ebookdealinfo 1.0.0 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b2b469d9f1996f015d320bbf4948873186bea439
-  data.tar.gz: 3ba1dad6388407f5fff202de99e69afa8b5e0f95
+  metadata.gz: d3af5eefa942b5a80ab2d50d7b877eb201f1cbc6
+  data.tar.gz: ee53d579e8d2c724eb4b07ea04b0318d6dc9b11a
 SHA512:
-  metadata.gz: 231a456cddc2468a41eb3fbb05f28a417c669b830d38100389a1883a4ca7cfe9b027bafc578328010a2105d6c3eb40f262ce0372765e68c687de64e015e85930
-  data.tar.gz: db62e7b8dd07b00465778ee2d435aa9d988738e184e90f7764b6c31fa43ce25e4b0402546fd5fdc5370c9f27e46b9dd8ee6a14157b1fbc039a9f274d886d521e
+  metadata.gz: fe6a8fb850d8b257e3f5b7f625907e68456886b443e2a5a8d62ad0e5f444c0f9961be6691e2bac542fb4640b6537fe62a3c684d1daaa48a574be90272f15e0f3
+  data.tar.gz: 6e891715c2bb8af19bacd1d16aa8331f3a1322aff9602af74863ce36fd2c1794536a58305dceb0e6c5f3eae88acabe586050827668e73eed01b0ed518867fc16

data/lib/ebookdealinfo/deal_scraper.rb

@@ -10,19 +10,19 @@ class DealScraper
       if post.search("p.title").text.size > 0
         if post.search("p.title").text.include?(";") #for posts formatted "#~Author~; ~Title; ~Price~"
           author = post.search("p.title").text.split(";")[0].strip
-          #.search("p.title a").attribute("href").value
           title = post.search("p.title").text.split(";")[1].strip
-          price = post.search("p.title").text.split(";")[2].strip #can't handle free books
+          post.search("p.title").text.split(";")[2] != nil ? price = post.search("p.title").text.split(";")[2].strip : price = ""
           Book.create(author, title, price)
-          puts "Loaded book ##{index+1} of 25"
+          puts "Loaded book ##{index+1} of #{deals.search("div.link").size}"
         else #for posts formatted "~Title~ by ~author~ (~Price~)"
-          if post.search("p.title").text.slice(/\s([Bb]y)/) != nil #ignore wacky formatted posts
-            author = post.search("p.title").text.split("by")[1].slice(/\A[^(,$\/]+/).split(". Kindle")[0].split("-- Kindle")[0].strip
-            title = post.search("p.title").text.split("by").first.gsub(/\W+\z/, "").strip
-            price = post.search("p.title").text.slice(/[$]\d+[.]\d+/).strip #can't handle free books
+          if post.search("p.title").text.slice(/[,.-[ ]]([Bb]y)/) != nil #ignore wacky formatted posts
+            author = post.search("p.title").text.split("by")[1].strip.slice(/\A[^(,$\/]+/).split(". Kindle")[0].split("-- Kindle")[0].strip
+            title = post.search("p.title").text.split("by").first.gsub(/[(].+[)]/,"").gsub(/\W+\z/, "").strip
+            post.search("p.title").text.slice(/[$]\d+[.]\d+/) != nil ? price = post.search("p.title").text.slice(/[$]\d+[.]\d+/).strip : price = ""
             Book.create(author, title, price)
-            puts "Loaded book ##{index+1} of 25"
+            puts "Loaded book ##{index+1} of #{deals.search("div.link").size}"
           else
+            puts "Unable to load book ##{index+1} of #{deals.search("div.link").size}. Probably a bad post name."
             Book.create("","","",0)
           end
         end

data/lib/ebookdealinfo/info_scraper.rb

@@ -5,7 +5,6 @@ class InfoScraper
 
   def info_scrape(book) #for each instance of book in the class collection, go get blurb, series, gr rating/rates and add them to that instance; also author to deal with last name only from scrape?
     search_string = "#{book.title} #{book.author.gsub(".", ". ").gsub(/[^\w\s]/,"")}".gsub(/(\A|\s)\S\s/," ").gsub(/[^a-zA-Z0-9']+/, "+") #turns the author + title into a usable goodreads search string
-          #should remove anything joining multiple authors ("&", ",") that would break the search
     search_page = Nokogiri::HTML(open("https://www.goodreads.com/search?q=#{search_string}&search_type=books",'User-Agent' => 'Ruby')) #uses the search string to pull an item's goodreads page
     if search_page.css("table a").size != 0
       determinant = search_page.css("span.minirating").map.with_index {|i,index| [index, i.text.strip.slice(/\s(\d|,)+/).strip.gsub(",","").to_i]}.sort! {|x,y| x[1].to_i <=> y[1].to_i}.last #the search result with the most rates (and presumably most legitimate) is an array [result_index, #rates]

data/lib/ebookdealinfo/version.rb

@@ -1,3 +1,3 @@
 module EbookDealInfo
-  VERSION = "1.0.0"
+  VERSION = "1.0.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ebookdealinfo
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.2
 platform: ruby
 authors:
 - kylek
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-09-01 00:00:00.000000000 Z
+date: 2017-09-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler