getter_cyndi5 0.0.0
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 +7 -0
- data/bin/getter_cyndi5 +4 -0
- data/lib/getter_cyndi5.rb +24 -0
- data/lib/getter_cyndi5/parser.rb +19 -0
- data/lib/getter_cyndi5/retriever.rb +36 -0
- metadata +47 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 0261a7cc5ac7b72633634fc3ebb15ebe8d813dc3eda78406badb343f57bd19f2
|
4
|
+
data.tar.gz: ec5d527e1bcc161e20b6707648b38db740655869eb99c061661b5836f9037921
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 2620c48d2a9da1693d4bfb16635f108e42fda8558431b1b395273809359ed87696543d052fa652715775fa992b369d374f94f5cbefcba9ee0e0ebeb6f7920598
|
7
|
+
data.tar.gz: e01621b25e31263a700885fa58659ab61dc36ddbf71a8b003786a72e657748c588efa65c00c1201516acc67ec02beb32c538769f4f956d0478e5470f15fe04e9
|
data/bin/getter_cyndi5
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
# The main GetterCyndi5 driver
|
2
|
+
class GetterCyndi5
|
3
|
+
# Getter
|
4
|
+
#
|
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 = 0, './tmp/document.html')
|
7
|
+
# Arguments:
|
8
|
+
# base_url: (String)
|
9
|
+
# products_page_path: (String)
|
10
|
+
# item_row_selector: (String)
|
11
|
+
# item_anchor_selector: (String)
|
12
|
+
# mode: (Integer)
|
13
|
+
# filename: (String)
|
14
|
+
|
15
|
+
def self.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 = 1, filename = './tmp/document.html')
|
16
|
+
retriever = Retriever.new(base_url, products_page_path, item_row_selector, mode, filename)
|
17
|
+
retriever.retrieve
|
18
|
+
parser = Parser.new(retriever.document, base_url, item_row_selector, item_anchor_selector)
|
19
|
+
parser.parse
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
require 'getter_cyndi5/retriever'
|
24
|
+
require 'getter_cyndi5/parser'
|
@@ -0,0 +1,19 @@
|
|
1
|
+
class GetterCyndi5::Parser
|
2
|
+
def initialize(document, base_url, item_row_selector, item_anchor_selector)
|
3
|
+
@document = document
|
4
|
+
@base_url = base_url
|
5
|
+
@item_row_selector = item_row_selector
|
6
|
+
@item_anchor_selector = item_anchor_selector
|
7
|
+
end
|
8
|
+
|
9
|
+
def parse
|
10
|
+
item_rows = @document.css(@item_row_selector)
|
11
|
+
item_rows.each do |item_row|
|
12
|
+
product_element = item_row.css(@item_anchor_selector)[0]
|
13
|
+
product_name = product_element.text
|
14
|
+
product_url = "#{@base_url}#{product_element.attributes['href']}"
|
15
|
+
puts "#{product_name} #{product_url}"
|
16
|
+
puts "-----"
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
require 'httparty'
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'watir'
|
4
|
+
require 'webdrivers'
|
5
|
+
|
6
|
+
class GetterCyndi5::Retriever
|
7
|
+
def initialize(base_url, products_page_path, item_row_selector, mode, filename)
|
8
|
+
@base_url = base_url
|
9
|
+
@products_page_path = products_page_path
|
10
|
+
@products_page_url = "#{@base_url}#{@products_page_path}"
|
11
|
+
@item_row_selector = item_row_selector
|
12
|
+
@mode = mode
|
13
|
+
@filename = filename
|
14
|
+
end
|
15
|
+
|
16
|
+
def retrieve()
|
17
|
+
if @mode == 0 || @mode == 1
|
18
|
+
browser = Watir::Browser.new
|
19
|
+
browser.goto(@products_page_url)
|
20
|
+
item_row_elements = browser.elements(css: @item_row_selector)
|
21
|
+
end
|
22
|
+
if @mode == 1
|
23
|
+
File.write(@filename, browser.html)
|
24
|
+
end
|
25
|
+
if @mode == 0
|
26
|
+
@document = Nokogiri::HTML(browser.html)
|
27
|
+
end
|
28
|
+
if @mode == 1 || @mode == 2
|
29
|
+
@document = File.open(@filename) { |f| Nokogiri::HTML(f) }
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
def document
|
34
|
+
@document
|
35
|
+
end
|
36
|
+
end
|
metadata
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: getter_cyndi5
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Cyndi Cavanaugh
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2021-03-09 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: A simple getter cyndi5 gem
|
14
|
+
email: cynthiacavanaugh1@gmail.com
|
15
|
+
executables:
|
16
|
+
- getter_cyndi5
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- bin/getter_cyndi5
|
21
|
+
- lib/getter_cyndi5.rb
|
22
|
+
- lib/getter_cyndi5/parser.rb
|
23
|
+
- lib/getter_cyndi5/retriever.rb
|
24
|
+
homepage: https://cyndicavanaugh.com
|
25
|
+
licenses:
|
26
|
+
- MIT
|
27
|
+
metadata: {}
|
28
|
+
post_install_message:
|
29
|
+
rdoc_options: []
|
30
|
+
require_paths:
|
31
|
+
- lib
|
32
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
33
|
+
requirements:
|
34
|
+
- - ">="
|
35
|
+
- !ruby/object:Gem::Version
|
36
|
+
version: '0'
|
37
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - ">="
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '0'
|
42
|
+
requirements: []
|
43
|
+
rubygems_version: 3.1.4
|
44
|
+
signing_key:
|
45
|
+
specification_version: 4
|
46
|
+
summary: getter Cyndi5!
|
47
|
+
test_files: []
|