getter_cyndi5 0.0.2 → 0.0.7
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/bin/getter_cyndi5 +7 -1
- data/lib/getter_cyndi5.rb +10 -3
- data/lib/getter_cyndi5/parser.rb +7 -2
- data/lib/getter_cyndi5/product.rb +10 -0
- data/lib/getter_cyndi5/retriever.rb +2 -0
- metadata +60 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: f375f528599295fb8680b981577d5f4696a4f0a82dc6cd98c0e8e71c38adb900
|
4
|
+
data.tar.gz: 1e68edbf8781aa1d1ee17318d4a5cfb074cd4dc0b4b7fef78d5b8802ad15e37a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 3bed2a5ed995bafaaa11a157dd9c19888ae5ed6989ddbbe0bf10200e2b3cfb520717f176238c2299ae3ca8ff0fe4455c258f5b671c3b23bcd11ff1ade050e7e8
|
7
|
+
data.tar.gz: cf5821fea29ee00a65031413a62affa6f3fea672580b5a8c81c905f4fc9fc1f10ab2e54ea33cc95fa6f8eafc8b04d13bb42f7c09de38ced5c08fa2dbb899c21d
|
data/bin/getter_cyndi5
CHANGED
@@ -1,4 +1,10 @@
|
|
1
1
|
#!/usr/bin/env ruby
|
2
2
|
|
3
3
|
require 'getter_cyndi5'
|
4
|
-
|
4
|
+
base_url = ARGV[0] || 'https://thehappyco.com'
|
5
|
+
products_page_path = ARGV[1] || '/kelly/products'
|
6
|
+
item_row_selector = ARGV[2] || '.item-row'
|
7
|
+
item_anchor_selector = ARGV[3] || 'div > div.product-desc.text-center > div.product-title > h3 > a'
|
8
|
+
mode = (ARGV[4] || '2').to_i
|
9
|
+
filename = ARGV[5] || './tmp/document1.html'
|
10
|
+
GetterCyndi5.go(base_url, products_page_path, item_row_selector, item_anchor_selector, mode, filename)
|
data/lib/getter_cyndi5.rb
CHANGED
@@ -3,7 +3,7 @@ class GetterCyndi5
|
|
3
3
|
# Getter
|
4
4
|
#
|
5
5
|
# Example:
|
6
|
-
# >> GetterCyndi5.go(base_url = 'https://thehappyco.com', products_page_path = '/kelly/products', item_row_selector = '.item-row', item_anchor_selector = 'div > div.product-desc.text-center > div.product-title > h3 > a', mode =
|
6
|
+
# >> GetterCyndi5.go(base_url = 'https://thehappyco.com', products_page_path = '/kelly/products', item_row_selector = '.item-row', item_anchor_selector = 'div > div.product-desc.text-center > div.product-title > h3 > a', mode = 2, './tmp/document1.html')
|
7
7
|
# Arguments:
|
8
8
|
# base_url: (String)
|
9
9
|
# products_page_path: (String)
|
@@ -12,11 +12,18 @@ class GetterCyndi5
|
|
12
12
|
# mode: (Integer) 0 = retrieve and parse without saving HTML document to file, 1 = retrieve and parse saving HTML document to file, 2 = load and parse HTML document from file
|
13
13
|
# filename: (String)
|
14
14
|
|
15
|
-
def self.go(base_url
|
15
|
+
def self.go(base_url, products_page_path, item_row_selector, item_anchor_selector, mode, filename)
|
16
|
+
all_products = products(base_url, products_page_path, item_row_selector, item_anchor_selector, mode, filename)
|
17
|
+
all_products.each do |product|
|
18
|
+
puts "#{product.name} :-: #{product.url}"
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
def self.products(base_url, products_page_path, item_row_selector, item_anchor_selector, mode, filename)
|
16
23
|
retriever = Retriever.new(base_url, products_page_path, item_row_selector, mode, filename)
|
17
24
|
retriever.retrieve
|
18
25
|
parser = Parser.new(retriever.document, base_url, item_row_selector, item_anchor_selector)
|
19
|
-
parser.parse
|
26
|
+
products = parser.parse
|
20
27
|
end
|
21
28
|
end
|
22
29
|
|
data/lib/getter_cyndi5/parser.rb
CHANGED
@@ -1,9 +1,12 @@
|
|
1
|
+
require 'getter_cyndi5/product'
|
1
2
|
class GetterCyndi5::Parser
|
3
|
+
attr_reader :products
|
2
4
|
def initialize(document, base_url, item_row_selector, item_anchor_selector)
|
3
5
|
@document = document
|
4
6
|
@base_url = base_url
|
5
7
|
@item_row_selector = item_row_selector
|
6
8
|
@item_anchor_selector = item_anchor_selector
|
9
|
+
@products = []
|
7
10
|
end
|
8
11
|
|
9
12
|
def parse
|
@@ -12,7 +15,9 @@ class GetterCyndi5::Parser
|
|
12
15
|
product_element = item_row.css(@item_anchor_selector)[0]
|
13
16
|
product_name = product_element.text
|
14
17
|
product_url = "#{@base_url}#{product_element.attributes['href']}"
|
15
|
-
|
18
|
+
product = GetterCyndi5::Product.new(product_name, product_url)
|
19
|
+
products.append(product)
|
16
20
|
end
|
21
|
+
products
|
17
22
|
end
|
18
|
-
end
|
23
|
+
end
|
@@ -21,9 +21,11 @@ class GetterCyndi5::Retriever
|
|
21
21
|
end
|
22
22
|
if @mode == 1
|
23
23
|
File.write(@filename, browser.html)
|
24
|
+
browser.close
|
24
25
|
end
|
25
26
|
if @mode == 0
|
26
27
|
@document = Nokogiri::HTML(browser.html)
|
28
|
+
browser.close
|
27
29
|
end
|
28
30
|
if @mode == 1 || @mode == 2
|
29
31
|
@document = File.open(@filename) { |f| Nokogiri::HTML(f) }
|
metadata
CHANGED
@@ -1,15 +1,71 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: getter_cyndi5
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Cyndi Cavanaugh
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2021-03-
|
12
|
-
dependencies:
|
11
|
+
date: 2021-03-12 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: httparty
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.18.1
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.18.1
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: nokogiri
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 1.11.1
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 1.11.1
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: watir
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: 6.18.0
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 6.18.0
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: webdrivers
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 4.6.0
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 4.6.0
|
13
69
|
description: A simple getter cyndi5 gem
|
14
70
|
email: cynthiacavanaugh1@gmail.com
|
15
71
|
executables:
|
@@ -20,6 +76,7 @@ files:
|
|
20
76
|
- bin/getter_cyndi5
|
21
77
|
- lib/getter_cyndi5.rb
|
22
78
|
- lib/getter_cyndi5/parser.rb
|
79
|
+
- lib/getter_cyndi5/product.rb
|
23
80
|
- lib/getter_cyndi5/retriever.rb
|
24
81
|
homepage: https://cyndicavanaugh.com
|
25
82
|
licenses:
|