download_files 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +4 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +29 -0
- data/Rakefile +6 -0
- data/bin/download_files +34 -0
- data/download_files.gemspec +23 -0
- data/lib/download_files/version.rb +3 -0
- data/lib/download_files.rb +44 -0
- metadata +125 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Dustin Morrill
|
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
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# DownloadFiles
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'download_files'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install download_files
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/bin/download_files
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'fileutils'
|
4
|
+
require 'optparse'
|
5
|
+
require 'methadone'
|
6
|
+
require_relative '../lib/download_files.rb'
|
7
|
+
|
8
|
+
class App
|
9
|
+
include Methadone::Main
|
10
|
+
include Methadone::CLILogging
|
11
|
+
|
12
|
+
main do |page_address, pattern, directory|
|
13
|
+
dir = if directory
|
14
|
+
FileUtils.mkdir_p(directory) unless File.directory?(directory)
|
15
|
+
else
|
16
|
+
FileUtils.pwd
|
17
|
+
end
|
18
|
+
DownloadFiles.download_files(page_address, pattern, dir, logger)
|
19
|
+
end
|
20
|
+
|
21
|
+
# Declare command-line interface
|
22
|
+
description "Downloads files from the web page at the given address on the given domain that match the given regular expression pattern."
|
23
|
+
|
24
|
+
# Require an argument
|
25
|
+
arg :page_address
|
26
|
+
arg :pattern
|
27
|
+
arg :directory, :optional
|
28
|
+
|
29
|
+
version DownloadFiles::VERSION
|
30
|
+
|
31
|
+
use_log_level_option
|
32
|
+
|
33
|
+
go!
|
34
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/download_files/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Dustin Morrill"]
|
6
|
+
gem.email = ["dmorrill10@gmail.com"]
|
7
|
+
gem.description = %q{Download all files at a particular URL that match a certain pattern.}
|
8
|
+
gem.summary = %q{Download all files at a particular URL that match a certain pattern.}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "download_files"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = DownloadFiles::VERSION
|
17
|
+
|
18
|
+
gem.add_development_dependency('rake', '~> 0.9.2')
|
19
|
+
|
20
|
+
gem.add_dependency('methadone', '~> 1.2.5')
|
21
|
+
gem.add_dependency('mechanize')
|
22
|
+
gem.add_dependency('nullobject')
|
23
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
require_relative "download_files/version"
|
2
|
+
|
3
|
+
require 'mechanize'
|
4
|
+
require 'nullobject'
|
5
|
+
|
6
|
+
class Mechanize
|
7
|
+
def self.start
|
8
|
+
yield(new)
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.go(page_address)
|
12
|
+
start do |agent|
|
13
|
+
agent.get(page_address) do |page|
|
14
|
+
yield agent, page
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
module DownloadFiles
|
21
|
+
def self.download_files(page_address, pattern, dir=FileUtils.pwd, logger=Null::Object.instance)
|
22
|
+
logger.debug "DownloadFiles.download_files: " + {page_address: page_address, pattern: pattern, dir: dir, logger: logger}.inspect
|
23
|
+
|
24
|
+
abs_dir = File.expand_path(dir, FileUtils.pwd)
|
25
|
+
|
26
|
+
Mechanize.go(page_address) do |agent, page|
|
27
|
+
logger.debug page.inspect
|
28
|
+
logger.info "On #{page.uri}"
|
29
|
+
|
30
|
+
agent.pluggable_parser.default = Mechanize::Download
|
31
|
+
|
32
|
+
page.links.each do |link|
|
33
|
+
logger.debug "Checking link #{link.href}"
|
34
|
+
|
35
|
+
next unless link.href.match(pattern)
|
36
|
+
|
37
|
+
full_file_name = File.expand_path(File.basename(link.href), abs_dir)
|
38
|
+
logger.info "Downloading #{link.click.uri} to #{full_file_name}"
|
39
|
+
|
40
|
+
agent.get(link.click.uri).save(full_file_name)
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
metadata
ADDED
@@ -0,0 +1,125 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: download_files
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Dustin Morrill
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-03-10 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rake
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 0.9.2
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 0.9.2
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: methadone
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ~>
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: 1.2.5
|
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: 1.2.5
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: mechanize
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :runtime
|
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: nullobject
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :runtime
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
description: Download all files at a particular URL that match a certain pattern.
|
79
|
+
email:
|
80
|
+
- dmorrill10@gmail.com
|
81
|
+
executables:
|
82
|
+
- download_files
|
83
|
+
extensions: []
|
84
|
+
extra_rdoc_files: []
|
85
|
+
files:
|
86
|
+
- .gitignore
|
87
|
+
- Gemfile
|
88
|
+
- LICENSE
|
89
|
+
- README.md
|
90
|
+
- Rakefile
|
91
|
+
- bin/download_files
|
92
|
+
- download_files.gemspec
|
93
|
+
- lib/download_files.rb
|
94
|
+
- lib/download_files/version.rb
|
95
|
+
homepage: ''
|
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
|
+
segments:
|
108
|
+
- 0
|
109
|
+
hash: 2836402041738517125
|
110
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
111
|
+
none: false
|
112
|
+
requirements:
|
113
|
+
- - ! '>='
|
114
|
+
- !ruby/object:Gem::Version
|
115
|
+
version: '0'
|
116
|
+
segments:
|
117
|
+
- 0
|
118
|
+
hash: 2836402041738517125
|
119
|
+
requirements: []
|
120
|
+
rubyforge_project:
|
121
|
+
rubygems_version: 1.8.24
|
122
|
+
signing_key:
|
123
|
+
specification_version: 3
|
124
|
+
summary: Download all files at a particular URL that match a certain pattern.
|
125
|
+
test_files: []
|