cx_extractor 0.1.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 311c0a47a060dc52cf13424390ee5a1ad413ed0909307e744c03b5842170b1cb
+  data.tar.gz: fcf666ae5b38807a38dbfadf7abffd1ed13089d3f894d7474ee9b33242f164a7
+SHA512:
+  metadata.gz: 606cf753ae242db3407f84af1f20feeddc9207913d1a725aa255ade80646a096a9f41d216d2e25a9dc8bf39a7c3fd8c1b6841222100a97ed06e4dc5ae415d656
+  data.tar.gz: 5e374a30a8a6fac753507653a99120cf464a7c30bf556e6ee0bac45c030c737a67d7ac67697037944674faf019db2931e8f7aef4b341cdd29356a24f901fd1b9

data/.gitignore

@@ -0,0 +1,13 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+distribution.png
+# rspec failure tracking
+.rspec_status
+.DS_Store
+*.py

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,10 @@
+
+Metrics/MethodLength:
+  Max: 20
+
+Metrics/AbcSize:
+  Max: 20
+
+Metrics/LineLength:
+   Max: 100
+

data/.travis.yml

@@ -0,0 +1,9 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.3.3
+before_install:
+  - sudo apt-get install imagemagick
+  - gem install bundler -v 1.16.2
+script:
+  - bundle exec rspec

data/Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in cx_extractor.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,51 @@
+PATH
+  remote: .
+  specs:
+    cx_extractor (0.1.2)
+      gruff (~> 0.7.0)
+      nokogiri (~> 1.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    charlock_holmes (0.7.6)
+    diff-lcs (1.3)
+    ethon (0.12.0)
+      ffi (>= 1.3.0)
+    ffi (1.11.1)
+    gruff (0.7.0)
+      rmagick (~> 2.13, >= 2.13.4)
+    mini_portile2 (2.4.0)
+    nokogiri (1.10.3)
+      mini_portile2 (~> 2.4.0)
+    rake (10.5.0)
+    rmagick (2.16.0)
+    rspec (3.8.0)
+      rspec-core (~> 3.8.0)
+      rspec-expectations (~> 3.8.0)
+      rspec-mocks (~> 3.8.0)
+    rspec-core (3.8.0)
+      rspec-support (~> 3.8.0)
+    rspec-expectations (3.8.3)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-mocks (3.8.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-support (3.8.0)
+    typhoeus (1.3.1)
+      ethon (>= 0.9.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.16)
+  charlock_holmes
+  cx_extractor!
+  rake (~> 10.0)
+  rspec (~> 3.0)
+  typhoeus
+
+BUNDLED WITH
+   1.16.6

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2018 Feng Ce
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,39 @@
+# CxExtractor
+
+[![Build Status](https://travis-ci.org/fcce/cx_extractor.svg?branch=master)](https://travis-ci.org/fcce/cx_extractor)
+
+Extract article from the web page, this gem is appropriate for the web page which contains lots of text.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'cx_extractor'
+```
+
+And then execute:
+
+    brew install imagemagick
+    brew link --force imagemagick@6
+    bundle
+
+Or install it yourself as:
+
+    gem install cx_extractor
+
+## Usage
+
+
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/fcce/cx_extractor. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the CxExtractor project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/cx_extractor/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/_config.yml

@@ -0,0 +1 @@
+theme: jekyll-theme-cayman

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require 'cx_extractor'
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require 'irb'
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/cx_extractor.gemspec

@@ -0,0 +1,34 @@
+lib = File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'cx_extractor/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'cx_extractor'
+  spec.version       = CxExtractor::VERSION
+  spec.authors       = ['Feng Ce']
+  spec.email         = ['kalelfc@gmail.com']
+
+  spec.summary       = 'Used to extract text from the web page.'
+  spec.description = <<-CONTENT
+Used to extract text from the web page.
+This tool is appropriate for the web page which contains lots of text.
+  CONTENT
+  spec.homepage      = 'https://fcce.github.io/cx_extractor/'
+  spec.license       = 'MIT'
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      f.match(%r{^(test|spec|features)/})
+    end
+  end
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'gruff', '~> 0.7.0'
+  spec.add_dependency 'nokogiri', '~> 1.0'
+  spec.add_development_dependency 'bundler', '~> 1.16'
+  spec.add_development_dependency 'charlock_holmes'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'typhoeus'
+end

data/lib/cx_extractor.rb

@@ -0,0 +1,67 @@
+require 'cx_extractor/version'
+require 'cx_extractor/config'
+require 'cx_extractor/chart'
+require 'cx_extractor/utils'
+require 'nokogiri'
+require 'typhoeus'
+require 'charlock_holmes'
+# nodoc
+module CxExtractor
+  extend Chart if explore_parent
+  extend Utils
+  class << self
+    TITLE_REGEXP = %r{<title>(.*?)</title>}.freeze
+
+    def article(html)
+      ctext = get_clean_text(html)
+      lines = ctext.split("\n").map(&:strip)
+      block_distribution = line_block_distribute(lines)
+      content = get_content(lines, block_distribution)
+      content = get_content_by_tag(html, content) if explore_parent
+      # content.gsub("\n",'') if remove_newline
+      content.squeeze.strip
+    end
+
+    def get_title(html)
+      matcher = TITLE_REGEXP.match(html) || []
+      matcher[1]
+    end
+
+    def get_content(lines, block_distribution)
+      from_line = to_line = 0
+      content = chart_points = []
+      loop do
+        from_line, to_line = get_contect_block(block_distribution, to_line)
+        content += lines[from_line..to_line]
+        break if from_line < 0
+
+        chart_points += [from_line, to_line]
+      end
+      if chart_distribution && !chart_points.empty?
+        chart(block_distribution, chart_points)
+      else
+        warn 'there is no content for the web page, cannot chart'
+      end
+      content.join("\n")
+    end
+
+    def get_contect_block(block_distribution, to_line)
+      from_line = find_surge(block_distribution, to_line, threshold)
+      to_line = find_dive(block_distribution, from_line)
+      [from_line, to_line]
+    end
+
+    def get_content_by_tag(html, block_content)
+      doc =  Nokogiri::HTML(html)
+      p_doms = doc.css('p')
+      ptext = []
+      p_doms.each do |p_dom|
+        ptext << p_dom.parent if block_content.include?(p_dom.text)
+      end
+      max_p = ptext.max_by { |i| ptext.count(i) }
+      get_clean_text(max_p.to_s).split("\n").map(&:strip).join(
+        "\n"
+      ).squeeze
+    end
+  end
+end

data/lib/cx_extractor/chart.rb

@@ -0,0 +1,47 @@
+require 'gruff'
+module CxExtractor
+  # make a chart for block_distribution
+  module Chart
+    def cal_labels(distribution)
+      labels = {}
+      index_distribution_length = distribution.length
+      [0, 1, 2, 4, 8].each do |i|
+        v = index_distribution_length / (2**i)
+        labels[v] = v.to_s
+      end
+      percentile_seventy_five = index_distribution_length * 3 / 4
+      labels[percentile_seventy_five] = percentile_seventy_five.to_s
+      labels
+    end
+
+    def cal_color(index)
+      if index % 2 > 0
+        '#85AF99'
+      else
+        '#E5E5E5'
+      end
+    end
+
+    def chart(distribution, chart_points, filename = chart_file_name)
+      g = Gruff::Line.new
+      g.theme = chart_theme
+      g.labels = cal_labels(distribution)
+      chart_points.unshift 0
+      gruff_line(g, chart_points, distribution)
+      g.hide_legend = true
+      g.minimum_value = 0
+      g.write(filename)
+    end
+
+    def gruff_line(gruff, chart_points, distribution)
+      start_point = end_point = 0
+      chart_points.each_with_index do |break_point, index|
+        start_point = break_point
+        end_point = chart_points[index + 1] || distribution.length - 1
+        gruff.dataxy('line' + break_point.to_s,
+                     (start_point..end_point).to_a,
+                     distribution[start_point..end_point], cal_color(index))
+      end
+    end
+  end
+end

data/lib/cx_extractor/config.rb

@@ -0,0 +1,37 @@
+# configure
+module CxExtractor
+  DEFAULTS = {
+    threshold: 86,
+    balck_width: 3,
+    explore_parent: true,
+    chart_distribution: false,
+    chart_file_name: 'distribution.png',
+    chart_theme: {
+      marker_color: '#AEA9A9',
+      font_color: 'black',
+      background_colors: 'white'
+    }
+  }.freeze
+
+  class << self
+    def options
+      @options ||= DEFAULTS.dup
+    end
+
+    attr_writer :options
+
+    def configure
+      yield self
+    end
+  end
+
+  DEFAULTS.each do |k, _v|
+    define_singleton_method "#{k}=" do |value|
+      options.merge!(k => value)
+    end
+
+    define_singleton_method k do
+      options[k]
+    end
+  end
+end

data/lib/cx_extractor/utils.rb

@@ -0,0 +1,63 @@
+module CxExtractor
+  # utils for cx_extractor
+  module Utils
+    def line_block_distribute(lines)
+      block_distribution = []
+      index_distribution = lines.map(&:length)
+      (0...(lines.length - balck_width + 1)).each do |i|
+        word_num = 0
+        (0...balck_width).each do |j|
+          word_num += index_distribution[i + j]
+        end
+        block_distribution[i] = word_num
+      end
+      block_distribution
+    end
+
+    def find_surge(block_distribution, start, threshold)
+      ((start + 1)...block_distribution.length - 3).each do |index|
+        if block_distribution[index] > threshold && (
+           block_distribution[index + 1] > 0 ||
+           block_distribution[index + 2] > 0 ||
+           block_distribution[index + 3] > 0)
+          return index
+        end
+      end
+      -1
+    end
+
+    def find_dive(block_distribution, surge_point)
+      ((surge_point + 1)...(block_distribution.size - 2)).each do |index|
+        if block_distribution[index].zero? &&
+           block_distribution[index + 1].zero?
+          return index - 1
+        end
+      end
+      block_distribution.size - 1
+    end
+
+    def get_clean_text(dom)
+      # remove html comment
+      html = dom.clone
+      html.gsub!(/<!--.*?(.|\n)*?-->/, "\n")
+      # remove javascript
+      html.gsub!(%r{<script.*?>.*?(.|\n)*?</script>}, "\n")
+      # remove a
+      html.gsub!(%r{<a[\t|\n|\r|\f].*?>.*?</a>}, '')
+      # remove css
+      html.gsub!(%r{<style.*?>.*?(.|\n)*?</style>}, "\n")
+      # remove tag
+      html.gsub!(/<.*?(.|\n)*?>/, '')
+      replace_special_char(html)
+    end
+
+    def replace_special_char(str)
+      str.gsub!('&#8226;', '·')
+      str.gsub!('&amp;', '&')
+      str.gsub!('&nbsp;', ' ')
+      str.gsub!('&copy;', '@')
+      str.gsub!("\r\n|\r", "\n")
+      str
+    end
+  end
+end

data/lib/cx_extractor/version.rb

@@ -0,0 +1,3 @@
+module CxExtractor
+  VERSION = '0.1.2'.freeze
+end

metadata

@@ -0,0 +1,162 @@
+--- !ruby/object:Gem::Specification
+name: cx_extractor
+version: !ruby/object:Gem::Version
+  version: 0.1.2
+platform: ruby
+authors:
+- Feng Ce
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2019-06-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: gruff
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.7.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.7.0
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !ruby/object:Gem::Dependency
+  name: charlock_holmes
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !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: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: typhoeus
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: |
+  Used to extract text from the web page.
+  This tool is appropriate for the web page which contains lots of text.
+email:
+- kalelfc@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- ".travis.yml"
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- _config.yml
+- bin/console
+- bin/setup
+- cx_extractor.gemspec
+- lib/cx_extractor.rb
+- lib/cx_extractor/chart.rb
+- lib/cx_extractor/config.rb
+- lib/cx_extractor/utils.rb
+- lib/cx_extractor/version.rb
+homepage: https://fcce.github.io/cx_extractor/
+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: 2.7.9
+signing_key: 
+specification_version: 4
+summary: Used to extract text from the web page.
+test_files: []