tomosia_wallhere_crawl 0.1.0 → 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile +3 -0
- data/Gemfile.lock +45 -0
- data/README.md +9 -1
- data/Rakefile +8 -0
- data/exe/tomosia_wallhere_crawl +4 -0
- data/lib/tomosia_wallhere_crawl.rb +64 -44
- data/lib/tomosia_wallhere_crawl/cli.rb +17 -0
- data/lib/tomosia_wallhere_crawl/version.rb +1 -1
- data/pkg/tomosia_wallhere_crawl-0.1.1.gem +0 -0
- data/tomosia_wallhere_crawl-0.1.0.gem +0 -0
- data/tomosia_wallhere_crawl.gemspec +11 -6
- metadata +94 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a6c61da5b1321f6aedfbcd3ba4dba8e5fb101ec4f36ca4e6c974e1f26ab01cf7
|
4
|
+
data.tar.gz: 8b3d0be435727d25a4773a02b57d8f063bba8bb7b1a550724306dedf3003de39
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6a5064bca8a988c533b110ed2b31c6f7b264030dfd4fd7ecc1766dec801096bc85c9bf374157b21bd08f2b9fee1ed9743ed7aeea845e8195b85ee30490d3280f
|
7
|
+
data.tar.gz: b07d631fa4d6c33806e91641688cda81f872ebdfa9a77fc7af830eed579aaf9e1315bdf7ce623680263fa531e94bdac0f7ba0af67597880b0e92363f5bd3cbd0
|
data/Gemfile
CHANGED
data/Gemfile.lock
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
tomosia_wallhere_crawl (0.1.1)
|
5
|
+
nokogiri
|
6
|
+
thor
|
7
|
+
writeexcel
|
8
|
+
|
9
|
+
GEM
|
10
|
+
remote: https://rubygems.org/
|
11
|
+
specs:
|
12
|
+
diff-lcs (1.4.4)
|
13
|
+
mini_portile2 (2.4.0)
|
14
|
+
nokogiri (1.10.10)
|
15
|
+
mini_portile2 (~> 2.4.0)
|
16
|
+
rake (12.3.3)
|
17
|
+
rspec (3.9.0)
|
18
|
+
rspec-core (~> 3.9.0)
|
19
|
+
rspec-expectations (~> 3.9.0)
|
20
|
+
rspec-mocks (~> 3.9.0)
|
21
|
+
rspec-core (3.9.2)
|
22
|
+
rspec-support (~> 3.9.3)
|
23
|
+
rspec-expectations (3.9.2)
|
24
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
25
|
+
rspec-support (~> 3.9.0)
|
26
|
+
rspec-mocks (3.9.1)
|
27
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
28
|
+
rspec-support (~> 3.9.0)
|
29
|
+
rspec-support (3.9.3)
|
30
|
+
thor (1.0.1)
|
31
|
+
writeexcel (1.0.5)
|
32
|
+
|
33
|
+
PLATFORMS
|
34
|
+
ruby
|
35
|
+
|
36
|
+
DEPENDENCIES
|
37
|
+
bundler
|
38
|
+
nokogiri (~> 1.10, >= 1.10.10)
|
39
|
+
rake (~> 12.0)
|
40
|
+
rspec (~> 3.0)
|
41
|
+
tomosia_wallhere_crawl!
|
42
|
+
writeexcel (~> 1.0, >= 1.0.5)
|
43
|
+
|
44
|
+
BUNDLED WITH
|
45
|
+
2.1.4
|
data/README.md
CHANGED
@@ -21,9 +21,17 @@ Or install it yourself as:
|
|
21
21
|
$ gem install tomosia_wallhere_crawl
|
22
22
|
|
23
23
|
## Usage
|
24
|
+
_NOTE: key = "tag" , destination: "url saving" , max :number image
|
24
25
|
|
25
|
-
|
26
|
+
_/ Crawl all image in tag!
|
27
|
+
tomosia_wallhere_crawl crawl "key" --destination " "
|
28
|
+
=> tomosia_wallhere_crawl crawl "aaa" --destination "/home/tung/Desktop/img/"
|
26
29
|
|
30
|
+
_/ Crawl all images in tag with number of images!
|
31
|
+
tomosia_wallhere_crawl crawl "key" --destination " " --max
|
32
|
+
=> tomosia_wallhere_crawl crawl "aaa" --destination "/home/tung/Desktop/img/" --max=100
|
33
|
+
|
34
|
+
File save info images of tag in destination
|
27
35
|
## Development
|
28
36
|
|
29
37
|
After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
data/Rakefile
CHANGED
@@ -1,10 +1,12 @@
|
|
1
1
|
require 'open-uri'
|
2
2
|
require 'nokogiri'
|
3
3
|
require 'writeexcel'
|
4
|
+
require 'thor'
|
4
5
|
module TomosiaWallhereCrawl
|
5
6
|
class CrawlImage
|
6
|
-
|
7
|
-
|
7
|
+
|
8
|
+
def savedata (data = {}, destination)
|
9
|
+
workbook = WriteExcel.new("#{destination}/InfoImage.xls")
|
8
10
|
worksheet = workbook.add_worksheet
|
9
11
|
data.each_with_index do |row, stt|
|
10
12
|
row.each do |key, value|
|
@@ -14,13 +16,14 @@ module TomosiaWallhereCrawl
|
|
14
16
|
worksheet.write_string(stt, 3, row['size'])
|
15
17
|
end
|
16
18
|
end
|
17
|
-
|
19
|
+
workbook.close
|
20
|
+
puts "Save successfully"
|
18
21
|
end
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
+
|
23
|
+
def crawldata(key,destination,max=nil)
|
22
24
|
sum = 0
|
23
|
-
|
25
|
+
index = 1
|
26
|
+
images = []
|
24
27
|
while sum != max do
|
25
28
|
# Open url
|
26
29
|
url = "https://wallhere.com/en/wallpapers?q=#{key}&page=#{index}"
|
@@ -28,45 +31,62 @@ module TomosiaWallhereCrawl
|
|
28
31
|
content = document.read
|
29
32
|
parsed_content = Nokogiri::HTML(content)
|
30
33
|
length = parsed_content.css('.item').to_a.length - 1
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
34
|
+
total_img = parsed_content.css('div.hub-totalinfo').text.split(' HD Wallpapers')[0].to_i
|
35
|
+
if max == nil || max > total_img
|
36
|
+
max = total_img
|
37
|
+
puts "This tag has #{total_img} pictures"
|
38
|
+
end
|
39
|
+
i = 0
|
35
40
|
for i in i..length
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
size = File.size("#{description}#{nameimg}")
|
47
|
-
s = "#{size} kb"
|
48
|
-
row = {'stt'=>i, 'name'=>n, 'url'=>ui, 'extension'=>ex, 'size'=>s}
|
49
|
-
data.push(row)
|
50
|
-
end
|
51
|
-
end
|
52
|
-
sum += 1
|
53
|
-
if max == sum
|
54
|
-
break
|
55
|
-
end
|
56
|
-
end
|
41
|
+
urlimg = parsed_content.css('.item').to_a[i].children.children.first.to_h['src']
|
42
|
+
images.push(urlimg)
|
43
|
+
|
44
|
+
print '.'
|
45
|
+
sum += 1
|
46
|
+
if max == sum
|
47
|
+
break
|
48
|
+
end
|
49
|
+
end
|
50
|
+
index += 1
|
57
51
|
end
|
58
|
-
|
52
|
+
download(images,destination)
|
53
|
+
end
|
54
|
+
|
55
|
+
def download(images,destination)
|
56
|
+
data = []
|
57
|
+
row = {}
|
58
|
+
thread = []
|
59
|
+
images.each do |img|
|
60
|
+
thread << Thread.new(img) do
|
61
|
+
timeout = 0
|
62
|
+
begin
|
63
|
+
open(img) do |image|
|
64
|
+
nameimg = File.basename(img,".jpg!s")
|
65
|
+
ui = img
|
66
|
+
ex = File.extname(img).delete('.!s')
|
67
|
+
size = ""
|
68
|
+
File.open("#{destination}#{nameimg}","wb") do |file|
|
69
|
+
file.write(image.read)
|
70
|
+
size = image.size
|
71
|
+
end
|
72
|
+
size = size.to_s + " bytes"
|
73
|
+
row = {"name"=>nameimg, "url"=>ui, "extension"=> ex, "size" => size}
|
74
|
+
data.push(row)
|
75
|
+
end
|
76
|
+
rescue => exception
|
77
|
+
if timeout < 3
|
78
|
+
timeout += 1
|
79
|
+
retry
|
80
|
+
else
|
81
|
+
next
|
82
|
+
end
|
83
|
+
end
|
59
84
|
end
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
crawldata(key,description,max)
|
66
|
-
end
|
67
|
-
end
|
68
|
-
mutithread.map(&:join)
|
69
|
-
end
|
85
|
+
end
|
86
|
+
thread.each {|t| t.join}
|
87
|
+
puts " "
|
88
|
+
puts "Download successfully"
|
89
|
+
savedata(data,destination)
|
70
90
|
end
|
71
91
|
end
|
72
|
-
|
92
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'thor'
|
2
|
+
require_relative '../tomosia_wallhere_crawl'
|
3
|
+
|
4
|
+
module TomosiaWallhereCrawl
|
5
|
+
class Cli < Thor
|
6
|
+
desc "crawl KEYWORD", "enter KEYWORD to search"
|
7
|
+
option :destination
|
8
|
+
option :max
|
9
|
+
def crawl(keyword)
|
10
|
+
if options[:max] == nil
|
11
|
+
TomosiaWallhereCrawl::CrawlImage.new.crawldata(keyword, options[:destination], options[:max])
|
12
|
+
else
|
13
|
+
TomosiaWallhereCrawl::CrawlImage.new.crawldata(keyword, options[:destination], options[:max].to_i)
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
Binary file
|
Binary file
|
@@ -11,12 +11,17 @@ Gem::Specification.new do |spec|
|
|
11
11
|
spec.homepage = "https://github.com/nguyensontung183183/tomosia_wallhere_crawl.git"
|
12
12
|
spec.license = "MIT"
|
13
13
|
spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
|
14
|
-
|
15
|
-
|
16
|
-
spec.files =
|
17
|
-
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
-
end
|
14
|
+
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split("\n")
|
19
17
|
spec.bindir = "exe"
|
20
|
-
spec.executables =
|
18
|
+
spec.executables = ["tomosia_wallhere_crawl"]
|
21
19
|
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_runtime_dependency 'thor'
|
22
|
+
spec.add_runtime_dependency 'nokogiri'
|
23
|
+
spec.add_runtime_dependency 'writeexcel'
|
24
|
+
spec.add_development_dependency "bundler"
|
25
|
+
spec.add_development_dependency "rake"
|
26
|
+
spec.add_development_dependency "rspec"
|
22
27
|
end
|
metadata
CHANGED
@@ -1,31 +1,121 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: tomosia_wallhere_crawl
|
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
|
- nguyen son tung
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-08-
|
12
|
-
dependencies:
|
11
|
+
date: 2020-08-09 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: thor
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: nokogiri
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
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: writeexcel
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
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: bundler
|
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'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: rspec
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
13
97
|
description: Write a longer description or delete this line.
|
14
98
|
email:
|
15
99
|
- nguyensontung18183
|
16
|
-
executables:
|
100
|
+
executables:
|
101
|
+
- tomosia_wallhere_crawl
|
17
102
|
extensions: []
|
18
103
|
extra_rdoc_files: []
|
19
104
|
files:
|
20
105
|
- CODE_OF_CONDUCT.md
|
21
106
|
- Gemfile
|
107
|
+
- Gemfile.lock
|
22
108
|
- LICENSE.txt
|
23
109
|
- README.md
|
24
110
|
- Rakefile
|
25
111
|
- bin/console
|
26
112
|
- bin/setup
|
113
|
+
- exe/tomosia_wallhere_crawl
|
27
114
|
- lib/tomosia_wallhere_crawl.rb
|
115
|
+
- lib/tomosia_wallhere_crawl/cli.rb
|
28
116
|
- lib/tomosia_wallhere_crawl/version.rb
|
117
|
+
- pkg/tomosia_wallhere_crawl-0.1.1.gem
|
118
|
+
- tomosia_wallhere_crawl-0.1.0.gem
|
29
119
|
- tomosia_wallhere_crawl.gemspec
|
30
120
|
homepage: https://github.com/nguyensontung183183/tomosia_wallhere_crawl.git
|
31
121
|
licenses:
|