amazon-search 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: ffd9ecb7e82f05973d09530f4f8c6d4a305f3870
+  data.tar.gz: 9c3f15bce32b1ba1c6ba76affb5d9bb39e7ea62f
+SHA512:
+  metadata.gz: 20c6d71d9d20ceb3bc72c3256409f32e395198b87edb7cc9ab0f522765035c91a76bee96fc2714187e969ce11e9b1df4a3845ab292a25e320a92084d1681708c
+  data.tar.gz: ca2aac4a30a8b66de94263c9abca6c46618816342384e50e02db5fc98a17c5726847cce8689b3cf688e39627f1d41992943881af4b0bac9636cf6149eef404d9

data/lib/amazon-search.rb

@@ -0,0 +1,108 @@
+
+require 'mechanize'
+
+###########################################
+# Select Amazon search form and submit
+# the search criteria
+###########################################
+agent = Mechanize.new
+main_page = agent.get("http://amazon.com")
+search_form = main_page.form_with :name => "site-search"
+
+while true # until user cancels
+    puts "\nPlease enter keywords for Amazon search"
+    keywords = gets.chomp # asks for search terms
+    search_form.field_with(:name => "field-keywords").value = keywords # sets value of search box
+    search_results = agent.submit search_form # submits form
+    
+    
+    ###########################################
+    # Cycle through all result pages
+    # and list product links
+    ###########################################
+    
+    
+    next_page = agent.get(search_results.uri) # initial search results are the first page
+
+    # last page is disabled nav button in search results 
+    last_page_num = search_results.search '//*[contains(concat( " ", @class, " " ), concat( " ", "pagnDisabled", " " ))]'
+    last_page_num = last_page_num.text.to_i # change to int for upcoming iteration instructions
+    
+    count = 0 # start count variable
+    
+    last_page_num.times do # loop forever until stopped
+        count += 1
+    
+        page = agent.get(next_page.uri) # load the next page
+        
+        #--------- display page number ---------------------
+        # current_page = page.search '//*[contains(concat( " ", @class, " " ), concat( " ", "pagnCur", " " ))]'
+        # puts "\n", "=="*50
+        # puts "Displaying '#{current_page.text}' of '20' pages"
+        # puts "This is the current page's uri:"
+        # puts page.uri
+        
+        
+        product_divs = page.search('//li[starts-with(@id, "result")]') # find the div of each product
+        # '//li[starts-with(@id, "result")]' <-- this works but includes ads...
+        
+        # nokogiri syntax is needed when iterating...not mechanize!
+        product_divs.each do |product|
+            
+            #--------- nokogiri select html sections from css ---------------------
+            title = product.at_css(".s-access-title")
+            seller = product.at_css(".a-row > .a-spacing-none") #".a-spacing-small .a-spacing-none"
+            price = product.at_css(".s-price")
+            stars = product.at_css(".a-icon-star")
+            reviews = product.at_css("span+ .a-text-normal") # ".a-span-last .a-spacing-mini > span+ .a-text-normal"
+            image = product.at_css(".s-access-image")
+            url = product.at_css(".a-row > a") 
+            
+            
+            
+            if title == nil # if it's nil it's prob an ad 
+                break
+            else
+                title = title.text
+                
+                if seller == nil # if seller is nil it's prob a movie
+                    seller = "unknown"
+                else
+                    seller = seller.text
+                    if price == nil # no price? prob not worthy item
+                    break
+                    
+                    else
+                        price = price.text
+                        if stars == nil
+                            break
+                            
+                        else
+                            stars = stars.text
+                            reviews = reviews.text
+                            image = image['src'] 
+                            url = url['href']    
+                            
+                            puts "--"*50
+                            puts "title: \t\t#{title}"
+                            puts "seller: \t#{seller}"
+                            puts "price: \t\t#{price}"
+                            puts "stars: \t\t#{stars}"
+                            puts "reviews: \t#{reviews}"
+                            puts "image url: \t#{image}"
+                            puts "product url: \t#{url}"
+                            
+                        end # ends nil price if statement
+                    end # ends nil stars if statement
+                end # ends nil seller if statement
+            end # ends nil product if statement
+        end # ends each product div iteration (page is finished)
+       
+        next_page_link = page.link_with text: /Next Page/ # find the next page link
+        
+        next_page = next_page_link.click unless count == 20 # click to next page unless on page 20
+    end 
+    
+    puts "\n\n(end of search results)"
+
+end

metadata

@@ -0,0 +1,44 @@
+--- !ruby/object:Gem::Specification
+name: amazon-search
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- John Mason
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-09-17 00:00:00.000000000 Z
+dependencies: []
+description: A simple screenscraper to search Amazon
+email: mace2345@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/amazon-search.rb
+homepage: http://rubygems.org/gems/amazon-search
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.6
+signing_key: 
+specification_version: 4
+summary: Hola!
+test_files: []