html2record 0.0.1

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.
Files changed (11) hide show
  1. data/MIT-LICENSE +20 -0
  2. data/README.rdoc +67 -0
  3. data/Rakefile +38 -0
  4. data/lib/generators/parser_generator.rb +7 -0
  5. data/lib/generators/templates/parser.rb +9 -0
  6. data/lib/html2record.rb +17 -0
  7. data/lib/html2record/orm/activerecord.rb +27 -0
  8. data/lib/html2record/parser.rb +19 -0
  9. data/lib/html2record/version.rb +3 -0
  10. data/lib/tasks/html2record_tasks.rake +4 -0
  11. metadata +119 -0
data/MIT-LICENSE ADDED
@@ -0,0 +1,20 @@
1
+ Copyright 2012 YOURNAME
2
+
3
+ Permission is hereby granted, free of charge, to any person obtaining
4
+ a copy of this software and associated documentation files (the
5
+ "Software"), to deal in the Software without restriction, including
6
+ without limitation the rights to use, copy, modify, merge, publish,
7
+ distribute, sublicense, and/or sell copies of the Software, and to
8
+ permit persons to whom the Software is furnished to do so, subject to
9
+ the following conditions:
10
+
11
+ The above copyright notice and this permission notice shall be
12
+ included in all copies or substantial portions of the Software.
13
+
14
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
15
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
16
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
17
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
18
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
19
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
20
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
data/README.rdoc ADDED
@@ -0,0 +1,67 @@
1
+ # Html2record
2
+
3
+ This gem provide a simple way that bind html specific element to a record column
4
+
5
+ ## Installation
6
+
7
+ In Gemfile add follow line:
8
+
9
+ ```ruby
10
+ gem 'html2record'
11
+ ```
12
+
13
+ ## Get Start
14
+
15
+ init parser file
16
+ ```
17
+ rails g parser Taobao
18
+ ```
19
+
20
+ this command will generate a parser into folder app/parsers/
21
+
22
+ ```ruby
23
+ class TaobaoParser < Html2record::Parser::Base
24
+ end
25
+ ```
26
+
27
+ you can add column binding in class
28
+
29
+ ```ruby
30
+ class TaobaoParser < Html2record::Parser::Base
31
+ add :title, '#main .title'
32
+ end
33
+ ```
34
+
35
+ In model file include the class
36
+
37
+ ```ruby
38
+ include Html2record::ActiveRecord
39
+ ```
40
+
41
+ Use the model:
42
+
43
+ ```ruby
44
+ html =<<-page
45
+ <html>
46
+ <body>
47
+ <div id="main">
48
+ <div><span class="title">hello</span></div>
49
+ <div><span class="content">world</span></div>
50
+ </div>
51
+ <body>
52
+ </html>
53
+ page
54
+
55
+ good = Good.new
56
+ good.apply_html(Taobao,html) # good.title should be 'hello'
57
+ ```
58
+
59
+
60
+
61
+
62
+
63
+
64
+
65
+
66
+
67
+ This project rocks and uses MIT-LICENSE.
data/Rakefile ADDED
@@ -0,0 +1,38 @@
1
+ #!/usr/bin/env rake
2
+ begin
3
+ require 'bundler/setup'
4
+ rescue LoadError
5
+ puts 'You must `gem install bundler` and `bundle install` to run rake tasks'
6
+ end
7
+ begin
8
+ require 'rdoc/task'
9
+ rescue LoadError
10
+ require 'rdoc/rdoc'
11
+ require 'rake/rdoctask'
12
+ RDoc::Task = Rake::RDocTask
13
+ end
14
+
15
+ RDoc::Task.new(:rdoc) do |rdoc|
16
+ rdoc.rdoc_dir = 'rdoc'
17
+ rdoc.title = 'Html2record'
18
+ rdoc.options << '--line-numbers'
19
+ rdoc.rdoc_files.include('README.rdoc')
20
+ rdoc.rdoc_files.include('lib/**/*.rb')
21
+ end
22
+
23
+
24
+
25
+
26
+ Bundler::GemHelper.install_tasks
27
+
28
+ require 'rake/testtask'
29
+
30
+ Rake::TestTask.new(:test) do |t|
31
+ t.libs << 'lib'
32
+ t.libs << 'test'
33
+ t.pattern = 'test/**/*_test.rb'
34
+ t.verbose = false
35
+ end
36
+
37
+
38
+ task :default => :test
data/lib/generators/parser_generator.rb ADDED
@@ -0,0 +1,7 @@
1
+ class ParserGenerator < Rails::Generators::NamedBase
2
+ source_root File.expand_path("../templates", __FILE__)
3
+
4
+ def create_parser_file
5
+ template "parser.rb", "app/parsers/#{file_name}_parser.rb"
6
+ end
7
+ end
data/lib/generators/templates/parser.rb ADDED
@@ -0,0 +1,9 @@
1
+ class <%= class_name %>Parser < Html2record::Parser::Base
2
+ # add :title,'#main .title'
3
+ # add :content, '#main .content'
4
+ #
5
+ # you can customize by yourself
6
+ # add :title, '#main' do |doc|
7
+ # doc.css('.title').first
8
+ # end
9
+ end
data/lib/html2record.rb ADDED
@@ -0,0 +1,17 @@
1
+ module Html2record
2
+ autoload :ActiveRecord, 'html2record/orm/activerecord'
3
+ autoload :Parser,'html2record/parser'
4
+ end
5
+
6
+ if defined?(Rails)
7
+ module Html2record
8
+ class Railtie < Rails::Railtie
9
+ initializer "html2record.record" do
10
+ ActiveSupport.on_load :action_controller do
11
+
12
+ end
13
+ end
14
+ end
15
+ end
16
+
17
+ end
data/lib/html2record/orm/activerecord.rb ADDED
@@ -0,0 +1,27 @@
1
+ # encoding: utf-8
2
+ require 'active_record'
3
+ require 'nokogiri'
4
+
5
+ module Html2record
6
+ module ActiveRecord
7
+ def apply_html(paser_class,html,&block)
8
+ doc = Nokogiri::HTML.parse(html)
9
+ paser_class.parsers.each do |x|
10
+ column = x[:column]
11
+ selector = x[:selector]
12
+ xblock = x[:block]
13
+ content= ''
14
+
15
+ element = doc.css(selector)
16
+ if xblock.nil?
17
+ element = element.first if element.kind_of?(Array)
18
+ content = element.text
19
+ else
20
+ content = xblock.call(element)
21
+ end
22
+ write_attribute(column,content)
23
+ end
24
+ end
25
+ end
26
+ end
27
+
data/lib/html2record/parser.rb ADDED
@@ -0,0 +1,19 @@
1
+ #encoding: utf-8
2
+
3
+ module Html2record
4
+ module Parser
5
+ class Base
6
+ attr_accessor :uri
7
+
8
+ class << self
9
+ attr_accessor :parsers
10
+ def add(column,selector,&block)
11
+ @parsers ||= Array.new
12
+ @parsers << {:column=>column,:selector=>selector, :block=>block}
13
+ end
14
+ end
15
+
16
+ end
17
+ end
18
+ end
19
+
data/lib/html2record/version.rb ADDED
@@ -0,0 +1,3 @@
1
+ module Html2record
2
+ VERSION = "0.0.1"
3
+ end
data/lib/tasks/html2record_tasks.rake ADDED
@@ -0,0 +1,4 @@
1
+ # desc "Explaining what the task does"
2
+ #task :html2record do
3
+ # Task goes here
4
+ #end
metadata ADDED
@@ -0,0 +1,119 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: html2record
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ prerelease:
6
+ platform: ruby
7
+ authors:
8
+ - Jonny Zheng
9
+ autorequire:
10
+ bindir: bin
11
+ cert_chain: []
12
+ date: 2012-08-24 00:00:00.000000000 Z
13
+ dependencies:
14
+ - !ruby/object:Gem::Dependency
15
+ name: rails
16
+ requirement: !ruby/object:Gem::Requirement
17
+ none: false
18
+ requirements:
19
+ - - ~>
20
+ - !ruby/object:Gem::Version
21
+ version: 3.2.0
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: 3.2.0
30
+ - !ruby/object:Gem::Dependency
31
+ name: nokogiri
32
+ requirement: !ruby/object:Gem::Requirement
33
+ none: false
34
+ requirements:
35
+ - - ! '>='
36
+ - !ruby/object:Gem::Version
37
+ version: '0'
38
+ type: :runtime
39
+ prerelease: false
40
+ version_requirements: !ruby/object:Gem::Requirement
41
+ none: false
42
+ requirements:
43
+ - - ! '>='
44
+ - !ruby/object:Gem::Version
45
+ version: '0'
46
+ - !ruby/object:Gem::Dependency
47
+ name: mysql2
48
+ requirement: !ruby/object:Gem::Requirement
49
+ none: false
50
+ requirements:
51
+ - - ! '>='
52
+ - !ruby/object:Gem::Version
53
+ version: '0'
54
+ type: :development
55
+ prerelease: false
56
+ version_requirements: !ruby/object:Gem::Requirement
57
+ none: false
58
+ requirements:
59
+ - - ! '>='
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ - !ruby/object:Gem::Dependency
63
+ name: rspec
64
+ requirement: !ruby/object:Gem::Requirement
65
+ none: false
66
+ requirements:
67
+ - - ~>
68
+ - !ruby/object:Gem::Version
69
+ version: '2.0'
70
+ type: :development
71
+ prerelease: false
72
+ version_requirements: !ruby/object:Gem::Requirement
73
+ none: false
74
+ requirements:
75
+ - - ~>
76
+ - !ruby/object:Gem::Version
77
+ version: '2.0'
78
+ description: ! 'convert html into activerecord '
79
+ email:
80
+ - mars131@gmail.com
81
+ executables: []
82
+ extensions: []
83
+ extra_rdoc_files: []
84
+ files:
85
+ - lib/generators/parser_generator.rb
86
+ - lib/generators/templates/parser.rb
87
+ - lib/html2record/orm/activerecord.rb
88
+ - lib/html2record/parser.rb
89
+ - lib/html2record/version.rb
90
+ - lib/html2record.rb
91
+ - lib/tasks/html2record_tasks.rake
92
+ - MIT-LICENSE
93
+ - Rakefile
94
+ - README.rdoc
95
+ homepage: https://github.com/jonnyzheng/html2record
96
+ licenses: []
97
+ post_install_message:
98
+ rdoc_options: []
99
+ require_paths:
100
+ - lib
101
+ required_ruby_version: !ruby/object:Gem::Requirement
102
+ none: false
103
+ requirements:
104
+ - - ! '>='
105
+ - !ruby/object:Gem::Version
106
+ version: '0'
107
+ required_rubygems_version: !ruby/object:Gem::Requirement
108
+ none: false
109
+ requirements:
110
+ - - ! '>='
111
+ - !ruby/object:Gem::Version
112
+ version: '0'
113
+ requirements: []
114
+ rubyforge_project:
115
+ rubygems_version: 1.8.24
116
+ signing_key:
117
+ specification_version: 3
118
+ summary: convert html into activerecord
119
+ test_files: []