kindle-highlights 0.0.8 → 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c7c203ab1e9aad56bd379b3e6b5cc664136f2c18
+  data.tar.gz: 8182d4dfbfce7296a66785a2b595929cc6c18a3a
+SHA512:
+  metadata.gz: 7414e1b4930c3aaaec740d37815749aa1e4f6ce87852d9051059688d1e7b978586cb5ee2694ed212ee0fb4f0c3a27741d07968e5a3c807cce53dd752c165a505
+  data.tar.gz: aef2a7e0ea42a2c40c02abc42d4af20329645e1c5f9ca137dc2a57818205762f18226826a2bb8cb86f128fd767f12eb55230fc24d00a3360c6ecca71a43be1aa

data/lib/kindle_highlights.rb

@@ -4,7 +4,7 @@ require 'json'
 require 'kindle_highlights/client'
 
 module KindleHighlights  
-  
   KINDLE_LOGIN_PAGE      = "http://kindle.amazon.com/login"
   SIGNIN_FORM_IDENTIFIER = "signIn"
-end
+  BATCH_SIZE             = 200
+end

data/lib/kindle_highlights/client.rb

@@ -1,50 +1,93 @@
 module KindleHighlights
   class Client
-    attr_reader :books
-        
-    def initialize(email_address, password)
-      @email_address   = email_address
-      @password        = password
-      
-      setup_mechanize_agent
-      load_books_from_kindle_account
+    class CaptchaError < StandardError; end
+
+    attr_writer :mechanize_agent
+    attr_accessor :kindle_logged_in_page
+
+    def initialize(email_address:, password:, mechanize_options: {})
+      @email_address     = email_address
+      @password          = password
+      @mechanize_options = mechanize_options
+    end
+
+    def books
+      @books ||= load_books_from_kindle_account
     end
-  
+
     def highlights_for(asin)
-      highlights = @mechanize_agent.get("https://kindle.amazon.com/kcw/highlights?asin=#{asin}&cursor=0&count=1000")
-      json = JSON.parse(highlights.body)
-      json["items"]
+      conditionally_sign_in_to_amazon
+
+      cursor     = 0
+      highlights = []
+
+      loop do
+        # This endpoint includes a `hasMore` field. Unfortunately at the time of this writing is always `false`.
+        page  = mechanize_agent.get("https://kindle.amazon.com/kcw/highlights?asin=#{asin}&cursor=#{cursor}&count=#{BATCH_SIZE}")
+        items = JSON.parse(page.body).fetch("items", [])
+
+        break unless items.any?
+
+        highlights.concat(items)
+        cursor += BATCH_SIZE
+      end
+      highlights
     end
-    
+
     private
-   
+
+    attr_accessor :email_address, :password, :mechanize_options
+
+    def conditionally_sign_in_to_amazon
+      if @kindle_logged_in_page.nil?
+        signin_page            = mechanize_agent.get(KINDLE_LOGIN_PAGE)
+        signin_form            = signin_page.form(SIGNIN_FORM_IDENTIFIER)
+        signin_form.email      = email_address
+        signin_form.password   = password
+        post_signin_page       = mechanize_agent.submit(signin_form)
+
+        if post_signin_page.search("#ap_captcha_img").any?
+          resolution_url = post_signin_page.link_with(text: /See a new challenge/).resolved_uri.to_s
+          raise CaptchaError, "Received a CAPTCHA while attempting to sign in to your Amazon account. You will need to resolve this manually at #{resolution_url}"
+        else
+          @kindle_logged_in_page = post_signin_page
+        end
+      end
+    end
+
     def load_books_from_kindle_account
-      @books = Hash.new
-      signin_page = @mechanize_agent.get(KINDLE_LOGIN_PAGE)
-      
-      signin_form = signin_page.form(SIGNIN_FORM_IDENTIFIER)
-      signin_form.email = @email_address
-      signin_form.password = @password
-      
-      kindle_logged_in_page = @mechanize_agent.submit(signin_form)
-      highlights_page = @mechanize_agent.click(kindle_logged_in_page.link_with(:text => /Your Books/))
+      conditionally_sign_in_to_amazon
+
+      books           = {}
+      highlights_page = mechanize_agent.click(kindle_logged_in_page.link_with(text: /Your Books/))
 
       loop do
-        books = highlights_page.search(".//td[@class='titleAndAuthor']")
-        books.each do |book|
-          asin = book.search("a").first.attributes["href"].value.split("/").last
-          title = book.search("a").first.inner_html
-          @books[asin] = title
+        highlights_page.search(".//td[@class='titleAndAuthor']").each do |book|
+          asin_and_title_element = book.search("a").first
+          asin                   = asin_and_title_element.attributes.fetch("href").value.split("/").last
+          title                  = asin_and_title_element.inner_html
+          books[asin]            = title
         end
+
         break if highlights_page.link_with(text: /Next/).nil?
-        highlights_page = @mechanize_agent.click(highlights_page.link_with(text: /Next/))
+        highlights_page = mechanize_agent.click(highlights_page.link_with(text: /Next/))
       end
+      books
+    end
+
+    def mechanize_agent
+      @mechanize_agent ||= initialize_mechanize_agent
     end
-    
-    def setup_mechanize_agent
-      @mechanize_agent = Mechanize.new
-      @mechanize_agent.user_agent_alias = 'Windows Mozilla'
-      @mechanize_agent.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+
+    def initialize_mechanize_agent
+      mechanize_agent                        = Mechanize.new
+      mechanize_agent.user_agent_alias       = 'Windows Mozilla'
+      mechanize_agent.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+
+      mechanize_options.each do |mech_attr, value|
+        mechanize_agent.send("#{mech_attr}=", value)
+      end
+      mechanize_agent
     end
   end
-end
+end

metadata

@@ -1,32 +1,71 @@
 --- !ruby/object:Gem::Specification
 name: kindle-highlights
 version: !ruby/object:Gem::Version
-  version: 0.0.8
-  prerelease: 
+  version: 1.0.0
 platform: ruby
 authors:
 - Eric Farkas
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-21 00:00:00.000000000 Z
+date: 2016-03-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 2.7.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 2.7.2
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
 description: Until there is a Kindle API, this will suffice.
 email: eric@prudentiadigital.com
 executables: []
@@ -36,28 +75,28 @@ files:
 - lib/kindle_highlights.rb
 - lib/kindle_highlights/client.rb
 homepage: https://github.com/speric/kindle-highlights
-licenses: []
+licenses:
+- MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.22
+rubygems_version: 2.2.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Kindle highlights
 test_files: []
 has_rdoc: