telegraph-parser 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +88 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/telegraph/parser/article.rb +22 -0
- data/lib/telegraph/parser/binding.rb +31 -0
- data/lib/telegraph/parser/parser.rb +54 -0
- data/lib/telegraph/parser/version.rb +5 -0
- data/lib/telegraph/parser.rb +9 -0
- data/telegraph-parser.gemspec +25 -0
- metadata +113 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: c27c84d13c2d7725fbb32104dc5a42a92998ceb0
|
4
|
+
data.tar.gz: f42a5d5cc5a7c1135d615df81de818cbec4e85ea
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 656239f075164f8d6dd4a241cc000d166ba1c9ad60071e905e979d2c1f9bc1914badf8d314146af878ba7d3f7a9a3ae8ebc29268a0d3301b5207dc2c8399f4e4
|
7
|
+
data.tar.gz: d62631df9d0482117e006283bb43adb40743dfccff430e5b7e8623f3a9dd4894f50b53685b1c8d8a1ca6822c255458333c4d59e58d232c28807cbf466615d06e
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 TODO: Write your name
|
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.
|
data/README.md
ADDED
@@ -0,0 +1,88 @@
|
|
1
|
+
# telegraph-parser
|
2
|
+
|
3
|
+
Gem to pull and parse articles from Telegra.ph.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'telegraph-parser'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install telegraph-parser
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
Load parser to your project.
|
24
|
+
|
25
|
+
```ruby
|
26
|
+
require 'telegraph/parser'
|
27
|
+
|
28
|
+
```
|
29
|
+
|
30
|
+
Load article from Telegra.ph:
|
31
|
+
|
32
|
+
```ruby
|
33
|
+
article = Telegraph::Parser::Article.load('Пять-врагов-государства-12-10')
|
34
|
+
```
|
35
|
+
|
36
|
+
Article contains attributes:
|
37
|
+
|
38
|
+
```ruby
|
39
|
+
article.id
|
40
|
+
=> "Пять-врагов-государства-12-10"
|
41
|
+
|
42
|
+
article.title
|
43
|
+
=> "Пять врагов государства"
|
44
|
+
|
45
|
+
article.author
|
46
|
+
=> "Алексей ШЕРСТНЕВ"
|
47
|
+
|
48
|
+
article.content
|
49
|
+
=> "<article><p><br></p>\n<figure><div class=\"figure_wrapper\">....
|
50
|
+
|
51
|
+
article.imagese.images
|
52
|
+
=> {"/6e4ecf2f73df0e2a97028.gif"=>
|
53
|
+
"GIF89a\xF4\x01\xDC\x00\xF7\xFF\x00\x00\x00\x00/B9\x8A\x94\x8C\xAB\xB0\xAA\x15\x18!z\x87\x840\x01\x05&)1\xC7\xA0\xA0WffK\x01\x06\x06\x14\x15\x93\n'\xA21Gvzy\xA8\x00\x12ivv)CC\x13!\x18\x....
|
54
|
+
|
55
|
+
```
|
56
|
+
|
57
|
+
telegraph-parser will change images names in src attribute
|
58
|
+
|
59
|
+
```
|
60
|
+
http://telegra.ph/file/6e4ecf2f73df0e2a97028.gif => 6e4ecf2f73df0e2a97028.gif
|
61
|
+
|
62
|
+
```
|
63
|
+
|
64
|
+
|
65
|
+
You can add prefix to image filenames:
|
66
|
+
|
67
|
+
```ruby
|
68
|
+
article = Telegraph::Parser::Article.load('Пять-врагов-государства-12-10', image_prefix: '/static')
|
69
|
+
|
70
|
+
article.images.keys.first
|
71
|
+
=> "/static/6e4ecf2f73df0e2a97028.gif"
|
72
|
+
```
|
73
|
+
|
74
|
+
## Development
|
75
|
+
|
76
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
77
|
+
|
78
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
79
|
+
|
80
|
+
## Contributing
|
81
|
+
|
82
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/svernidub/telegraph-parser.
|
83
|
+
|
84
|
+
|
85
|
+
## License
|
86
|
+
|
87
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
88
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "telegraph/parser"
|
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
|
data/bin/setup
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
module Telegraph
|
2
|
+
module Parser
|
3
|
+
class Article
|
4
|
+
attr_accessor :id, :title, :author, :content, :images
|
5
|
+
|
6
|
+
def initialize(attributes)
|
7
|
+
attributes.each do |attr, val|
|
8
|
+
next unless respond_to?("#{attr}=")
|
9
|
+
send("#{attr}=", val)
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
def self.load(article_id, image_prefix: '')
|
14
|
+
binding = Binding.new(article_id)
|
15
|
+
|
16
|
+
Parser.new(binding, image_prefix).article.tap do |article|
|
17
|
+
article.id = article_id
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,31 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
|
3
|
+
module Telegraph
|
4
|
+
module Parser
|
5
|
+
class Binding
|
6
|
+
BASE_URI = 'telegra.ph'
|
7
|
+
|
8
|
+
attr_accessor :article_id
|
9
|
+
|
10
|
+
def initialize(article_id)
|
11
|
+
self.article_id = article_id
|
12
|
+
end
|
13
|
+
|
14
|
+
def content
|
15
|
+
Net::HTTP.get(BASE_URI, "/#{article_id}")
|
16
|
+
rescue EOFError
|
17
|
+
""
|
18
|
+
end
|
19
|
+
|
20
|
+
def image(src, prefix)
|
21
|
+
src.gsub!('http://telegra.ph', '')
|
22
|
+
{ image_id(src, prefix) => open("http://#{BASE_URI}#{src}").read }
|
23
|
+
end
|
24
|
+
|
25
|
+
def image_id(src, prefix)
|
26
|
+
src.gsub!('http://telegra.ph', '')
|
27
|
+
"#{prefix}/#{File.basename(URI.parse("#{BASE_URI}#{src}").path)}"
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
@@ -0,0 +1,54 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
|
3
|
+
module Telegraph
|
4
|
+
module Parser
|
5
|
+
class Parser
|
6
|
+
attr_accessor :bindings, :page, :article, :image_prefix
|
7
|
+
|
8
|
+
def initialize(binding, image_prefix)
|
9
|
+
self.bindings = binding
|
10
|
+
self.image_prefix = image_prefix
|
11
|
+
parse_html
|
12
|
+
end
|
13
|
+
|
14
|
+
private
|
15
|
+
|
16
|
+
def page
|
17
|
+
@page ||= Nokogiri::HTML(bindings.content).css('article')
|
18
|
+
end
|
19
|
+
|
20
|
+
def images
|
21
|
+
{}.tap do |images|
|
22
|
+
page.search('.//img').each do |image|
|
23
|
+
images.merge!(bindings.image(image.attributes['src'].value,
|
24
|
+
image_prefix))
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
def parse_html
|
30
|
+
images_hash = images
|
31
|
+
self.article = Article.new(title: tag_content(:h1),
|
32
|
+
author: tag_content(:address),
|
33
|
+
content: without_tags,
|
34
|
+
images: images_hash)
|
35
|
+
end
|
36
|
+
|
37
|
+
def tag_content(tag)
|
38
|
+
page.search(".//#{tag}").text
|
39
|
+
end
|
40
|
+
|
41
|
+
def without_tags
|
42
|
+
page_copy = page.dup
|
43
|
+
%i(h1 address).each { |tag| page.search(".//#{tag}").remove }
|
44
|
+
|
45
|
+
page_copy.search('.//img').each do |image|
|
46
|
+
image.attributes['src'].value =
|
47
|
+
bindings.image_id(image.attributes['src'].value, image_prefix)
|
48
|
+
end
|
49
|
+
|
50
|
+
page_copy.remove_attr('id').remove_class.to_s
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'telegraph/parser/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "telegraph-parser"
|
8
|
+
spec.version = Telegraph::Parser::VERSION
|
9
|
+
spec.authors = ["Sergey Vernidub"]
|
10
|
+
spec.email = ["svernidub@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Gem to pull and parse articles from Telegra.ph.}
|
13
|
+
spec.homepage = "https://github.com/svernidub/telegraph-parser"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
24
|
+
spec.add_development_dependency "nokogiri", "~> 1.6.8"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,113 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: telegraph-parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Sergey Vernidub
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-12-11 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.11'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.11'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: nokogiri
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 1.6.8
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 1.6.8
|
69
|
+
description:
|
70
|
+
email:
|
71
|
+
- svernidub@gmail.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- Gemfile
|
78
|
+
- LICENSE.txt
|
79
|
+
- README.md
|
80
|
+
- Rakefile
|
81
|
+
- bin/console
|
82
|
+
- bin/setup
|
83
|
+
- lib/telegraph/parser.rb
|
84
|
+
- lib/telegraph/parser/article.rb
|
85
|
+
- lib/telegraph/parser/binding.rb
|
86
|
+
- lib/telegraph/parser/parser.rb
|
87
|
+
- lib/telegraph/parser/version.rb
|
88
|
+
- telegraph-parser.gemspec
|
89
|
+
homepage: https://github.com/svernidub/telegraph-parser
|
90
|
+
licenses:
|
91
|
+
- MIT
|
92
|
+
metadata: {}
|
93
|
+
post_install_message:
|
94
|
+
rdoc_options: []
|
95
|
+
require_paths:
|
96
|
+
- lib
|
97
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - ">="
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
103
|
+
requirements:
|
104
|
+
- - ">="
|
105
|
+
- !ruby/object:Gem::Version
|
106
|
+
version: '0'
|
107
|
+
requirements: []
|
108
|
+
rubyforge_project:
|
109
|
+
rubygems_version: 2.4.5.1
|
110
|
+
signing_key:
|
111
|
+
specification_version: 4
|
112
|
+
summary: Gem to pull and parse articles from Telegra.ph.
|
113
|
+
test_files: []
|