wonder_scrape 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 +11 -0
- data/.rspec +3 -0
- data/.ruby-version +1 -0
- data/.travis.yml +6 -0
- data/CHANGELOG.md +0 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +7 -0
- data/Gemfile.lock +87 -0
- data/LICENSE.txt +21 -0
- data/README.md +47 -0
- data/Rakefile +8 -0
- data/bin/console +15 -0
- data/bin/setup +8 -0
- data/exe/wonder_scrape +19 -0
- data/lib/wonder_scrape.rb +7 -0
- data/lib/wonder_scrape/cli.rb +49 -0
- data/lib/wonder_scrape/command.rb +41 -0
- data/lib/wonder_scrape/commands/.gitkeep +1 -0
- data/lib/wonder_scrape/commands/scrape.rb +93 -0
- data/lib/wonder_scrape/recorder.rb +47 -0
- data/lib/wonder_scrape/scrapers/mfc/field_parsers.rb +71 -0
- data/lib/wonder_scrape/scrapers/mfc/item_parser.rb +146 -0
- data/lib/wonder_scrape/scrapers/mfc/mfc.rb +5 -0
- data/lib/wonder_scrape/scrapers/mfc/scraper.rb +72 -0
- data/lib/wonder_scrape/scrapers/scrapers.rb +5 -0
- data/lib/wonder_scrape/templates/.gitkeep +1 -0
- data/lib/wonder_scrape/templates/scrape/.gitkeep +1 -0
- data/lib/wonder_scrape/version.rb +5 -0
- data/lib/wonder_scrape/writers/csv.rb +32 -0
- data/lib/wonder_scrape/writers/hash.rb +22 -0
- data/lib/wonder_scrape/writers/writers.rb +3 -0
- data/wonder_scrape.gemspec +38 -0
- metadata +150 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: c27721fddd799f4cb631710d07c090a17abdaef56be4b9e725ac15e95bacce36
|
4
|
+
data.tar.gz: fc6469515a2d78a505d0911c0d8698b39a56a2ba7d1774aaf53723bf533c4ef3
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 23f4a73f08832f3ce85d06991ca879efb6a01c1592d53b8684d3a4a3cd8057c3e1335e8a4cb5f247c69026fa853df71e4d7d55c39f55be3cc14a27e60ffd549a
|
7
|
+
data.tar.gz: 8cc004a61c5a3f032c0f3a1e8e2e4028ce14c39ba04f62c77712ead4933418d3b7cdb08cf5fe324446c3f1d7626aaf9a1e2c6a67d2951d9e95ac018c2e90416f
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
2.7.0
|
data/.travis.yml
ADDED
data/CHANGELOG.md
ADDED
File without changes
|
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 bendawson.rb@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 [https://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: https://contributor-covenant.org
|
74
|
+
[version]: https://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,87 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
wonder_scrape (0.1.0)
|
5
|
+
nokogiri (~> 1.10.9)
|
6
|
+
thor
|
7
|
+
tty-progressbar
|
8
|
+
tty-prompt
|
9
|
+
upton (~> 0.3.6)
|
10
|
+
|
11
|
+
GEM
|
12
|
+
remote: https://rubygems.org/
|
13
|
+
specs:
|
14
|
+
diff-lcs (1.3)
|
15
|
+
domain_name (0.5.20190701)
|
16
|
+
unf (>= 0.0.5, < 1.0.0)
|
17
|
+
equatable (0.6.1)
|
18
|
+
http-accept (1.7.0)
|
19
|
+
http-cookie (1.0.3)
|
20
|
+
domain_name (~> 0.5)
|
21
|
+
mime-types (3.3.1)
|
22
|
+
mime-types-data (~> 3.2015)
|
23
|
+
mime-types-data (3.2020.0425)
|
24
|
+
mini_portile2 (2.4.0)
|
25
|
+
necromancer (0.5.1)
|
26
|
+
netrc (0.11.0)
|
27
|
+
nokogiri (1.10.9)
|
28
|
+
mini_portile2 (~> 2.4.0)
|
29
|
+
pastel (0.7.3)
|
30
|
+
equatable (~> 0.6)
|
31
|
+
tty-color (~> 0.5)
|
32
|
+
rake (12.3.3)
|
33
|
+
rest-client (2.1.0)
|
34
|
+
http-accept (>= 1.7.0, < 2.0)
|
35
|
+
http-cookie (>= 1.0.2, < 2.0)
|
36
|
+
mime-types (>= 1.16, < 4.0)
|
37
|
+
netrc (~> 0.8)
|
38
|
+
rspec (3.9.0)
|
39
|
+
rspec-core (~> 3.9.0)
|
40
|
+
rspec-expectations (~> 3.9.0)
|
41
|
+
rspec-mocks (~> 3.9.0)
|
42
|
+
rspec-core (3.9.1)
|
43
|
+
rspec-support (~> 3.9.1)
|
44
|
+
rspec-expectations (3.9.1)
|
45
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
46
|
+
rspec-support (~> 3.9.0)
|
47
|
+
rspec-mocks (3.9.1)
|
48
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
49
|
+
rspec-support (~> 3.9.0)
|
50
|
+
rspec-support (3.9.2)
|
51
|
+
strings-ansi (0.1.0)
|
52
|
+
thor (1.0.1)
|
53
|
+
tty-color (0.5.1)
|
54
|
+
tty-cursor (0.7.1)
|
55
|
+
tty-progressbar (0.17.0)
|
56
|
+
strings-ansi (~> 0.1.0)
|
57
|
+
tty-cursor (~> 0.7)
|
58
|
+
tty-screen (~> 0.7)
|
59
|
+
unicode-display_width (~> 1.6)
|
60
|
+
tty-prompt (0.21.0)
|
61
|
+
necromancer (~> 0.5.0)
|
62
|
+
pastel (~> 0.7.0)
|
63
|
+
tty-reader (~> 0.7.0)
|
64
|
+
tty-reader (0.7.0)
|
65
|
+
tty-cursor (~> 0.7)
|
66
|
+
tty-screen (~> 0.7)
|
67
|
+
wisper (~> 2.0.0)
|
68
|
+
tty-screen (0.7.1)
|
69
|
+
unf (0.1.4)
|
70
|
+
unf_ext
|
71
|
+
unf_ext (0.0.7.7)
|
72
|
+
unicode-display_width (1.7.0)
|
73
|
+
upton (0.3.6)
|
74
|
+
nokogiri (~> 1.5)
|
75
|
+
rest-client (~> 2.0, >= 1.6)
|
76
|
+
wisper (2.0.1)
|
77
|
+
|
78
|
+
PLATFORMS
|
79
|
+
ruby
|
80
|
+
|
81
|
+
DEPENDENCIES
|
82
|
+
rake (~> 12.0)
|
83
|
+
rspec (~> 3.0)
|
84
|
+
wonder_scrape!
|
85
|
+
|
86
|
+
BUNDLED WITH
|
87
|
+
2.1.4
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2020 Benjamin Dawson
|
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 +1,47 @@
|
|
1
|
+
# WonderScrape
|
2
|
+
|
3
|
+
A project to collect useful information from figure collecting websites.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'wonder_scrape'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle install
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install wonder_scrape
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
To get started, run:
|
24
|
+
|
25
|
+
$ wonder_scrape scrape
|
26
|
+
|
27
|
+
For more configuration options, run:
|
28
|
+
|
29
|
+
# wonder_scrape help scrape
|
30
|
+
|
31
|
+
## Development
|
32
|
+
|
33
|
+
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.
|
34
|
+
|
35
|
+
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).
|
36
|
+
|
37
|
+
## Contributing
|
38
|
+
|
39
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/wonder_scrape. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/[USERNAME]/wonder_scrape/blob/master/CODE_OF_CONDUCT.md).
|
40
|
+
|
41
|
+
## License
|
42
|
+
|
43
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
44
|
+
|
45
|
+
## Code of Conduct
|
46
|
+
|
47
|
+
Everyone interacting in the WonderScrape project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/wonder_scrape/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
require 'bundler/setup'
|
5
|
+
require 'wonder_scrape'
|
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
|
+
# Pry.start
|
13
|
+
|
14
|
+
require 'irb'
|
15
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/exe/wonder_scrape
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
lib_path = File.expand_path('../lib', __dir__)
|
5
|
+
$LOAD_PATH.unshift(lib_path) unless $LOAD_PATH.include?(lib_path)
|
6
|
+
require 'wonder_scrape'
|
7
|
+
require 'wonder_scrape/cli'
|
8
|
+
|
9
|
+
Signal.trap('INT') do
|
10
|
+
warn("\n#{caller.join("\n")}: interrupted")
|
11
|
+
exit(1)
|
12
|
+
end
|
13
|
+
|
14
|
+
begin
|
15
|
+
WonderScrape::CLI.start
|
16
|
+
rescue WonderScrape::CLI::Error => e
|
17
|
+
puts "ERROR: #{e.message}"
|
18
|
+
exit 1
|
19
|
+
end
|
@@ -0,0 +1,49 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'thor'
|
4
|
+
require_relative 'commands/scrape'
|
5
|
+
|
6
|
+
module WonderScrape
|
7
|
+
# Handle the application command line parsing
|
8
|
+
# and the dispatch to various command objects
|
9
|
+
#
|
10
|
+
# @api public
|
11
|
+
class CLI < Thor
|
12
|
+
# Error raised by this runner
|
13
|
+
Error = Class.new(StandardError)
|
14
|
+
|
15
|
+
desc 'version', 'wonder_scrape version'
|
16
|
+
def version
|
17
|
+
require_relative 'version'
|
18
|
+
puts "v#{WonderScrape::VERSION}"
|
19
|
+
end
|
20
|
+
map %w[--version -v] => :version
|
21
|
+
|
22
|
+
desc 'scrape', 'Scrape a target website for item data'
|
23
|
+
method_option :target, aliases: '-t', type: :string, banner: 'targetWebsite',
|
24
|
+
desc: 'Sets the target website for scraping.',
|
25
|
+
enum: WonderScrape::Commands::Scrape::VALID_SCRAPER_NAMES
|
26
|
+
method_option :output, aliases: '-o', type: :string, banner: 'csv',
|
27
|
+
desc: 'Specifies the output format',
|
28
|
+
enum: %w[csv json]
|
29
|
+
method_option :file, aliases: '-f', type: :string, banner: 'path/to/file',
|
30
|
+
desc: 'Path to the file to write output to. Only necessary for CSV.'
|
31
|
+
method_option :num_pages, aliases: '-n', type: :numeric, banner: 2,
|
32
|
+
desc: 'Expected number of pages for search results.'
|
33
|
+
method_option :start_page, aliases: '-s', type: :numeric, banner: 1,
|
34
|
+
desc: 'What page of search results to begin scraping from.'
|
35
|
+
method_option :request_delay, aliases: '-d', type: :numeric, banner: 5,
|
36
|
+
desc: 'How long in seconds to wait between requests. Useful to avoid tripping rate limits.'
|
37
|
+
method_option :verbose, aliases: '-v', type: :boolean,
|
38
|
+
desc: 'Runs in verbose mode, outputting in greater detail'
|
39
|
+
method_option :help, aliases: '-h', type: :boolean,
|
40
|
+
desc: 'Display usage information'
|
41
|
+
def scrape(*)
|
42
|
+
if options[:help]
|
43
|
+
invoke :help, ['scrape']
|
44
|
+
else
|
45
|
+
WonderScrape::Commands::Scrape.new(options).execute
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
@@ -0,0 +1,41 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'forwardable'
|
4
|
+
|
5
|
+
module WonderScrape
|
6
|
+
class Command
|
7
|
+
extend Forwardable
|
8
|
+
|
9
|
+
def_delegators :command, :run
|
10
|
+
|
11
|
+
# Execute this command
|
12
|
+
#
|
13
|
+
# @api public
|
14
|
+
def execute(*)
|
15
|
+
raise(
|
16
|
+
NotImplementedError,
|
17
|
+
"#{self.class}##{__method__} must be implemented"
|
18
|
+
)
|
19
|
+
end
|
20
|
+
|
21
|
+
# The external commands runner
|
22
|
+
#
|
23
|
+
# @see http://www.rubydoc.info/gems/tty-command
|
24
|
+
#
|
25
|
+
# @api public
|
26
|
+
def command(**options)
|
27
|
+
require 'tty-command'
|
28
|
+
TTY::Command.new(options)
|
29
|
+
end
|
30
|
+
|
31
|
+
# The interactive prompt
|
32
|
+
#
|
33
|
+
# @see http://www.rubydoc.info/gems/tty-prompt
|
34
|
+
#
|
35
|
+
# @api public
|
36
|
+
def prompt
|
37
|
+
require 'tty-prompt'
|
38
|
+
TTY::Prompt.new(interrupt: :exit)
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1 @@
|
|
1
|
+
#
|
@@ -0,0 +1,93 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'tty-progressbar'
|
4
|
+
|
5
|
+
require_relative '../command'
|
6
|
+
require_relative '../scrapers/mfc/scraper'
|
7
|
+
require_relative '../writers/csv'
|
8
|
+
require_relative '../writers/hash'
|
9
|
+
require_relative '../recorder'
|
10
|
+
|
11
|
+
module WonderScrape
|
12
|
+
module Commands
|
13
|
+
class Scrape < WonderScrape::Command
|
14
|
+
VALID_SCRAPER_NAMES = [
|
15
|
+
WonderScrape::Scrapers::MFC::Scraper::NAME
|
16
|
+
].freeze
|
17
|
+
|
18
|
+
VALID_WRITERS = [
|
19
|
+
WonderScrape::Writers::CSV::NAME,
|
20
|
+
WonderScrape::Writers::Hash::NAME
|
21
|
+
].freeze
|
22
|
+
|
23
|
+
def initialize(raw_options)
|
24
|
+
@raw_options = raw_options
|
25
|
+
end
|
26
|
+
|
27
|
+
def execute(input: $stdin, output: $stdout)
|
28
|
+
recorder = WonderScrape::Recorder.new(output, options)
|
29
|
+
writer = build_writer
|
30
|
+
scraper = build_scraper(writer, recorder)
|
31
|
+
|
32
|
+
scraper.scrape
|
33
|
+
writer.output_results
|
34
|
+
recorder.print
|
35
|
+
end
|
36
|
+
|
37
|
+
private
|
38
|
+
|
39
|
+
attr_reader :raw_options
|
40
|
+
|
41
|
+
def build_scraper(writer, recorder)
|
42
|
+
target_module.new(writer, recorder, options)
|
43
|
+
end
|
44
|
+
|
45
|
+
def build_writer
|
46
|
+
case output
|
47
|
+
when WonderScrape::Writers::CSV::NAME
|
48
|
+
WonderScrape::Writers::CSV.new(file, target_module::FIELDS)
|
49
|
+
when WonderScrape::Writers::Hash::NAME
|
50
|
+
WonderScrape::Writers::Hash.new
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def target_module
|
55
|
+
@target_module ||= case target
|
56
|
+
when WonderScrape::Scrapers::MFC::Scraper::NAME
|
57
|
+
WonderScrape::Scrapers::MFC::Scraper
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def progress_bar
|
62
|
+
TTY::ProgressBar.new('[:bar] :percent', total: approximate_records)
|
63
|
+
end
|
64
|
+
|
65
|
+
def target
|
66
|
+
@target ||= raw_options[:target] || prompt.select('What website would you like to scrape?', VALID_SCRAPER_NAMES)
|
67
|
+
end
|
68
|
+
|
69
|
+
def output
|
70
|
+
@output ||= raw_options[:format] || prompt.select('How would you like to output?', VALID_WRITERS)
|
71
|
+
end
|
72
|
+
|
73
|
+
def file
|
74
|
+
@file ||= raw_options[:file] || prompt.ask('Please specify the file path you want to write to:', required: true)
|
75
|
+
end
|
76
|
+
|
77
|
+
def options
|
78
|
+
@options ||= raw_options.merge({
|
79
|
+
progress_bar: progress_bar,
|
80
|
+
num_pages: num_pages
|
81
|
+
})
|
82
|
+
end
|
83
|
+
|
84
|
+
def approximate_records
|
85
|
+
target_module::RESULTS_PER_PAGE * num_pages
|
86
|
+
end
|
87
|
+
|
88
|
+
def num_pages
|
89
|
+
@num_pages ||= raw_options[:num_pages] || prompt.ask('How many pages of search results do you want to scrape?', default: target_module::DEFAULT_MAX_PAGES, convert: :int)
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
93
|
+
end
|
@@ -0,0 +1,47 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'json'
|
4
|
+
|
5
|
+
class WonderScrape::Recorder
|
6
|
+
def initialize(output, options = {})
|
7
|
+
@output = output
|
8
|
+
@verbose = options[:verbose] || false
|
9
|
+
@progress_bar = options[:progress_bar]
|
10
|
+
@items_scraped = 0
|
11
|
+
@item_issues = {}
|
12
|
+
@unexpected_fields = []
|
13
|
+
end
|
14
|
+
|
15
|
+
def print
|
16
|
+
output.puts "Successfully processed #{items_scraped} items!"
|
17
|
+
|
18
|
+
if unexpected_fields.count > 0
|
19
|
+
output.puts "Encountered the following unexpected fields: #{unexpected_fields}"
|
20
|
+
end
|
21
|
+
|
22
|
+
if item_issues.count > 0
|
23
|
+
output.puts "Had issues with #{item_issues.count} items below"
|
24
|
+
output.puts JSON.pretty_generate(item_issues)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
def increment_items_scraped(item)
|
29
|
+
@items_scraped += 1
|
30
|
+
if verbose
|
31
|
+
output.puts JSON.pretty_generate(item)
|
32
|
+
else
|
33
|
+
progress_bar&.advance(1)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
def record_unexpected_field(item_id, field_name)
|
38
|
+
item_issues[item_id] ||= []
|
39
|
+
item_issues[item_id] << "Unexpected field: #{field_name}"
|
40
|
+
unexpected_fields << field_name
|
41
|
+
end
|
42
|
+
|
43
|
+
private
|
44
|
+
|
45
|
+
attr_reader :output, :verbose, :items_scraped, :progress_bar
|
46
|
+
attr_accessor :item_issues, :unexpected_fields
|
47
|
+
end
|
@@ -0,0 +1,71 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'mfc'
|
4
|
+
|
5
|
+
module WonderScrape::Scrapers::MFC
|
6
|
+
module FieldParsers
|
7
|
+
class Standard
|
8
|
+
def self.parse(field_content)
|
9
|
+
field_content.text
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
class StandardList
|
14
|
+
def self.parse(field_content)
|
15
|
+
field_content.search('a').map(&:text)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
class Price
|
20
|
+
def self.parse(field_content)
|
21
|
+
field_content.search('.item-price').text
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
class Dates
|
26
|
+
def self.parse(field_content)
|
27
|
+
field_content.search('a.time').map(&:text)
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
class Events
|
32
|
+
def self.parse(field_content)
|
33
|
+
field_content.search('a.item-entry > span').map(&:text)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
class MainImage
|
38
|
+
def self.parse(field_content)
|
39
|
+
image_url = field_content.search('#content .item-picture a.main img').attr('src')
|
40
|
+
|
41
|
+
parsed_uri = URI.parse(image_url)
|
42
|
+
parsed_uri.query = nil
|
43
|
+
parsed_uri.path = parsed_uri.path.gsub('/big/', '/large/')
|
44
|
+
parsed_uri.to_s
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
class AdditionalImages
|
49
|
+
STYLE_URL_REGEX = /url\(([^\(\)]+)\)/.freeze
|
50
|
+
|
51
|
+
class << self
|
52
|
+
def parse(field_content)
|
53
|
+
field_content.search('#content .item-picture a.more').map do |image_link|
|
54
|
+
extract_clean_url(image_link.attr('style'))
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
private
|
59
|
+
|
60
|
+
def extract_clean_url(style_string)
|
61
|
+
image_url = style_string.scan(STYLE_URL_REGEX).flatten.first
|
62
|
+
|
63
|
+
parsed_uri = URI.parse(image_url)
|
64
|
+
parsed_uri.query = nil
|
65
|
+
parsed_uri.path = parsed_uri.path.gsub('/thumbnails/', '/')
|
66
|
+
parsed_uri.to_s
|
67
|
+
end
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
@@ -0,0 +1,146 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'nokogiri'
|
4
|
+
require_relative 'mfc'
|
5
|
+
require_relative 'field_parsers'
|
6
|
+
|
7
|
+
module WonderScrape::Scrapers::MFC
|
8
|
+
class ItemParser
|
9
|
+
DUPLICATE_FIELD_NAMES = {
|
10
|
+
'Artist' => 'Artists',
|
11
|
+
'Character' => 'Characters',
|
12
|
+
'Classification' => 'Classifications',
|
13
|
+
'Event' => 'Events',
|
14
|
+
'Material' => 'Materials',
|
15
|
+
'Release date' => 'Release dates'
|
16
|
+
}.freeze
|
17
|
+
|
18
|
+
VALID_FIELD_NAMES = [
|
19
|
+
'Title',
|
20
|
+
'Artists',
|
21
|
+
'Category',
|
22
|
+
'Characters',
|
23
|
+
'Classifications',
|
24
|
+
'Company',
|
25
|
+
'Events',
|
26
|
+
'JAN',
|
27
|
+
'Materials',
|
28
|
+
'Numbering',
|
29
|
+
'Origin',
|
30
|
+
'Price',
|
31
|
+
'Release dates',
|
32
|
+
'Scale & Dimensions',
|
33
|
+
'Various',
|
34
|
+
'Version',
|
35
|
+
'Images'
|
36
|
+
].freeze
|
37
|
+
|
38
|
+
ID_SELECTOR = '#content #ariadne > a.current'
|
39
|
+
TITLE_SELECTOR = '#content h1 span.headline'
|
40
|
+
FIELD_ELEMENTS_SELECTOR = '#content .data > .form > .form-field'
|
41
|
+
FIELD_NAME_SELECTOR = '.form-label'
|
42
|
+
FIELD_CONTENT_SELECTOR = '.form-input'
|
43
|
+
|
44
|
+
def self.parse(writer, recorder)
|
45
|
+
proc do |item_html_text|
|
46
|
+
item_html = ::Nokogiri::HTML(item_html_text)
|
47
|
+
new(writer, recorder, item_html).parse
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
def initialize(writer, recorder, item_html)
|
52
|
+
@writer = writer
|
53
|
+
@recorder = recorder
|
54
|
+
@item_html = item_html
|
55
|
+
@unexpected_fields = []
|
56
|
+
end
|
57
|
+
|
58
|
+
def parse
|
59
|
+
result = {}
|
60
|
+
result['Title'] = parsed_title
|
61
|
+
result.merge! parsed_fields
|
62
|
+
result['Images'] = parsed_images
|
63
|
+
|
64
|
+
writer.write(result)
|
65
|
+
recorder.increment_items_scraped(result)
|
66
|
+
end
|
67
|
+
|
68
|
+
private
|
69
|
+
|
70
|
+
attr_reader :writer, :recorder, :item_html
|
71
|
+
|
72
|
+
def parsed_id
|
73
|
+
id_element.text
|
74
|
+
end
|
75
|
+
|
76
|
+
def parsed_title
|
77
|
+
title_element.text
|
78
|
+
end
|
79
|
+
|
80
|
+
def parsed_fields
|
81
|
+
fields = {}
|
82
|
+
|
83
|
+
field_elements.each do |field_element|
|
84
|
+
field_name = dedupe_field_name(field_name_for(field_element))
|
85
|
+
|
86
|
+
if unexpected_field?(field_name)
|
87
|
+
recorder.record_unexpected_field(parsed_id, field_name)
|
88
|
+
next
|
89
|
+
end
|
90
|
+
|
91
|
+
field_content_element = field_content_element_for(field_element)
|
92
|
+
field_value = case field_name
|
93
|
+
when 'Price'
|
94
|
+
FieldParsers::Price.parse(field_content_element)
|
95
|
+
when 'Release dates'
|
96
|
+
FieldParsers::Dates.parse(field_content_element)
|
97
|
+
when 'Events'
|
98
|
+
FieldParsers::Events.parse(field_content_element)
|
99
|
+
when 'Artists', 'Characters', 'Classifications', 'Materials'
|
100
|
+
FieldParsers::StandardList.parse(field_content_element)
|
101
|
+
else
|
102
|
+
FieldParsers::Standard.parse(field_content_element)
|
103
|
+
end
|
104
|
+
|
105
|
+
fields[field_name] = field_value
|
106
|
+
end
|
107
|
+
|
108
|
+
fields
|
109
|
+
end
|
110
|
+
|
111
|
+
def parsed_images
|
112
|
+
images = []
|
113
|
+
images << FieldParsers::MainImage.parse(item_html)
|
114
|
+
images.concat FieldParsers::AdditionalImages.parse(item_html)
|
115
|
+
images.compact.uniq
|
116
|
+
end
|
117
|
+
|
118
|
+
def id_element
|
119
|
+
item_html.search(ID_SELECTOR)
|
120
|
+
end
|
121
|
+
|
122
|
+
def title_element
|
123
|
+
item_html.search(TITLE_SELECTOR)
|
124
|
+
end
|
125
|
+
|
126
|
+
def field_elements
|
127
|
+
item_html.search(FIELD_ELEMENTS_SELECTOR)
|
128
|
+
end
|
129
|
+
|
130
|
+
def field_name_for(field_element)
|
131
|
+
field_element.search(FIELD_NAME_SELECTOR).text
|
132
|
+
end
|
133
|
+
|
134
|
+
def dedupe_field_name(field_name)
|
135
|
+
DUPLICATE_FIELD_NAMES[field_name] || field_name
|
136
|
+
end
|
137
|
+
|
138
|
+
def field_content_element_for(field_element)
|
139
|
+
field_element.search(FIELD_CONTENT_SELECTOR)
|
140
|
+
end
|
141
|
+
|
142
|
+
def unexpected_field?(field_name)
|
143
|
+
!VALID_FIELD_NAMES.include?(field_name)
|
144
|
+
end
|
145
|
+
end
|
146
|
+
end
|
@@ -0,0 +1,72 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'upton'
|
4
|
+
require_relative 'mfc'
|
5
|
+
require_relative 'item_parser'
|
6
|
+
|
7
|
+
module WonderScrape::Scrapers::MFC
|
8
|
+
class Scraper
|
9
|
+
NAME = 'MFC'
|
10
|
+
FIELDS = ItemParser::VALID_FIELD_NAMES
|
11
|
+
|
12
|
+
BASE_URL = 'myfigurecollection.net'
|
13
|
+
SEARCH_PATH = '/browse.v4.php'
|
14
|
+
SEARCH_RESULT_ITEM_SELECTOR = 'ul.listing div.item-icons span.item-icon > a.tbx-tooltip'
|
15
|
+
RESULTS_PER_PAGE = 81
|
16
|
+
|
17
|
+
DEFAULT_DELAY_BETWEEN_REQUESTS = 2 # seconds
|
18
|
+
DEFAULT_MAX_PAGES = 2
|
19
|
+
DEFAULT_START_PAGE = 1
|
20
|
+
DEFAULT_SEARCH_CATEGORY = 4 # Garage kits
|
21
|
+
|
22
|
+
def initialize(writer, recorder, options = {})
|
23
|
+
@writer = writer
|
24
|
+
@recorder = recorder
|
25
|
+
@options = options
|
26
|
+
end
|
27
|
+
|
28
|
+
def scrape
|
29
|
+
scraper.scrape(&ItemParser.parse(writer, recorder))
|
30
|
+
end
|
31
|
+
|
32
|
+
private
|
33
|
+
|
34
|
+
attr_reader :writer, :recorder, :options
|
35
|
+
|
36
|
+
def scraper
|
37
|
+
@scraper ||= build_scraper
|
38
|
+
end
|
39
|
+
|
40
|
+
def build_scraper
|
41
|
+
new_scraper = Upton::Scraper.new(
|
42
|
+
search_url,
|
43
|
+
SEARCH_RESULT_ITEM_SELECTOR
|
44
|
+
)
|
45
|
+
|
46
|
+
new_scraper.paginated = true
|
47
|
+
new_scraper.pagination_start_index = options[:start_page] || DEFAULT_START_PAGE
|
48
|
+
new_scraper.pagination_max_pages = options[:num_pages] || DEFAULT_MAX_PAGES
|
49
|
+
new_scraper.verbose = options[:verbose] || false
|
50
|
+
new_scraper.sleep_time_between_requests = options[:request_delay] || DEFAULT_DELAY_BETWEEN_REQUESTS
|
51
|
+
|
52
|
+
new_scraper
|
53
|
+
end
|
54
|
+
|
55
|
+
def search_url
|
56
|
+
URI::HTTPS.build(
|
57
|
+
host: BASE_URL,
|
58
|
+
path: SEARCH_PATH,
|
59
|
+
query: build_search_query_params
|
60
|
+
).to_s
|
61
|
+
end
|
62
|
+
|
63
|
+
def build_search_query_params
|
64
|
+
URI.encode_www_form({
|
65
|
+
'mode': 'search',
|
66
|
+
'categoryId': DEFAULT_SEARCH_CATEGORY,
|
67
|
+
'sort': 'date',
|
68
|
+
'order': 'desc'
|
69
|
+
})
|
70
|
+
end
|
71
|
+
end
|
72
|
+
end
|
@@ -0,0 +1 @@
|
|
1
|
+
#
|
@@ -0,0 +1 @@
|
|
1
|
+
#
|
@@ -0,0 +1,32 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'csv'
|
4
|
+
require_relative 'writers'
|
5
|
+
|
6
|
+
class WonderScrape::Writers::CSV
|
7
|
+
NAME = 'csv'
|
8
|
+
|
9
|
+
def initialize(file_name, headers)
|
10
|
+
@headers = headers
|
11
|
+
@csv = build_csv_writer(file_name)
|
12
|
+
end
|
13
|
+
|
14
|
+
def write(entry)
|
15
|
+
csv << entry.values_at(*headers)
|
16
|
+
end
|
17
|
+
|
18
|
+
def output_results
|
19
|
+
csv.close
|
20
|
+
end
|
21
|
+
|
22
|
+
private
|
23
|
+
|
24
|
+
attr_reader :headers
|
25
|
+
attr_accessor :csv
|
26
|
+
|
27
|
+
def build_csv_writer(file_name)
|
28
|
+
new_csv = CSV.open(file_name, 'wb')
|
29
|
+
new_csv << headers
|
30
|
+
new_csv
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'json'
|
4
|
+
require_relative 'writers'
|
5
|
+
|
6
|
+
class WonderScrape::Writers::Hash
|
7
|
+
NAME = 'hash'
|
8
|
+
|
9
|
+
def initialize
|
10
|
+
@results = []
|
11
|
+
end
|
12
|
+
|
13
|
+
attr_reader :results
|
14
|
+
|
15
|
+
def write(entry)
|
16
|
+
@results << entry
|
17
|
+
end
|
18
|
+
|
19
|
+
def output_results
|
20
|
+
puts JSON.pretty_generate(@results)
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'lib/wonder_scrape/version'
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = 'wonder_scrape'
|
7
|
+
spec.version = WonderScrape::VERSION
|
8
|
+
spec.authors = ['Ben Dawson']
|
9
|
+
spec.email = ['bendawson.rb@gmail.com']
|
10
|
+
|
11
|
+
spec.summary = 'A project to collect useful information from figure collecting websites.'
|
12
|
+
spec.homepage = 'https://gitlab.com/maleckai/wonder_scrape'
|
13
|
+
spec.license = 'MIT'
|
14
|
+
spec.required_ruby_version = Gem::Requirement.new('>= 2.3.0')
|
15
|
+
|
16
|
+
spec.metadata['homepage_uri'] = spec.homepage
|
17
|
+
spec.metadata['source_code_uri'] = spec.homepage
|
18
|
+
spec.metadata['changelog_uri'] = "#{spec.homepage}/-/blob/master/CHANGELOG.md"
|
19
|
+
spec.required_ruby_version = Gem::Requirement.new('>= 2.3.0')
|
20
|
+
|
21
|
+
spec.metadata['allowed_push_host'] = 'https://rubygems.org'
|
22
|
+
|
23
|
+
# Specify which files should be added to the gem when it is released.
|
24
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
25
|
+
spec.files = Dir.chdir(File.expand_path(__dir__)) do
|
26
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
27
|
+
end
|
28
|
+
spec.bindir = 'exe'
|
29
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
30
|
+
spec.require_paths = ['lib']
|
31
|
+
|
32
|
+
spec.add_dependency 'thor'
|
33
|
+
spec.add_dependency 'tty-progressbar'
|
34
|
+
spec.add_dependency 'tty-prompt'
|
35
|
+
|
36
|
+
spec.add_runtime_dependency 'nokogiri', ['~> 1.10.9']
|
37
|
+
spec.add_runtime_dependency 'upton', ['~> 0.3.6']
|
38
|
+
end
|
metadata
ADDED
@@ -0,0 +1,150 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: wonder_scrape
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ben Dawson
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2020-05-05 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: thor
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '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'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: tty-progressbar
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
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: tty-prompt
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '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: 1.10.9
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 1.10.9
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: upton
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 0.3.6
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 0.3.6
|
83
|
+
description:
|
84
|
+
email:
|
85
|
+
- bendawson.rb@gmail.com
|
86
|
+
executables:
|
87
|
+
- wonder_scrape
|
88
|
+
extensions: []
|
89
|
+
extra_rdoc_files: []
|
90
|
+
files:
|
91
|
+
- ".gitignore"
|
92
|
+
- ".rspec"
|
93
|
+
- ".ruby-version"
|
94
|
+
- ".travis.yml"
|
95
|
+
- CHANGELOG.md
|
96
|
+
- CODE_OF_CONDUCT.md
|
97
|
+
- Gemfile
|
98
|
+
- Gemfile.lock
|
99
|
+
- LICENSE.txt
|
100
|
+
- README.md
|
101
|
+
- Rakefile
|
102
|
+
- bin/console
|
103
|
+
- bin/setup
|
104
|
+
- exe/wonder_scrape
|
105
|
+
- lib/wonder_scrape.rb
|
106
|
+
- lib/wonder_scrape/cli.rb
|
107
|
+
- lib/wonder_scrape/command.rb
|
108
|
+
- lib/wonder_scrape/commands/.gitkeep
|
109
|
+
- lib/wonder_scrape/commands/scrape.rb
|
110
|
+
- lib/wonder_scrape/recorder.rb
|
111
|
+
- lib/wonder_scrape/scrapers/mfc/field_parsers.rb
|
112
|
+
- lib/wonder_scrape/scrapers/mfc/item_parser.rb
|
113
|
+
- lib/wonder_scrape/scrapers/mfc/mfc.rb
|
114
|
+
- lib/wonder_scrape/scrapers/mfc/scraper.rb
|
115
|
+
- lib/wonder_scrape/scrapers/scrapers.rb
|
116
|
+
- lib/wonder_scrape/templates/.gitkeep
|
117
|
+
- lib/wonder_scrape/templates/scrape/.gitkeep
|
118
|
+
- lib/wonder_scrape/version.rb
|
119
|
+
- lib/wonder_scrape/writers/csv.rb
|
120
|
+
- lib/wonder_scrape/writers/hash.rb
|
121
|
+
- lib/wonder_scrape/writers/writers.rb
|
122
|
+
- wonder_scrape.gemspec
|
123
|
+
homepage: https://gitlab.com/maleckai/wonder_scrape
|
124
|
+
licenses:
|
125
|
+
- MIT
|
126
|
+
metadata:
|
127
|
+
homepage_uri: https://gitlab.com/maleckai/wonder_scrape
|
128
|
+
source_code_uri: https://gitlab.com/maleckai/wonder_scrape
|
129
|
+
changelog_uri: https://gitlab.com/maleckai/wonder_scrape/-/blob/master/CHANGELOG.md
|
130
|
+
allowed_push_host: https://rubygems.org
|
131
|
+
post_install_message:
|
132
|
+
rdoc_options: []
|
133
|
+
require_paths:
|
134
|
+
- lib
|
135
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
136
|
+
requirements:
|
137
|
+
- - ">="
|
138
|
+
- !ruby/object:Gem::Version
|
139
|
+
version: 2.3.0
|
140
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
141
|
+
requirements:
|
142
|
+
- - ">="
|
143
|
+
- !ruby/object:Gem::Version
|
144
|
+
version: '0'
|
145
|
+
requirements: []
|
146
|
+
rubygems_version: 3.1.2
|
147
|
+
signing_key:
|
148
|
+
specification_version: 4
|
149
|
+
summary: A project to collect useful information from figure collecting websites.
|
150
|
+
test_files: []
|