website_inspector 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +4 -0
- data/.travis.yml +6 -0
- data/Gemfile +5 -0
- data/Gemfile.lock +72 -0
- data/LICENSE.txt +202 -0
- data/README.md +76 -0
- data/README.rdoc +54 -0
- data/Rakefile +11 -0
- data/bin/website_inspector +58 -0
- data/features/step_definitions/website_inspector_steps.rb +1 -0
- data/features/support/env.rb +16 -0
- data/features/website_inspector.feature +58 -0
- data/lib/website_inspector.rb +5 -0
- data/lib/website_inspector/version.rb +3 -0
- data/lib/website_inspector/website.rb +84 -0
- data/website_inspector.gemspec +28 -0
- metadata +163 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 35bddb0b3d1f10a1bfc46df0159896776143071b
|
4
|
+
data.tar.gz: bcaebf0afa0e501aa5284ab4a021d12fdeb0daed
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a02436ec2e237104455aaceb484b32bd76258ba5abc68acd227f31b6c1affbcfbc621d4b09ddb6220516f10316abb80288fc105e5b8e3265edaa48a8792fa92f
|
7
|
+
data.tar.gz: 06e5b72b657b1f8f326b42f7871ed46b2c7a9cbd6a22f3681a3a6b922c4ee970e708dcd73a50ff0bd729d47ad653d330ef0e91681e2c9e47bd1e806120ee5717
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,72 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
website_inspector (0.0.3)
|
5
|
+
methadone (~> 1.3.2)
|
6
|
+
|
7
|
+
GEM
|
8
|
+
remote: https://rubygems.org/
|
9
|
+
specs:
|
10
|
+
aruba (0.5.4)
|
11
|
+
childprocess (>= 0.3.6)
|
12
|
+
cucumber (>= 1.1.1)
|
13
|
+
rspec-expectations (>= 2.7.0)
|
14
|
+
builder (3.2.2)
|
15
|
+
childprocess (0.5.1)
|
16
|
+
ffi (~> 1.0, >= 1.0.11)
|
17
|
+
cucumber (1.3.11)
|
18
|
+
builder (>= 2.1.2)
|
19
|
+
diff-lcs (>= 1.1.3)
|
20
|
+
gherkin (~> 2.12)
|
21
|
+
multi_json (>= 1.7.5, < 2.0)
|
22
|
+
multi_test (>= 0.0.2)
|
23
|
+
diff-lcs (1.2.5)
|
24
|
+
domain_name (0.5.16)
|
25
|
+
unf (>= 0.0.5, < 1.0.0)
|
26
|
+
ffi (1.9.3)
|
27
|
+
gherkin (2.12.2)
|
28
|
+
multi_json (~> 1.3)
|
29
|
+
http-cookie (1.0.2)
|
30
|
+
domain_name (~> 0.5)
|
31
|
+
json (1.8.1)
|
32
|
+
mechanize (2.7.3)
|
33
|
+
domain_name (~> 0.5, >= 0.5.1)
|
34
|
+
http-cookie (~> 1.0)
|
35
|
+
mime-types (~> 2.0)
|
36
|
+
net-http-digest_auth (~> 1.1, >= 1.1.1)
|
37
|
+
net-http-persistent (~> 2.5, >= 2.5.2)
|
38
|
+
nokogiri (~> 1.4)
|
39
|
+
ntlm-http (~> 0.1, >= 0.1.1)
|
40
|
+
webrobots (>= 0.0.9, < 0.2)
|
41
|
+
methadone (1.3.2)
|
42
|
+
bundler
|
43
|
+
mime-types (2.1)
|
44
|
+
mini_portile (0.5.2)
|
45
|
+
multi_json (1.9.0)
|
46
|
+
multi_test (0.0.3)
|
47
|
+
net-http-digest_auth (1.4)
|
48
|
+
net-http-persistent (2.9.4)
|
49
|
+
nokogiri (1.6.1)
|
50
|
+
mini_portile (~> 0.5.0)
|
51
|
+
ntlm-http (0.1.1)
|
52
|
+
rake (10.1.1)
|
53
|
+
rdoc (4.1.1)
|
54
|
+
json (~> 1.4)
|
55
|
+
rspec-expectations (2.14.5)
|
56
|
+
diff-lcs (>= 1.1.3, < 2.0)
|
57
|
+
unf (0.1.3)
|
58
|
+
unf_ext
|
59
|
+
unf_ext (0.0.6)
|
60
|
+
webrobots (0.1.1)
|
61
|
+
|
62
|
+
PLATFORMS
|
63
|
+
ruby
|
64
|
+
|
65
|
+
DEPENDENCIES
|
66
|
+
aruba
|
67
|
+
bundler (~> 1.5)
|
68
|
+
cucumber
|
69
|
+
mechanize (~> 2.7.3)
|
70
|
+
rake
|
71
|
+
rdoc
|
72
|
+
website_inspector!
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,202 @@
|
|
1
|
+
|
2
|
+
Apache License
|
3
|
+
Version 2.0, January 2004
|
4
|
+
http://www.apache.org/licenses/
|
5
|
+
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
7
|
+
|
8
|
+
1. Definitions.
|
9
|
+
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
12
|
+
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
14
|
+
the copyright owner that is granting the License.
|
15
|
+
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
17
|
+
other entities that control, are controlled by, or are under common
|
18
|
+
control with that entity. For the purposes of this definition,
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
20
|
+
direction or management of such entity, whether by contract or
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
23
|
+
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
25
|
+
exercising permissions granted by this License.
|
26
|
+
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
28
|
+
including but not limited to software source code, documentation
|
29
|
+
source, and configuration files.
|
30
|
+
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
32
|
+
transformation or translation of a Source form, including but
|
33
|
+
not limited to compiled object code, generated documentation,
|
34
|
+
and conversions to other media types.
|
35
|
+
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
37
|
+
Object form, made available under the License, as indicated by a
|
38
|
+
copyright notice that is included in or attached to the work
|
39
|
+
(an example is provided in the Appendix below).
|
40
|
+
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
47
|
+
the Work and Derivative Works thereof.
|
48
|
+
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
50
|
+
the original version of the Work and any modifications or additions
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
62
|
+
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
65
|
+
subsequently incorporated within the Work.
|
66
|
+
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
73
|
+
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
79
|
+
where such license applies only to those patent claims licensable
|
80
|
+
by such Contributor that are necessarily infringed by their
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
83
|
+
institute patent litigation against any entity (including a
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
86
|
+
or contributory patent infringement, then any patent licenses
|
87
|
+
granted to You under this License for that Work shall terminate
|
88
|
+
as of the date such litigation is filed.
|
89
|
+
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
92
|
+
modifications, and in Source or Object form, provided that You
|
93
|
+
meet the following conditions:
|
94
|
+
|
95
|
+
(a) You must give any other recipients of the Work or
|
96
|
+
Derivative Works a copy of this License; and
|
97
|
+
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
99
|
+
stating that You changed the files; and
|
100
|
+
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
103
|
+
attribution notices from the Source form of the Work,
|
104
|
+
excluding those notices that do not pertain to any part of
|
105
|
+
the Derivative Works; and
|
106
|
+
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
109
|
+
include a readable copy of the attribution notices contained
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
112
|
+
of the following places: within a NOTICE text file distributed
|
113
|
+
as part of the Derivative Works; within the Source form or
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
115
|
+
within a display generated by the Derivative Works, if and
|
116
|
+
wherever such third-party notices normally appear. The contents
|
117
|
+
of the NOTICE file are for informational purposes only and
|
118
|
+
do not modify the License. You may add Your own attribution
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
121
|
+
that such additional attribution notices cannot be construed
|
122
|
+
as modifying the License.
|
123
|
+
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
125
|
+
may provide additional or different license terms and conditions
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
129
|
+
the conditions stated in this License.
|
130
|
+
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
134
|
+
this License, without any additional terms or conditions.
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
136
|
+
the terms of any separate license agreement you may have executed
|
137
|
+
with Licensor regarding such Contributions.
|
138
|
+
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
141
|
+
except as required for reasonable and customary use in describing the
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
143
|
+
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
153
|
+
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
159
|
+
incidental, or consequential damages of any character arising as a
|
160
|
+
result of this License or out of the use or inability to use the
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
163
|
+
other commercial damages or losses), even if such Contributor
|
164
|
+
has been advised of the possibility of such damages.
|
165
|
+
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
169
|
+
or other liability obligations and/or rights consistent with this
|
170
|
+
License. However, in accepting such obligations, You may act only
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
175
|
+
of your accepting any such warranty or additional liability.
|
176
|
+
|
177
|
+
END OF TERMS AND CONDITIONS
|
178
|
+
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
180
|
+
|
181
|
+
To apply the Apache License to your work, attach the following
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
183
|
+
replaced with your own identifying information. (Don't include
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
185
|
+
comment syntax for the file format. We also recommend that a
|
186
|
+
file or class name and description of purpose be included on the
|
187
|
+
same "printed page" as the copyright notice for easier
|
188
|
+
identification within third-party archives.
|
189
|
+
|
190
|
+
Copyright [yyyy] [name of copyright owner]
|
191
|
+
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
193
|
+
you may not use this file except in compliance with the License.
|
194
|
+
You may obtain a copy of the License at
|
195
|
+
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
197
|
+
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
201
|
+
See the License for the specific language governing permissions and
|
202
|
+
limitations under the License.
|
data/README.md
ADDED
@@ -0,0 +1,76 @@
|
|
1
|
+
# Website Inspector
|
2
|
+
|
3
|
+
Website Inspector is a command line gem that allows you to quickly search any website url using the command line. It allows you to specify any list of search terms and will search the given url links, images, page source, page content, page title and more and will print the results to the terminal.
|
4
|
+
|
5
|
+
|
6
|
+
Build Status (Travis CI):
|
7
|
+
|
8
|
+
[![Build Status](https://travis-ci.org/rukk86/website_inspector.png?branch=master)](https://travis-ci.org/rukk86/website_inspector)
|
9
|
+
|
10
|
+
|
11
|
+
Code Climate Coverage:
|
12
|
+
|
13
|
+
[![Code Climate](https://codeclimate.com/github/rukk86/website_inspector.png)](https://codeclimate.com/github/rukk86/website_inspector)
|
14
|
+
|
15
|
+
## Links
|
16
|
+
|
17
|
+
* Source on Github: https://github.com/rukk86/website_inspector
|
18
|
+
* RDoc: https://github.com/rukk86/website_inspector/blob/master/README.rdoc
|
19
|
+
* Download from RubyGems.org: http://rubygems.org/gems/website_inspector
|
20
|
+
|
21
|
+
|
22
|
+
## Installation
|
23
|
+
|
24
|
+
Add this line to your application's Gemfile:
|
25
|
+
|
26
|
+
gem 'website_inspector'
|
27
|
+
|
28
|
+
And then execute:
|
29
|
+
|
30
|
+
$ bundle
|
31
|
+
|
32
|
+
Or install it yourself as:
|
33
|
+
|
34
|
+
$ gem install website_inspector
|
35
|
+
|
36
|
+
## Usage
|
37
|
+
|
38
|
+
Run 'website_inspector' to see a list of sub commands available to run.
|
39
|
+
|
40
|
+
Here's an example of how you might search the title of a website for the words 'shoes' and 'horses':
|
41
|
+
|
42
|
+
```
|
43
|
+
website_inspector www.zappos.com shoes, horses --links
|
44
|
+
|
45
|
+
---------------------------
|
46
|
+
SEARCHING TITLE
|
47
|
+
While scanning: 'online shoes, clothing, always shipped free | zappos.com'
|
48
|
+
found: shoes
|
49
|
+
|
50
|
+
Website Inspector has finished running
|
51
|
+
|
52
|
+
```
|
53
|
+
|
54
|
+
Search options include:
|
55
|
+
* page object
|
56
|
+
* title
|
57
|
+
* html/xml
|
58
|
+
* webpage source code
|
59
|
+
* hyperlinks
|
60
|
+
* images
|
61
|
+
* image hyperlinks
|
62
|
+
* page forms
|
63
|
+
* default - if no option selected will search ALL the above
|
64
|
+
|
65
|
+
## Contributing
|
66
|
+
|
67
|
+
1. Fork it ( http://github.com/<my-github-username>/website_inspector/fork )
|
68
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
69
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
70
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
71
|
+
5. Create new Pull Request
|
72
|
+
|
73
|
+
## TODO For Release Version 1.0
|
74
|
+
1. Add ability to follow and repeat searches on each link found on each page
|
75
|
+
2. Improve displaying search results (maybe use a table format)
|
76
|
+
3. Add option to save results to an output file
|
data/README.rdoc
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
= Website Inspector
|
2
|
+
|
3
|
+
Author:: Rukia Fahim (Rukk86@gmail.com)
|
4
|
+
Copyright:: Copyright (c) 2014 Rukia Fahim
|
5
|
+
License:: The MIT License, see LICENSE.txt
|
6
|
+
|
7
|
+
Website Inspector is simple command line tool that allows you to search a website url for any number of multiple words.
|
8
|
+
It provides various search options to quickly search links, images, html and much more. It is very easy to use.
|
9
|
+
|
10
|
+
Build Status (Travis CI):
|
11
|
+
{<img
|
12
|
+
src="https://travis-ci.org/rukk86/website_inspector.png?branch=master"
|
13
|
+
alt="Build Status" />}[https://travis-ci.org/rukk86/website_inspector]
|
14
|
+
|
15
|
+
Code Climate Coverage:
|
16
|
+
{<img
|
17
|
+
src="https://codeclimate.com/github/rukk86/website_inspector.png"
|
18
|
+
/>}[https://codeclimate.com/github/rukk86/website_inspector]
|
19
|
+
|
20
|
+
|
21
|
+
== Links
|
22
|
+
|
23
|
+
* {Source on Github}[https://github.com/rukk86/website_inspector]
|
24
|
+
* {RDoc}[https://github.com/rukk86/website_inspector/blob/master/README.rdoc]
|
25
|
+
* {Download from RubyGems.org}[http://rubygems.org/gems/website_inspector]
|
26
|
+
|
27
|
+
== Install
|
28
|
+
Add this line to your application's Gemfile:
|
29
|
+
|
30
|
+
gem 'website_inspector'
|
31
|
+
|
32
|
+
And then execute:
|
33
|
+
|
34
|
+
$ bundle
|
35
|
+
|
36
|
+
Or install it yourself as:
|
37
|
+
|
38
|
+
$ gem install website_inspector
|
39
|
+
|
40
|
+
== Examples
|
41
|
+
For example:
|
42
|
+
`website_inspector www.zappos.com shoes, horses --links`
|
43
|
+
|
44
|
+
Search options include:
|
45
|
+
* Search the url page
|
46
|
+
* Search the url title
|
47
|
+
* Search the url html/xml
|
48
|
+
* Search the displayed page source code
|
49
|
+
* Search hyperlinks
|
50
|
+
* Search images
|
51
|
+
* Search image hyperlinks
|
52
|
+
* Search page forms
|
53
|
+
* default - Search all the above
|
54
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'optparse'
|
4
|
+
require 'methadone'
|
5
|
+
require 'mechanize'
|
6
|
+
require 'website_inspector.rb'
|
7
|
+
require 'website_inspector/website'
|
8
|
+
|
9
|
+
class App
|
10
|
+
include Methadone::Main
|
11
|
+
include Methadone::CLILogging
|
12
|
+
include Methadone::SH
|
13
|
+
include WebsiteInspector
|
14
|
+
|
15
|
+
main do |website_url, *search_terms|
|
16
|
+
Website.start website_url, search_terms
|
17
|
+
if options[:page_object]
|
18
|
+
Website.search_type "PAGE"
|
19
|
+
elsif options[:title]
|
20
|
+
Website.search_type "TITLE"
|
21
|
+
elsif options[:html]
|
22
|
+
Website.search_type "HTML/XML"
|
23
|
+
elsif options[:source]
|
24
|
+
Website.search_type "WEBPAGE SOURCE"
|
25
|
+
elsif options[:hyperlinks]
|
26
|
+
Website.search_type "HYPERLINKS"
|
27
|
+
elsif options[:images]
|
28
|
+
Website.search_type "IMAGES"
|
29
|
+
elsif options[:image_hyperlinks]
|
30
|
+
Website.search_type "IMAGE URLS"
|
31
|
+
elsif options[:page_forms]
|
32
|
+
Website.search_type "PAGE FORMS"
|
33
|
+
else
|
34
|
+
Website.search_all
|
35
|
+
end
|
36
|
+
puts "\n"
|
37
|
+
info "Website Inspector has finished running"
|
38
|
+
end
|
39
|
+
|
40
|
+
version WebsiteInspector::VERSION
|
41
|
+
description 'Provides a command line interface to quickly search and inspect a website for specific content or search terms, if search type option is not provided, it will default to searching all data source types'
|
42
|
+
|
43
|
+
on("--page_object", "Search the page object")
|
44
|
+
on("--title", "Search title only")
|
45
|
+
on("--html", "Search page html/xml only")
|
46
|
+
on("--source", "Search page source only")
|
47
|
+
on("--hyperlinks", "Search listed hyperlinks only")
|
48
|
+
on("--images", "Search images only")
|
49
|
+
on("--image_hyperlinks", "Search image urls only")
|
50
|
+
on("--page_forms", "Search page forms only")
|
51
|
+
|
52
|
+
arg :website_url, "URL of the website to inspect and scan for specified search terms"
|
53
|
+
arg :search_terms, "An array of terms to search for in the specified websites"
|
54
|
+
|
55
|
+
use_log_level_option
|
56
|
+
|
57
|
+
go!
|
58
|
+
end
|
@@ -0,0 +1 @@
|
|
1
|
+
# Put your step definitions here
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require 'aruba/cucumber'
|
2
|
+
require 'methadone/cucumber'
|
3
|
+
|
4
|
+
ENV['PATH'] = "#{File.expand_path(File.dirname(__FILE__) + '/../../bin')}#{File::PATH_SEPARATOR}#{ENV['PATH']}"
|
5
|
+
LIB_DIR = File.join(File.expand_path(File.dirname(__FILE__)),'..','..','lib')
|
6
|
+
|
7
|
+
Before do
|
8
|
+
# Using "announce" causes massive warnings on 1.9.2
|
9
|
+
@puts = true
|
10
|
+
@original_rubylib = ENV['RUBYLIB']
|
11
|
+
ENV['RUBYLIB'] = LIB_DIR + File::PATH_SEPARATOR + ENV['RUBYLIB'].to_s
|
12
|
+
end
|
13
|
+
|
14
|
+
After do
|
15
|
+
ENV['RUBYLIB'] = @original_rubylib
|
16
|
+
end
|
@@ -0,0 +1,58 @@
|
|
1
|
+
Feature: Use the website inspector command line app
|
2
|
+
In order to quickly inspect a website
|
3
|
+
I want a quick command line app to search a website
|
4
|
+
|
5
|
+
Scenario: Monitor status of the website scraper
|
6
|
+
When I get help for "website_inspector"
|
7
|
+
Then the exit status should be 0
|
8
|
+
And the banner should be present
|
9
|
+
And there should be a one line summary of what the app does
|
10
|
+
And the banner should include the version
|
11
|
+
And the banner should document that this app takes options
|
12
|
+
And the banner should document that this app's arguments are:
|
13
|
+
|website_url | which is required |
|
14
|
+
|search_terms | which is required |
|
15
|
+
And the following options should be documented:
|
16
|
+
|page_object |
|
17
|
+
|title |
|
18
|
+
|html |
|
19
|
+
|source |
|
20
|
+
|hyperlinks |
|
21
|
+
|images |
|
22
|
+
|image_hyperlinks |
|
23
|
+
|page_forms |
|
24
|
+
|
25
|
+
Scenario: Successfully start the website inspector
|
26
|
+
Given I run `website_inspector http://www.google.com shop`
|
27
|
+
Then the exit status should be 0
|
28
|
+
And the stdout should contain "INFO -- : Website Inspector has finished running"
|
29
|
+
|
30
|
+
Scenario: Return accurate results
|
31
|
+
Given I run `website_inspector zappos.com shoes`
|
32
|
+
Then the exit status should be 0
|
33
|
+
And the stdout should contain "SEARCHING TITLE"
|
34
|
+
|
35
|
+
Scenario: Display Error if no website urls are provided
|
36
|
+
Given I run `website_inspector`
|
37
|
+
Then the exit status should not be 0
|
38
|
+
And the stderr should contain "ERROR -- : parse error: 'website_url' is required"
|
39
|
+
|
40
|
+
Scenario: Display Error if no search terms are provided
|
41
|
+
Given I run `website_inspector www.google.com`
|
42
|
+
Then the exit status should not be 0
|
43
|
+
And the stderr should contain "ERROR -- : parse error: 'search_terms' is required"
|
44
|
+
|
45
|
+
Scenario Outline: Successfully run website inspector with any of the options
|
46
|
+
When I run `website_inspector www.zappos.com "option"`
|
47
|
+
Then the exit status should be 0
|
48
|
+
And the stdout should contain "option"
|
49
|
+
Examples:
|
50
|
+
|option | stdout |
|
51
|
+
|--page_object | "PAGE" |
|
52
|
+
|--title | "TITLE" |
|
53
|
+
|--html | "HTML/XML" |
|
54
|
+
|--source | "WEBPAGE SOURCE" |
|
55
|
+
|--hyperlinks | "LINKS" |
|
56
|
+
|--images | "IMAGES" |
|
57
|
+
|--image_hyperlinks | "IMAGE URLS" |
|
58
|
+
|--page_forms | "PAGE FORMS" |
|
@@ -0,0 +1,84 @@
|
|
1
|
+
module WebsiteInspector
|
2
|
+
class Website
|
3
|
+
include Methadone::CLILogging
|
4
|
+
include Methadone::Main
|
5
|
+
include Methadone::SH
|
6
|
+
|
7
|
+
attr_accessor :search_terms, :url, :page, :title, :html, :body, :links, :site_data
|
8
|
+
|
9
|
+
def self.start website_url, search_terms
|
10
|
+
agent = Mechanize.new
|
11
|
+
|
12
|
+
@search_terms = clean_input search_terms
|
13
|
+
@regex_search = Regexp.union(@search_terms)
|
14
|
+
@website_url = Website.validate_url website_url
|
15
|
+
|
16
|
+
@site_data = Hash.new
|
17
|
+
@site_data["PAGE"] = @page = agent.get(@website_url) # Mechanize Page
|
18
|
+
@site_data["TITLE"] = @title = @page.title # String
|
19
|
+
@site_data["HTML/XML"] = @html = @page.parser # Nokogiri HTML
|
20
|
+
@site_data["WEBPAGE SOURCE"] = @source = @page.body # String
|
21
|
+
@site_data["LINKS"] = @links = @page.links # Array
|
22
|
+
@site_data["IMAGES"] = @images = @page.images
|
23
|
+
@site_data["IMAGE URLS"] = @image_urls = @page.image_urls
|
24
|
+
@site_data["PAGE FORMS"] = @forms = @page.forms
|
25
|
+
end
|
26
|
+
|
27
|
+
def self.validate_url website_url
|
28
|
+
site = website_url.chomp(",") #get rid of trailing commas
|
29
|
+
uri = URI(site)
|
30
|
+
if uri.instance_of?(URI::Generic)
|
31
|
+
uri = URI::HTTP.build({:host => uri.to_s})
|
32
|
+
end
|
33
|
+
uri
|
34
|
+
end
|
35
|
+
|
36
|
+
def self.clean_input search_terms
|
37
|
+
terms = Array.new
|
38
|
+
search_terms.each do |term|
|
39
|
+
term = term.to_s.gsub(",", "")
|
40
|
+
terms << term
|
41
|
+
end
|
42
|
+
terms
|
43
|
+
end
|
44
|
+
|
45
|
+
def self.search data
|
46
|
+
no_match = true
|
47
|
+
sections = data.scan /\S.{1,80}(?!\S)/
|
48
|
+
sections.each do |section|
|
49
|
+
matches = section.scan(@regex_search)
|
50
|
+
if !matches.empty?
|
51
|
+
no_match = false
|
52
|
+
puts "While scanning: '#{section}'"
|
53
|
+
puts "found: #{matches.join(', ')}\n"
|
54
|
+
end
|
55
|
+
end
|
56
|
+
if no_match
|
57
|
+
puts "No matches found for: #{@search_terms.join(', ')}\n"
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def self.console_print section_name
|
62
|
+
puts "---------------------------\nSEARCHING #{section_name}"
|
63
|
+
end
|
64
|
+
|
65
|
+
def self.search_all
|
66
|
+
@site_data.each do |k, v|
|
67
|
+
Website.console_print "#{k}"
|
68
|
+
Website.search v.to_s.downcase
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
def self.search_type key
|
73
|
+
Website.console_print "#{key}"
|
74
|
+
value = @site_data[key]
|
75
|
+
if value.kind_of? Array
|
76
|
+
value.each do |v|
|
77
|
+
Website.search v.to_s.downcase
|
78
|
+
end
|
79
|
+
else
|
80
|
+
Website.search value.to_s.downcase
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'website_inspector/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "website_inspector"
|
8
|
+
spec.version = WebsiteInspector::VERSION
|
9
|
+
spec.authors = ["Rukia Fahim"]
|
10
|
+
spec.email = ["RukK86@gmail.com"]
|
11
|
+
spec.summary = %q{Quickly search a website using the command line.}
|
12
|
+
spec.description = %q{A command line app packaged as a ruby gem that allows users to search a website for specific terms.}
|
13
|
+
spec.homepage = "https://github.com/rukk86/website_inspector"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.5"
|
22
|
+
spec.add_development_dependency "rdoc"
|
23
|
+
spec.add_development_dependency "cucumber"
|
24
|
+
spec.add_development_dependency "aruba"
|
25
|
+
spec.add_dependency "rake", "~> 0.9.2"
|
26
|
+
spec.add_dependency "mechanize", "~> 2.7.3"
|
27
|
+
spec.add_dependency "methadone", "~> 1.3.2"
|
28
|
+
end
|
metadata
ADDED
@@ -0,0 +1,163 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: website_inspector
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.4
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Rukia Fahim
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-03-14 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: '1.5'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.5'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rdoc
|
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: cucumber
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: aruba
|
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: rake
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ~>
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 0.9.2
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ~>
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 0.9.2
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: mechanize
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ~>
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: 2.7.3
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ~>
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: 2.7.3
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: methadone
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ~>
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: 1.3.2
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ~>
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 1.3.2
|
111
|
+
description: A command line app packaged as a ruby gem that allows users to search
|
112
|
+
a website for specific terms.
|
113
|
+
email:
|
114
|
+
- RukK86@gmail.com
|
115
|
+
executables:
|
116
|
+
- website_inspector
|
117
|
+
extensions: []
|
118
|
+
extra_rdoc_files: []
|
119
|
+
files:
|
120
|
+
- .gitignore
|
121
|
+
- .travis.yml
|
122
|
+
- Gemfile
|
123
|
+
- Gemfile.lock
|
124
|
+
- LICENSE.txt
|
125
|
+
- README.md
|
126
|
+
- README.rdoc
|
127
|
+
- Rakefile
|
128
|
+
- bin/website_inspector
|
129
|
+
- features/step_definitions/website_inspector_steps.rb
|
130
|
+
- features/support/env.rb
|
131
|
+
- features/website_inspector.feature
|
132
|
+
- lib/website_inspector.rb
|
133
|
+
- lib/website_inspector/version.rb
|
134
|
+
- lib/website_inspector/website.rb
|
135
|
+
- website_inspector.gemspec
|
136
|
+
homepage: https://github.com/rukk86/website_inspector
|
137
|
+
licenses:
|
138
|
+
- MIT
|
139
|
+
metadata: {}
|
140
|
+
post_install_message:
|
141
|
+
rdoc_options: []
|
142
|
+
require_paths:
|
143
|
+
- lib
|
144
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
145
|
+
requirements:
|
146
|
+
- - '>='
|
147
|
+
- !ruby/object:Gem::Version
|
148
|
+
version: '0'
|
149
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
150
|
+
requirements:
|
151
|
+
- - '>='
|
152
|
+
- !ruby/object:Gem::Version
|
153
|
+
version: '0'
|
154
|
+
requirements: []
|
155
|
+
rubyforge_project:
|
156
|
+
rubygems_version: 2.2.1
|
157
|
+
signing_key:
|
158
|
+
specification_version: 4
|
159
|
+
summary: Quickly search a website using the command line.
|
160
|
+
test_files:
|
161
|
+
- features/step_definitions/website_inspector_steps.rb
|
162
|
+
- features/support/env.rb
|
163
|
+
- features/website_inspector.feature
|