tomosia_amanaplus_crawl 0.1.7 → 0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7417a6975d3b4a05ce160b1101b099aaa0fd4eed979da04677b3c5e538861caf
-  data.tar.gz: 17855a57cc28703ad72838e0ed175ff28093a08d3f2e353f8183b65de4a2eaa1
+  metadata.gz: e3bc628d6f82c6357d3a4362464870e6e1ac3bc696ad7bc3f91fd7fd5901b7fe
+  data.tar.gz: 7184c0c7edaecb96312ab0650fb4395cc02d50175e51c0d35ce2600e6c9ac61b
 SHA512:
-  metadata.gz: 62e31fa47bca97901c73118e55e9fdf20ea0a169d295220beb400382d2f8fda4dc64b12f3155183aa2684ea8c6f31166c36d329533103ce988c9e978acb7c15d
-  data.tar.gz: e120af5fcf53c387ab277fbeb5c7caa73e068f1b6c790cbd8c6c7794fb90502718465c58fd40f9fe075c788135bec6c3a3d305868ffcc1496bbd37bb037c9c5d
+  metadata.gz: ab5bc7f49db71fb490d1cf99da244c1321edcf98aec5678415229f4faf6a29fa5edd2589d8abf90b66790e142c1ef276a8e24bb65755c6b2eb5f2ea805dff1f6
+  data.tar.gz: b89334b70ee3693add75baa2e49bff8e2b968c1caac0d21adea45c41a31984b21e713127d8412cde046a478d714da2bd3a9186e0838923c964262967c1f60bf4

data/Gemfile.lock

@@ -1,10 +1,11 @@
 PATH
   remote: .
   specs:
-    tomosia_amanaplus_crawl (0.1.5)
+    tomosia_amanaplus_crawl (0.1.8)
       httparty (= 0.18.1)
       nokogiri (= 1.10.10)
       spreadsheet (= 1.2.6)
+      thor
 
 GEM
   remote: https://rubygems.org/
@@ -37,6 +38,7 @@ 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

@@ -2,16 +2,15 @@ require "tomosia_amanaplus_crawl/version"
 
 module TomosiaAmanaplusCrawl
   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
@@ -19,7 +18,7 @@ module TomosiaAmanaplusCrawl
     
       # 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
+      total = total[(6 + keyword.length)..(total.length - 1)].chop.chop.chop.gsub(',', '').to_i
       if max > total # nếu max lớn hơn total thì max = total => vẫn lấy hết
         max = total
       end
@@ -36,7 +35,7 @@ module TomosiaAmanaplusCrawl
       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")
     
@@ -63,20 +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 }
@@ -84,7 +93,7 @@ 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
@@ -102,9 +111,4 @@ module TomosiaAmanaplusCrawl
     end
 
   end
-
-  def self.crawl(keyword = "Yêu", destination = "chị", max = "My")
-    puts "msg: #{keyword} #{destination} #{you}"
-    # 
-  end
 end

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].to_i)
+    end
+  end
+end

data/lib/tomosia_amanaplus_crawl/version.rb

@@ -1,3 +1,3 @@
 module TomosiaAmanaplusCrawl
-  VERSION = "0.1.7"
+  VERSION = "0.2.3"
 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: 0.1.7
+  version: 0.2.3
 platform: ruby
 authors:
 - Nhat Huy
 autorequire: 
-bindir: bin
+bindir: exe
 cert_chain: []
-date: 2020-08-07 00:00:00.000000000 Z
+date: 2020-08-10 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: []