amazon-review 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/amazon-review.rb +40 -0
- data/lib/amazon-review/review.rb +79 -0
- metadata +63 -0
@@ -0,0 +1,40 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'open-uri'
|
3
|
+
|
4
|
+
module AmazonReview
|
5
|
+
|
6
|
+
def self.find_reviews(asin)
|
7
|
+
reviews = []
|
8
|
+
delay = 0.5
|
9
|
+
page = 1
|
10
|
+
|
11
|
+
# iterate through the pages of reviews
|
12
|
+
|
13
|
+
begin
|
14
|
+
url = "http://www.amazon.com/product-reviews/#{asin}/?ie=UTF8&showViewpoints=0&pageNumber=#{page}&sortBy=bySubmissionDateAscending"
|
15
|
+
doc = Nokogiri::HTML(open(url))
|
16
|
+
|
17
|
+
# parse each review
|
18
|
+
new_reviews = 0
|
19
|
+
doc.css("#productReviews td > a[name]").each do |review_html|
|
20
|
+
reviews << Review.new(review_html)
|
21
|
+
new_reviews += 1
|
22
|
+
end
|
23
|
+
# go to next page
|
24
|
+
page += 1
|
25
|
+
|
26
|
+
# delay to prevent 503 errors
|
27
|
+
delay = [0, delay - 0.1].max # decrease delay
|
28
|
+
sleep delay
|
29
|
+
|
30
|
+
rescue Exception => e # error while parsing (likely a 503)
|
31
|
+
delay += 0.5 # increase delay
|
32
|
+
|
33
|
+
end until new_reviews == 0
|
34
|
+
|
35
|
+
reviews
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
39
|
+
|
40
|
+
require_relative "amazon-review/review"
|
@@ -0,0 +1,79 @@
|
|
1
|
+
module AmazonReview
|
2
|
+
class Review
|
3
|
+
|
4
|
+
def initialize(html)
|
5
|
+
@html = html
|
6
|
+
@div = html.next_element.next_element
|
7
|
+
end
|
8
|
+
|
9
|
+
def inspect
|
10
|
+
"<Review: id=#{id}>"
|
11
|
+
end
|
12
|
+
|
13
|
+
def id
|
14
|
+
@id ||= @html['name']
|
15
|
+
end
|
16
|
+
|
17
|
+
def url
|
18
|
+
@url ||= "http://www.amazon.com/review/#{id}"
|
19
|
+
end
|
20
|
+
|
21
|
+
def user_id
|
22
|
+
regex = /[A-Z0-9]+/
|
23
|
+
@user_id ||= @div.css('a[href^="/gp/pdp/profile"]').first["href"][regex]
|
24
|
+
end
|
25
|
+
|
26
|
+
def title
|
27
|
+
@title ||= @div.css("b").first.text.strip
|
28
|
+
end
|
29
|
+
|
30
|
+
def date
|
31
|
+
@date ||= Date.parse(@div.css("nobr").first.text)
|
32
|
+
end
|
33
|
+
|
34
|
+
def text
|
35
|
+
# remove leading and trailing line returns, tabs, and spaces
|
36
|
+
@text ||= @div.css(".reviewText").first.content.strip #sub(/\A[\n\t\s]+/,"").sub(/[\n\t\s]+\Z/,"")
|
37
|
+
end
|
38
|
+
|
39
|
+
def rating
|
40
|
+
regex = /[0-9\.]+/
|
41
|
+
@rating ||= Float( @div.css("span.swSprite").first['title'][regex] )
|
42
|
+
end
|
43
|
+
|
44
|
+
def helpful_count
|
45
|
+
if helpful_match
|
46
|
+
@helpful_count ||= Float(helpful_match.captures[0])
|
47
|
+
else
|
48
|
+
@helpful_count = nil
|
49
|
+
end
|
50
|
+
|
51
|
+
@helpful_count
|
52
|
+
end
|
53
|
+
|
54
|
+
def helpful_ratio
|
55
|
+
if helpful_match
|
56
|
+
@helpful_ratio ||= Float(helpful_match.captures[0]) / Float(helpful_match.captures[1])
|
57
|
+
else
|
58
|
+
@helpful_ratio = nil
|
59
|
+
end
|
60
|
+
|
61
|
+
@helpful_ratio
|
62
|
+
end
|
63
|
+
|
64
|
+
def to_hash
|
65
|
+
attrs = [:id, :url, :user_id, :title, :date, :text, :rating, :helpful_count, :helpful_ratio]
|
66
|
+
attrs.inject({}) do |r,attr|
|
67
|
+
r[attr] = self.send(attr)
|
68
|
+
r
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
private
|
73
|
+
|
74
|
+
def helpful_match
|
75
|
+
@helpful_match ||= @div.text.match(/(\d+) of (\d+) people/)
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
end
|
metadata
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: amazon-review
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Jeff Mekler
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2014-09-09 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>'
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 1.5.6
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>'
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 1.5.6
|
30
|
+
description: A simple gem to parse Amazon product reviews
|
31
|
+
email: contact@jeffmekler.com
|
32
|
+
executables: []
|
33
|
+
extensions: []
|
34
|
+
extra_rdoc_files: []
|
35
|
+
files:
|
36
|
+
- lib/amazon-review.rb
|
37
|
+
- lib/amazon-review/review.rb
|
38
|
+
homepage: http://rubygems.org/gems/amazon-review
|
39
|
+
licenses:
|
40
|
+
- MIT
|
41
|
+
post_install_message:
|
42
|
+
rdoc_options: []
|
43
|
+
require_paths:
|
44
|
+
- lib
|
45
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
46
|
+
none: false
|
47
|
+
requirements:
|
48
|
+
- - ! '>='
|
49
|
+
- !ruby/object:Gem::Version
|
50
|
+
version: '0'
|
51
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ! '>='
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '0'
|
57
|
+
requirements: []
|
58
|
+
rubyforge_project:
|
59
|
+
rubygems_version: 1.8.24
|
60
|
+
signing_key:
|
61
|
+
specification_version: 3
|
62
|
+
summary: A simple gem to parse Amazon product reviews
|
63
|
+
test_files: []
|