outrider 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.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/.ruby-version +1 -0
- data/.travis.yml +3 -0
- data/Capfile +30 -0
- data/Gemfile +20 -0
- data/Gemfile.lock +119 -0
- data/LICENSE.txt +21 -0
- data/README.md +261 -0
- data/Rakefile +52 -0
- data/app/run.rb +15 -0
- data/bin/console +14 -0
- data/bin/outrider +8 -0
- data/bin/setup +7 -0
- data/config.ru +2 -0
- data/config/messages.yml +1 -0
- data/config/schema.sql +40 -0
- data/lib/ignite.rb +8 -0
- data/lib/outrider.rb +94 -0
- data/lib/outrider/commandify.rb +49 -0
- data/lib/outrider/engine.rb +20 -0
- data/lib/outrider/intel.rb +14 -0
- data/lib/outrider/project.rb +146 -0
- data/lib/outrider/tools.rb +224 -0
- data/lib/outrider/version.rb +3 -0
- data/outrider.gemspec +27 -0
- data/projects/nz_herald/auxiliary.rb +56 -0
- data/projects/stuff/auxiliary.rb +71 -0
- data/projects/test_project/auxiliary.rb +63 -0
- data/projects/theage/auxiliary.rb +29 -0
- data/public/index.html +0 -0
- data/tmp/x.txt +1 -0
- metadata +122 -0
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
class Theage < Project
|
|
2
|
+
def initialize
|
|
3
|
+
project_name :theage
|
|
4
|
+
end
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
def crawl options
|
|
8
|
+
p OutriderTools::Crawl::site( @config, ->(page, uri){
|
|
9
|
+
|
|
10
|
+
unless( page.css('.cN-headingPage').text.strip.empty? )
|
|
11
|
+
clean_date = DateTime.strptime(page.css('.dtstamp time').text.strip, '%B %d, %Y').to_s #Tue Mar 03 08:27:23 UTC 2015
|
|
12
|
+
return {
|
|
13
|
+
:title_raw => page.css('h1.cN-headingPage').text.strip,
|
|
14
|
+
:author => page.css('.authorName a').text.strip,
|
|
15
|
+
:content_raw => page.css('.articleBody p').map{ |paragraph| paragraph.text.strip }.to_json,
|
|
16
|
+
:date_published_raw => page.css('.dtstamp time').text.strip,
|
|
17
|
+
:date_published_timestamp => clean_date,
|
|
18
|
+
:status => 'scraped'
|
|
19
|
+
}
|
|
20
|
+
else
|
|
21
|
+
return {
|
|
22
|
+
:status => 'rejected'
|
|
23
|
+
}
|
|
24
|
+
end
|
|
25
|
+
})
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
end
|
data/public/index.html
ADDED
|
File without changes
|
data/tmp/x.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
|
metadata
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: outrider
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.1
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Jaap Badlands
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2015-05-06 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: bundler
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - ~>
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '1.9'
|
|
20
|
+
type: :development
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - ~>
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '1.9'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: rspec
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - '>='
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '0'
|
|
34
|
+
type: :development
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - '>='
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '0'
|
|
41
|
+
- !ruby/object:Gem::Dependency
|
|
42
|
+
name: rake
|
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
|
44
|
+
requirements:
|
|
45
|
+
- - ~>
|
|
46
|
+
- !ruby/object:Gem::Version
|
|
47
|
+
version: '10.0'
|
|
48
|
+
type: :development
|
|
49
|
+
prerelease: false
|
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
51
|
+
requirements:
|
|
52
|
+
- - ~>
|
|
53
|
+
- !ruby/object:Gem::Version
|
|
54
|
+
version: '10.0'
|
|
55
|
+
description: 'Outrider''s purpose is to provide an easy-to-use programming interface
|
|
56
|
+
and organisational structure, to create and run tasks that can automatically visit,
|
|
57
|
+
interact with and test websites and also that process, clean and store data, and
|
|
58
|
+
tools for statistical analysis. '
|
|
59
|
+
email:
|
|
60
|
+
- jaap@deadlysyntax.com
|
|
61
|
+
executables:
|
|
62
|
+
- outrider
|
|
63
|
+
extensions: []
|
|
64
|
+
extra_rdoc_files: []
|
|
65
|
+
files:
|
|
66
|
+
- .gitignore
|
|
67
|
+
- .rspec
|
|
68
|
+
- .ruby-version
|
|
69
|
+
- .travis.yml
|
|
70
|
+
- Capfile
|
|
71
|
+
- Gemfile
|
|
72
|
+
- Gemfile.lock
|
|
73
|
+
- LICENSE.txt
|
|
74
|
+
- README.md
|
|
75
|
+
- Rakefile
|
|
76
|
+
- app/run.rb
|
|
77
|
+
- bin/console
|
|
78
|
+
- bin/outrider
|
|
79
|
+
- bin/setup
|
|
80
|
+
- config.ru
|
|
81
|
+
- config/messages.yml
|
|
82
|
+
- config/schema.sql
|
|
83
|
+
- lib/ignite.rb
|
|
84
|
+
- lib/outrider.rb
|
|
85
|
+
- lib/outrider/commandify.rb
|
|
86
|
+
- lib/outrider/engine.rb
|
|
87
|
+
- lib/outrider/intel.rb
|
|
88
|
+
- lib/outrider/project.rb
|
|
89
|
+
- lib/outrider/tools.rb
|
|
90
|
+
- lib/outrider/version.rb
|
|
91
|
+
- outrider.gemspec
|
|
92
|
+
- projects/nz_herald/auxiliary.rb
|
|
93
|
+
- projects/stuff/auxiliary.rb
|
|
94
|
+
- projects/test_project/auxiliary.rb
|
|
95
|
+
- projects/theage/auxiliary.rb
|
|
96
|
+
- public/index.html
|
|
97
|
+
- tmp/x.txt
|
|
98
|
+
homepage: https://github.com/deadlysyntax/outrider
|
|
99
|
+
licenses: []
|
|
100
|
+
metadata: {}
|
|
101
|
+
post_install_message:
|
|
102
|
+
rdoc_options: []
|
|
103
|
+
require_paths:
|
|
104
|
+
- lib
|
|
105
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
106
|
+
requirements:
|
|
107
|
+
- - '>='
|
|
108
|
+
- !ruby/object:Gem::Version
|
|
109
|
+
version: '0'
|
|
110
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
111
|
+
requirements:
|
|
112
|
+
- - '>='
|
|
113
|
+
- !ruby/object:Gem::Version
|
|
114
|
+
version: '0'
|
|
115
|
+
requirements: []
|
|
116
|
+
rubyforge_project:
|
|
117
|
+
rubygems_version: 2.0.14
|
|
118
|
+
signing_key:
|
|
119
|
+
specification_version: 4
|
|
120
|
+
summary: Outrider Web Automation Framework provides structure and tools for writing
|
|
121
|
+
web-automation tasks
|
|
122
|
+
test_files: []
|