cx_extractor 0.1.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA256:
3
+ metadata.gz: 311c0a47a060dc52cf13424390ee5a1ad413ed0909307e744c03b5842170b1cb
4
+ data.tar.gz: fcf666ae5b38807a38dbfadf7abffd1ed13089d3f894d7474ee9b33242f164a7
5
+ SHA512:
6
+ metadata.gz: 606cf753ae242db3407f84af1f20feeddc9207913d1a725aa255ade80646a096a9f41d216d2e25a9dc8bf39a7c3fd8c1b6841222100a97ed06e4dc5ae415d656
7
+ data.tar.gz: 5e374a30a8a6fac753507653a99120cf464a7c30bf556e6ee0bac45c030c737a67d7ac67697037944674faf019db2931e8f7aef4b341cdd29356a24f901fd1b9
@@ -0,0 +1,13 @@
1
+ /.bundle/
2
+ /.yardoc
3
+ /_yardoc/
4
+ /coverage/
5
+ /doc/
6
+ /pkg/
7
+ /spec/reports/
8
+ /tmp/
9
+ distribution.png
10
+ # rspec failure tracking
11
+ .rspec_status
12
+ .DS_Store
13
+ *.py
data/.rspec ADDED
@@ -0,0 +1,3 @@
1
+ --format documentation
2
+ --color
3
+ --require spec_helper
@@ -0,0 +1,10 @@
1
+
2
+ Metrics/MethodLength:
3
+ Max: 20
4
+
5
+ Metrics/AbcSize:
6
+ Max: 20
7
+
8
+ Metrics/LineLength:
9
+ Max: 100
10
+
@@ -0,0 +1,9 @@
1
+ sudo: false
2
+ language: ruby
3
+ rvm:
4
+ - 2.3.3
5
+ before_install:
6
+ - sudo apt-get install imagemagick
7
+ - gem install bundler -v 1.16.2
8
+ script:
9
+ - bundle exec rspec
data/Gemfile ADDED
@@ -0,0 +1,6 @@
1
+ source 'https://rubygems.org'
2
+
3
+ git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
4
+
5
+ # Specify your gem's dependencies in cx_extractor.gemspec
6
+ gemspec
@@ -0,0 +1,51 @@
1
+ PATH
2
+ remote: .
3
+ specs:
4
+ cx_extractor (0.1.2)
5
+ gruff (~> 0.7.0)
6
+ nokogiri (~> 1.0)
7
+
8
+ GEM
9
+ remote: https://rubygems.org/
10
+ specs:
11
+ charlock_holmes (0.7.6)
12
+ diff-lcs (1.3)
13
+ ethon (0.12.0)
14
+ ffi (>= 1.3.0)
15
+ ffi (1.11.1)
16
+ gruff (0.7.0)
17
+ rmagick (~> 2.13, >= 2.13.4)
18
+ mini_portile2 (2.4.0)
19
+ nokogiri (1.10.3)
20
+ mini_portile2 (~> 2.4.0)
21
+ rake (10.5.0)
22
+ rmagick (2.16.0)
23
+ rspec (3.8.0)
24
+ rspec-core (~> 3.8.0)
25
+ rspec-expectations (~> 3.8.0)
26
+ rspec-mocks (~> 3.8.0)
27
+ rspec-core (3.8.0)
28
+ rspec-support (~> 3.8.0)
29
+ rspec-expectations (3.8.3)
30
+ diff-lcs (>= 1.2.0, < 2.0)
31
+ rspec-support (~> 3.8.0)
32
+ rspec-mocks (3.8.0)
33
+ diff-lcs (>= 1.2.0, < 2.0)
34
+ rspec-support (~> 3.8.0)
35
+ rspec-support (3.8.0)
36
+ typhoeus (1.3.1)
37
+ ethon (>= 0.9.0)
38
+
39
+ PLATFORMS
40
+ ruby
41
+
42
+ DEPENDENCIES
43
+ bundler (~> 1.16)
44
+ charlock_holmes
45
+ cx_extractor!
46
+ rake (~> 10.0)
47
+ rspec (~> 3.0)
48
+ typhoeus
49
+
50
+ BUNDLED WITH
51
+ 1.16.6
@@ -0,0 +1,21 @@
1
+ The MIT License (MIT)
2
+
3
+ Copyright (c) 2018 Feng Ce
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in
13
+ all copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21
+ THE SOFTWARE.
@@ -0,0 +1,39 @@
1
+ # CxExtractor
2
+
3
+ [![Build Status](https://travis-ci.org/fcce/cx_extractor.svg?branch=master)](https://travis-ci.org/fcce/cx_extractor)
4
+
5
+ Extract article from the web page, this gem is appropriate for the web page which contains lots of text.
6
+
7
+ ## Installation
8
+
9
+ Add this line to your application's Gemfile:
10
+
11
+ ```ruby
12
+ gem 'cx_extractor'
13
+ ```
14
+
15
+ And then execute:
16
+
17
+ brew install imagemagick
18
+ brew link --force imagemagick@6
19
+ bundle
20
+
21
+ Or install it yourself as:
22
+
23
+ gem install cx_extractor
24
+
25
+ ## Usage
26
+
27
+
28
+
29
+ ## Contributing
30
+
31
+ 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.
32
+
33
+ ## License
34
+
35
+ The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
36
+
37
+ ## Code of Conduct
38
+
39
+ 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).
@@ -0,0 +1,6 @@
1
+ require 'bundler/gem_tasks'
2
+ require 'rspec/core/rake_task'
3
+
4
+ RSpec::Core::RakeTask.new(:spec)
5
+
6
+ task default: :spec
@@ -0,0 +1 @@
1
+ theme: jekyll-theme-cayman
@@ -0,0 +1,14 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require 'bundler/setup'
4
+ require 'cx_extractor'
5
+
6
+ # You can add fixtures and/or initialization code here to make experimenting
7
+ # with your gem easier. You can also use a different console, if you like.
8
+
9
+ # (If you use this, don't forget to add pry to your Gemfile!)
10
+ # require "pry"
11
+ # Pry.start
12
+
13
+ require 'irb'
14
+ IRB.start(__FILE__)
@@ -0,0 +1,8 @@
1
+ #!/usr/bin/env bash
2
+ set -euo pipefail
3
+ IFS=$'\n\t'
4
+ set -vx
5
+
6
+ bundle install
7
+
8
+ # Do any other automated setup that you need to do here
@@ -0,0 +1,34 @@
1
+ lib = File.expand_path('lib', __dir__)
2
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
3
+ require 'cx_extractor/version'
4
+
5
+ Gem::Specification.new do |spec|
6
+ spec.name = 'cx_extractor'
7
+ spec.version = CxExtractor::VERSION
8
+ spec.authors = ['Feng Ce']
9
+ spec.email = ['kalelfc@gmail.com']
10
+
11
+ spec.summary = 'Used to extract text from the web page.'
12
+ spec.description = <<-CONTENT
13
+ Used to extract text from the web page.
14
+ This tool is appropriate for the web page which contains lots of text.
15
+ CONTENT
16
+ spec.homepage = 'https://fcce.github.io/cx_extractor/'
17
+ spec.license = 'MIT'
18
+ spec.files = Dir.chdir(File.expand_path(__dir__)) do
19
+ `git ls-files -z`.split("\x0").reject do |f|
20
+ f.match(%r{^(test|spec|features)/})
21
+ end
22
+ end
23
+ spec.bindir = 'exe'
24
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
25
+ spec.require_paths = ['lib']
26
+
27
+ spec.add_dependency 'gruff', '~> 0.7.0'
28
+ spec.add_dependency 'nokogiri', '~> 1.0'
29
+ spec.add_development_dependency 'bundler', '~> 1.16'
30
+ spec.add_development_dependency 'charlock_holmes'
31
+ spec.add_development_dependency 'rake', '~> 10.0'
32
+ spec.add_development_dependency 'rspec', '~> 3.0'
33
+ spec.add_development_dependency 'typhoeus'
34
+ end
@@ -0,0 +1,67 @@
1
+ require 'cx_extractor/version'
2
+ require 'cx_extractor/config'
3
+ require 'cx_extractor/chart'
4
+ require 'cx_extractor/utils'
5
+ require 'nokogiri'
6
+ require 'typhoeus'
7
+ require 'charlock_holmes'
8
+ # nodoc
9
+ module CxExtractor
10
+ extend Chart if explore_parent
11
+ extend Utils
12
+ class << self
13
+ TITLE_REGEXP = %r{<title>(.*?)</title>}.freeze
14
+
15
+ def article(html)
16
+ ctext = get_clean_text(html)
17
+ lines = ctext.split("\n").map(&:strip)
18
+ block_distribution = line_block_distribute(lines)
19
+ content = get_content(lines, block_distribution)
20
+ content = get_content_by_tag(html, content) if explore_parent
21
+ # content.gsub("\n",'') if remove_newline
22
+ content.squeeze.strip
23
+ end
24
+
25
+ def get_title(html)
26
+ matcher = TITLE_REGEXP.match(html) || []
27
+ matcher[1]
28
+ end
29
+
30
+ def get_content(lines, block_distribution)
31
+ from_line = to_line = 0
32
+ content = chart_points = []
33
+ loop do
34
+ from_line, to_line = get_contect_block(block_distribution, to_line)
35
+ content += lines[from_line..to_line]
36
+ break if from_line < 0
37
+
38
+ chart_points += [from_line, to_line]
39
+ end
40
+ if chart_distribution && !chart_points.empty?
41
+ chart(block_distribution, chart_points)
42
+ else
43
+ warn 'there is no content for the web page, cannot chart'
44
+ end
45
+ content.join("\n")
46
+ end
47
+
48
+ def get_contect_block(block_distribution, to_line)
49
+ from_line = find_surge(block_distribution, to_line, threshold)
50
+ to_line = find_dive(block_distribution, from_line)
51
+ [from_line, to_line]
52
+ end
53
+
54
+ def get_content_by_tag(html, block_content)
55
+ doc = Nokogiri::HTML(html)
56
+ p_doms = doc.css('p')
57
+ ptext = []
58
+ p_doms.each do |p_dom|
59
+ ptext << p_dom.parent if block_content.include?(p_dom.text)
60
+ end
61
+ max_p = ptext.max_by { |i| ptext.count(i) }
62
+ get_clean_text(max_p.to_s).split("\n").map(&:strip).join(
63
+ "\n"
64
+ ).squeeze
65
+ end
66
+ end
67
+ end
@@ -0,0 +1,47 @@
1
+ require 'gruff'
2
+ module CxExtractor
3
+ # make a chart for block_distribution
4
+ module Chart
5
+ def cal_labels(distribution)
6
+ labels = {}
7
+ index_distribution_length = distribution.length
8
+ [0, 1, 2, 4, 8].each do |i|
9
+ v = index_distribution_length / (2**i)
10
+ labels[v] = v.to_s
11
+ end
12
+ percentile_seventy_five = index_distribution_length * 3 / 4
13
+ labels[percentile_seventy_five] = percentile_seventy_five.to_s
14
+ labels
15
+ end
16
+
17
+ def cal_color(index)
18
+ if index % 2 > 0
19
+ '#85AF99'
20
+ else
21
+ '#E5E5E5'
22
+ end
23
+ end
24
+
25
+ def chart(distribution, chart_points, filename = chart_file_name)
26
+ g = Gruff::Line.new
27
+ g.theme = chart_theme
28
+ g.labels = cal_labels(distribution)
29
+ chart_points.unshift 0
30
+ gruff_line(g, chart_points, distribution)
31
+ g.hide_legend = true
32
+ g.minimum_value = 0
33
+ g.write(filename)
34
+ end
35
+
36
+ def gruff_line(gruff, chart_points, distribution)
37
+ start_point = end_point = 0
38
+ chart_points.each_with_index do |break_point, index|
39
+ start_point = break_point
40
+ end_point = chart_points[index + 1] || distribution.length - 1
41
+ gruff.dataxy('line' + break_point.to_s,
42
+ (start_point..end_point).to_a,
43
+ distribution[start_point..end_point], cal_color(index))
44
+ end
45
+ end
46
+ end
47
+ end
@@ -0,0 +1,37 @@
1
+ # configure
2
+ module CxExtractor
3
+ DEFAULTS = {
4
+ threshold: 86,
5
+ balck_width: 3,
6
+ explore_parent: true,
7
+ chart_distribution: false,
8
+ chart_file_name: 'distribution.png',
9
+ chart_theme: {
10
+ marker_color: '#AEA9A9',
11
+ font_color: 'black',
12
+ background_colors: 'white'
13
+ }
14
+ }.freeze
15
+
16
+ class << self
17
+ def options
18
+ @options ||= DEFAULTS.dup
19
+ end
20
+
21
+ attr_writer :options
22
+
23
+ def configure
24
+ yield self
25
+ end
26
+ end
27
+
28
+ DEFAULTS.each do |k, _v|
29
+ define_singleton_method "#{k}=" do |value|
30
+ options.merge!(k => value)
31
+ end
32
+
33
+ define_singleton_method k do
34
+ options[k]
35
+ end
36
+ end
37
+ end
@@ -0,0 +1,63 @@
1
+ module CxExtractor
2
+ # utils for cx_extractor
3
+ module Utils
4
+ def line_block_distribute(lines)
5
+ block_distribution = []
6
+ index_distribution = lines.map(&:length)
7
+ (0...(lines.length - balck_width + 1)).each do |i|
8
+ word_num = 0
9
+ (0...balck_width).each do |j|
10
+ word_num += index_distribution[i + j]
11
+ end
12
+ block_distribution[i] = word_num
13
+ end
14
+ block_distribution
15
+ end
16
+
17
+ def find_surge(block_distribution, start, threshold)
18
+ ((start + 1)...block_distribution.length - 3).each do |index|
19
+ if block_distribution[index] > threshold && (
20
+ block_distribution[index + 1] > 0 ||
21
+ block_distribution[index + 2] > 0 ||
22
+ block_distribution[index + 3] > 0)
23
+ return index
24
+ end
25
+ end
26
+ -1
27
+ end
28
+
29
+ def find_dive(block_distribution, surge_point)
30
+ ((surge_point + 1)...(block_distribution.size - 2)).each do |index|
31
+ if block_distribution[index].zero? &&
32
+ block_distribution[index + 1].zero?
33
+ return index - 1
34
+ end
35
+ end
36
+ block_distribution.size - 1
37
+ end
38
+
39
+ def get_clean_text(dom)
40
+ # remove html comment
41
+ html = dom.clone
42
+ html.gsub!(/<!--.*?(.|\n)*?-->/, "\n")
43
+ # remove javascript
44
+ html.gsub!(%r{<script.*?>.*?(.|\n)*?</script>}, "\n")
45
+ # remove a
46
+ html.gsub!(%r{<a[\t|\n|\r|\f].*?>.*?</a>}, '')
47
+ # remove css
48
+ html.gsub!(%r{<style.*?>.*?(.|\n)*?</style>}, "\n")
49
+ # remove tag
50
+ html.gsub!(/<.*?(.|\n)*?>/, '')
51
+ replace_special_char(html)
52
+ end
53
+
54
+ def replace_special_char(str)
55
+ str.gsub!('&#8226;', '·')
56
+ str.gsub!('&amp;', '&')
57
+ str.gsub!('&nbsp;', ' ')
58
+ str.gsub!('&copy;', '@')
59
+ str.gsub!("\r\n|\r", "\n")
60
+ str
61
+ end
62
+ end
63
+ end
@@ -0,0 +1,3 @@
1
+ module CxExtractor
2
+ VERSION = '0.1.2'.freeze
3
+ end
metadata ADDED
@@ -0,0 +1,162 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: cx_extractor
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.2
5
+ platform: ruby
6
+ authors:
7
+ - Feng Ce
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2019-06-10 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: gruff
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: 0.7.0
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: 0.7.0
27
+ - !ruby/object:Gem::Dependency
28
+ name: nokogiri
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '1.0'
34
+ type: :runtime
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '1.0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: bundler
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: '1.16'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - "~>"
53
+ - !ruby/object:Gem::Version
54
+ version: '1.16'
55
+ - !ruby/object:Gem::Dependency
56
+ name: charlock_holmes
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: rake
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - "~>"
74
+ - !ruby/object:Gem::Version
75
+ version: '10.0'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - "~>"
81
+ - !ruby/object:Gem::Version
82
+ version: '10.0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: rspec
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - "~>"
88
+ - !ruby/object:Gem::Version
89
+ version: '3.0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - "~>"
95
+ - !ruby/object:Gem::Version
96
+ version: '3.0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: typhoeus
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ description: |
112
+ Used to extract text from the web page.
113
+ This tool is appropriate for the web page which contains lots of text.
114
+ email:
115
+ - kalelfc@gmail.com
116
+ executables: []
117
+ extensions: []
118
+ extra_rdoc_files: []
119
+ files:
120
+ - ".gitignore"
121
+ - ".rspec"
122
+ - ".rubocop.yml"
123
+ - ".travis.yml"
124
+ - Gemfile
125
+ - Gemfile.lock
126
+ - LICENSE.txt
127
+ - README.md
128
+ - Rakefile
129
+ - _config.yml
130
+ - bin/console
131
+ - bin/setup
132
+ - cx_extractor.gemspec
133
+ - lib/cx_extractor.rb
134
+ - lib/cx_extractor/chart.rb
135
+ - lib/cx_extractor/config.rb
136
+ - lib/cx_extractor/utils.rb
137
+ - lib/cx_extractor/version.rb
138
+ homepage: https://fcce.github.io/cx_extractor/
139
+ licenses:
140
+ - MIT
141
+ metadata: {}
142
+ post_install_message:
143
+ rdoc_options: []
144
+ require_paths:
145
+ - lib
146
+ required_ruby_version: !ruby/object:Gem::Requirement
147
+ requirements:
148
+ - - ">="
149
+ - !ruby/object:Gem::Version
150
+ version: '0'
151
+ required_rubygems_version: !ruby/object:Gem::Requirement
152
+ requirements:
153
+ - - ">="
154
+ - !ruby/object:Gem::Version
155
+ version: '0'
156
+ requirements: []
157
+ rubyforge_project:
158
+ rubygems_version: 2.7.9
159
+ signing_key:
160
+ specification_version: 4
161
+ summary: Used to extract text from the web page.
162
+ test_files: []