tomosia_amanaplus_crawl 0.1.7 → 0.2.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +3 -1
- data/README.md +2 -2
- data/Rakefile +6 -0
- data/exe/tomosia_amanaplus_crawl +5 -0
- data/lib/tomosia_amanaplus_crawl.rb +22 -18
- data/lib/tomosia_amanaplus_crawl/cli.rb +14 -0
- data/lib/tomosia_amanaplus_crawl/version.rb +1 -1
- data/spec/spec_helper.rb +14 -0
- data/spec/tomosia_amanaplus_crawl_spec.rb +9 -0
- data/tomosia_amanaplus_crawl.gemspec +4 -5
- metadata +20 -15
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: e3bc628d6f82c6357d3a4362464870e6e1ac3bc696ad7bc3f91fd7fd5901b7fe
|
4
|
+
data.tar.gz: 7184c0c7edaecb96312ab0650fb4395cc02d50175e51c0d35ce2600e6c9ac61b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: ab5bc7f49db71fb490d1cf99da244c1321edcf98aec5678415229f4faf6a29fa5edd2589d8abf90b66790e142c1ef276a8e24bb65755c6b2eb5f2ea805dff1f6
|
7
|
+
data.tar.gz: b89334b70ee3693add75baa2e49bff8e2b968c1caac0d21adea45c41a31984b21e713127d8412cde046a478d714da2bd3a9186e0838923c964262967c1f60bf4
|
data/Gemfile.lock
CHANGED
@@ -1,10 +1,11 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
tomosia_amanaplus_crawl (0.1.
|
4
|
+
tomosia_amanaplus_crawl (0.1.8)
|
5
5
|
httparty (= 0.18.1)
|
6
6
|
nokogiri (= 1.10.10)
|
7
7
|
spreadsheet (= 1.2.6)
|
8
|
+
thor
|
8
9
|
|
9
10
|
GEM
|
10
11
|
remote: https://rubygems.org/
|
@@ -37,6 +38,7 @@ GEM
|
|
37
38
|
ruby-ole (1.2.12.2)
|
38
39
|
spreadsheet (1.2.6)
|
39
40
|
ruby-ole (>= 1.0)
|
41
|
+
thor (1.0.1)
|
40
42
|
|
41
43
|
PLATFORMS
|
42
44
|
ruby
|
data/README.md
CHANGED
@@ -23,9 +23,9 @@ Or install it yourself as:
|
|
23
23
|
## Usage
|
24
24
|
|
25
25
|
```ruby
|
26
|
-
|
27
|
-
TomosiaAmanaplusCrawl::Crawler.new.run(keyword, path, max)
|
26
|
+
tomosia_amanaplus_crawl crawl "keyword" --destination "/home/usr/Documents" --max=123
|
28
27
|
```
|
28
|
+
Example: tomosia_amanaplus_crawl crawl "hoian" --destination "./" --max=123
|
29
29
|
keyword: hoian, danang, ...
|
30
30
|
path: './', '/desktop/', ...
|
31
31
|
max: số lượng ảnh muốn lấy về. Nếu max lớn hơn tổng số ảnh các page thì vẫn lấy hết tất cả ảnh
|
data/Rakefile
CHANGED
@@ -2,16 +2,15 @@ require "tomosia_amanaplus_crawl/version"
|
|
2
2
|
|
3
3
|
module TomosiaAmanaplusCrawl
|
4
4
|
require 'nokogiri'
|
5
|
-
require 'httparty'
|
6
5
|
require 'open-uri'
|
7
6
|
require 'fileutils'
|
8
7
|
require 'spreadsheet'
|
9
8
|
|
10
9
|
class Crawler
|
11
|
-
URL = "https://plus.amanaimages.com/items/search
|
10
|
+
URL = "https://plus.amanaimages.com/items/search"
|
12
11
|
|
13
12
|
def run(keyword, destination, max)
|
14
|
-
unparsed_page =
|
13
|
+
unparsed_page = open("#{URL}/#{keyword}").read
|
15
14
|
parsed_page = Nokogiri::HTML(unparsed_page)
|
16
15
|
|
17
16
|
pages = parsed_page.css("div.c-paginate__nums").css('a').last.text.to_i # tổng số page
|
@@ -19,7 +18,7 @@ module TomosiaAmanaplusCrawl
|
|
19
18
|
|
20
19
|
# lấy tổng số image
|
21
20
|
total = parsed_page.css("h1.p-search-result__ttl").text.split(' ').first
|
22
|
-
total = total[
|
21
|
+
total = total[(6 + keyword.length)..(total.length - 1)].chop.chop.chop.gsub(',', '').to_i
|
23
22
|
if max > total # nếu max lớn hơn total thì max = total => vẫn lấy hết
|
24
23
|
max = total
|
25
24
|
end
|
@@ -36,7 +35,7 @@ module TomosiaAmanaplusCrawl
|
|
36
35
|
while curr_page <= pages
|
37
36
|
puts "Crawling page #{curr_page}..........."
|
38
37
|
|
39
|
-
pagination_unparsed_page =
|
38
|
+
pagination_unparsed_page = open("#{URL}/#{keyword}?page=#{curr_page}").read
|
40
39
|
pagination_parsed_page = Nokogiri::HTML(pagination_unparsed_page)
|
41
40
|
pagination_images_listings = pagination_parsed_page.css("div.p-item-thumb")
|
42
41
|
|
@@ -63,20 +62,30 @@ module TomosiaAmanaplusCrawl
|
|
63
62
|
|
64
63
|
# tải hình và cập nhật lại size
|
65
64
|
def downloadImages(images, destination)
|
66
|
-
path = "#{destination}
|
65
|
+
path = "#{destination}//Downloads" # lưu hình ở folder Downloads
|
67
66
|
Dir.mkdir path unless File.exist? path
|
68
67
|
|
69
68
|
threads = []
|
70
69
|
print "\nDownloading"
|
71
70
|
images.each do |curr_image|
|
72
71
|
threads << Thread.new(curr_image) {
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
curr_image[:
|
77
|
-
|
72
|
+
timeout = 0
|
73
|
+
begin
|
74
|
+
URI.open(curr_image[:url]) do |image|
|
75
|
+
File.open("#{path}/#{curr_image[:url].split('/').last}", "a+") do |file|
|
76
|
+
file.write(image.read) # lưu hình ảnh
|
77
|
+
curr_image[:size] = image.size # cập nhật lại size trong mảng images
|
78
|
+
print "."
|
79
|
+
end
|
80
|
+
end # end open
|
81
|
+
rescue => exception
|
82
|
+
if timeout < 3
|
83
|
+
timeout += 1
|
84
|
+
retry
|
85
|
+
else
|
86
|
+
next
|
78
87
|
end
|
79
|
-
end
|
88
|
+
end
|
80
89
|
}
|
81
90
|
end
|
82
91
|
threads.each { |t| t.join }
|
@@ -84,7 +93,7 @@ module TomosiaAmanaplusCrawl
|
|
84
93
|
end
|
85
94
|
|
86
95
|
def writeToExcel(images, destination)
|
87
|
-
path = "#{destination}
|
96
|
+
path = "#{destination}//File Excel" # lưu file ở folder File Excel
|
88
97
|
Dir.mkdir path unless File.exist? path
|
89
98
|
|
90
99
|
book = Spreadsheet::Workbook.new
|
@@ -102,9 +111,4 @@ module TomosiaAmanaplusCrawl
|
|
102
111
|
end
|
103
112
|
|
104
113
|
end
|
105
|
-
|
106
|
-
def self.crawl(keyword = "Yêu", destination = "chị", max = "My")
|
107
|
-
puts "msg: #{keyword} #{destination} #{you}"
|
108
|
-
#
|
109
|
-
end
|
110
114
|
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
require 'thor'
|
2
|
+
require_relative '../tomosia_amanaplus_crawl'
|
3
|
+
|
4
|
+
module TomosiaAmanaplusCrawl
|
5
|
+
class Cli < Thor
|
6
|
+
|
7
|
+
desc "crawl KEYWORD", "enter KEYWORD to search"
|
8
|
+
option :destination
|
9
|
+
option :max
|
10
|
+
def crawl(keyword)
|
11
|
+
TomosiaAmanaplusCrawl::Crawler.new.run(keyword, options[:destination], options[:max].to_i)
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
require "bundler/setup"
|
2
|
+
require "tomosia_amanaplus_crawl"
|
3
|
+
|
4
|
+
RSpec.configure do |config|
|
5
|
+
# Enable flags like --only-failures and --next-failure
|
6
|
+
config.example_status_persistence_file_path = ".rspec_status"
|
7
|
+
|
8
|
+
# Disable RSpec exposing methods globally on `Module` and `main`
|
9
|
+
config.disable_monkey_patching!
|
10
|
+
|
11
|
+
config.expect_with :rspec do |c|
|
12
|
+
c.syntax = :expect
|
13
|
+
end
|
14
|
+
end
|
@@ -9,13 +9,12 @@ Gem::Specification.new do |spec|
|
|
9
9
|
spec.homepage = "https://github.com/tthuydang/tomosia_amanaplus_crawl"
|
10
10
|
spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
|
11
11
|
|
12
|
-
spec.files =
|
13
|
-
|
14
|
-
|
15
|
-
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
12
|
+
spec.files = `git ls-files`.split("\n")
|
13
|
+
spec.bindir = "exe"
|
14
|
+
spec.executables = 'tomosia_amanaplus_crawl'
|
16
15
|
spec.require_paths = ["lib"]
|
17
16
|
|
18
|
-
spec.add_runtime_dependency('httparty', '0.18.1')
|
19
17
|
spec.add_runtime_dependency('nokogiri', '1.10.10')
|
20
18
|
spec.add_runtime_dependency('spreadsheet', '1.2.6')
|
19
|
+
spec.add_runtime_dependency('thor')
|
21
20
|
end
|
metadata
CHANGED
@@ -1,60 +1,61 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: tomosia_amanaplus_crawl
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Nhat Huy
|
8
8
|
autorequire:
|
9
|
-
bindir:
|
9
|
+
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-08-
|
11
|
+
date: 2020-08-10 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
|
-
name:
|
14
|
+
name: nokogiri
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
17
|
- - '='
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version:
|
19
|
+
version: 1.10.10
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - '='
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version:
|
26
|
+
version: 1.10.10
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
|
-
name:
|
28
|
+
name: spreadsheet
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
31
|
- - '='
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: 1.
|
33
|
+
version: 1.2.6
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
38
|
- - '='
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: 1.
|
40
|
+
version: 1.2.6
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
|
-
name:
|
42
|
+
name: thor
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- -
|
45
|
+
- - ">="
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version:
|
47
|
+
version: '0'
|
48
48
|
type: :runtime
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- -
|
52
|
+
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version:
|
54
|
+
version: '0'
|
55
55
|
description:
|
56
56
|
email:
|
57
|
-
executables:
|
57
|
+
executables:
|
58
|
+
- tomosia_amanaplus_crawl
|
58
59
|
extensions: []
|
59
60
|
extra_rdoc_files: []
|
60
61
|
files:
|
@@ -69,8 +70,12 @@ files:
|
|
69
70
|
- Rakefile
|
70
71
|
- bin/console
|
71
72
|
- bin/setup
|
73
|
+
- exe/tomosia_amanaplus_crawl
|
72
74
|
- lib/tomosia_amanaplus_crawl.rb
|
75
|
+
- lib/tomosia_amanaplus_crawl/cli.rb
|
73
76
|
- lib/tomosia_amanaplus_crawl/version.rb
|
77
|
+
- spec/spec_helper.rb
|
78
|
+
- spec/tomosia_amanaplus_crawl_spec.rb
|
74
79
|
- tomosia_amanaplus_crawl.gemspec
|
75
80
|
homepage: https://github.com/tthuydang/tomosia_amanaplus_crawl
|
76
81
|
licenses: []
|