pointmd_comments 0.1.3 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 564a71620179d2b409489f0b96711361c2dfceb07d268bbb47fb4e164934de35
-  data.tar.gz: 2c77c09da91a7ccaad9f429107633cd04dce8747945b5063e45ddb9bf71e7414
+  metadata.gz: fca56a444c6f4243e673339bf85174fbb71dd2a959d3ad2b52b9728fbd598dbe
+  data.tar.gz: 208e3c91a53f539a08cf9d6a3dec0606f25851ac576898c9caa2975c08251018
 SHA512:
-  metadata.gz: 211f18075aed368f744d3fb7d902849b09f642f8ac9275fe47a2b5ec6fb9a47acf327528f36941373b00f26d9f606685f4c372c88c35f5c06a8f46292823985d
-  data.tar.gz: fa6938170ae9ed200a6b19ef385c0751c2bf03f48150bbb1ae591fab8ab01912c738a7d9cdd94b19c21a735a0356579f4579bbabd40aff2d2d5f2a0470450fed
+  metadata.gz: 170db4ed751423521520ce60d48fd30c40dd8212685c07672e749c90ccea7ef8a688e58a7f7bd4880885c621188e8414e883878669c65b83e43861d861dd1a37
+  data.tar.gz: cd3966ec082acbcbd6484b586593ea9b8b1c08fe3cba235c8c2292ef48044454575a39bd7f171afb0930effa215c55a72d4d60dc9ea0950e4965527dd24f474c

data/bin/pointmd_comments

@@ -1,4 +1,4 @@
 #!/usr/bin/env ruby
 require 'pointmd_comments'
 
-PointmdComments.collect
+PointmdComments.collect_from_shell

data/lib/pointmd_comments.rb

@@ -16,7 +16,11 @@ require 'pointmd_comments/errors/unknown_source'
 module PointmdComments
   class Error < StandardError; end
 
-  def self.collect
+  def self.collect(options = {})
+    Aggregators::Main.new(options).call
+  end
+
+  def self.collect_from_shell
     args = ARGV.dup
     options = OptParser.new.parse
     Aggregators::Main.new(options).call

data/lib/pointmd_comments/aggregators/main.rb

@@ -1,16 +1,23 @@
 module PointmdComments
   module Aggregators
     class Main
+      CHROME_ARGS = %w[disable-dev-shm-usage disable-software-rasterizer no-sandbox].freeze
+
       attr_reader :posts_aggregator, :browser, :comments_aggregator, :all_comments, :posts, :source, :output, :path
 
       def initialize(options)
         # Currently 'path' is not supported
         @path                = nil
-        @output              = options[:output]
-        @source              = options[:source]
+        @output              = options[:output] || default_output_path
+        @source              = options[:source] || Aggregators::Posts::DEFAULT_SOURCE
         @posts_aggregator    = Aggregators::Posts.new(source: source, path: path)
         @comments_aggregator = Aggregators::Comments.new
-        @browser             = ::Watir::Browser.new :chrome, headless: true
+
+        client = Selenium::WebDriver::Remote::Http::Default.new
+        # NOTE: #timeout= is deprecated, use #read_timeout= and #open_timeout= instead
+        client.timeout = 600 # instead of the default 60 (seconds)
+
+        @browser             = ::Watir::Browser.new :chrome, http_client: client, headless: true, args: CHROME_ARGS
         @all_comments        = []
       end
 
@@ -46,7 +53,9 @@ module PointmdComments
       end
 
       def write_to_csv
-        file_path = output || default_output_path
+        # File#expand_path is needed to process paths like '~/test.txt' => '/Users/me/test.txt'
+        file_path = File.expand_path(output)
+        puts "File Path is #{file_path}"
 
         CSV.open(file_path, 'w') do |csv|
           all_comments.each { |c| csv << c }

data/lib/pointmd_comments/aggregators/posts.rb

@@ -3,6 +3,7 @@ module PointmdComments
     class Posts
       # NOTE: This array may be populated with other website sections in the future.
       ALLOWED_SOURCES = %i[news today].freeze
+      DEFAULT_SOURCE  = :news
       MAIN_PAGE       = 'https://point.md/ru/'.freeze
 
       attr_reader :source, :urls
@@ -10,7 +11,6 @@ module PointmdComments
       def initialize(source:, path:)
         @source = source
         @path   = path
-        @urls   = []
       end
 
       def call
@@ -40,22 +40,12 @@ module PointmdComments
       end
 
       def fetch_news_posts
-        posts_block = @page.css('.post-blocks-wrap')
-        main_post_heading = posts_block.children.css('.post-big-block').children.css('h2')
+        # NOTE: .post-blocks-wrap does not exist anymore
+        # Find <article> tags instead
+        articles = @page.css('article')
 
-        main_post   = main_post_heading.children.css('a').first['href']
-        other_posts = posts_block.children.css('.post-small-blocks-wrap')
-
-        populate_urls(main_post, other_posts)
-      end
-
-      def populate_urls(main_post, other_posts)
-        @urls << main_post
-
-        @urls += other_posts.children.map do |child|
-          child.css('article').css('h2').children[1]['href']
-        rescue StandardError
-          next
+        @urls = articles.map do |article|
+          article.css('a').attribute('href').to_s
         end.compact
       end
 

data/lib/pointmd_comments/version.rb

@@ -1,3 +1,3 @@
 module PointmdComments
-  VERSION = '0.1.3'.freeze
+  VERSION = '0.2.0'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pointmd_comments
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.2.0
 platform: ruby
 authors:
 - Nicolai Stoianov
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-11-11 00:00:00.000000000 Z
+date: 2021-04-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pry
@@ -120,7 +120,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
+rubygems_version: 3.2.3
 signing_key:
 specification_version: 4
 summary: Point.md comments aggregator