mechanizer 0.10
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/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +6 -0
- data/LICENSE.txt +21 -0
- data/README.md +164 -0
- data/Rakefile +38 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/mechanizer.rb +17 -0
- data/lib/mechanizer/noko.rb +96 -0
- data/lib/mechanizer/version.rb +3 -0
- data/mechanizer.gemspec +70 -0
- metadata +190 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 2979f001e4be4e144e42a73c29ebed077b36396d4af8d900efabccd0899dcc4c
|
4
|
+
data.tar.gz: faf0a614ca0ad4f2c60a3e2f5dcf7ba654b33b759338f93f7e4e99ae74986cf9
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a92ad83c37908b4bdfec287e9a8762aa7f14c6310e217757367d5b98404ee3610906ec5dc82026200744053a8fb65a9e40d49dc3022307b4fc838dea97ce3ba5
|
7
|
+
data.tar.gz: 6d26cdba0d8b484d16e9f9d1b2f4dd38ec9fad2b688ff21236718baadbebde0cb624e44435af6f2461294d3a421d9639ce17e632f4d02440acec53eb9eb6d4c1
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
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 4rlm@protonmail.ch. 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/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2018 Adam Booth
|
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 +1,164 @@
|
|
1
|
+
# Mechanizer
|
2
|
+
|
3
|
+
[![Gem Version](https://badge.fury.io/rb/mechanizer.svg)](https://badge.fury.io/rb/mechanizer)
|
4
|
+
[![MIT License](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
|
5
|
+
|
6
|
+
### Mechanize & NokoGiri Wrapper for Automated WebScraping and WebPage Parsing.
|
7
|
+
|
8
|
+
Light, easy to use wrapper for Mechanize and NokoGiri. No configuration or error handling to worry about. Simply enter the target URL and Mechanizer scrapes the page for you to easily parse.
|
9
|
+
|
10
|
+
#### Recommended Gems
|
11
|
+
Note: URL MUST be in proper format and be valid, example:
|
12
|
+
Correct: https://www.example.com
|
13
|
+
Incorrect: www.example.com, example.com, https://example.com
|
14
|
+
|
15
|
+
##### 1. If you need to pre-format your URLs, try using `CrmFormatter gem`
|
16
|
+
##### 2. If you need to verify your URLs, try using `UrlVerifier gem`, which includes the `CrmFormatter gem` inside of it.
|
17
|
+
|
18
|
+
Then, feed the results from those gems into this gem. The documentation below assumes the URLs are correctly formatted and have been verified before passing them through the `Mechanizer gem`.
|
19
|
+
|
20
|
+
## Installation
|
21
|
+
|
22
|
+
Add this line to your application's Gemfile:
|
23
|
+
|
24
|
+
```ruby
|
25
|
+
gem 'mechanizer'
|
26
|
+
```
|
27
|
+
|
28
|
+
And then execute:
|
29
|
+
|
30
|
+
$ bundle
|
31
|
+
|
32
|
+
Or install it yourself as:
|
33
|
+
|
34
|
+
$ gem install mechanizer
|
35
|
+
|
36
|
+
## Usage
|
37
|
+
|
38
|
+
#### 1. Instantiate & Pass URL
|
39
|
+
|
40
|
+
```
|
41
|
+
noko = Mechanizer::Noko.new
|
42
|
+
noko_hash = noko.scrape({url: 'https://www.wikipedia.org'})
|
43
|
+
```
|
44
|
+
|
45
|
+
#### 2. To Customize Timeout:
|
46
|
+
Default timeout is set to 60. You can adjust that time or omit it if 60 is fine.
|
47
|
+
|
48
|
+
```
|
49
|
+
noko = Mechanizer::Noko.new
|
50
|
+
args = {url: 'https://www.wikipedia.org', timeout: 30}
|
51
|
+
noko_hash = noko.scrape(args)
|
52
|
+
```
|
53
|
+
|
54
|
+
#### 3. Noko Result in Hash Format
|
55
|
+
|
56
|
+
```
|
57
|
+
err_msg = noko_hash[:err_msg]
|
58
|
+
page = noko_hash[:page]
|
59
|
+
texts_and_hrefs = noko_hash[:texts_and_hrefs]
|
60
|
+
```
|
61
|
+
|
62
|
+
#### 4. Example Texts & Hrefs:
|
63
|
+
|
64
|
+
```
|
65
|
+
texts_and_hrefs = [
|
66
|
+
{:text=>"english 5 675 000+ articles", :href=>"//en.wikipedia.org/"},
|
67
|
+
{:text=>"日本語 1 111 000+ 記事", :href=>"//ja.wikipedia.org/"},
|
68
|
+
{:text=>"español 1 427 000+ artículos", :href=>"//es.wikipedia.org/"},
|
69
|
+
{:text=>"deutsch 2 195 000+ artikel", :href=>"//de.wikipedia.org/"},
|
70
|
+
{:text=>"русский 1 481 000+ статей", :href=>"//ru.wikipedia.org/"},
|
71
|
+
{:text=>"français 1 997 000+ articles", :href=>"//fr.wikipedia.org/"},
|
72
|
+
{:text=>"italiano 1 446 000+ voci", :href=>"//it.wikipedia.org/"}
|
73
|
+
]
|
74
|
+
```
|
75
|
+
|
76
|
+
#### 5. Example Parsing Page:
|
77
|
+
There are several ways to parse and manipulate `noko_hash[:page]`. Essentially, you can parse the page using its css classes and html tags. You can use either or both together. Some pages are very straight forward, but others can require a lot of skill. Here is a good reference guide: [Nokogiri Tutorials](http://www.nokogiri.org/tutorials). All Nokogiri methods are available through this wrapper. This wrapper simply helps you avoid setting up, manages and reduces errors, and helps to automate your scraping process.
|
78
|
+
|
79
|
+
##### For the Wikipedia URL in the example above, at the time of this README there is a group of icons on its homepage. If you right-click on any of them you can inspect. Look for any classes that interest you. In this example, it's `.other-project`. Simply paste it like below to get started. Remember, there are several ways to do this, so read the docs and explore what's available.
|
80
|
+
|
81
|
+
```
|
82
|
+
other_projects = page.css('.other-project')&.text
|
83
|
+
other_projects = other_projects.split("\n").reject(&:blank?)
|
84
|
+
```
|
85
|
+
|
86
|
+
##### 6. Results from Parsing Page (from example 5):
|
87
|
+
|
88
|
+
```
|
89
|
+
other_projects = [
|
90
|
+
"Commons",
|
91
|
+
"Freely usable photos & more",
|
92
|
+
"Wikivoyage",
|
93
|
+
"Free travel guide",
|
94
|
+
"Wiktionary",
|
95
|
+
"Free dictionary",
|
96
|
+
"Wikibooks",
|
97
|
+
"Free textbooks",
|
98
|
+
"Wikinews",
|
99
|
+
"Free news source",
|
100
|
+
"Wikidata",
|
101
|
+
"Free knowledge base",
|
102
|
+
"Wikiversity",
|
103
|
+
"Free course materials",
|
104
|
+
"Wikiquote",
|
105
|
+
"Free quote compendium",
|
106
|
+
"MediaWiki",
|
107
|
+
"Free & open wiki application",
|
108
|
+
"Wikisource",
|
109
|
+
"Free library",
|
110
|
+
"Wikispecies",
|
111
|
+
"Free species directory",
|
112
|
+
"Meta-Wiki",
|
113
|
+
"Community coordination & documentation"
|
114
|
+
]
|
115
|
+
```
|
116
|
+
|
117
|
+
##### 7. Automating Your Scraping:
|
118
|
+
You may wish to automate your scraping for various reasons including:
|
119
|
+
|
120
|
+
* Verifing Inventory Items and Pricing (car dealers, retail, menus, etc.),
|
121
|
+
* Categorizing News Headlines and Events,
|
122
|
+
* Creating Data Sets (financials, economic, weather, crime, health)
|
123
|
+
|
124
|
+
Regardless of how you intend to scrape, you will need to find common patterns on the pages. If visiting different websites, each might use their own css, so you might like to create templates for certain ones. So, in your database next to the URL, you might specify which template to use for which URL. Each template has it's own CSS for that URL.
|
125
|
+
|
126
|
+
You could create a wrapper around these results, like so (just an example):
|
127
|
+
|
128
|
+
```
|
129
|
+
city_urls = ['https://en.wikipedia.org/wiki/Austin,_Texas', https://en.wikipedia.org/wiki/Chicago, https://en.wikipedia.org/wiki/Denver]
|
130
|
+
noko = Mechanizer::Noko.new
|
131
|
+
|
132
|
+
city_data = city_urls.map do |city_url|
|
133
|
+
noko_hash = noko.scrape({ url: city_url })
|
134
|
+
city_parser(noko_hash)
|
135
|
+
end
|
136
|
+
|
137
|
+
def city_parser(noko_hash)
|
138
|
+
# Your logic here.
|
139
|
+
end
|
140
|
+
```
|
141
|
+
|
142
|
+
|
143
|
+
## Author
|
144
|
+
|
145
|
+
Adam J Booth - [4rlm](https://github.com/4rlm)
|
146
|
+
|
147
|
+
|
148
|
+
## Development
|
149
|
+
|
150
|
+
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.
|
151
|
+
|
152
|
+
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).
|
153
|
+
|
154
|
+
## Contributing
|
155
|
+
|
156
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/mechanizer. 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.
|
157
|
+
|
158
|
+
## License
|
159
|
+
|
160
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
161
|
+
|
162
|
+
## Code of Conduct
|
163
|
+
|
164
|
+
Everyone interacting in the Mechanizer project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/mechanizer/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
2
|
+
require "rspec/core/rake_task"
|
3
|
+
require 'mechanizer'
|
4
|
+
|
5
|
+
|
6
|
+
RSpec::Core::RakeTask.new(:spec)
|
7
|
+
|
8
|
+
task :default => :spec
|
9
|
+
task :test => :spec
|
10
|
+
|
11
|
+
###################
|
12
|
+
task :console do
|
13
|
+
require 'irb'
|
14
|
+
require 'irb/completion'
|
15
|
+
require 'mechanizer'
|
16
|
+
require "active_support/all"
|
17
|
+
ARGV.clear
|
18
|
+
|
19
|
+
noko_page_hash = run_mechanizer
|
20
|
+
binding.pry
|
21
|
+
|
22
|
+
IRB.start
|
23
|
+
end
|
24
|
+
|
25
|
+
|
26
|
+
def run_mechanizer
|
27
|
+
noko = Mechanizer::Noko.new
|
28
|
+
args = {url: 'https://www.wikipedia.org', timeout: 30}
|
29
|
+
noko_hash = noko.scrape(args)
|
30
|
+
|
31
|
+
err_msg = noko_hash[:err_msg]
|
32
|
+
page = noko_hash[:page]
|
33
|
+
texts_and_hrefs = noko_hash[:texts_and_hrefs]
|
34
|
+
|
35
|
+
other_projects = page.css('.other-project')&.text
|
36
|
+
other_projects = other_projects.split("\n").reject(&:blank?)
|
37
|
+
|
38
|
+
end
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "mechanizer"
|
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__)
|
data/bin/setup
ADDED
data/lib/mechanizer.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
require "mechanizer/version"
|
2
|
+
require "mechanizer/noko"
|
3
|
+
|
4
|
+
require 'pry'
|
5
|
+
require 'utf8_sanitizer'
|
6
|
+
require 'crm_formatter'
|
7
|
+
require 'mechanize'
|
8
|
+
|
9
|
+
require 'timeout'
|
10
|
+
# require 'net/ping'
|
11
|
+
# require 'curb'
|
12
|
+
|
13
|
+
|
14
|
+
module Mechanizer
|
15
|
+
|
16
|
+
|
17
|
+
end
|
@@ -0,0 +1,96 @@
|
|
1
|
+
# Call: FindTemp.new.start_find_temp
|
2
|
+
|
3
|
+
# require 'mechanize'
|
4
|
+
# require 'nokogiri'
|
5
|
+
# require 'open-uri'
|
6
|
+
# require 'whois'
|
7
|
+
# require 'delayed_job'
|
8
|
+
#
|
9
|
+
# require 'timeout'
|
10
|
+
# require 'net/ping'
|
11
|
+
|
12
|
+
module Mechanizer
|
13
|
+
class Noko
|
14
|
+
|
15
|
+
def initialize
|
16
|
+
@timeout = 60
|
17
|
+
end
|
18
|
+
|
19
|
+
def scrape(args)
|
20
|
+
@timeout = args.fetch(:timeout, 60)
|
21
|
+
url = args.fetch(:url)
|
22
|
+
noko_hash = { url: url, err_msg: nil, texts_and_hrefs: {}, page: nil }
|
23
|
+
noko_hash = start_noko(noko_hash)
|
24
|
+
noko_hash = extract_links(noko_hash)
|
25
|
+
noko_hash
|
26
|
+
end
|
27
|
+
|
28
|
+
def extract_links(noko_hash)
|
29
|
+
links = noko_hash[:page]&.links
|
30
|
+
unless noko_hash[:err_msg].present? || !links.present?
|
31
|
+
noko_hash[:texts_and_hrefs] = links.map do |link|
|
32
|
+
text = link.text&.downcase&.gsub(/\s+/, ' ')&.strip
|
33
|
+
href = link&.href&.downcase&.strip
|
34
|
+
text_and_href = {text: text, href: href}
|
35
|
+
end
|
36
|
+
end
|
37
|
+
noko_hash
|
38
|
+
end
|
39
|
+
|
40
|
+
def start_noko(noko_hash)
|
41
|
+
url = noko_hash[:url]
|
42
|
+
begin
|
43
|
+
begin
|
44
|
+
pre_noko_msg(url)
|
45
|
+
Timeout::timeout(@timeout) do
|
46
|
+
|
47
|
+
agent = Mechanize.new # { |agent| agent.follow_meta_refresh = true }
|
48
|
+
agent.user_agent_alias = 'Mac Safari'
|
49
|
+
agent.follow_meta_refresh = true
|
50
|
+
agent.read_timeout = @timeout
|
51
|
+
agent.open_timeout = @timeout # Length of time to wait until a connection is opened in seconds
|
52
|
+
agent.idle_timeout = @timeout # Reset connections that have not been used in this many seconds
|
53
|
+
agent.keep_alive = false # enable
|
54
|
+
|
55
|
+
begin
|
56
|
+
uri = URI(url)
|
57
|
+
page = agent.get(uri)
|
58
|
+
rescue Mechanize::ResponseReadError => e
|
59
|
+
page = e.force_parse
|
60
|
+
end
|
61
|
+
|
62
|
+
page.respond_to?('at_css') ? noko_hash[:page] = page : noko_hash[:err_msg] = "Error: Not-Noko-Obj"
|
63
|
+
end
|
64
|
+
rescue Timeout::Error # timeout rescue
|
65
|
+
noko_hash[:err_msg] = 'Error: Timeout'
|
66
|
+
end
|
67
|
+
rescue StandardError => e
|
68
|
+
err_msg = error_parser("Error: #{$!.message}")
|
69
|
+
noko_hash[:err_msg] = err_msg
|
70
|
+
end
|
71
|
+
noko_hash
|
72
|
+
end
|
73
|
+
|
74
|
+
def pre_noko_msg(url)
|
75
|
+
puts "\n\n#{'='*40}\nSCRAPING: #{url}\nMax Wait Set: #{@timeout} Seconds\n\n"
|
76
|
+
end
|
77
|
+
|
78
|
+
def error_parser(err_msg)
|
79
|
+
if err_msg.include?("404 => Net::HTTPNotFound")
|
80
|
+
err_msg = "Error: 404"
|
81
|
+
elsif err_msg.include?("connection refused")
|
82
|
+
err_msg = "Error: Connection"
|
83
|
+
elsif err_msg.include?("undefined method")
|
84
|
+
err_msg = "Error: Method"
|
85
|
+
elsif err_msg.include?("TCP connection")
|
86
|
+
err_msg = "Error: TCP"
|
87
|
+
elsif err_msg.include?("execution expired")
|
88
|
+
err_msg = "Error: Runtime"
|
89
|
+
else
|
90
|
+
err_msg = "Error: Undefined"
|
91
|
+
end
|
92
|
+
err_msg
|
93
|
+
end
|
94
|
+
|
95
|
+
end
|
96
|
+
end
|
data/mechanizer.gemspec
ADDED
@@ -0,0 +1,70 @@
|
|
1
|
+
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "mechanizer/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "mechanizer"
|
8
|
+
spec.version = Mechanizer::VERSION
|
9
|
+
spec.authors = ["Adam Booth"]
|
10
|
+
spec.email = ["4rlm@protonmail.ch"]
|
11
|
+
|
12
|
+
spec.summary = %q{Mechanize & NokoGiri Wrapper for Automated WebScraping and WebPage Parsing}
|
13
|
+
spec.description = %q{Mechanize & NokoGiri Wrapper for Automated WebScraping and WebPage Parsing.}
|
14
|
+
|
15
|
+
spec.homepage = 'https://github.com/4rlm/mechanizer'
|
16
|
+
spec.license = "MIT"
|
17
|
+
|
18
|
+
if spec.respond_to?(:metadata)
|
19
|
+
spec.metadata['allowed_push_host'] = 'https://rubygems.org'
|
20
|
+
else
|
21
|
+
raise 'RubyGems 2.0 or newer is required to protect against ' \
|
22
|
+
'public gem pushes.'
|
23
|
+
end
|
24
|
+
|
25
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
26
|
+
f.match(%r{^(test|spec|features)/})
|
27
|
+
end
|
28
|
+
|
29
|
+
spec.bindir = "exe"
|
30
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
31
|
+
spec.require_paths = ["lib"]
|
32
|
+
|
33
|
+
spec.required_ruby_version = '~> 2.5.1'
|
34
|
+
spec.add_dependency 'activesupport', '~> 5.2'
|
35
|
+
spec.add_dependency 'utf8_sanitizer', '~> 2.16'
|
36
|
+
spec.add_dependency 'crm_formatter', '~> 2.62'
|
37
|
+
spec.add_dependency 'mechanize', '~> 2.7', '>= 2.7.6'
|
38
|
+
|
39
|
+
# spec.add_dependency "activesupport-inflector", ['~> 0.1.0']
|
40
|
+
spec.add_development_dependency 'bundler', '~> 1.16', '>= 1.16.2'
|
41
|
+
spec.add_development_dependency 'pry', '~> 0.11.3'
|
42
|
+
spec.add_development_dependency 'rake', '~> 12.3', '>= 12.3.1'
|
43
|
+
spec.add_development_dependency 'rspec', '~> 3.7'
|
44
|
+
# spec.add_development_dependency 'byebug', '~> 10.0', '>= 10.0.2'
|
45
|
+
# spec.add_development_dependency 'class_indexer', '~> 0.3.0'
|
46
|
+
# spec.add_development_dependency 'irbtools', '~> 2.2', '>= 2.2.1'
|
47
|
+
# spec.add_development_dependency 'rubocop', '~> 0.56.0'
|
48
|
+
# spec.add_development_dependency 'ruby-beautify', '~> 0.97.4'
|
49
|
+
# spec.add_runtime_dependency 'library', '~> 2.2'
|
50
|
+
# spec.add_dependency 'activerecord', '>= 3.0'
|
51
|
+
# spec.add_dependency 'actionpack', '>= 3.0'
|
52
|
+
# spec.add_dependency 'polyamorous', '~> 1.3.2'
|
53
|
+
# spec.add_development_dependency 'machinist', '~> 1.0.6'
|
54
|
+
# spec.add_development_dependency 'faker', '~> 0.9.5'
|
55
|
+
# spec.add_development_dependency 'sqlite3', '~> 1.3.3'
|
56
|
+
# spec.add_development_dependency 'pg', '~> 0.21'
|
57
|
+
# spec.add_development_dependency 'mysql2', '0.3.20'
|
58
|
+
|
59
|
+
# spec.requirements << 'libmagick, v6.0'
|
60
|
+
# spec.requirements << 'A good graphics card'
|
61
|
+
# # This gem will work with 1.8.6 or greater...
|
62
|
+
# spec.required_ruby_version = '>= 1.8.6'
|
63
|
+
#
|
64
|
+
# # Only with ruby 2.0.x
|
65
|
+
# spec.required_ruby_version = '~> 2.0'
|
66
|
+
#
|
67
|
+
# # Only with ruby between 2.2.0 and 2.2.2
|
68
|
+
# spec.required_ruby_version = ['>= 2.2.0', '< 2.2.3']
|
69
|
+
|
70
|
+
end
|
metadata
ADDED
@@ -0,0 +1,190 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: mechanizer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: '0.10'
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Adam Booth
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-07-02 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: activesupport
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '5.2'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '5.2'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: utf8_sanitizer
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '2.16'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '2.16'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: crm_formatter
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.62'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.62'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: mechanize
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '2.7'
|
62
|
+
- - ">="
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: 2.7.6
|
65
|
+
type: :runtime
|
66
|
+
prerelease: false
|
67
|
+
version_requirements: !ruby/object:Gem::Requirement
|
68
|
+
requirements:
|
69
|
+
- - "~>"
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: '2.7'
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: 2.7.6
|
75
|
+
- !ruby/object:Gem::Dependency
|
76
|
+
name: bundler
|
77
|
+
requirement: !ruby/object:Gem::Requirement
|
78
|
+
requirements:
|
79
|
+
- - "~>"
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '1.16'
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: 1.16.2
|
85
|
+
type: :development
|
86
|
+
prerelease: false
|
87
|
+
version_requirements: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - "~>"
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: '1.16'
|
92
|
+
- - ">="
|
93
|
+
- !ruby/object:Gem::Version
|
94
|
+
version: 1.16.2
|
95
|
+
- !ruby/object:Gem::Dependency
|
96
|
+
name: pry
|
97
|
+
requirement: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - "~>"
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: 0.11.3
|
102
|
+
type: :development
|
103
|
+
prerelease: false
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
105
|
+
requirements:
|
106
|
+
- - "~>"
|
107
|
+
- !ruby/object:Gem::Version
|
108
|
+
version: 0.11.3
|
109
|
+
- !ruby/object:Gem::Dependency
|
110
|
+
name: rake
|
111
|
+
requirement: !ruby/object:Gem::Requirement
|
112
|
+
requirements:
|
113
|
+
- - "~>"
|
114
|
+
- !ruby/object:Gem::Version
|
115
|
+
version: '12.3'
|
116
|
+
- - ">="
|
117
|
+
- !ruby/object:Gem::Version
|
118
|
+
version: 12.3.1
|
119
|
+
type: :development
|
120
|
+
prerelease: false
|
121
|
+
version_requirements: !ruby/object:Gem::Requirement
|
122
|
+
requirements:
|
123
|
+
- - "~>"
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '12.3'
|
126
|
+
- - ">="
|
127
|
+
- !ruby/object:Gem::Version
|
128
|
+
version: 12.3.1
|
129
|
+
- !ruby/object:Gem::Dependency
|
130
|
+
name: rspec
|
131
|
+
requirement: !ruby/object:Gem::Requirement
|
132
|
+
requirements:
|
133
|
+
- - "~>"
|
134
|
+
- !ruby/object:Gem::Version
|
135
|
+
version: '3.7'
|
136
|
+
type: :development
|
137
|
+
prerelease: false
|
138
|
+
version_requirements: !ruby/object:Gem::Requirement
|
139
|
+
requirements:
|
140
|
+
- - "~>"
|
141
|
+
- !ruby/object:Gem::Version
|
142
|
+
version: '3.7'
|
143
|
+
description: Mechanize & NokoGiri Wrapper for Automated WebScraping and WebPage Parsing.
|
144
|
+
email:
|
145
|
+
- 4rlm@protonmail.ch
|
146
|
+
executables: []
|
147
|
+
extensions: []
|
148
|
+
extra_rdoc_files: []
|
149
|
+
files:
|
150
|
+
- ".gitignore"
|
151
|
+
- ".rspec"
|
152
|
+
- ".travis.yml"
|
153
|
+
- CODE_OF_CONDUCT.md
|
154
|
+
- Gemfile
|
155
|
+
- Gemfile.lock
|
156
|
+
- LICENSE.txt
|
157
|
+
- README.md
|
158
|
+
- Rakefile
|
159
|
+
- bin/console
|
160
|
+
- bin/setup
|
161
|
+
- lib/mechanizer.rb
|
162
|
+
- lib/mechanizer/noko.rb
|
163
|
+
- lib/mechanizer/version.rb
|
164
|
+
- mechanizer.gemspec
|
165
|
+
homepage: https://github.com/4rlm/mechanizer
|
166
|
+
licenses:
|
167
|
+
- MIT
|
168
|
+
metadata:
|
169
|
+
allowed_push_host: https://rubygems.org
|
170
|
+
post_install_message:
|
171
|
+
rdoc_options: []
|
172
|
+
require_paths:
|
173
|
+
- lib
|
174
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
175
|
+
requirements:
|
176
|
+
- - "~>"
|
177
|
+
- !ruby/object:Gem::Version
|
178
|
+
version: 2.5.1
|
179
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
180
|
+
requirements:
|
181
|
+
- - ">="
|
182
|
+
- !ruby/object:Gem::Version
|
183
|
+
version: '0'
|
184
|
+
requirements: []
|
185
|
+
rubyforge_project:
|
186
|
+
rubygems_version: 2.7.6
|
187
|
+
signing_key:
|
188
|
+
specification_version: 4
|
189
|
+
summary: Mechanize & NokoGiri Wrapper for Automated WebScraping and WebPage Parsing
|
190
|
+
test_files: []
|