driller 0.1.0 → 0.1.1
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 +8 -8
- metadata +4 -14
- data/.gitignore +0 -14
- data/Gemfile +0 -3
- data/LICENSE.txt +0 -22
- data/README.md +0 -52
- data/Rakefile +0 -2
- data/bin/driller +0 -68
- data/driller.gemspec +0 -25
- data/lib/driller.rb +0 -8
- data/lib/driller/uri_helper.rb +0 -8
- data/lib/driller/version.rb +0 -3
checksums.yaml
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
---
|
2
2
|
!binary "U0hBMQ==":
|
3
3
|
metadata.gz: !binary |-
|
4
|
-
|
4
|
+
ZWQzNGUxOWVjMmE4ZThmMjVmMTYwMTA2OTk4ZTYxZjk0ZGIzNDUzOQ==
|
5
5
|
data.tar.gz: !binary |-
|
6
|
-
|
6
|
+
ZjFkNmFlOWE5Njg0YzhlODlmODcxMWI5NGI4MTZkYzM4NzQyZmFlZg==
|
7
7
|
SHA512:
|
8
8
|
metadata.gz: !binary |-
|
9
|
-
|
10
|
-
|
11
|
-
|
9
|
+
NGM5ZjcyMDk1MjU2NzZmYzZhZWVkNmFjODk0M2Y5Nzg3Y2VjOWFiYmU0ZWEz
|
10
|
+
NDM5MDFlMDhjZDhjZjQ0NjBiNTg4NzAyNjVlNzYzY2ZmNzY5MDUyMTMwYWUx
|
11
|
+
NzY4MDkxNDU2ZTk2NjRlYTI0NWVhMjI3YjlmNGViOGNlMDQ4YjA=
|
12
12
|
data.tar.gz: !binary |-
|
13
|
-
|
14
|
-
|
15
|
-
|
13
|
+
NzAxNmE4Y2VmZDkyZTM0MjVkNTM3Y2QxOGM1NmRlODhmZDQyYTViOWQ3Mjg0
|
14
|
+
NjQyMzUyYTNjMDViODg0Y2M3YzU1OWYzZjE0MjU2YTQ3YzZhMzZlOWUyZGFk
|
15
|
+
MzEyODVkODQyN2I0OTAyYjk1ZGJhNmM2OTg4OWJhZmJhZDE4ZjM=
|
metadata
CHANGED
@@ -1,10 +1,11 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: driller
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Shashikant86
|
8
|
+
- Qambar
|
8
9
|
autorequire:
|
9
10
|
bindir: bin
|
10
11
|
cert_chain: []
|
@@ -56,21 +57,10 @@ description: Driller is a command line Ruby based web crawler based on Anemone.
|
|
56
57
|
can crawl website and reports error pages which are not 200 or 301.
|
57
58
|
email:
|
58
59
|
- shashikant.jagtap@aol.co.uk
|
59
|
-
executables:
|
60
|
-
- driller
|
60
|
+
executables: []
|
61
61
|
extensions: []
|
62
62
|
extra_rdoc_files: []
|
63
|
-
files:
|
64
|
-
- .gitignore
|
65
|
-
- Gemfile
|
66
|
-
- LICENSE.txt
|
67
|
-
- README.md
|
68
|
-
- Rakefile
|
69
|
-
- bin/driller
|
70
|
-
- driller.gemspec
|
71
|
-
- lib/driller.rb
|
72
|
-
- lib/driller/uri_helper.rb
|
73
|
-
- lib/driller/version.rb
|
63
|
+
files: []
|
74
64
|
homepage: https://github.com/Shashikant86/driller
|
75
65
|
licenses:
|
76
66
|
- MIT
|
data/.gitignore
DELETED
data/Gemfile
DELETED
data/LICENSE.txt
DELETED
@@ -1,22 +0,0 @@
|
|
1
|
-
Copyright (c) 2015 Shashikant86
|
2
|
-
|
3
|
-
MIT License
|
4
|
-
|
5
|
-
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
-
a copy of this software and associated documentation files (the
|
7
|
-
"Software"), to deal in the Software without restriction, including
|
8
|
-
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
-
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
-
permit persons to whom the Software is furnished to do so, subject to
|
11
|
-
the following conditions:
|
12
|
-
|
13
|
-
The above copyright notice and this permission notice shall be
|
14
|
-
included in all copies or substantial portions of the Software.
|
15
|
-
|
16
|
-
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
-
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
-
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
-
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
-
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
-
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
-
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
DELETED
@@ -1,52 +0,0 @@
|
|
1
|
-
# Driller
|
2
|
-
|
3
|
-
Driller is a command line Ruby based web crawler based on Anemone. Driller can
|
4
|
-
|
5
|
-
* Crawl website and reports error pages which are not 200 or 301. This will report all other HTTP codes.
|
6
|
-
* Driller will report slow pages which are returned response time > 5000
|
7
|
-
* This will create three HTML files valid_urls.html which are 200 response. broken.html wich are not 200. slow_pages.html which are retuned reaponse time > 5000
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
## Installation
|
12
|
-
|
13
|
-
Add this line to your application's Gemfile:
|
14
|
-
|
15
|
-
```ruby
|
16
|
-
gem 'driller'
|
17
|
-
```
|
18
|
-
|
19
|
-
And then execute:
|
20
|
-
|
21
|
-
$ bundle
|
22
|
-
|
23
|
-
Or install it yourself as:
|
24
|
-
|
25
|
-
$ gem install driller
|
26
|
-
|
27
|
-
## Usage
|
28
|
-
|
29
|
-
Driller takes two arguments
|
30
|
-
|
31
|
-
* URL of the page to be crawled
|
32
|
-
* Depth of the crawling
|
33
|
-
|
34
|
-
|
35
|
-
$ driller http://www.example.com 2
|
36
|
-
|
37
|
-
If you have installed it from bundle the
|
38
|
-
|
39
|
-
$ bundle exec driller http://www.example.com 2
|
40
|
-
|
41
|
-
|
42
|
-
This will crawl website upto level 2. You can increase depth as per your need. This will create three HTML files valid_urls.html which are 200 response. broken.html wich are not 200. slow_pages.html which are retuned reaponse time > 5000
|
43
|
-
|
44
|
-
You an display these html files to CI server.
|
45
|
-
|
46
|
-
## Contributing
|
47
|
-
|
48
|
-
1. Fork it ( https://github.com/[my-github-username]/driller/fork )
|
49
|
-
2. Create your feature branch (`git checkout -b my-new-feature`)
|
50
|
-
3. Commit your changes (`git commit -am 'Add some feature'`)
|
51
|
-
4. Push to the branch (`git push origin my-new-feature`)
|
52
|
-
5. Create a new Pull Request
|
data/Rakefile
DELETED
data/bin/driller
DELETED
@@ -1,68 +0,0 @@
|
|
1
|
-
#!/usr/bin/env ruby
|
2
|
-
require 'driller/version'
|
3
|
-
require 'driller/uri_helper'
|
4
|
-
require 'fileutils'
|
5
|
-
require "rubygems"
|
6
|
-
require "anemone"
|
7
|
-
|
8
|
-
webpage = ARGV[0]
|
9
|
-
depth = ARGV[1]
|
10
|
-
|
11
|
-
Anemone.crawl(webpage) do |anemone|
|
12
|
-
|
13
|
-
anemone.depth_limit = depth.to_i
|
14
|
-
puts "============= Driller is now checking your website links. If any of the link returned non 200, it will be displayed here========="
|
15
|
-
anemone.focus_crawl do |page|
|
16
|
-
page.links.select { |url| url.starts_with? webpage }
|
17
|
-
end
|
18
|
-
|
19
|
-
file = File.new('valid_pages.html', 'w')
|
20
|
-
file = File.new('broken.html', 'w')
|
21
|
-
file = File.new('slow_pages.html', 'w')
|
22
|
-
file = File.new('extremely_slow_pages.html', 'w')
|
23
|
-
|
24
|
-
anemone.on_every_page do |page|
|
25
|
-
|
26
|
-
if page.code != 200
|
27
|
-
puts "=======This page is broken ======\n"
|
28
|
-
puts page.url
|
29
|
-
puts "\n returned response code of\n"
|
30
|
-
puts page.code
|
31
|
-
puts "=======Plese fix it ======\n"
|
32
|
-
file = File.open('broken.html', 'a+')
|
33
|
-
file.puts page.url
|
34
|
-
file.write("\n")
|
35
|
-
file.write("Returned with response code \n")
|
36
|
-
file.write("\n")
|
37
|
-
file.puts page.code
|
38
|
-
else if
|
39
|
-
page.code == 200
|
40
|
-
file = File.open('valid_pages.html', 'a+')
|
41
|
-
file.puts page.url
|
42
|
-
file.write("\n")
|
43
|
-
else if
|
44
|
-
page.response_time > 5000
|
45
|
-
puts "=======Slow Page======\n"
|
46
|
-
puts page.url
|
47
|
-
file = File.open('slow_pages.html', 'a+')
|
48
|
-
file.puts page.url
|
49
|
-
file.write("\n")
|
50
|
-
file.write("Returned with response time \n")
|
51
|
-
file.write("\n")
|
52
|
-
file.puts page.response_time
|
53
|
-
else if
|
54
|
-
page.response_time > 10000
|
55
|
-
puts "=======Very Slow Page======\n"
|
56
|
-
puts page.url
|
57
|
-
file = File.open('extremely_slow_pages.html', 'a+')
|
58
|
-
file.puts page.url
|
59
|
-
file.write("\n")
|
60
|
-
file.write("Returned with response time which is not acceptable at all \n")
|
61
|
-
file.write("\n")
|
62
|
-
file.puts page.response_time
|
63
|
-
end
|
64
|
-
end
|
65
|
-
end
|
66
|
-
end
|
67
|
-
end
|
68
|
-
end
|
data/driller.gemspec
DELETED
@@ -1,25 +0,0 @@
|
|
1
|
-
# coding: utf-8
|
2
|
-
lib = File.expand_path('../lib', __FILE__)
|
3
|
-
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
-
require 'driller/version'
|
5
|
-
|
6
|
-
Gem::Specification.new do |spec|
|
7
|
-
spec.name = "driller"
|
8
|
-
spec.version = Driller::VERSION
|
9
|
-
spec.authors = ["Shashikant86"]
|
10
|
-
spec.email = ["shashikant.jagtap@aol.co.uk"]
|
11
|
-
spec.summary = %q{Drill your website for error and slow pages}
|
12
|
-
spec.description = %q{Driller is a command line Ruby based web crawler based on Anemone. Driller can crawl website and reports error pages which are not 200 or 301.}
|
13
|
-
spec.homepage = "https://github.com/Shashikant86/driller"
|
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
|
-
|
22
|
-
spec.add_runtime_dependency "bundler", "~> 1.0"
|
23
|
-
spec.add_runtime_dependency "rake"
|
24
|
-
spec.add_runtime_dependency "anemone"
|
25
|
-
end
|
data/lib/driller.rb
DELETED
data/lib/driller/uri_helper.rb
DELETED
data/lib/driller/version.rb
DELETED