site_prism-tableish 0.0.1 → 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +87 -4
- data/lib/site_prism/tableish.rb +10 -1
- data/lib/site_prism/tableish/definition.rb +15 -0
- data/lib/site_prism/tableish/element.rb +26 -0
- data/lib/site_prism/tableish/version.rb +1 -1
- data/site_prism-tableish.gemspec +2 -0
- metadata +32 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 43956014fa7ce3841366f6ca476c2a2307d53305
|
4
|
+
data.tar.gz: 5a8b7bedc3684cb5ec3e0b5ca14eb2c316f3002e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 83c8b02cf5d011938f6bf53f874af550c9e04cbeae4d894d9b4f2bf1bc2eb1a97fc09ac5441c2567f2083cb53d0bfedbb73e1773bbfacef26fd34c36135d43f6
|
7
|
+
data.tar.gz: d7f09ddc9899f7357627670e76cc76042b7cd9844480b2e13f85b1830d8ba54c5ecbfa743802bd4f6412a3c8810f165641d48bbebe6be234e13bfa92921c0824
|
data/README.md
CHANGED
@@ -1,8 +1,9 @@
|
|
1
1
|
# SitePrism::Tableish
|
2
2
|
|
3
|
-
|
3
|
+
SitePrism::Tableish extends [SitePrism](https://github.com/natritmeyer/site_prism)
|
4
|
+
making it easer and faster to parse `<table>` elements.
|
4
5
|
|
5
|
-
|
6
|
+
Inspied by [SitePrism::Table](https://github.com/investtools/site_prism-table)
|
6
7
|
|
7
8
|
## Installation
|
8
9
|
|
@@ -22,7 +23,85 @@ Or install it yourself as:
|
|
22
23
|
|
23
24
|
## Usage
|
24
25
|
|
25
|
-
|
26
|
+
Example:
|
27
|
+
|
28
|
+
```ruby
|
29
|
+
require 'site_prism'
|
30
|
+
require 'capybara/dsl'
|
31
|
+
require 'site_prism/tableish'
|
32
|
+
require 'selenium-webdriver'
|
33
|
+
require 'pp'
|
34
|
+
|
35
|
+
Capybara.default_driver = :selenium
|
36
|
+
|
37
|
+
class W3SchoolsTablesPage < SitePrism::Page
|
38
|
+
extend SitePrism::Tableish
|
39
|
+
set_url 'http://www.w3schools.com/html/html_tables.asp'
|
40
|
+
table :customers, '#customers' do
|
41
|
+
column :company
|
42
|
+
column :contact
|
43
|
+
column :country
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
page = W3SchoolsTablesPage.new
|
48
|
+
page.load
|
49
|
+
pp page.customers.rows
|
50
|
+
|
51
|
+
# [{:company=>
|
52
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[2]/td[1]">,
|
53
|
+
# :contact=>
|
54
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[2]/td[2]">,
|
55
|
+
# :country=>
|
56
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[2]/td[3]">},
|
57
|
+
# {:company=>
|
58
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[3]/td[1]">,
|
59
|
+
# :contact=>
|
60
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[3]/td[2]">,
|
61
|
+
# :country=>
|
62
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[3]/td[3]">},
|
63
|
+
# {:company=>
|
64
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[4]/td[1]">,
|
65
|
+
# :contact=>
|
66
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[4]/td[2]">,
|
67
|
+
# :country=>
|
68
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[4]/td[3]">},
|
69
|
+
# {:company=>
|
70
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[5]/td[1]">,
|
71
|
+
# :contact=>
|
72
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[5]/td[2]">,
|
73
|
+
# :country=>
|
74
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[5]/td[3]">},
|
75
|
+
# {:company=>
|
76
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[6]/td[1]">,
|
77
|
+
# :contact=>
|
78
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[6]/td[2]">,
|
79
|
+
# :country=>
|
80
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[6]/td[3]">},
|
81
|
+
# {:company=>
|
82
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[7]/td[1]">,
|
83
|
+
# :contact=>
|
84
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[7]/td[2]">,
|
85
|
+
# :country=>
|
86
|
+
# #<Capybara::Node::Element tag="td" path="/html/body/div[6]/div[1]/div[1]/div[3]/div/table/tbody/tr[7]/td[3]">}]
|
87
|
+
|
88
|
+
pp page.customers.rows.map{|row| row.map{|k, v| [k, v.text.strip]}.to_h }
|
89
|
+
|
90
|
+
# [{:company=>"Alfreds Futterkiste",
|
91
|
+
# :contact=>"MARIA ANDERS",
|
92
|
+
# :country=>"Germany"},
|
93
|
+
# {:company=>"Centro comercial Moctezuma",
|
94
|
+
# :contact=>"FRANCISCO CHANG",
|
95
|
+
# :country=>"Mexico"},
|
96
|
+
# {:company=>"Ernst Handel", :contact=>"ROLAND MENDEL", :country=>"Austria"},
|
97
|
+
# {:company=>"Island Trading", :contact=>"HELEN BENNETT", :country=>"UK"},
|
98
|
+
# {:company=>"Laughing Bacchus Winecellars",
|
99
|
+
# :contact=>"YOSHI TANNAMURI",
|
100
|
+
# :country=>"Canada"},
|
101
|
+
# {:company=>"Magazzini Alimentari Riuniti",
|
102
|
+
# :contact=>"GIOVANNI ROVELLI",
|
103
|
+
# :country=>"Italy"}]
|
104
|
+
```
|
26
105
|
|
27
106
|
## Development
|
28
107
|
|
@@ -32,5 +111,9 @@ To install this gem onto your local machine, run `bundle exec rake install`. To
|
|
32
111
|
|
33
112
|
## Contributing
|
34
113
|
|
35
|
-
Bug reports and pull requests are welcome on GitHub at https://github.com/
|
114
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/fkshom/site_prism-tableish. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
115
|
+
|
116
|
+
|
117
|
+
## License
|
36
118
|
|
119
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/lib/site_prism/tableish.rb
CHANGED
@@ -2,6 +2,15 @@ require "site_prism/tableish/version"
|
|
2
2
|
|
3
3
|
module SitePrism
|
4
4
|
module Tableish
|
5
|
-
|
5
|
+
|
6
|
+
autoload :Element, 'site_prism/tableish/element'
|
7
|
+
autoload :Definition, 'site_prism/tableish/definition'
|
8
|
+
|
9
|
+
def table(table_name, *args, &block)
|
10
|
+
definition = Definition.new(&block)
|
11
|
+
define_method table_name do |*runtime_args, &element_block|
|
12
|
+
Element.new(page.find(*args), definition)
|
13
|
+
end
|
14
|
+
end
|
6
15
|
end
|
7
16
|
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
module SitePrism
|
2
|
+
module Tableish
|
3
|
+
class Element
|
4
|
+
include Capybara::DSL
|
5
|
+
def initialize(root_element, definition)
|
6
|
+
@root_element = root_element
|
7
|
+
@definition = definition
|
8
|
+
end
|
9
|
+
|
10
|
+
def rows
|
11
|
+
[].tap do |result|
|
12
|
+
Capybara.within(@root_element){
|
13
|
+
all(:xpath, ".//tbody/tr | .//body/tr").each do |row_in|
|
14
|
+
row_out = {}
|
15
|
+
row_in.all(:xpath, "td").each_with_index do |cell, i|
|
16
|
+
name, options = @definition.columns[i]
|
17
|
+
row_out[name] = cell
|
18
|
+
end
|
19
|
+
result << row_out unless row_out.empty?
|
20
|
+
end
|
21
|
+
}
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
data/site_prism-tableish.gemspec
CHANGED
@@ -24,4 +24,6 @@ Gem::Specification.new do |spec|
|
|
24
24
|
spec.add_development_dependency "bundler", "~> 1.14"
|
25
25
|
spec.add_development_dependency "rake", "~> 10.0"
|
26
26
|
spec.add_development_dependency "rspec", "~> 3.0"
|
27
|
+
spec.add_development_dependency "selenium-webdriver"
|
28
|
+
spec.add_dependency "site_prism"
|
27
29
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: site_prism-tableish
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0
|
4
|
+
version: 0.1.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Shoma FUKUDA
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-05-
|
11
|
+
date: 2017-05-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -52,6 +52,34 @@ dependencies:
|
|
52
52
|
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: selenium-webdriver
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: site_prism
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
55
83
|
description: Table scraping for SitePrism
|
56
84
|
email:
|
57
85
|
- fkshom@gmail.com
|
@@ -68,6 +96,8 @@ files:
|
|
68
96
|
- bin/console
|
69
97
|
- bin/setup
|
70
98
|
- lib/site_prism/tableish.rb
|
99
|
+
- lib/site_prism/tableish/definition.rb
|
100
|
+
- lib/site_prism/tableish/element.rb
|
71
101
|
- lib/site_prism/tableish/version.rb
|
72
102
|
- site_prism-tableish.gemspec
|
73
103
|
homepage: https://github.com/fkshom/site_prism-tableish
|