royal_mail_scraper 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.travis.yml +8 -0
- data/Gemfile +12 -0
- data/LICENSE.txt +22 -0
- data/README.md +42 -0
- data/Rakefile +6 -0
- data/lib/royal_mail_scraper/tracker/detail.rb +12 -0
- data/lib/royal_mail_scraper/tracker/request.rb +23 -0
- data/lib/royal_mail_scraper/tracker/response.rb +36 -0
- data/lib/royal_mail_scraper/tracker/status_map.rb +27 -0
- data/lib/royal_mail_scraper/tracker.rb +35 -0
- data/lib/royal_mail_scraper/version.rb +3 -0
- data/lib/royal_mail_scraper.rb +16 -0
- data/royal_mail_scraper.gemspec +24 -0
- data/spec/assets/collected.html +633 -0
- data/spec/assets/delivered.html +638 -0
- data/spec/assets/not_found.html +624 -0
- data/spec/assets/on_delivery.html +633 -0
- data/spec/royal_mail_scraper_spec.rb +20 -0
- data/spec/spec_helper.rb +9 -0
- data/spec/tracker_spec.rb +80 -0
- metadata +114 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 4f34da7f0b92b97623f600d4658ed8507f3b67c9
|
4
|
+
data.tar.gz: 0db41cda4ecd1213132d0ceb6611447859275d13
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 3ef7758c075bc74a6b7ae8ccaba8138f7ce2c631f37b1f7ef91441494effe5eb2407a48b441130df69acbd694270bcc06a73f806f103446280e91a09a9b6c58f
|
7
|
+
data.tar.gz: a42572c88d4fc72279051e776ff278af118bb1a2f60ebd2b37eda1d90c7f5bcd728f374806c1b17ec814677af23347fd334a417f640c58d3ad236b0d9ba004c9
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Laurynas Butkus
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,42 @@
|
|
1
|
+
# RoyalMailScraper
|
2
|
+
|
3
|
+
[](http://travis-ci.org/laurynas/royal_mail_scraper)
|
4
|
+
|
5
|
+
A simple page scraper for Royal Mail Track and Trace.
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
gem 'royal_mail_scraper'
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install royal_mail_scraper
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
tracker = RoyalMailScraper::Tracker.fetch('TRACKING_CODE')
|
24
|
+
|
25
|
+
p tracker.status
|
26
|
+
p tracker.message
|
27
|
+
p tracker.details
|
28
|
+
|
29
|
+
## Contributing
|
30
|
+
|
31
|
+
1. Fork it
|
32
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
33
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
34
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
35
|
+
5. Create new Pull Request
|
36
|
+
|
37
|
+
## Credits
|
38
|
+
|
39
|
+
This GEM is originally inspired by
|
40
|
+
[PHP-Royal-Mail-Track-and-Trace](https://github.com/roldershaw/PHP-Royal-Mail-Track-and-Trace) script.
|
41
|
+
|
42
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,12 @@
|
|
1
|
+
module RoyalMailScraper
|
2
|
+
class Tracker::Detail
|
3
|
+
attr_reader :datetime, :message, :location, :status
|
4
|
+
|
5
|
+
def initialize(datetime, message, location)
|
6
|
+
@datetime = datetime
|
7
|
+
@message = message
|
8
|
+
@location = location
|
9
|
+
@status = Tracker::StatusMap.resolve(message)
|
10
|
+
end
|
11
|
+
end
|
12
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
|
3
|
+
module RoyalMailScraper
|
4
|
+
class Tracker::Request < Struct.new(:tracking_number)
|
5
|
+
REQUEST_URI = URI('http://www.royalmail.com/trackdetails')
|
6
|
+
TIMEOUT = 10
|
7
|
+
|
8
|
+
def execute
|
9
|
+
params = { tracking_number: tracking_number }
|
10
|
+
|
11
|
+
req = Net::HTTP::Post.new(REQUEST_URI.request_uri)
|
12
|
+
req.form_data = params
|
13
|
+
|
14
|
+
http = Net::HTTP.new(REQUEST_URI.host, REQUEST_URI.port)
|
15
|
+
http.open_timeout = TIMEOUT
|
16
|
+
http.read_timeout = TIMEOUT
|
17
|
+
|
18
|
+
res = http.request(req)
|
19
|
+
|
20
|
+
Tracker::Response.new(res.body)
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
|
3
|
+
module RoyalMailScraper
|
4
|
+
class Tracker::Response
|
5
|
+
attr_reader :html
|
6
|
+
|
7
|
+
DETAILS_PATH = '//*[@id="bt-tracked-track-trace-form"]/div/div/div/div[1]/table/tbody/tr'
|
8
|
+
ERROR_PATH = '//*[@id="bt-tracked-track-trace-form"]/div/div/div/div[1]/div[5]/text()'
|
9
|
+
|
10
|
+
TIME_FORMAT = '%d/%m/%y %H:%M'
|
11
|
+
|
12
|
+
def initialize(body)
|
13
|
+
@html = Nokogiri::HTML(body)
|
14
|
+
end
|
15
|
+
|
16
|
+
def tracker
|
17
|
+
Tracker.new(tracking_number, details.reverse)
|
18
|
+
end
|
19
|
+
|
20
|
+
private
|
21
|
+
|
22
|
+
def tracking_number
|
23
|
+
el = @html.at('input[@name="tracking_number"]')
|
24
|
+
el ? el.attr(:value).to_s.strip : nil
|
25
|
+
end
|
26
|
+
|
27
|
+
def details
|
28
|
+
html.xpath(DETAILS_PATH).map do |tr|
|
29
|
+
date, time, message, location = tr.css('td').map(&:content).map(&:strip)
|
30
|
+
time = '00:00' unless time =~ /\A\d+:\d+\z/
|
31
|
+
datetime = DateTime.strptime([date, time].join(' '), TIME_FORMAT) rescue DateTime.new
|
32
|
+
Tracker::Detail.new(datetime, message, location)
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module RoyalMailScraper
|
2
|
+
class Tracker::StatusMap
|
3
|
+
UNRECOGNISED = 'unrecognised'
|
4
|
+
IN_TRANSIT = 'in_transit'
|
5
|
+
ON_DELIVERY = 'on_delivery'
|
6
|
+
UNDELIVERED = 'undelivered'
|
7
|
+
HELD_AT_ENQUIRY_OFFICE = 'held_at_enquiry_office'
|
8
|
+
DELIVERED = 'delivered'
|
9
|
+
|
10
|
+
def self.resolve(message)
|
11
|
+
case message
|
12
|
+
when /^(ACCEPTED|RECEIVED|DESPATCHABLE|DESPATCHED|COLLECTED|ARRIVED)/
|
13
|
+
IN_TRANSIT
|
14
|
+
when /^ON DELIVERY/
|
15
|
+
ON_DELIVERY
|
16
|
+
when /^UNDELIVERED/
|
17
|
+
UNDELIVERED
|
18
|
+
when /^HELD AT ENQUIRY/
|
19
|
+
HELD_AT_ENQUIRY_OFFICE
|
20
|
+
when /^DELIVERED/
|
21
|
+
DELIVERED
|
22
|
+
else
|
23
|
+
UNRECOGNISED
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
module RoyalMailScraper
|
2
|
+
class Tracker < Struct.new(:tracking_number, :details)
|
3
|
+
def self.fetch(tracking_number)
|
4
|
+
request = Request.new(tracking_number)
|
5
|
+
response = request.execute
|
6
|
+
response.tracker
|
7
|
+
end
|
8
|
+
|
9
|
+
def datetime
|
10
|
+
last_detail.datetime if last_detail
|
11
|
+
end
|
12
|
+
|
13
|
+
def status
|
14
|
+
last_detail.status if last_detail
|
15
|
+
end
|
16
|
+
|
17
|
+
def message
|
18
|
+
last_detail.message if last_detail
|
19
|
+
end
|
20
|
+
|
21
|
+
def location
|
22
|
+
last_detail.location if last_detail
|
23
|
+
end
|
24
|
+
|
25
|
+
def recognised_details
|
26
|
+
details.select { |detail| detail.status != StatusMap::UNRECOGNISED }
|
27
|
+
end
|
28
|
+
|
29
|
+
private
|
30
|
+
|
31
|
+
def last_detail
|
32
|
+
@last_detail ||= details.last
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require "royal_mail_scraper/version"
|
2
|
+
require "royal_mail_scraper/tracker"
|
3
|
+
require "royal_mail_scraper/tracker/request"
|
4
|
+
require "royal_mail_scraper/tracker/response"
|
5
|
+
require "royal_mail_scraper/tracker/detail"
|
6
|
+
require "royal_mail_scraper/tracker/status_map"
|
7
|
+
|
8
|
+
module RoyalMailScraper
|
9
|
+
TRACKING_NUMBER_FORMAT = /\A[A-Z]{2}\d{9}GB\z/i
|
10
|
+
|
11
|
+
class << self
|
12
|
+
def tracking_number?(tracking_number)
|
13
|
+
!!(tracking_number.to_s =~ TRACKING_NUMBER_FORMAT)
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'royal_mail_scraper/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "royal_mail_scraper"
|
8
|
+
spec.version = RoyalMailScraper::VERSION
|
9
|
+
spec.authors = ["Laurynas Butkus"]
|
10
|
+
spec.email = ["laurynas.butkus@gmail.com"]
|
11
|
+
spec.description = %q{A simple page scraper for Royal Mail Track and Trace}
|
12
|
+
spec.summary = %q{Fetches tracking information from Royal Mail page}
|
13
|
+
spec.homepage = "https://github.com/laurynas/royal_mail_scraper"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency "nokogiri", "~> 1.5"
|
22
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
23
|
+
spec.add_development_dependency "rake"
|
24
|
+
end
|