web_dump 0.0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/LICENSE +20 -0
- data/README.rdoc +59 -0
- data/Rakefile +58 -0
- data/lib/web_dump/version.rb +16 -0
- data/lib/web_dump.rb +104 -0
- data/test/test_web_dump.rb +47 -0
- data/web_dump.gemspec +50 -0
- metadata +87 -0
data/.document
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Marcel Massana
|
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 +1,59 @@
|
|
1
|
+
= web_dump
|
2
|
+
|
3
|
+
Little tiny class to easily save and retrieve web pages
|
4
|
+
|
5
|
+
In web related client applications, such as spiders, it is frequently necessary
|
6
|
+
to save pages into files with adecuate naming convention. WebDump comes to the
|
7
|
+
rescue. It manages the details of assigning unique readable names and save files
|
8
|
+
after URIs that have been visited. Additionally, saving data could also be
|
9
|
+
conveniently compressed with gzip for deep web spidering. It only depends on
|
10
|
+
telling the correct file extension when saving.
|
11
|
+
|
12
|
+
Conversely, file read operation is available through convenient methods
|
13
|
+
indicating either a pathname or a URI.
|
14
|
+
|
15
|
+
== Installation
|
16
|
+
|
17
|
+
$ sudo gem install web_dump
|
18
|
+
|
19
|
+
The main source repository is http://github.com/syborg/web_dump.
|
20
|
+
|
21
|
+
== Usage
|
22
|
+
|
23
|
+
First of all ...
|
24
|
+
|
25
|
+
require 'rubygems'
|
26
|
+
require 'web_dump'
|
27
|
+
|
28
|
+
Instantiate an object. You may add some options that can be passed through an
|
29
|
+
array
|
30
|
+
|
31
|
+
wd = WebDump,new :base_dir => '~/mydir', :file_ext => '.gz'
|
32
|
+
|
33
|
+
`wd`, when asked to, will save all files inside expanded directory '~/mydir'
|
34
|
+
with an appended file extension at the end '.gz' (if not overwriten later)
|
35
|
+
|
36
|
+
Other options could be passed when instantiating an object.
|
37
|
+
|
38
|
+
* `:file_ext => extension` (String that will be appended at the end to every filename if not changed from _save_ method)
|
39
|
+
|
40
|
+
Most of them are also passed along to an UriPathname object that is created.
|
41
|
+
|
42
|
+
* `:base_dir => dir_name` (directory where everything will be stored. Defaults to '~/web_dumps')
|
43
|
+
* `:pth_sep => psep` (String that will be used to substitute '/' inside URI's path and queries (defaults to UriPathname::PTH_SEP='_|_'))
|
44
|
+
* `:host_sep => hsep` (String that will be used separate the URI¡s hostname and path when constructing the pathname. if '/' is used, hostname will actually become a subdirectory -defaults to UriPathname::HOST_SEP='__|'-)
|
45
|
+
* `:no_path => nopath` (String that will be used as a path placeholder when no URI's path exists, -default UriPathname::NO_PTH = '_NOPATH_'-)
|
46
|
+
|
47
|
+
== Note on Patches/Pull Requests
|
48
|
+
|
49
|
+
* Fork the project.
|
50
|
+
* Make your feature addition or bug fix.
|
51
|
+
* Add tests for it. This is important so I don't break it in a
|
52
|
+
future version unintentionally.
|
53
|
+
* Commit, do not mess with rakefile, version, or history.
|
54
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
55
|
+
* Send me a pull request. Bonus points for topic branches.
|
56
|
+
|
57
|
+
== Copyright
|
58
|
+
|
59
|
+
Copyright (c) 2011 Marcel Massana. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
require './lib/web_dump/version'
|
7
|
+
Jeweler::Tasks.new do |gem|
|
8
|
+
gem.name = "web_dump"
|
9
|
+
gem.summary = %Q{Saves and Retrieves data in files given an URI}
|
10
|
+
gem.description = %Q{Saves and Retrieves data given an URI. The filename
|
11
|
+
will be automatically choosed using that URI freeing the user to think
|
12
|
+
about that}.gsub(/\s+/,' ')
|
13
|
+
gem.email = "xaxaupua@gmail.com"
|
14
|
+
gem.homepage = "http://github.com/syborg/web_dump"
|
15
|
+
gem.authors = ["Marcel Massana"]
|
16
|
+
gem.add_dependency "uri_pathname", ">= 0"
|
17
|
+
# gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
|
18
|
+
gem.version = WebDump::Version::STRING
|
19
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
20
|
+
end
|
21
|
+
Jeweler::GemcutterTasks.new
|
22
|
+
rescue LoadError
|
23
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
24
|
+
end
|
25
|
+
|
26
|
+
require 'rake/testtask'
|
27
|
+
Rake::TestTask.new(:test) do |test|
|
28
|
+
test.libs << 'lib' << 'test'
|
29
|
+
test.pattern = 'test/**/test_*.rb'
|
30
|
+
test.verbose = true
|
31
|
+
end
|
32
|
+
|
33
|
+
begin
|
34
|
+
require 'rcov/rcovtask'
|
35
|
+
Rcov::RcovTask.new do |test|
|
36
|
+
test.libs << 'test'
|
37
|
+
test.pattern = 'test/**/test_*.rb'
|
38
|
+
test.verbose = true
|
39
|
+
end
|
40
|
+
rescue LoadError
|
41
|
+
task :rcov do
|
42
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
task :test => :check_dependencies
|
47
|
+
|
48
|
+
task :default => :test
|
49
|
+
|
50
|
+
require 'rake/rdoctask'
|
51
|
+
Rake::RDocTask.new do |rdoc|
|
52
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
53
|
+
|
54
|
+
rdoc.rdoc_dir = 'rdoc'
|
55
|
+
rdoc.title = "web_dump #{version}"
|
56
|
+
rdoc.rdoc_files.include('README*')
|
57
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
58
|
+
end
|
data/lib/web_dump.rb
ADDED
@@ -0,0 +1,104 @@
|
|
1
|
+
# WebDump
|
2
|
+
# MME 31/8/2011
|
3
|
+
#
|
4
|
+
# Allows saving and reading data related to URIs (i.e. pages)
|
5
|
+
|
6
|
+
require 'web_dump/version'
|
7
|
+
require 'uri'
|
8
|
+
require 'zlib'
|
9
|
+
require 'fileutils'
|
10
|
+
require 'rubygems'
|
11
|
+
require 'uri_pathname'
|
12
|
+
|
13
|
+
# Allows saving and reading data related to URIs (i.e. pages)
|
14
|
+
class WebDump
|
15
|
+
|
16
|
+
#default attributes
|
17
|
+
DEFAULT_ATTRS = {
|
18
|
+
:base_dir => '~/web_dumps',
|
19
|
+
:file_ext => '.html'
|
20
|
+
}
|
21
|
+
|
22
|
+
attr_accessor :up, *(DEFAULT_ATTRS.keys)
|
23
|
+
|
24
|
+
# initializes a WebDump object. +options+ should be a hash with options for
|
25
|
+
# an UriPathname object that will be internally created. Default UriPathnames
|
26
|
+
# options and additionally:
|
27
|
+
# :base_dir => directory where everything will be stored (def. '~/web_dumps')
|
28
|
+
# :file_ext => extension that will be appended to filenames (def. '.html')
|
29
|
+
def initialize(options = {})
|
30
|
+
|
31
|
+
attributes = DEFAULT_ATTRS.merge options if options.is_a? Hash
|
32
|
+
attributes.each { |k,v| instance_eval("@#{k}='#{v}'") if DEFAULT_ATTRS.keys.include?(k) }
|
33
|
+
|
34
|
+
@up=UriPathname.new attributes # any valid option passed will be delivered
|
35
|
+
|
36
|
+
end
|
37
|
+
|
38
|
+
# saves the +content+ (String) into a file named after
|
39
|
+
# UriPathname#uri_to_pathname(+uri+).
|
40
|
+
# If +extension+ is nil initialize :file_ext option will be used:
|
41
|
+
# 'anything'+'.gz' -> gzipped (less storage requirements)
|
42
|
+
# other -> as is
|
43
|
+
# returns a String containing the complete pathname of the file if OK else nil
|
44
|
+
def save(uri, content, extension = nil)
|
45
|
+
extension = @file_ext unless extension
|
46
|
+
pathname = @up.uri_to_pathname(uri,nil,extension)
|
47
|
+
return nil unless pathname
|
48
|
+
mkdir_if_not_exists(File.dirname(pathname))
|
49
|
+
num_bytes = nil
|
50
|
+
case extension
|
51
|
+
when /\.gz$/ # ...gz
|
52
|
+
File.open(pathname, 'w') do |f|
|
53
|
+
gz = Zlib::GzipWriter.new(f)
|
54
|
+
# gz.comment="#dumped with web_dump #{Version::STRING}: #{uri}" # no sembla fer res
|
55
|
+
num_bytes = gz.write content
|
56
|
+
gz.close
|
57
|
+
end
|
58
|
+
else # any other
|
59
|
+
File.open(pathname, 'w') do |f|
|
60
|
+
num_bytes = f.write(content)
|
61
|
+
end
|
62
|
+
end
|
63
|
+
num_bytes ? pathname : nil
|
64
|
+
end
|
65
|
+
|
66
|
+
# returns the stored content corresponding to file +pathname+. In case there
|
67
|
+
# isn't any file it returns nil.
|
68
|
+
def read_pathname(pathname)
|
69
|
+
content = nil
|
70
|
+
arr = @up.parse pathname
|
71
|
+
complete_pathname = File.expand_path(pathname)
|
72
|
+
extension = arr[2]
|
73
|
+
case extension
|
74
|
+
when /.gz/
|
75
|
+
File.open(complete_pathname, 'r') do |f|
|
76
|
+
gz = Zlib::GzipReader.new(f)
|
77
|
+
content = gz.read
|
78
|
+
gz.close
|
79
|
+
end
|
80
|
+
else # others as is
|
81
|
+
File.open(complete_pathname, 'r') do |f|
|
82
|
+
content = f.read
|
83
|
+
end
|
84
|
+
end
|
85
|
+
content
|
86
|
+
end
|
87
|
+
|
88
|
+
# returns the stored content corresponding to +uri+ URI. In case there
|
89
|
+
# isn't any file it returns nil.
|
90
|
+
def read_uri(uri, filext=nil)
|
91
|
+
filext = @file_ext unless filext
|
92
|
+
pathname = @up.uri_to_pathname(uri,nil,filext)
|
93
|
+
read_pathname(pathname)
|
94
|
+
end
|
95
|
+
|
96
|
+
private
|
97
|
+
|
98
|
+
# creates +directory+ if it doesn't exist
|
99
|
+
def mkdir_if_not_exists(directory)
|
100
|
+
dir = File.expand_path(directory)
|
101
|
+
FileUtils.mkdir_p(dir) unless (File.exist?(dir) and File.directory?(dir))
|
102
|
+
end
|
103
|
+
|
104
|
+
end
|
@@ -0,0 +1,47 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require 'web_dump'
|
3
|
+
require 'fileutils'
|
4
|
+
|
5
|
+
class TC_WebDump < Test::Unit::TestCase
|
6
|
+
|
7
|
+
TEST_DIR = '~/tmp/web_dump'
|
8
|
+
|
9
|
+
# called before every test
|
10
|
+
def setup
|
11
|
+
FileUtils.remove_dir(File.expand_path(TEST_DIR), true)
|
12
|
+
@wd = WebDump.new :base_dir => TEST_DIR
|
13
|
+
end
|
14
|
+
|
15
|
+
# called after every test
|
16
|
+
def teardown
|
17
|
+
FileUtils.remove_dir(File.expand_path(TEST_DIR), true)
|
18
|
+
end
|
19
|
+
|
20
|
+
def test_automatic_dir_and_file_creation
|
21
|
+
wd = WebDump.new :base_dir => TEST_DIR, :host_sep => '/'
|
22
|
+
pathname = wd.save 'http://www.fake.fak/fakpath', 'Hello World!'
|
23
|
+
assert(File.exist?(pathname))
|
24
|
+
end
|
25
|
+
|
26
|
+
def test_raw_file_sr_cycle
|
27
|
+
input = 'Hello World!'
|
28
|
+
uri = 'http://www.com/prova'
|
29
|
+
pathname = @wd.save(uri,input)
|
30
|
+
output = @wd.read_pathname(pathname)
|
31
|
+
assert_equal input, output, "retrieved through pathname"
|
32
|
+
output = @wd.read_uri(uri)
|
33
|
+
assert_equal input, output, "retrieved through uri"
|
34
|
+
end
|
35
|
+
|
36
|
+
def test_gzipped_file_sr_cycle
|
37
|
+
input = 'Hello World!'
|
38
|
+
uri = 'http://www.com/prova'
|
39
|
+
pathname = @wd.save(uri,input,".gz")
|
40
|
+
output = @wd.read_pathname(pathname)
|
41
|
+
assert_equal input, output, "retrieved through pathname"
|
42
|
+
output = @wd.read_uri(uri,"gz")
|
43
|
+
assert_equal input, output, "retrieved through uri"
|
44
|
+
end
|
45
|
+
|
46
|
+
|
47
|
+
end
|
data/web_dump.gemspec
ADDED
@@ -0,0 +1,50 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = "web_dump"
|
8
|
+
s.version = "0.0.1.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Marcel Massana"]
|
12
|
+
s.date = "2011-08-31"
|
13
|
+
s.description = "Saves and Retrieves data given an URI. The filename will be automatically choosed using that URI freeing the user to think about that"
|
14
|
+
s.email = "xaxaupua@gmail.com"
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.rdoc"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
".goutputstream-6QBL0V",
|
22
|
+
".goutputstream-6X1P0V",
|
23
|
+
".goutputstream-IR2O0V",
|
24
|
+
".goutputstream-TK420V",
|
25
|
+
"LICENSE",
|
26
|
+
"README.rdoc",
|
27
|
+
"Rakefile",
|
28
|
+
"lib/web_dump.rb",
|
29
|
+
"lib/web_dump/version.rb",
|
30
|
+
"test/test_web_dump.rb",
|
31
|
+
"web_dump.gemspec"
|
32
|
+
]
|
33
|
+
s.homepage = "http://github.com/syborg/web_dump"
|
34
|
+
s.require_paths = ["lib"]
|
35
|
+
s.rubygems_version = "1.8.10"
|
36
|
+
s.summary = "Saves and Retrieves data in files given an URI"
|
37
|
+
|
38
|
+
if s.respond_to? :specification_version then
|
39
|
+
s.specification_version = 3
|
40
|
+
|
41
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
42
|
+
s.add_runtime_dependency(%q<uri_pathname>, [">= 0"])
|
43
|
+
else
|
44
|
+
s.add_dependency(%q<uri_pathname>, [">= 0"])
|
45
|
+
end
|
46
|
+
else
|
47
|
+
s.add_dependency(%q<uri_pathname>, [">= 0"])
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
metadata
ADDED
@@ -0,0 +1,87 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: web_dump
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 75
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 1
|
10
|
+
- 0
|
11
|
+
version: 0.0.1.0
|
12
|
+
platform: ruby
|
13
|
+
authors:
|
14
|
+
- Marcel Massana
|
15
|
+
autorequire:
|
16
|
+
bindir: bin
|
17
|
+
cert_chain: []
|
18
|
+
|
19
|
+
date: 2011-08-31 00:00:00 Z
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: uri_pathname
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 3
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
version: "0"
|
33
|
+
type: :runtime
|
34
|
+
version_requirements: *id001
|
35
|
+
description: Saves and Retrieves data given an URI. The filename will be automatically choosed using that URI freeing the user to think about that
|
36
|
+
email: xaxaupua@gmail.com
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files:
|
42
|
+
- LICENSE
|
43
|
+
- README.rdoc
|
44
|
+
files:
|
45
|
+
- .document
|
46
|
+
- LICENSE
|
47
|
+
- README.rdoc
|
48
|
+
- Rakefile
|
49
|
+
- lib/web_dump.rb
|
50
|
+
- lib/web_dump/version.rb
|
51
|
+
- test/test_web_dump.rb
|
52
|
+
- web_dump.gemspec
|
53
|
+
homepage: http://github.com/syborg/web_dump
|
54
|
+
licenses: []
|
55
|
+
|
56
|
+
post_install_message:
|
57
|
+
rdoc_options: []
|
58
|
+
|
59
|
+
require_paths:
|
60
|
+
- lib
|
61
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
62
|
+
none: false
|
63
|
+
requirements:
|
64
|
+
- - ">="
|
65
|
+
- !ruby/object:Gem::Version
|
66
|
+
hash: 3
|
67
|
+
segments:
|
68
|
+
- 0
|
69
|
+
version: "0"
|
70
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
71
|
+
none: false
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
hash: 3
|
76
|
+
segments:
|
77
|
+
- 0
|
78
|
+
version: "0"
|
79
|
+
requirements: []
|
80
|
+
|
81
|
+
rubyforge_project:
|
82
|
+
rubygems_version: 1.8.10
|
83
|
+
signing_key:
|
84
|
+
specification_version: 3
|
85
|
+
summary: Saves and Retrieves data in files given an URI
|
86
|
+
test_files: []
|
87
|
+
|