title_grabber 0.2.3 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 870ae6b9b5903d1516e9678f25a85f3852a059ed2bd1b6a23d8289dcf75370b2
-  data.tar.gz: 26e430fb06e441b39297b416b27c21428b24eedd8d8f28dd9e329e1f6027ebec
+  metadata.gz: 7532ff11d949765bb08b4ae1deeefc1aea1c70e8b794139cf747cf10c948e433
+  data.tar.gz: f59192b55720a85dab8767b03346fc335e825d5696d20f7ac46e0880a081b96d
 SHA512:
-  metadata.gz: 4a76a1cfe72a0296a1db4d46e38ee43f54cddd07a0cf1a11c40eb95f687376f610a810e87886b6910c6ecb9673723b9f35b4d13fca6a0bbcb8ee799a929ae420
-  data.tar.gz: 64fc74972c50ea504aa44d35079db6e0ffd4531df7a2b1e7f9f0df1a134e0f12edf76009a31eeed795f7d905c224ebd2b653c8885716199cecf1fa23575ff7ec
+  metadata.gz: 1102126705a068b7e7e92721c93cc283bf9b4bef28a49c7799aeb3f03825548751ebb108861e73952ba79de57620d4e9390a6a95df32b9a04cc2e7a75df704c5
+  data.tar.gz: 24f10e575e1f5b706877e952e7fefdcba17a589a3a0f0282c697d6b1882e79f40066bac01509e5d3ed43d50f2102e68ff3f2baae5c5bd9c3eecd295e86f5af03

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    title_grabber (0.2.3)
+    title_grabber (0.2.4)
       http (~> 4.1)
       oga (~> 2.15)
 

data/lib/title_grabber/version.rb

@@ -1,3 +1,3 @@
 module TitleGrabber
-  VERSION = "0.2.3"
+  VERSION = "0.2.4"
 end

data/lib/title_grabber.rb

@@ -16,32 +16,23 @@ module TitleGrabber
   ART_TIT_HEAD = -"article_title"
   HEADERS = [URL_HEADER, PAGE_TIT_HEAD, ART_TIT_HEAD].freeze
 
-  class << self
+  def self.call(lines, options)
+    MultiThreadedGrabber.new(lines, options).call
+  end
+
+  class MultiThreadedGrabber
     include HTTPHelper
     include TextHelper
 
-    def call(lines, options)
-      out_path = options[:output]
-
-      processed_urls = if out_path.exist?
-                         arr_of_h = CSV.read(out_path, headers: true)
-                         arr_of_h.each_with_object({}) { |r, h|
-                           page_tit = r[PAGE_TIT_HEAD]
-                           art_tit = r[ART_TIT_HEAD]
-
-                           unless page_tit.empty? && art_tit.empty?
-                             h[r[URL_HEADER]] = { PAGE_TIT_HEAD => page_tit,
-                                                  ART_TIT_HEAD => art_tit }
-                           end
-                         }.tap do
-                           arr_of_h = nil
-                         end
-                       else
-                         {}
-                       end
+    attr_reader :lines, :out_path
 
-      queue = Queue.new
+    def initialize(lines, options)
+      @lines = lines
+      @out_path = options[:output]
+    end
 
+    def call
+      queue = Queue.new
       tmp_path = out_path.sub_ext(".tmp#{out_path.extname}")
       CSV.open(tmp_path, "w", force_quotes: true) do |csv|
         csv << HEADERS
@@ -89,5 +80,27 @@ module TitleGrabber
 
       FileUtils.mv(tmp_path, out_path)
     end
+
+    private
+
+    def processed_urls
+      @processed_urls ||= begin
+                            urls = {}
+
+                            if out_path.exist?
+                              CSV.foreach(out_path, headers: true) do |r|
+                                page_tit = r[PAGE_TIT_HEAD]
+                                art_tit = r[ART_TIT_HEAD]
+
+                                unless page_tit.empty? && art_tit.empty?
+                                  urls[r[URL_HEADER]] = { PAGE_TIT_HEAD => page_tit,
+                                                          ART_TIT_HEAD => art_tit }
+                                end
+                              end
+                            end
+
+                            urls
+                          end
+    end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: title_grabber
 version: !ruby/object:Gem::Version
-  version: 0.2.3
+  version: 0.2.4
 platform: ruby
 authors:
 - Cristian Rasch