botz 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +14 -0
- data/.rspec +3 -0
- data/.rubocop.yml +23 -0
- data/.rubocop_todo.yml +13 -0
- data/.ruby-version +1 -0
- data/.travis.yml +7 -0
- data/CHANGELOG.md +9 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +6 -0
- data/Gemfile.lock +86 -0
- data/LICENSE.txt +21 -0
- data/README.md +43 -0
- data/Rakefile +8 -0
- data/bin/console +20 -0
- data/bin/setup +8 -0
- data/botz.gemspec +35 -0
- data/exe/botz +17 -0
- data/lib/botz/command.rb +45 -0
- data/lib/botz/downloader.rb +43 -0
- data/lib/botz/html_scraper_macro.rb +72 -0
- data/lib/botz/macro.rb +70 -0
- data/lib/botz/spider.rb +17 -0
- data/lib/botz/version.rb +5 -0
- data/lib/botz.rb +38 -0
- metadata +166 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: f954d590343d6a8b8d94dddb90e405105fd1574f97c7b6b781248401e5694d45
|
4
|
+
data.tar.gz: d6757990b3ba7c9a1c57e3ea2537924dbf0df15132f8abda5041a507470be2d0
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 21b3758166a2a16069ea8c408a906390f650bc1a9cbd063cd298ea68c5566d6c598af1642a64872e6051bc90025e4cd850b3a8cd4375cbb45513d117121cb78e
|
7
|
+
data.tar.gz: 6f12d1277d08d6d2bc3b9f18f69e18f608d669bfab90a77eecf9edb1da3ebd1ce20a5a2d722c106f670378bea05eba3bfc9a461d6f2110f97b3dd63c224d2c1a
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.rubocop.yml
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
inherit_from: .rubocop_todo.yml
|
2
|
+
AllCops:
|
3
|
+
DisplayCopNames: true
|
4
|
+
TargetRubyVersion: 2.6
|
5
|
+
|
6
|
+
Style/ClassAndModuleChildren:
|
7
|
+
Enabled: false
|
8
|
+
|
9
|
+
Style/SignalException:
|
10
|
+
EnforcedStyle: semantic
|
11
|
+
|
12
|
+
Naming/UncommunicativeMethodParamName:
|
13
|
+
AllowedNames:
|
14
|
+
- as
|
15
|
+
|
16
|
+
Metrics/LineLength:
|
17
|
+
Max: 120
|
18
|
+
|
19
|
+
Metrics/BlockLength:
|
20
|
+
Max: 120
|
21
|
+
|
22
|
+
SignalException:
|
23
|
+
EnforcedStyle: semantic
|
data/.rubocop_todo.yml
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
# This configuration was generated by
|
2
|
+
# `rubocop --auto-gen-config`
|
3
|
+
# on 2019-03-29 18:00:03 +0900 using RuboCop version 0.66.0.
|
4
|
+
# The point is for the user to remove these configuration records
|
5
|
+
# one by one as the offenses are removed from the code base.
|
6
|
+
# Note that changes in the inspected code, or installation of new
|
7
|
+
# versions of RuboCop, may require this file to be generated again.
|
8
|
+
|
9
|
+
# Offense count: 7
|
10
|
+
# Configuration parameters: AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, IgnoredPatterns.
|
11
|
+
# URISchemes: http, https
|
12
|
+
Metrics/LineLength:
|
13
|
+
Max: 96
|
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
2.6.2
|
data/.travis.yml
ADDED
data/CHANGELOG.md
ADDED
@@ -0,0 +1,9 @@
|
|
1
|
+
# Change Log
|
2
|
+
All notable changes to this project will be documented in this file.
|
3
|
+
|
4
|
+
The format is based on [Keep a Changelog](http://keepachangelog.com/)
|
5
|
+
and this project adheres to [Semantic Versioning](http://semver.org/).
|
6
|
+
|
7
|
+
## [Unreleased]
|
8
|
+
|
9
|
+
## [0.1.0]
|
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at aileron.cc@gmail.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
botz (0.1.0)
|
5
|
+
activemodel (~> 5.2)
|
6
|
+
activesupport (~> 5.2)
|
7
|
+
mechanize
|
8
|
+
|
9
|
+
GEM
|
10
|
+
remote: https://rubygems.org/
|
11
|
+
specs:
|
12
|
+
activemodel (5.2.3)
|
13
|
+
activesupport (= 5.2.3)
|
14
|
+
activesupport (5.2.3)
|
15
|
+
concurrent-ruby (~> 1.0, >= 1.0.2)
|
16
|
+
i18n (>= 0.7, < 2)
|
17
|
+
minitest (~> 5.1)
|
18
|
+
tzinfo (~> 1.1)
|
19
|
+
coderay (1.1.2)
|
20
|
+
concurrent-ruby (1.1.5)
|
21
|
+
connection_pool (2.2.2)
|
22
|
+
diff-lcs (1.3)
|
23
|
+
domain_name (0.5.20180417)
|
24
|
+
unf (>= 0.0.5, < 1.0.0)
|
25
|
+
http-cookie (1.0.3)
|
26
|
+
domain_name (~> 0.5)
|
27
|
+
i18n (1.6.0)
|
28
|
+
concurrent-ruby (~> 1.0)
|
29
|
+
mechanize (2.7.6)
|
30
|
+
domain_name (~> 0.5, >= 0.5.1)
|
31
|
+
http-cookie (~> 1.0)
|
32
|
+
mime-types (>= 1.17.2)
|
33
|
+
net-http-digest_auth (~> 1.1, >= 1.1.1)
|
34
|
+
net-http-persistent (>= 2.5.2)
|
35
|
+
nokogiri (~> 1.6)
|
36
|
+
ntlm-http (~> 0.1, >= 0.1.1)
|
37
|
+
webrobots (>= 0.0.9, < 0.2)
|
38
|
+
method_source (0.9.2)
|
39
|
+
mime-types (3.2.2)
|
40
|
+
mime-types-data (~> 3.2015)
|
41
|
+
mime-types-data (3.2019.0331)
|
42
|
+
mini_portile2 (2.4.0)
|
43
|
+
minitest (5.11.3)
|
44
|
+
net-http-digest_auth (1.4.1)
|
45
|
+
net-http-persistent (3.0.1)
|
46
|
+
connection_pool (~> 2.2)
|
47
|
+
nokogiri (1.10.3)
|
48
|
+
mini_portile2 (~> 2.4.0)
|
49
|
+
ntlm-http (0.1.1)
|
50
|
+
pry (0.12.2)
|
51
|
+
coderay (~> 1.1.0)
|
52
|
+
method_source (~> 0.9.0)
|
53
|
+
rake (10.5.0)
|
54
|
+
rspec (3.8.0)
|
55
|
+
rspec-core (~> 3.8.0)
|
56
|
+
rspec-expectations (~> 3.8.0)
|
57
|
+
rspec-mocks (~> 3.8.0)
|
58
|
+
rspec-core (3.8.0)
|
59
|
+
rspec-support (~> 3.8.0)
|
60
|
+
rspec-expectations (3.8.2)
|
61
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
62
|
+
rspec-support (~> 3.8.0)
|
63
|
+
rspec-mocks (3.8.0)
|
64
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
65
|
+
rspec-support (~> 3.8.0)
|
66
|
+
rspec-support (3.8.0)
|
67
|
+
thread_safe (0.3.6)
|
68
|
+
tzinfo (1.2.5)
|
69
|
+
thread_safe (~> 0.1)
|
70
|
+
unf (0.1.4)
|
71
|
+
unf_ext
|
72
|
+
unf_ext (0.0.7.6)
|
73
|
+
webrobots (0.1.2)
|
74
|
+
|
75
|
+
PLATFORMS
|
76
|
+
ruby
|
77
|
+
|
78
|
+
DEPENDENCIES
|
79
|
+
botz!
|
80
|
+
bundler (~> 2.0)
|
81
|
+
pry
|
82
|
+
rake (~> 10.0)
|
83
|
+
rspec (~> 3.0)
|
84
|
+
|
85
|
+
BUNDLED WITH
|
86
|
+
2.0.1
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2019 aileron
|
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 +1,43 @@
|
|
1
|
+
# Botz
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/crawler`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'botz'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install botz
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
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.
|
30
|
+
|
31
|
+
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).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/crawler. 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.
|
36
|
+
|
37
|
+
## License
|
38
|
+
|
39
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
40
|
+
|
41
|
+
## Code of Conduct
|
42
|
+
|
43
|
+
Everyone interacting in the Crawler project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/crawler/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
require 'bundler/setup'
|
5
|
+
require 'botz'
|
6
|
+
|
7
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
8
|
+
# with your gem easier. You can also use a different console, if you like.
|
9
|
+
|
10
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
11
|
+
require 'pry'
|
12
|
+
def reload!
|
13
|
+
files = $LOADED_FEATURES.select { |feat| feat =~ %r{/gem_name/} }
|
14
|
+
files.each { |file| load file }
|
15
|
+
load 'lib/botz.rb'
|
16
|
+
end
|
17
|
+
Pry.start
|
18
|
+
|
19
|
+
# require 'irb'
|
20
|
+
# IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/botz.gemspec
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
lib = File.expand_path('lib', __dir__)
|
4
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
5
|
+
require 'botz/version'
|
6
|
+
|
7
|
+
Gem::Specification.new do |spec|
|
8
|
+
spec.name = 'botz'
|
9
|
+
spec.version = Botz::VERSION
|
10
|
+
spec.authors = ['aileron']
|
11
|
+
spec.email = ['aileron.cc@gmail.com']
|
12
|
+
|
13
|
+
spec.summary = 'web bot crawling dsl'
|
14
|
+
# spec.description = 'TODO: Write a longer description or delete this line.'
|
15
|
+
spec.homepage = 'https://github.com/aileron-inc/botz'
|
16
|
+
spec.license = 'MIT'
|
17
|
+
|
18
|
+
# Specify which files should be added to the gem when it is released.
|
19
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
20
|
+
spec.files = Dir.chdir(File.expand_path(__dir__)) do
|
21
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
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_development_dependency 'bundler', '~> 2.0'
|
28
|
+
spec.add_development_dependency 'pry'
|
29
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
30
|
+
spec.add_development_dependency 'rspec', '~> 3.0'
|
31
|
+
|
32
|
+
spec.add_runtime_dependency 'activemodel', '~> 5.2'
|
33
|
+
spec.add_runtime_dependency 'activesupport', '~> 5.2'
|
34
|
+
spec.add_runtime_dependency 'mechanize'
|
35
|
+
end
|
data/exe/botz
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
require 'botz'
|
5
|
+
crawler = Botz.open(ARGV[0])
|
6
|
+
if ARGV[1]
|
7
|
+
crawler.call(ARGV[1], ARGV[2])
|
8
|
+
else
|
9
|
+
print <<~SHELL
|
10
|
+
function spider() {
|
11
|
+
botz #{ARGV[0]} spider $1
|
12
|
+
}
|
13
|
+
function scraper() {
|
14
|
+
botz #{ARGV[0]} scraper $1
|
15
|
+
}
|
16
|
+
SHELL
|
17
|
+
end
|
data/lib/botz/command.rb
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
#
|
4
|
+
# Class representing a website defined by DSL
|
5
|
+
#
|
6
|
+
class Botz::Command
|
7
|
+
class_attribute :definition
|
8
|
+
|
9
|
+
class << self
|
10
|
+
delegate :domain, :spiders, :scrapers, to: :definition
|
11
|
+
|
12
|
+
def call(category, name)
|
13
|
+
case category.to_sym
|
14
|
+
when :spider then spider(name)
|
15
|
+
when :scraper then scraper(name)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
# rubocop:disable Lint/AssignmentInCondition, Style/RescueStandardError
|
20
|
+
def scraper(name)
|
21
|
+
command = scrapers[name.to_sym]
|
22
|
+
while line = STDIN.gets
|
23
|
+
url = line.strip
|
24
|
+
begin
|
25
|
+
command.call(url)
|
26
|
+
rescue
|
27
|
+
STDERR.puts "ERROR #{command} #{url}"
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
# rubocop:enable Lint/AssignmentInCondition, Style/RescueStandardError
|
32
|
+
|
33
|
+
def spider(name)
|
34
|
+
command = spiders[name.to_sym]
|
35
|
+
if File.pipe?(STDIN)
|
36
|
+
STDIN.each_line do |line|
|
37
|
+
start_url = line.strip
|
38
|
+
command.call(start_url) { |url| puts url }
|
39
|
+
end
|
40
|
+
else
|
41
|
+
command.call { |url| puts url }
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,43 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
#
|
4
|
+
# This class is responsible for actually making a network connection and downloading hypertext
|
5
|
+
#
|
6
|
+
class Botz::Downloader
|
7
|
+
include ActiveModel::Model
|
8
|
+
include ActiveModel::Attributes
|
9
|
+
USER_AGENT = [
|
10
|
+
'Mozilla/5.0',
|
11
|
+
'(Macintosh; Intel Mac OS X 10_12_6)',
|
12
|
+
'AppleWebKit/537.36',
|
13
|
+
'(KHTML, like Gecko)',
|
14
|
+
'Chrome/64.0.3282.186',
|
15
|
+
'Safari/537.36'
|
16
|
+
].join(' ')
|
17
|
+
|
18
|
+
html_loader = lambda do |ctx, url, block|
|
19
|
+
block_result = nil
|
20
|
+
agent = Mechanize.new
|
21
|
+
agent.user_agent = USER_AGENT
|
22
|
+
ctx&.call(agent)
|
23
|
+
agent.get(url) { |page| block_result = block.call(page) }
|
24
|
+
block_result
|
25
|
+
end
|
26
|
+
|
27
|
+
json_loader = lambda do |_ctx, url, block|
|
28
|
+
block.call JSON.parse(OpenURI.open_uri(url, 'User-Agent' => USER_AGENT))
|
29
|
+
end
|
30
|
+
|
31
|
+
class_attribute :loaders, default: { html: html_loader, json: json_loader }
|
32
|
+
|
33
|
+
attribute :context
|
34
|
+
attribute :loader
|
35
|
+
|
36
|
+
def initialize(name, context = nil)
|
37
|
+
super(loader: loaders[name], context: context)
|
38
|
+
end
|
39
|
+
|
40
|
+
def call(url, &block)
|
41
|
+
loader.call(context, url, block)
|
42
|
+
end
|
43
|
+
end
|
@@ -0,0 +1,72 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
#
|
4
|
+
# DSL for parsing html into objects
|
5
|
+
#
|
6
|
+
class Botz::HtmlScraperMacro
|
7
|
+
include ActiveModel::Model
|
8
|
+
include ActiveModel::Attributes
|
9
|
+
|
10
|
+
#
|
11
|
+
# Scraper error class
|
12
|
+
#
|
13
|
+
class Error < StandardError
|
14
|
+
def initialize(scraper_class, url, errors)
|
15
|
+
super("#{scraper_class}(#{url}) # #{errors.full_messages}")
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
attr_reader :scraper_class
|
20
|
+
attr_reader :url
|
21
|
+
attr_reader :html
|
22
|
+
attr_reader :writer
|
23
|
+
|
24
|
+
def initialize(scraper_class, resource, writer)
|
25
|
+
@scraper_class = scraper_class
|
26
|
+
@url = resource.uri
|
27
|
+
@html = resource
|
28
|
+
@writer = writer
|
29
|
+
end
|
30
|
+
|
31
|
+
class << self
|
32
|
+
def field_names
|
33
|
+
@field_names ||= []
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
def primary_key
|
38
|
+
url.to_s
|
39
|
+
end
|
40
|
+
|
41
|
+
def to_h
|
42
|
+
fetched_at = Time.current
|
43
|
+
fetched_on = fetched_at.beginning_of_day
|
44
|
+
timestamps = { fetched_on: fetched_on, fetched_at: fetched_at }
|
45
|
+
self.class.field_names.map { |field| [field, send(field)] }.to_h.merge(timestamps)
|
46
|
+
end
|
47
|
+
|
48
|
+
def save
|
49
|
+
fail Error.new(scraper_class, url, errors) if invalid?
|
50
|
+
|
51
|
+
writer.call(to_h)
|
52
|
+
end
|
53
|
+
|
54
|
+
# rubocop:disable Metrics/AbcSize, Metrics/MethodLength
|
55
|
+
def self.field(name, path = nil, persist: true, &block)
|
56
|
+
if persist
|
57
|
+
field_names << name
|
58
|
+
case name
|
59
|
+
when /.*\?/
|
60
|
+
validates name, inclusion: { in: [true, false] }
|
61
|
+
else
|
62
|
+
validates name, presence: true, allow_blank: true
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
return define_method(name) { instance_exec(html, &block) } if path.nil?
|
67
|
+
return define_method(name) { html.search(path).text.strip } if block.nil?
|
68
|
+
|
69
|
+
define_method(name) { html.search(path).first.try { |e| instance_exec(e, &block) } }
|
70
|
+
end
|
71
|
+
# rubocop:enable Metrics/AbcSize, Metrics/MethodLength
|
72
|
+
end
|
data/lib/botz/macro.rb
ADDED
@@ -0,0 +1,70 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
#
|
4
|
+
# Class representing a website defined by DSL
|
5
|
+
#
|
6
|
+
class Botz::Macro
|
7
|
+
Output = ->(result) { STDOUT.puts(result.to_json) }
|
8
|
+
|
9
|
+
class_attribute :name
|
10
|
+
class_attribute :domain
|
11
|
+
class_attribute :command
|
12
|
+
class_attribute :spiders, default: {}
|
13
|
+
class_attribute :scrapers, default: {}
|
14
|
+
|
15
|
+
# rubocop:disable Metrics/MethodLength, Metrics/AbcSize
|
16
|
+
class << self
|
17
|
+
def output(&block)
|
18
|
+
remove_const(:Output)
|
19
|
+
const_set(:Output, block)
|
20
|
+
end
|
21
|
+
|
22
|
+
def scraper(name, as: :html, output: Output, &block)
|
23
|
+
class_name = "#{name}_scraper".classify
|
24
|
+
downloader = Botz::Downloader.new(as)
|
25
|
+
binder_base = Botz.const_get "#{as}_scraper_macro".classify
|
26
|
+
binder = Class.new(binder_base, &block)
|
27
|
+
binder.define_singleton_method(:name) { class_name }
|
28
|
+
crawler_class = self
|
29
|
+
scraper_class = Class.new do
|
30
|
+
define_singleton_method(:crawler_class) { crawler_class }
|
31
|
+
define_singleton_method(:bind) do |url|
|
32
|
+
downloader.call(url) do |resource|
|
33
|
+
binder.new(scraper_class, resource, output)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
define_singleton_method(:call) { |url| bind(url).save }
|
37
|
+
end
|
38
|
+
const_set(class_name, scraper_class)
|
39
|
+
scrapers[name] = scraper_class
|
40
|
+
end
|
41
|
+
|
42
|
+
def spider(name, start_url = nil, as: :html, &block)
|
43
|
+
downloader = Botz::Downloader.new(as)
|
44
|
+
spider = Botz::Spider.new(&block)
|
45
|
+
spider_class = Class.new do
|
46
|
+
define_singleton_method(:call) do |url = start_url, &spider_block|
|
47
|
+
downloader.call(url) do |resource|
|
48
|
+
spider.call(resource, &spider_block)
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
const_set("#{name}_spider".classify, spider_class)
|
53
|
+
spiders[name] = spider_class
|
54
|
+
end
|
55
|
+
|
56
|
+
def before_context(url:)
|
57
|
+
downloader = Botz::Downloader.new(:html)
|
58
|
+
before_context_class = Class.new do
|
59
|
+
define_singleton_method(:call) do
|
60
|
+
downloader.call(url) do |page|
|
61
|
+
yield(page)
|
62
|
+
page.mech
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
const_set('before_context'.classify, before_context_class)
|
67
|
+
end
|
68
|
+
end
|
69
|
+
# rubocop:enable Metrics/MethodLength, Metrics/AbcSize
|
70
|
+
end
|
data/lib/botz/spider.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
#
|
4
|
+
# Spider
|
5
|
+
#
|
6
|
+
class Botz::Spider
|
7
|
+
def initialize(&block)
|
8
|
+
define_singleton_method(:bind, &block)
|
9
|
+
end
|
10
|
+
|
11
|
+
def call(resource)
|
12
|
+
yielder = lambda do |url|
|
13
|
+
yield url if block_given?
|
14
|
+
end
|
15
|
+
bind(resource, yielder)
|
16
|
+
end
|
17
|
+
end
|
data/lib/botz/version.rb
ADDED
data/lib/botz.rb
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'botz/version'
|
4
|
+
require 'active_support/all'
|
5
|
+
require 'active_model'
|
6
|
+
require 'mechanize'
|
7
|
+
|
8
|
+
#
|
9
|
+
# web bot dsl engine
|
10
|
+
#
|
11
|
+
module Botz
|
12
|
+
extend ActiveSupport::Autoload
|
13
|
+
autoload :Command
|
14
|
+
autoload :Macro
|
15
|
+
autoload :Spider
|
16
|
+
autoload :Downloader
|
17
|
+
autoload :HtmlScraperMacro
|
18
|
+
|
19
|
+
def self.open(filepath)
|
20
|
+
remove_const(:Crawler) if const_defined?(:Crawler)
|
21
|
+
const_set(:Crawler, Module.new)
|
22
|
+
# rubocop:disable Security/Eval
|
23
|
+
eval(File.open(filepath).read)
|
24
|
+
# rubocop:enable Security/Eval
|
25
|
+
end
|
26
|
+
|
27
|
+
def self.define(name, domain:, &block)
|
28
|
+
crawler_definition = Class.new(Botz::Macro, &block)
|
29
|
+
crawler_definition.domain = domain
|
30
|
+
|
31
|
+
command_class = Class.new(Botz::Command)
|
32
|
+
command_class.definition = crawler_definition
|
33
|
+
crawler_definition.command = command_class
|
34
|
+
|
35
|
+
Crawler.const_set(name.to_s.camelize, crawler_definition)
|
36
|
+
command_class
|
37
|
+
end
|
38
|
+
end
|
metadata
ADDED
@@ -0,0 +1,166 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: botz
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- aileron
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2019-06-25 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: '2.0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '2.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: pry
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rspec
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '3.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '3.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: activemodel
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '5.2'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '5.2'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: activesupport
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '5.2'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '5.2'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: mechanize
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
description:
|
112
|
+
email:
|
113
|
+
- aileron.cc@gmail.com
|
114
|
+
executables:
|
115
|
+
- botz
|
116
|
+
extensions: []
|
117
|
+
extra_rdoc_files: []
|
118
|
+
files:
|
119
|
+
- ".gitignore"
|
120
|
+
- ".rspec"
|
121
|
+
- ".rubocop.yml"
|
122
|
+
- ".rubocop_todo.yml"
|
123
|
+
- ".ruby-version"
|
124
|
+
- ".travis.yml"
|
125
|
+
- CHANGELOG.md
|
126
|
+
- CODE_OF_CONDUCT.md
|
127
|
+
- Gemfile
|
128
|
+
- Gemfile.lock
|
129
|
+
- LICENSE.txt
|
130
|
+
- README.md
|
131
|
+
- Rakefile
|
132
|
+
- bin/console
|
133
|
+
- bin/setup
|
134
|
+
- botz.gemspec
|
135
|
+
- exe/botz
|
136
|
+
- lib/botz.rb
|
137
|
+
- lib/botz/command.rb
|
138
|
+
- lib/botz/downloader.rb
|
139
|
+
- lib/botz/html_scraper_macro.rb
|
140
|
+
- lib/botz/macro.rb
|
141
|
+
- lib/botz/spider.rb
|
142
|
+
- lib/botz/version.rb
|
143
|
+
homepage: https://github.com/aileron-inc/botz
|
144
|
+
licenses:
|
145
|
+
- MIT
|
146
|
+
metadata: {}
|
147
|
+
post_install_message:
|
148
|
+
rdoc_options: []
|
149
|
+
require_paths:
|
150
|
+
- lib
|
151
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
152
|
+
requirements:
|
153
|
+
- - ">="
|
154
|
+
- !ruby/object:Gem::Version
|
155
|
+
version: '0'
|
156
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
157
|
+
requirements:
|
158
|
+
- - ">="
|
159
|
+
- !ruby/object:Gem::Version
|
160
|
+
version: '0'
|
161
|
+
requirements: []
|
162
|
+
rubygems_version: 3.0.3
|
163
|
+
signing_key:
|
164
|
+
specification_version: 4
|
165
|
+
summary: web bot crawling dsl
|
166
|
+
test_files: []
|