlr_spec.rb

@@ -1,28 +0,0 @@
-require 'spec_helper'
-
-describe Tweetlr do
-
-  config_file = File.join( Dir.pwd, 'config', 'tweetlr.yml')
-  config = YAML.load_file(config_file)
-  TIMESTAMP = config['twitter_timestamp']
-  WHITELIST = config['whitelist']
-
-  before :each do
-    @first_link = "http://url.com"
-    @second_link = "http://instagr.am/p/DzCWn/"
-    @third_link = "https://imageurl.com"
-    @twitter_response = {"from_user_id_str"=>"1915714", "profile_image_url"=>"http://a0.twimg.com/profile_images/386000279/2_normal.jpg", "created_at"=>"Sun, 17 Apr 2011 16:48:42 +0000", "from_user"=>"whitey_Mc_whIteLIst", "id_str"=>"59659561224765440", "metadata"=>{"result_type"=>"recent"}, "to_user_id"=>nil, "text"=>"Rigaer #wirsounterwegs #{@first_link}  @ Augenarzt Dr. Lierow #{@second_link} #{@third_link}", "id"=>59659561224765440, "from_user_id"=>1915714, "geo"=>{"type"=>"Point", "coordinates"=>[52.5182, 13.454]}, "iso_language_code"=>"de", "place"=>{"id"=>"3078869807f9dd36", "type"=>"city", "full_name"=>"Berlin, Berlin"}, "to_user_id_str"=>nil, "source"=>"<a href="http://instagr.am" rel="nofollow">instagram</a>"}
-    @tweetlr_config =  {
-      :since_id => 0,
-      :search_term => 'moped',
-      :results_per_page => 100,
-      :result_type => 'recent',  
-      :api_endpoint_twitter => Tweetlr::API_ENDPOINT_TWITTER
-    }
-  end
-  it "crawls twitter and posts to tumblr" do 
-    stub_tumblr
-    stub_twitter
-    Tweetlr.crawl(@tweetlr_config)
-  end
-end