fetch_news 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a70ed2e1e968f7d3bddda5494e166e13e5440ce2
+  data.tar.gz: 62eb6f62a5e32817095af66084cdcf711a6cce91
+SHA512:
+  metadata.gz: 1f9cf7a25ac8b3a31e90f6df1947659c6e6853a722f9a8a9d7900fbef8d2711c82a33e8a16dc224cd7bae52a3ee6ffc7ee1c7f27fb5c7e62efc9a21454c45515
+  data.tar.gz: f83935885b4ab32a4eac94fb3514efebbb89a02fa895440f251869bf012a08261667f3f3119805f24922d9b71066c0998db7c7a8374e17c3aee63a28b4da8fff

data/lib/fetch_news/configuration.rb

@@ -0,0 +1,5 @@
+module FetchNews
+  class Configuration
+    attr_accessor :headless, :browser
+  end
+end

data/lib/fetch_news/dynamic_page.rb

@@ -0,0 +1,29 @@
+require 'nokogiri'
+
+module FetchNews
+  class FetchDynamicContent
+    attr_reader :browser
+
+    def initialize
+      @browser = Watir::Browser.new FetchNews.configuration.browser.to_sym, headless: FetchNews.configuration.headless
+    end
+
+    def go url
+      browser.goto url
+    end
+
+    def get_content target_html, &block
+      result = []
+      target_html.each do |link|
+        result << block.call(link) if block_given?
+      end
+
+      result
+    end
+
+    def quit
+      puts "browser exist with code 0"
+      browser.close
+    end
+  end
+end

data/lib/fetch_news/static_page.rb

@@ -0,0 +1,20 @@
+module FetchNews
+  class FetchStaticContent
+    attr_reader :agent
+    attr_accessor :page
+
+    def initialize
+      @agent = Mechanize.new
+    end
+
+    def go url
+      @page = @agent.get(url)
+    end
+
+    def get_content target_html, &block
+      target_html.map do |link|
+        block.call(link) if block_given?
+      end
+    end
+  end
+end

data/lib/fetch_news.rb

@@ -0,0 +1,28 @@
+require 'mechanize'
+require 'watir'
+require_relative './fetch_news/static_page.rb'
+require_relative './fetch_news/dynamic_page.rb'
+require_relative './fetch_news/configuration.rb'
+
+module FetchNews
+  class << self
+    attr_accessor :configuration
+
+    def init(type)
+      case type
+        when "dynamic"
+          FetchNews::FetchDynamicContent.new
+        when "static"
+          FetchNews::FetchStaticContent.new
+        else
+          raise "invalid type"
+      end
+    end
+
+    def configure
+      @configuration = FetchNews::Configuration.new
+
+      yield configuration
+    end
+  end
+end

metadata

@@ -0,0 +1,75 @@
+--- !ruby/object:Gem::Specification
+name: fetch_news
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Jim He
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-06-11 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: watir
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A simple spider gem
+email: 6756971174@qq.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/fetch_news.rb
+- lib/fetch_news/configuration.rb
+- lib/fetch_news/dynamic_page.rb
+- lib/fetch_news/static_page.rb
+homepage: 
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.14
+signing_key: 
+specification_version: 4
+summary: fetch page content from page!
+test_files: []