tomosia_amanaplus_crawl 0.1.8 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 793268d3d7e8d3c1f3fd17ca9f1283839dda2a20dfb1a8769c65fd6d25bf0236
-  data.tar.gz: 115062f473eb2ca55c9ceea17265b73827b53feb548a48861b808b9baa64447f
+  metadata.gz: 78adb558a362c9594df8a864dad75bf4bc95472eb64e2aa9ef1499d2a39f6837
+  data.tar.gz: d2d670dbc023aa1f1ce265f78245b18a2177da373b0e4436a8a88ced97f9677b
 SHA512:
-  metadata.gz: 83ee2ae24471817f907373dd2130fd54726786eb2fca7732e9fbe10ec841b4b5cbfc3fa4925753d725eb23362c330cec055a8b43eb8f0321053e7ce497f77930
-  data.tar.gz: 5b92ea21908fa8288a2fa26af61c8c198b525f0de6f6aba7766e89931f064edd0bd37059d2fc205b8090bf0aac2825865fa5fe9ce8226dd7003efb74f55ecf2b
+  metadata.gz: 382535d1072a6803ffd0166ee70b99187514b9119656e94c852519ef3c608ed6d829a86d19d4d8a20027a6fc1e1a3fe909defc4644e139002998751a40bb124c
+  data.tar.gz: d18803def75f4efa16e4e4339e3f0b1e64a6a54f77c4a8a6b45d5cb8991e6a3e5a87a0c4d1047c22ad8fdab4266c1c3dedac07660663aeb6557624266e6c6809

data/Gemfile.lock

@@ -1,23 +1,16 @@
 PATH
   remote: .
   specs:
-    tomosia_amanaplus_crawl (0.1.5)
-      httparty (= 0.18.1)
+    tomosia_amanaplus_crawl (0.2.3)
       nokogiri (= 1.10.10)
       spreadsheet (= 1.2.6)
+      thor
 
 GEM
   remote: https://rubygems.org/
   specs:
     diff-lcs (1.4.4)
-    httparty (0.18.1)
-      mime-types (~> 3.0)
-      multi_xml (>= 0.5.2)
-    mime-types (3.3.1)
-      mime-types-data (~> 3.2015)
-    mime-types-data (3.2020.0512)
     mini_portile2 (2.4.0)
-    multi_xml (0.6.0)
     nokogiri (1.10.10)
       mini_portile2 (~> 2.4.0)
     rake (12.3.3)
@@ -37,6 +30,7 @@ GEM
     ruby-ole (1.2.12.2)
     spreadsheet (1.2.6)
       ruby-ole (>= 1.0)
+    thor (1.0.1)
 
 PLATFORMS
   ruby

data/README.md

@@ -23,9 +23,9 @@ Or install it yourself as:
 ## Usage
 
 ```ruby
-    require 'tomosia_amanaplus_crawl'
-    TomosiaAmanaplusCrawl::Crawler.new.run(keyword, path, max)
+    tomosia_amanaplus_crawl crawl "keyword" --destination "/home/usr/Documents" --max=123
 ```
+    Example: tomosia_amanaplus_crawl crawl "hoian" --destination "./" --max=123
     keyword: hoian, danang, ...
     path: './', '/desktop/', ...
     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

@@ -4,3 +4,9 @@ require "rspec/core/rake_task"
 RSpec::Core::RakeTask.new(:spec)
 
 task :default => :spec
+
+namespace :gem do
+  task :build do
+    system "rake build && rake install"
+  end
+end

data/exe/tomosia_amanaplus_crawl

@@ -0,0 +1,5 @@
+#!/usr/bin/env ruby
+
+require 'tomosia_amanaplus_crawl/cli'
+
+TomosiaAmanaplusCrawl::Cli.start

data/lib/tomosia_amanaplus_crawl.rb

@@ -1,30 +1,25 @@
 require "tomosia_amanaplus_crawl/version"
 
 module TomosiaAmanaplusCrawl
-  def self.yeuNgucLep
-    puts "Yeu chi My nhieu lam"
-  end
-
   require 'nokogiri'
-  require 'httparty'
   require 'open-uri'
   require 'fileutils'
   require 'spreadsheet'
 
   class Crawler
-    URL = "https://plus.amanaimages.com/items/search/"
+    URL = "https://plus.amanaimages.com/items/search"
 
     def run(keyword, destination, max)
-      unparsed_page = HTTParty.get("#{URL}/#{keyword}")
+      unparsed_page = open("#{URL}/#{keyword}").read
       parsed_page = Nokogiri::HTML(unparsed_page)
 
       pages = parsed_page.css("div.c-paginate__nums").css('a').last.text.to_i # tổng số page
       images_listings = parsed_page.css("div.p-search-result__body") # danh sách các thẻ div chứa image
-    
+
       # lấy tổng số image
       total = parsed_page.css("h1.p-search-result__ttl").text.split(' ').first
-      total = total[11..(total.length - 1)].chop.chop.chop.sub(',', '').to_i
-      if max > total # nếu max lớn hơn total thì max = total => vẫn lấy hết
+      total = total[(6 + keyword.length)..(total.length - 1)].chop.chop.chop.gsub(',', '').to_i
+      if max == nil || max > total # nếu max lớn hơn total thì max = total => vẫn lấy hết
         max = total
       end
 
@@ -39,11 +34,11 @@ module TomosiaAmanaplusCrawl
       curr_index = 1
       while curr_page <= pages
         puts "Crawling page #{curr_page}..........."
-    
-        pagination_unparsed_page = HTTParty.get("https://plus.amanaimages.com/items/search/#{keyword}?page=#{curr_page}")
+
+        pagination_unparsed_page = open("#{URL}/#{keyword}?page=#{curr_page}").read
         pagination_parsed_page = Nokogiri::HTML(pagination_unparsed_page)
         pagination_images_listings = pagination_parsed_page.css("div.p-item-thumb")
-    
+
         pagination_images_listings.each do |img|
           if curr_index > max
             return images
@@ -59,7 +54,7 @@ module TomosiaAmanaplusCrawl
           images << current_image
           curr_index += 1
         end
-    
+
         curr_page += 1
       end
       images
@@ -67,20 +62,30 @@ module TomosiaAmanaplusCrawl
 
     # tải hình và cập nhật lại size
     def downloadImages(images, destination)
-      path = "#{destination}/Downloads"       # lưu hình ở folder Downloads
+      path = "#{destination}//Downloads"       # lưu hình ở folder Downloads
       Dir.mkdir path unless File.exist? path
 
       threads = []
       print "\nDownloading"
       images.each do |curr_image|
         threads << Thread.new(curr_image) {
-          open(curr_image[:url]) do |image|
-            File.open("#{path}/#{curr_image[:url].split('/').last}", "a+") do |file|
-              file.write(image.read) # lưu hình ảnh
-              curr_image[:size] = image.size # cập nhật lại size trong mảng images
-              print "."
+          timeout = 0
+          begin
+            URI.open(curr_image[:url]) do |image|
+              File.open("#{path}/#{curr_image[:url].split('/').last}", "a+") do |file|
+                file.write(image.read) # lưu hình ảnh
+                curr_image[:size] = image.size # cập nhật lại size trong mảng images
+                print '.'
+              end
+            end # end open
+          rescue => exception
+            if timeout < 3
+              timeout += 1
+              retry
+            else
+              next
             end
-          end # end open
+          end
         }
       end
       threads.each { |t| t.join }
@@ -88,16 +93,15 @@ module TomosiaAmanaplusCrawl
     end
 
     def writeToExcel(images, destination)
-      path = "#{destination}/File Excel"      # lưu file ở folder File Excel
+      path = "#{destination}//File Excel"      # lưu file ở folder File Excel
       Dir.mkdir path unless File.exist? path
 
       book = Spreadsheet::Workbook.new
       sheet1 = book.create_worksheet
 
-      i = 0
       sheet1.row(0).concat %w{Title Url Size(bytes) Extension}
       puts "Writing..........."
-      images.each do |img|
+      images.each_with_index do |img, i|
         sheet1.row(i += 1).push img[:title], img[:url], img[:size], img[:extension]
       end
       puts "Writed."

data/lib/tomosia_amanaplus_crawl/cli.rb

@@ -0,0 +1,14 @@
+require 'thor'
+require_relative '../tomosia_amanaplus_crawl'
+
+module TomosiaAmanaplusCrawl
+  class Cli < Thor
+
+    desc "crawl KEYWORD", "enter KEYWORD to search"
+    option :destination
+    option :max
+    def crawl(keyword)
+      TomosiaAmanaplusCrawl::Crawler.new.run(keyword, options[:destination], options[:max] == nil ? nil : options[:max].to_i)
+    end
+  end
+end

data/lib/tomosia_amanaplus_crawl/version.rb

@@ -1,3 +1,3 @@
 module TomosiaAmanaplusCrawl
-  VERSION = "0.1.8"
+  VERSION = "0.2.4"
 end

data/spec/spec_helper.rb

@@ -0,0 +1,14 @@
+require "bundler/setup"
+require "tomosia_amanaplus_crawl"
+
+RSpec.configure do |config|
+  # Enable flags like --only-failures and --next-failure
+  config.example_status_persistence_file_path = ".rspec_status"
+
+  # Disable RSpec exposing methods globally on `Module` and `main`
+  config.disable_monkey_patching!
+
+  config.expect_with :rspec do |c|
+    c.syntax = :expect
+  end
+end

data/spec/tomosia_amanaplus_crawl_spec.rb

@@ -0,0 +1,9 @@
+RSpec.describe TomosiaAmanaplusCrawl do
+  it "has a version number" do
+    expect(TomosiaAmanaplusCrawl::VERSION).not_to be nil
+  end
+
+  it "does something useful" do
+    expect(false).to eq(true)
+  end
+end

data/tomosia_amanaplus_crawl.gemspec

@@ -9,13 +9,12 @@ Gem::Specification.new do |spec|
   spec.homepage      = "https://github.com/tthuydang/tomosia_amanaplus_crawl"
   spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
 
-  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
-    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
-  end
-  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.files         = `git ls-files`.split("\n")
+  spec.bindir        = "exe"
+  spec.executables   = 'tomosia_amanaplus_crawl'
   spec.require_paths = ["lib"]
 
-  spec.add_runtime_dependency('httparty', '0.18.1')
   spec.add_runtime_dependency('nokogiri', '1.10.10')
   spec.add_runtime_dependency('spreadsheet', '1.2.6')
+  spec.add_runtime_dependency('thor')
 end

metadata

@@ -1,60 +1,61 @@
 --- !ruby/object:Gem::Specification
 name: tomosia_amanaplus_crawl
 version: !ruby/object:Gem::Version
-  version: 0.1.8
+  version: 0.2.4
 platform: ruby
 authors:
 - Nhat Huy
 autorequire: 
-bindir: bin
+bindir: exe
 cert_chain: []
-date: 2020-08-07 00:00:00.000000000 Z
+date: 2020-08-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: httparty
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.18.1
+        version: 1.10.10
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.18.1
+        version: 1.10.10
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: spreadsheet
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 1.10.10
+        version: 1.2.6
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 1.10.10
+        version: 1.2.6
 - !ruby/object:Gem::Dependency
-  name: spreadsheet
+  name: thor
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 1.2.6
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 1.2.6
+        version: '0'
 description: 
 email: 
-executables: []
+executables:
+- tomosia_amanaplus_crawl
 extensions: []
 extra_rdoc_files: []
 files:
@@ -69,8 +70,12 @@ files:
 - Rakefile
 - bin/console
 - bin/setup
+- exe/tomosia_amanaplus_crawl
 - lib/tomosia_amanaplus_crawl.rb
+- lib/tomosia_amanaplus_crawl/cli.rb
 - lib/tomosia_amanaplus_crawl/version.rb
+- spec/spec_helper.rb
+- spec/tomosia_amanaplus_crawl_spec.rb
 - tomosia_amanaplus_crawl.gemspec
 homepage: https://github.com/tthuydang/tomosia_amanaplus_crawl
 licenses: []