image_downloader 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE.txt +20 -0
- data/README.rdoc +19 -0
- data/bin/download_any_images +9 -0
- data/bin/download_icon +9 -0
- data/bin/download_images +9 -0
- data/lib/image_downloader.rb +82 -0
- data/lib/image_downloader/arguments.rb +27 -0
- data/lib/image_downloader/download.rb +23 -0
- data/lib/image_downloader/images.rb +61 -0
- data/lib/image_downloader/parser.rb +111 -0
- data/lib/image_downloader/url.rb +18 -0
- metadata +155 -0
data/LICENSE.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2011 Malykh Oleg
|
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 +1,19 @@
|
|
1
|
+
= image_downloader
|
2
|
+
|
3
|
+
Description goes here.
|
4
|
+
|
5
|
+
== Contributing to image_downloader
|
6
|
+
|
7
|
+
* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
|
8
|
+
* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
|
9
|
+
* Fork the project
|
10
|
+
* Start a feature/bugfix branch
|
11
|
+
* Commit and push until you are happy with your contribution
|
12
|
+
* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
|
13
|
+
* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
|
14
|
+
|
15
|
+
== Copyright
|
16
|
+
|
17
|
+
Copyright (c) 2011 Malykh Oleg. See LICENSE.txt for
|
18
|
+
further details.
|
19
|
+
|
data/bin/download_icon
ADDED
data/bin/download_images
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
# gems
|
2
|
+
require 'nokogiri'
|
3
|
+
# core lib
|
4
|
+
require 'open-uri'
|
5
|
+
require 'thread'
|
6
|
+
require 'uri'
|
7
|
+
require 'net/http'
|
8
|
+
require 'optparse'
|
9
|
+
# local lib
|
10
|
+
require 'image_downloader/images'
|
11
|
+
require 'image_downloader/url'
|
12
|
+
require 'image_downloader/arguments'
|
13
|
+
require 'image_downloader/parser'
|
14
|
+
require 'image_downloader/download'
|
15
|
+
|
16
|
+
module ImageDownloader
|
17
|
+
|
18
|
+
options = {}
|
19
|
+
OptionParser.new do |opts|
|
20
|
+
opts.on("-d", "--debug", "Run debug mode") do |d|
|
21
|
+
options[:debug] = d
|
22
|
+
$debug_option = true
|
23
|
+
end
|
24
|
+
end.parse!
|
25
|
+
|
26
|
+
class Process
|
27
|
+
attr_accessor :argument, :images
|
28
|
+
|
29
|
+
def initialize(url, path)
|
30
|
+
@argument = Arguments.new(url, path)
|
31
|
+
@argument.check
|
32
|
+
@argument.normalize
|
33
|
+
@images = []
|
34
|
+
end
|
35
|
+
|
36
|
+
# :any_looks_like_image => true
|
37
|
+
# :ignore_without => {:(extension|image_extension) => true}
|
38
|
+
# Nokogiri gem is required:
|
39
|
+
# :collect => {:all => true, :(img_src|a_href|style_url|link_icon) => true},
|
40
|
+
def parse(h={:collect => {}, :ignore_without => {}})
|
41
|
+
self.rebuild_collect_hash(h)
|
42
|
+
|
43
|
+
parser = Parser.new(self.argument.url)
|
44
|
+
if h[:any_looks_like_image]
|
45
|
+
parser.get_content_raw
|
46
|
+
parser.get_images_raw(self.argument.path, h[:collect])
|
47
|
+
else
|
48
|
+
parser.get_content
|
49
|
+
parser.get_images(self.argument.path, h[:collect])
|
50
|
+
end
|
51
|
+
|
52
|
+
parser.ignore_file_without(h[:ignore_without])
|
53
|
+
|
54
|
+
self.images = parser.images
|
55
|
+
end
|
56
|
+
|
57
|
+
# :(parallel|consequentially)
|
58
|
+
def download(*args)
|
59
|
+
if !args.first || args.first == :parallel
|
60
|
+
Download.parallel(self.images)
|
61
|
+
elsif args.first == :consequentially
|
62
|
+
Download.consequentially(self.images)
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
protected
|
67
|
+
|
68
|
+
def rebuild_collect_hash(h={})
|
69
|
+
if !h[:collect] || h[:collect].empty? || h[:collect][:all]
|
70
|
+
h[:collect] = Parser.all_image_places
|
71
|
+
else
|
72
|
+
collect_new = {}
|
73
|
+
h[:collect].each_key{|k|
|
74
|
+
collect_new[(Parser::COLLECT_METHODS_PREFIX + k.to_s).to_sym] = true
|
75
|
+
}
|
76
|
+
h[:collect].merge!(collect_new)
|
77
|
+
h[:collect].delete_if{|k,v| !Parser.all_image_places.has_key?(k)}
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
end
|
82
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module ImageDownloader
|
2
|
+
class Arguments
|
3
|
+
attr_accessor :url, :path
|
4
|
+
|
5
|
+
def initialize(url, path)
|
6
|
+
@url = url
|
7
|
+
@path = path
|
8
|
+
end
|
9
|
+
|
10
|
+
def check
|
11
|
+
if !self.url
|
12
|
+
p "Not specified url"
|
13
|
+
exit
|
14
|
+
end
|
15
|
+
if !self.path
|
16
|
+
p "Not specified path"
|
17
|
+
exit
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
def normalize
|
22
|
+
self.url = URL.normalize(self.url)
|
23
|
+
self.path = self.path.gsub(/\/+$/,'')
|
24
|
+
end
|
25
|
+
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
module ImageDownloader
|
2
|
+
class Download
|
3
|
+
|
4
|
+
def self.parallel(images)
|
5
|
+
threads = []
|
6
|
+
for image in images
|
7
|
+
threads << Thread.new(image) {|local_image|
|
8
|
+
p "upload from url #{local_image.absolute_src} to file #{local_image.file_name}" if $debug_option
|
9
|
+
local_image.download
|
10
|
+
}
|
11
|
+
end
|
12
|
+
threads.each { |aThread| aThread.join }
|
13
|
+
end
|
14
|
+
|
15
|
+
def self.consequentially(images)
|
16
|
+
for image in images
|
17
|
+
p "upload from url #{image.absolute_src} to file #{image.file_name}" if $debug_option
|
18
|
+
image.download
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,61 @@
|
|
1
|
+
module ImageDownloader
|
2
|
+
class Images
|
3
|
+
attr_accessor :src, :file_name, :page_host, :absolute_src, :file_path_name
|
4
|
+
|
5
|
+
MAX_FILE_NAME_LENGTH_ALLOWED = 200
|
6
|
+
IMAGE_EXTENSIONS = ["jpg","jpeg","png","gif","ico","svg","bmp"]
|
7
|
+
EMPTY_FILE_NAME = 'EMPTY_'
|
8
|
+
|
9
|
+
def initialize(page_host,src,h = {})
|
10
|
+
@page_host = page_host
|
11
|
+
@src = src
|
12
|
+
|
13
|
+
# for fix Errno::ENAMETOOLONG & empty file name
|
14
|
+
file_name_suffix = @src.sub(/.*\//,'')
|
15
|
+
file_name_suffix = EMPTY_FILE_NAME + rand(100000).to_s if !file_name_suffix || file_name_suffix.empty?
|
16
|
+
if file_name_suffix.size > MAX_FILE_NAME_LENGTH_ALLOWED
|
17
|
+
file_name_suffix = file_name_suffix[-MAX_FILE_NAME_LENGTH_ALLOWED..file_name_suffix.size]
|
18
|
+
end
|
19
|
+
|
20
|
+
@file_name = h[:file_name_prefix] + file_name_suffix
|
21
|
+
@file_path_name = h[:catalog_path] + '/' + @file_name
|
22
|
+
@absolute_src = ((@src =~ /http/) ? @src : ('http://' + page_host + '/' + @src))
|
23
|
+
end
|
24
|
+
|
25
|
+
def download
|
26
|
+
url = URI.parse(self.absolute_src)
|
27
|
+
request = Net::HTTP::Get.new(url.path)
|
28
|
+
Net::HTTP.start(url.host) {|http|
|
29
|
+
# for exclude 403 and 404 errors from web servers (e.g. detect current client as script)
|
30
|
+
# you can use:
|
31
|
+
# - watir (with js support and other ...), but vary vary slow
|
32
|
+
# - mechanize (main web client), slow
|
33
|
+
# - wget, quick, but cannot support some ability (403, 404 responses)
|
34
|
+
# - sockets, independent request, quick, but low-level (many lines of code)
|
35
|
+
self.download_by_segment(http,request)
|
36
|
+
# self.download_simple(http,request)
|
37
|
+
}
|
38
|
+
end
|
39
|
+
|
40
|
+
def download_by_segment(http,request)
|
41
|
+
file = open(self.file_path_name, "wb")
|
42
|
+
begin
|
43
|
+
http.request_get(request.path, "User-Agent"=> "Mozilla/5.0") do |response|
|
44
|
+
response.read_body do |segment|
|
45
|
+
file.write(segment)
|
46
|
+
end
|
47
|
+
end
|
48
|
+
ensure
|
49
|
+
file.close()
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def download_simple(http,request)
|
54
|
+
response = http.get(request.path, "User-Agent"=> "Mozilla/5.0")
|
55
|
+
open(self.file_path_name, "wb") { |file|
|
56
|
+
file.write(response.body)
|
57
|
+
}
|
58
|
+
end
|
59
|
+
|
60
|
+
end
|
61
|
+
end
|
@@ -0,0 +1,111 @@
|
|
1
|
+
class Array
|
2
|
+
def to_hash_keys(&block)
|
3
|
+
Hash[*self.collect { |v|
|
4
|
+
[v, block.call(v)]
|
5
|
+
}.flatten]
|
6
|
+
end
|
7
|
+
|
8
|
+
def to_hash_values(&block)
|
9
|
+
Hash[*self.collect { |v|
|
10
|
+
[block.call(v), v]
|
11
|
+
}.flatten]
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
module ImageDownloader
|
16
|
+
class Parser
|
17
|
+
attr_accessor :url, :argument_url, :content, :images, :images_hash
|
18
|
+
|
19
|
+
A_HREF_IMAGE_PREFIX = '_a_href_'
|
20
|
+
STYLE_URL_IMAGE_PREFIX = '_style_url_'
|
21
|
+
LINK_ICON_IMAGE_PREFIX = '_link_icon_'
|
22
|
+
COLLECT_METHODS_PREFIX = 'collect_from_'
|
23
|
+
|
24
|
+
def initialize(url)
|
25
|
+
@argument_url = url
|
26
|
+
@url = URI.parse(url)
|
27
|
+
@images = []
|
28
|
+
@images_hash = {}
|
29
|
+
end
|
30
|
+
|
31
|
+
def get_content_raw
|
32
|
+
@content = open(self.argument_url).read
|
33
|
+
@content.gsub!(/[\n\r\t]+/,' ')
|
34
|
+
end
|
35
|
+
|
36
|
+
def get_images_raw(path,h={})
|
37
|
+
self.content.scan(/['"]+[^'"]+\.(?:#{Images::IMAGE_EXTENSIONS.join('|')})['"]+/).map{|src|
|
38
|
+
src.gsub!(/['"]/,'')
|
39
|
+
self.push_to_images(path,src)
|
40
|
+
}
|
41
|
+
end
|
42
|
+
|
43
|
+
def get_content
|
44
|
+
@content = Nokogiri::HTML(open(self.argument_url))
|
45
|
+
end
|
46
|
+
|
47
|
+
def get_images(path,h={})
|
48
|
+
h.each_key{|key| self.send(key, path)}
|
49
|
+
end
|
50
|
+
|
51
|
+
def collect_from_img_src(path)
|
52
|
+
self.content.xpath('//img').each do |img|
|
53
|
+
src = img[:src]
|
54
|
+
URL.remove_new_line_symbols!(src)
|
55
|
+
self.push_to_images(path,src)
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
def collect_from_a_href(path)
|
60
|
+
self.content.xpath('//a').each do |a|
|
61
|
+
href = a[:href]
|
62
|
+
URL.remove_new_line_symbols!(href)
|
63
|
+
next if href !~ /\.(?:#{Images::IMAGE_EXTENSIONS.join('|')})/i
|
64
|
+
self.push_to_images(path,href,{:file_name_prefix => A_HREF_IMAGE_PREFIX})
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
def collect_from_style_url(path)
|
69
|
+
self.content.xpath("//*[@style]").each do |element|
|
70
|
+
style = element[:style]
|
71
|
+
next if style !~ /(?:background|background-image):\s*url\(['"]?(.*?)['"]?\)/i
|
72
|
+
src = $1
|
73
|
+
next if !src
|
74
|
+
URL.remove_new_line_symbols!(src)
|
75
|
+
self.push_to_images(path,src,{:file_name_prefix => STYLE_URL_IMAGE_PREFIX})
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
def collect_from_link_icon(path)
|
80
|
+
self.content.xpath('//link[@rel="shortcut icon"]').each do |link|
|
81
|
+
src = link[:href]
|
82
|
+
URL.remove_new_line_symbols!(src)
|
83
|
+
self.push_to_images(path,src,{:file_name_prefix => LINK_ICON_IMAGE_PREFIX})
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
87
|
+
def push_to_images(path,src,h={})
|
88
|
+
if !self.images_hash.has_key?(src)
|
89
|
+
self.images_hash[src] = 1
|
90
|
+
self.images.push Images.new(self.url.host,URI.escape(src), {
|
91
|
+
:catalog_path => path,
|
92
|
+
:file_name_prefix => (h[:file_name_prefix] || '')})
|
93
|
+
end
|
94
|
+
end
|
95
|
+
|
96
|
+
def ignore_file_without(h={})
|
97
|
+
return if !h
|
98
|
+
self.images.delete_if {|image| image.file_name !~ /\.[a-z]{0,5}$/i } if h[:extension]
|
99
|
+
self.images.delete_if {|image| image.file_name !~ /\.(?:#{Images::IMAGE_EXTENSIONS.join('|')})$/i } if h[:image_extension]
|
100
|
+
end
|
101
|
+
|
102
|
+
def self.all_collect_from_methods
|
103
|
+
Parser.instance_methods.select{|m| m =~ /#{COLLECT_METHODS_PREFIX}/}.map{|m| m.to_sym}.to_hash_keys{true}
|
104
|
+
end
|
105
|
+
|
106
|
+
class << self
|
107
|
+
alias all_image_places all_collect_from_methods
|
108
|
+
end
|
109
|
+
|
110
|
+
end
|
111
|
+
end
|
@@ -0,0 +1,18 @@
|
|
1
|
+
module ImageDownloader
|
2
|
+
class URL
|
3
|
+
|
4
|
+
def self.contain_http?(url)
|
5
|
+
url =~ /^(http|https)/i ? true : false
|
6
|
+
end
|
7
|
+
|
8
|
+
def self.normalize(url)
|
9
|
+
contain_http?(url) ? url : 'http://' + url
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.remove_new_line_symbols!(str)
|
13
|
+
str.gsub!(/\r/,'') if str
|
14
|
+
str.gsub!(/\n/,'') if str
|
15
|
+
end
|
16
|
+
|
17
|
+
end
|
18
|
+
end
|
metadata
ADDED
@@ -0,0 +1,155 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: image_downloader
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease: false
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Malykh Oleg
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2011-07-15 00:00:00 +04:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
name: shoulda
|
25
|
+
version_requirements: &id001 !ruby/object:Gem::Requirement
|
26
|
+
none: false
|
27
|
+
requirements:
|
28
|
+
- - ">="
|
29
|
+
- !ruby/object:Gem::Version
|
30
|
+
hash: 3
|
31
|
+
segments:
|
32
|
+
- 0
|
33
|
+
version: "0"
|
34
|
+
requirement: *id001
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
type: :development
|
37
|
+
prerelease: false
|
38
|
+
name: bundler
|
39
|
+
version_requirements: &id002 !ruby/object:Gem::Requirement
|
40
|
+
none: false
|
41
|
+
requirements:
|
42
|
+
- - ~>
|
43
|
+
- !ruby/object:Gem::Version
|
44
|
+
hash: 23
|
45
|
+
segments:
|
46
|
+
- 1
|
47
|
+
- 0
|
48
|
+
- 0
|
49
|
+
version: 1.0.0
|
50
|
+
requirement: *id002
|
51
|
+
- !ruby/object:Gem::Dependency
|
52
|
+
type: :development
|
53
|
+
prerelease: false
|
54
|
+
name: jeweler
|
55
|
+
version_requirements: &id003 !ruby/object:Gem::Requirement
|
56
|
+
none: false
|
57
|
+
requirements:
|
58
|
+
- - ~>
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
hash: 7
|
61
|
+
segments:
|
62
|
+
- 1
|
63
|
+
- 6
|
64
|
+
- 4
|
65
|
+
version: 1.6.4
|
66
|
+
requirement: *id003
|
67
|
+
- !ruby/object:Gem::Dependency
|
68
|
+
type: :development
|
69
|
+
prerelease: false
|
70
|
+
name: rcov
|
71
|
+
version_requirements: &id004 !ruby/object:Gem::Requirement
|
72
|
+
none: false
|
73
|
+
requirements:
|
74
|
+
- - ">="
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
hash: 3
|
77
|
+
segments:
|
78
|
+
- 0
|
79
|
+
version: "0"
|
80
|
+
requirement: *id004
|
81
|
+
- !ruby/object:Gem::Dependency
|
82
|
+
type: :development
|
83
|
+
prerelease: false
|
84
|
+
name: nokogiri
|
85
|
+
version_requirements: &id005 !ruby/object:Gem::Requirement
|
86
|
+
none: false
|
87
|
+
requirements:
|
88
|
+
- - ">="
|
89
|
+
- !ruby/object:Gem::Version
|
90
|
+
hash: 15
|
91
|
+
segments:
|
92
|
+
- 1
|
93
|
+
- 4
|
94
|
+
- 4
|
95
|
+
version: 1.4.4
|
96
|
+
requirement: *id005
|
97
|
+
description: Detailed description for image-downloader
|
98
|
+
email: malykholeg@gmail.com
|
99
|
+
executables:
|
100
|
+
- download_any_images
|
101
|
+
- download_images
|
102
|
+
- download_icon
|
103
|
+
extensions: []
|
104
|
+
|
105
|
+
extra_rdoc_files:
|
106
|
+
- LICENSE.txt
|
107
|
+
- README.rdoc
|
108
|
+
files:
|
109
|
+
- lib/image_downloader.rb
|
110
|
+
- lib/image_downloader/arguments.rb
|
111
|
+
- lib/image_downloader/download.rb
|
112
|
+
- lib/image_downloader/images.rb
|
113
|
+
- lib/image_downloader/parser.rb
|
114
|
+
- lib/image_downloader/url.rb
|
115
|
+
- LICENSE.txt
|
116
|
+
- README.rdoc
|
117
|
+
- bin/download_any_images
|
118
|
+
- bin/download_images
|
119
|
+
- bin/download_icon
|
120
|
+
has_rdoc: true
|
121
|
+
homepage: http://github.com/Fotom/image_downloader
|
122
|
+
licenses:
|
123
|
+
- MIT
|
124
|
+
post_install_message:
|
125
|
+
rdoc_options: []
|
126
|
+
|
127
|
+
require_paths:
|
128
|
+
- lib
|
129
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
130
|
+
none: false
|
131
|
+
requirements:
|
132
|
+
- - ">="
|
133
|
+
- !ruby/object:Gem::Version
|
134
|
+
hash: 3
|
135
|
+
segments:
|
136
|
+
- 0
|
137
|
+
version: "0"
|
138
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
139
|
+
none: false
|
140
|
+
requirements:
|
141
|
+
- - ">="
|
142
|
+
- !ruby/object:Gem::Version
|
143
|
+
hash: 3
|
144
|
+
segments:
|
145
|
+
- 0
|
146
|
+
version: "0"
|
147
|
+
requirements: []
|
148
|
+
|
149
|
+
rubyforge_project:
|
150
|
+
rubygems_version: 1.3.7
|
151
|
+
signing_key:
|
152
|
+
specification_version: 3
|
153
|
+
summary: Parsing web page, finding images in specified locations and downloading them simultaneously or sequentially
|
154
|
+
test_files: []
|
155
|
+
|