amazon_wish_miner 0.2.0 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/amazon_wish_miner/amazon_wish.rb +10 -0
- data/lib/amazon_wish_miner/amazon_wish_list.rb +13 -0
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 540e25cc6d5661cf2c65b24a2827cfa670caa455c845c1a039cfe94ef44c536f
|
4
|
+
data.tar.gz: f2f7d46b8eca7e5d088416757f842edf5d6ebc078e374dd8477bf17d5d48a303
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6c73aaca8ec8b6a58ed3ad6ab808d0e163345beed25d571b7e782197d198bbf22b9a6b126ede29a42a6eae7a5e596b848ca580e1cbfc8c1eaf84cc0a72a2a3dc
|
7
|
+
data.tar.gz: 24d4a0577dea49247f4fc1569321b5f254d280c12024de29a400acbb7920657fecfc8a161aa52ec3acd023d83dd961c9c8f32e96a5dad4ee6502fdea7b61e7c1
|
@@ -80,4 +80,14 @@ class AmazonWish
|
|
80
80
|
chars.drop_while(&TITLE_TRIMMER).reverse.drop_while(&TITLE_TRIMMER).reverse.join
|
81
81
|
end
|
82
82
|
|
83
|
+
def self.attributes_from_responses(page_responses)
|
84
|
+
page_responses.each_with_object(Array.new) do |pr, item_attrs|
|
85
|
+
Nokogiri::HTML(pr).css('ul#g-items li').each do |li|
|
86
|
+
aln = li.css('.a-link-normal')
|
87
|
+
attrs_hash = { title: aln.attribute('title').value, href: aln.attribute('href').value }
|
88
|
+
item_attrs << attrs_hash
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
92
|
+
|
83
93
|
end
|
@@ -12,6 +12,19 @@ class AmazonWishList
|
|
12
12
|
@wishes = wishes
|
13
13
|
end
|
14
14
|
|
15
|
+
# the method below only sends one request, so it less likely to be identified as being used by a scraper
|
16
|
+
def self.wishlist_attributes(amazon_list_id, reveal = :all, sort = :date_added, tld = 'com')
|
17
|
+
raise "invalid reveal" unless REVEAL_OPTIONS.include?(reveal)
|
18
|
+
raise "invalid sort" unless SORT_OPTIONS[sort]
|
19
|
+
|
20
|
+
query_params = {reveal: reveal.to_s, sort_string: SORT_OPTIONS[sort]}
|
21
|
+
# lek is nil for the first page
|
22
|
+
url_without_qstring = "http://www.amazon.#{tld}/hz/wishlist/ls/#{amazon_list_id}"
|
23
|
+
|
24
|
+
pages = self.get_all_wishlist_pages(url_without_qstring, query_params)
|
25
|
+
AmazonWish.attributes_from_responses(pages)
|
26
|
+
end
|
27
|
+
|
15
28
|
# TODO: https://www.amazon.com/hz/wishlist/ls/2WHUDN1UIDVUT/ref=cm_sw_r_cp_ep_ws_8xNVBb731TTMS,
|
16
29
|
#=> https://www.amazon.com/gp/registry/wishlist/2WHUDN1UIDVUT/ref=cm_sw_r_cp_ep_ws_8xNVBb731TTMS,
|
17
30
|
#=> and https://www.amazon.com/registry/wishlist/2WHUDN1UIDVUT/ref=cm_sw_r_cp_ep_ws_8xNVBb731TTMS
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: amazon_wish_miner
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Alexander V. Trujillo
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2018-
|
11
|
+
date: 2018-11-12 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rest-client
|
@@ -38,7 +38,7 @@ dependencies:
|
|
38
38
|
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '1.8'
|
41
|
-
description:
|
41
|
+
description: Loosely modeled after Amazon Wish Lister http://doitlikejustin.github.io/amazon-wish-lister/
|
42
42
|
email:
|
43
43
|
executables: []
|
44
44
|
extensions: []
|