web_scraping_hw3 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7743fcccfdcb5290baf52086b06d20d0877f81a49e332988a745e9a76ede3223
-  data.tar.gz: d8abde69d146cab6bc55f4122b52d0017ad6b9d8c073bab6872b03b1b1651aca
+  metadata.gz: 8ee22802b8989c0ef31b5023dc5241567fc06737aed4e90ca17ad194d07a6ae4
+  data.tar.gz: 12d6cb27f8e2dfaa3276887117901866230cfb0207e40eadfb45501e371243d4
 SHA512:
-  metadata.gz: 46027922d9b6111c8bf522da2362db15a9da055a105bebc12542b8f5415182e8b3c0f48fc77dfb570406f3b083053c5b3cfd5174c513570ec286aaeadb41362a
-  data.tar.gz: bca3567cad0b8aa66da5210a589fedbafbf3b52a0cd0218fd7244776b4bd3c6bdd150eb778e9cf58d22ede36103bd0f10b0d68de4076c76ec95f0653ddbdb09b
+  metadata.gz: f9fc1f53c42d6b5dd32c6fa1b1e99bbb1e75fa61d727266ae2f4ae0cb9333d1302df40aeba614ab968e3b3376cf3c7590d320d2809d105255347176e7b418a29
+  data.tar.gz: 3dc8f234fa68c013c9fc627afb03bff006a56fc0f676f9f35948d38a665c01af636a6a0ca97435c4983255097f26404635305155a0826786430b872ac0edb571

data/CHANGELOG.md

@@ -5,12 +5,18 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres
 to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.1.0] - 2021-02-04
+## [Unreleased]
+
+## [0.1.2] - 2021-02-05
 
 ### Added
 
-- Add the scraping for all list of corporation
-- Scrape only the Asset of each corporations
+- Make the Web scraping in function
+- Can run this gem now read more information in [Readme Usage](https://github.com/james31366/Web-Scraping-HW3-SSD#usage)
+
+### Changed
+
+- Move the sort the newer version first in CHANGELOG.md
 
 ## [0.1.1] - 2021-02-04
 
@@ -18,4 +24,12 @@ to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 - Changed the date in CHANGELOG.md to published date.
 - Add some information of the gem description.
-- Add surname in author.
+- Add surname in author.
+
+## [0.1.0] - 2021-02-04
+
+### Added
+
+- Add the scraping for all list of corporation
+- Scrape only the Asset of each corporations
+

data/README.md

@@ -21,7 +21,10 @@ Or install it yourself as:
 
 ## Usage
 
-No usage of this gem for now.
+You can run all of the this ruby by
+```ruby
+WebScrapingHw3::Scrape.main_scrape
+```
 
 ## Development
 

data/lib/web_scraping_hw3.rb

@@ -13,31 +13,56 @@ module WebScrapingHw3
 
   BASE_URL = "https://www.set.or.th"
 
-  # Convert any url link from string to nokogiri html.
-  # To use with any nokogiri tools.
-  # @param [String] url
-  # @return [HTML]
-  def make_parsed(url)
-    unparsed_page = HTTParty.get(url)
-    Nokogiri::HTML(unparsed_page.body)
-  end
+  # Class to Scrape the set website
+  class Scrape
+    # Main function to scrape website.
+    # and print the corporation name and asset cost.
+    # @return [nil]
+    def self.main_scrape
+      url = "#{BASE_URL}/set/commonslookup.do"
+      companies_pages = self.find_companies_page(url)
+
+      companies_pages.each do |companies_page|
+        companies_table = self.find_companies_table(companies_page)
+
+        companies_table.each do |company_tag_a|
+          url_stock_highlight_page = self.find_company_highlight(company_tag_a)
+          stock_url = "#{BASE_URL}#{url_stock_highlight_page}"
+          self.print_asset(stock_url)
+        end
+      end
+    end
+
+    private
 
-  url = "#{BASE_URL}/set/commonslookup.do"
-  parsed_page = make_parsed(url)
-  companies_pages = parsed_page.css("div.col-xs-12.padding-top-10.text-center.capital-letter").css("a")
+    def self.find_companies_page(url)
+      parsed_page = make_parsed(url)
+      parsed_page.css("div.col-xs-12.padding-top-10.text-center.capital-letter").css("a")
+    end
 
-  companies_pages.each do |companies_page|
-    companies_url = "#{BASE_URL}#{companies_page.attributes["href"].value}"
-    companies_parsed_page = make_parsed(companies_url)
-    companies_table = companies_parsed_page.css("table.table-profile.table-hover.table-set-border-yellow").css("a")
+    def self.find_companies_table(companies_page)
+      companies_url = "#{BASE_URL}#{companies_page.attributes["href"].value}"
+      companies_parsed_page = make_parsed(companies_url)
+      companies_parsed_page.css("table.table-profile.table-hover.table-set-border-yellow").css("a")
+    end
 
-    companies_table.each do |company_tag_a|
-      url_stock_profile_page = "#{BASE_URL}#{company_tag_a.attributes["href"].value}"
-      stock_profile_page = make_parsed(url_stock_profile_page)
-      url_stock_highlight_page = stock_profile_page.css("ul.nav.nav-tabs.set-nav-tabs")
-                                                   .css("a")[1].attributes["href"].value
+    # Convert any url link from string to nokogiri html.
+    # To use with any nokogiri tools.
+    # @param [String] url
+    # @return [HTML]
+    def self.make_parsed(url)
+      unparsed_page = HTTParty.get(url)
+      Nokogiri::HTML(unparsed_page.body)
+    end
+
+    def self.find_company_highlight(company_tag_a)
+      stock_profile_page_url = "#{BASE_URL}#{company_tag_a.attributes["href"].value}"
+      stock_profile_page = make_parsed(stock_profile_page_url)
+      stock_profile_page.css("ul.nav.nav-tabs.set-nav-tabs")
+                        .css("a")[1].attributes["href"].value
+    end
 
-      stock_url = "#{BASE_URL}#{url_stock_highlight_page}"
+    def self.print_asset(stock_url)
       stock_parsed_page = make_parsed(stock_url)
 
       name = stock_parsed_page.css("div.col-xs-12.col-md-12.col-lg-8").css("h3").text

data/lib/web_scraping_hw3/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module WebScrapingHw3
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

data/web_scraping_hw3.gemspec

@@ -1,5 +1,8 @@
 # frozen_string_literal: true
 
+# Vichisorn Wejsupakul
+# 6210546013
+
 require_relative "lib/web_scraping_hw3/version"
 
 Gem::Specification.new do |spec|
@@ -32,6 +35,11 @@ Gem::Specification.new do |spec|
   spec.add_dependency "httparty", "~> 0.18.1"
   spec.add_dependency "nokogiri", "~> 1.11.1"
 
+  # Development dependency gem
+  spec.add_development_dependency "bundler", "~> 1.17"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "minitest", "~> 5.0"
+
   # For more information and examples about making a new gem, checkout our
   # guide at: https://bundler.io/guides/creating_gem.html
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: web_scraping_hw3
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Vichisorn Wejsupakul
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2021-02-04 00:00:00.000000000 Z
+date: 2021-02-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: httparty
@@ -38,6 +38,48 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 1.11.1
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
 description: This gem is web scraping from assignment 2 in Soft spec design lab.This
   gem is created by 6210546013 Vichisorn Wejsupakul
 email: