nypl-site-scraper 0.1.0
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 +9 -0
- data/.ruby-gemset +1 -0
- data/.ruby-version +1 -0
- data/Gemfile +4 -0
- data/README.md +51 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/nypl_site_scraper/scraper.rb +68 -0
- data/lib/nypl_site_scraper/version.rb +3 -0
- data/nypl-site-scraper.gemspec +35 -0
- metadata +117 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: b51638e35e43cd30bfcd290095e94d2a6b0a9a77
|
4
|
+
data.tar.gz: d0f055e818633850850acebdf5762a69cc78d9b8
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 151184cbadf8a2e37e6e3db7955e87ce5681218d18ae7467d2427d37610a75bfdad1e1218f74e57312ff15c65e8d070492cc25d18544f26fa573b663031120f6
|
7
|
+
data.tar.gz: 8d1b57050ae900ad0e11d8a5cf38d6fa7da8931ee031996c566012dda3307b8aeae9aa67b6190cbc4200db511428e3c0ecdbbbe72323bdf82a05146bc3832cf1
|
data/.gitignore
ADDED
data/.ruby-gemset
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
nypl-site-scraper
|
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
ruby-2.4.2
|
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
# NYPL Site Scraper
|
2
|
+
|
3
|
+
A (mechanize)[https://github.com/sparklemotion/mechanize] driven library for
|
4
|
+
getting information about your NYPL account by web scraping.
|
5
|
+
|
6
|
+
This library is an abstraction to get info from your account.
|
7
|
+
If you really want to concern yourself with markup, you're better off
|
8
|
+
using mechanize directly.
|
9
|
+
|
10
|
+
Examples of what it can get are your:
|
11
|
+
|
12
|
+
* Current Holds
|
13
|
+
* Fines (not implemented yet)
|
14
|
+
* Current Checkouts (not implemented yet)
|
15
|
+
|
16
|
+
## Installation
|
17
|
+
|
18
|
+
Add this line to your application's Gemfile:
|
19
|
+
|
20
|
+
```ruby
|
21
|
+
gem 'nypl-site-scraper'
|
22
|
+
```
|
23
|
+
|
24
|
+
And then execute:
|
25
|
+
|
26
|
+
$ bundle
|
27
|
+
|
28
|
+
Or install it yourself as:
|
29
|
+
|
30
|
+
$ gem install nypl-site-scraper
|
31
|
+
|
32
|
+
## Usage
|
33
|
+
|
34
|
+
```ruby
|
35
|
+
client = NyplSiteScraper::Client.new(barcode: '11111111111111', pin: '2222')
|
36
|
+
|
37
|
+
client.login! # This is the network call
|
38
|
+
|
39
|
+
client.get_holds
|
40
|
+
# {"holds"=>[{"title"=>"Persepolis. English", "statusString"=>"READY FOR PICKUP", "status"=>"ready", "pickupLocation"=>"Mid-Manhattan Library at 42nd St"}...
|
41
|
+
```
|
42
|
+
|
43
|
+
## Development
|
44
|
+
|
45
|
+
After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
46
|
+
|
47
|
+
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).
|
48
|
+
|
49
|
+
## Contributing
|
50
|
+
|
51
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/nodanaonlyzuul/nypl-site-scraper.
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "nypl_site_scraper/scraper"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
@@ -0,0 +1,68 @@
|
|
1
|
+
require 'mechanize'
|
2
|
+
|
3
|
+
module NyplSiteScraper
|
4
|
+
class Client
|
5
|
+
|
6
|
+
attr_reader :pin, :barcode, :homepage
|
7
|
+
|
8
|
+
def initialize(options = {barcode: nil, })
|
9
|
+
@barcode = options[:barcode]
|
10
|
+
@pin = options[:pin]
|
11
|
+
@agent = Mechanize.new
|
12
|
+
end
|
13
|
+
|
14
|
+
def login!
|
15
|
+
login_page = @agent.get('https://catalog.nypl.org/iii/cas/login?service=https%3A%2F%2Fcatalog.nypl.org%3A443%2Fpatroninfo~S1%2FIIITICKET&scope=1')
|
16
|
+
form = login_page.form
|
17
|
+
form.code = barcode
|
18
|
+
form.pin = pin
|
19
|
+
@homepage = @agent.submit(form, form.buttons.first)
|
20
|
+
true
|
21
|
+
end
|
22
|
+
|
23
|
+
def get_holds
|
24
|
+
@holds_page ||= @homepage.link_with(text: "My Holds").click
|
25
|
+
holds_rows = @holds_page.css('tr.patFuncEntry')
|
26
|
+
|
27
|
+
response_holds = []
|
28
|
+
|
29
|
+
holds_rows.each do |hold_row|
|
30
|
+
status_string = hold_row.css('td.patFuncStatus').text.strip
|
31
|
+
response_holds << {
|
32
|
+
title: hold_row.css('td.patFuncTitle').text.strip,
|
33
|
+
statusString: status_string,
|
34
|
+
status: map_status_string(status_string),
|
35
|
+
pickupLocation: get_pickup_location(hold_row),
|
36
|
+
}
|
37
|
+
end
|
38
|
+
{holds: response_holds}
|
39
|
+
end
|
40
|
+
private
|
41
|
+
|
42
|
+
def map_status_string(status_string)
|
43
|
+
|
44
|
+
if status_string == "READY FOR PICKUP"
|
45
|
+
return "ready"
|
46
|
+
elsif status_string == "IN TRANSIT"
|
47
|
+
return "in transit"
|
48
|
+
elsif status_string.include?('of')
|
49
|
+
return "pending"
|
50
|
+
else
|
51
|
+
return status_string
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
# Helper because markup for pending vs ready is different
|
56
|
+
def get_pickup_location(row)
|
57
|
+
pickUpCell = row.css('td.patFuncPickup')
|
58
|
+
if pickUpCell.search('div.patFuncPickupLabel').length > 0
|
59
|
+
row.css('td.patFuncPickup option[selected=selected]').first.text.strip
|
60
|
+
# pickUpCell.search('div.patFuncPickupLabel').text.strip
|
61
|
+
else
|
62
|
+
pickUpCell.text.strip
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
end
|
67
|
+
|
68
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'nypl_site_scraper/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "nypl-site-scraper"
|
8
|
+
spec.version = NyplSiteScraper::VERSION
|
9
|
+
spec.authors = ["nodanaonlyzuul"]
|
10
|
+
spec.licenses = ['MIT']
|
11
|
+
spec.summary = %q{A mechanize-driven client to scrape info about your account from NYPL}
|
12
|
+
# spec.description = %q{TODO: Write a longer description or delete this line.}
|
13
|
+
spec.homepage = "http://github.com/nodanaonlyzuul/nypl-site-scraper"
|
14
|
+
|
15
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
16
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
17
|
+
if spec.respond_to?(:metadata)
|
18
|
+
spec.metadata['allowed_push_host'] = "https://rubygems.org"
|
19
|
+
else
|
20
|
+
raise "RubyGems 2.0 or newer is required to protect against " \
|
21
|
+
"public gem pushes."
|
22
|
+
end
|
23
|
+
|
24
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
25
|
+
f.match(%r{^(test|spec|features)/})
|
26
|
+
end
|
27
|
+
spec.bindir = "exe"
|
28
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
29
|
+
spec.require_paths = ["lib"]
|
30
|
+
|
31
|
+
spec.add_dependency 'mechanize', '~> 2.7', '>= 2.7.3'
|
32
|
+
spec.add_development_dependency "pry", '~> 0.11.3'
|
33
|
+
spec.add_development_dependency "bundler", "~> 1.13"
|
34
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
35
|
+
end
|
metadata
ADDED
@@ -0,0 +1,117 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: nypl-site-scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- nodanaonlyzuul
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-12-08 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: mechanize
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '2.7'
|
20
|
+
- - ">="
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 2.7.3
|
23
|
+
type: :runtime
|
24
|
+
prerelease: false
|
25
|
+
version_requirements: !ruby/object:Gem::Requirement
|
26
|
+
requirements:
|
27
|
+
- - "~>"
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '2.7'
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 2.7.3
|
33
|
+
- !ruby/object:Gem::Dependency
|
34
|
+
name: pry
|
35
|
+
requirement: !ruby/object:Gem::Requirement
|
36
|
+
requirements:
|
37
|
+
- - "~>"
|
38
|
+
- !ruby/object:Gem::Version
|
39
|
+
version: 0.11.3
|
40
|
+
type: :development
|
41
|
+
prerelease: false
|
42
|
+
version_requirements: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - "~>"
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: 0.11.3
|
47
|
+
- !ruby/object:Gem::Dependency
|
48
|
+
name: bundler
|
49
|
+
requirement: !ruby/object:Gem::Requirement
|
50
|
+
requirements:
|
51
|
+
- - "~>"
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '1.13'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - "~>"
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '1.13'
|
61
|
+
- !ruby/object:Gem::Dependency
|
62
|
+
name: rake
|
63
|
+
requirement: !ruby/object:Gem::Requirement
|
64
|
+
requirements:
|
65
|
+
- - "~>"
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
version: '10.0'
|
68
|
+
type: :development
|
69
|
+
prerelease: false
|
70
|
+
version_requirements: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - "~>"
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '10.0'
|
75
|
+
description:
|
76
|
+
email:
|
77
|
+
executables: []
|
78
|
+
extensions: []
|
79
|
+
extra_rdoc_files: []
|
80
|
+
files:
|
81
|
+
- ".gitignore"
|
82
|
+
- ".ruby-gemset"
|
83
|
+
- ".ruby-version"
|
84
|
+
- Gemfile
|
85
|
+
- README.md
|
86
|
+
- Rakefile
|
87
|
+
- bin/console
|
88
|
+
- bin/setup
|
89
|
+
- lib/nypl_site_scraper/scraper.rb
|
90
|
+
- lib/nypl_site_scraper/version.rb
|
91
|
+
- nypl-site-scraper.gemspec
|
92
|
+
homepage: http://github.com/nodanaonlyzuul/nypl-site-scraper
|
93
|
+
licenses:
|
94
|
+
- MIT
|
95
|
+
metadata:
|
96
|
+
allowed_push_host: https://rubygems.org
|
97
|
+
post_install_message:
|
98
|
+
rdoc_options: []
|
99
|
+
require_paths:
|
100
|
+
- lib
|
101
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- - ">="
|
104
|
+
- !ruby/object:Gem::Version
|
105
|
+
version: '0'
|
106
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
requirements: []
|
112
|
+
rubyforge_project:
|
113
|
+
rubygems_version: 2.6.14
|
114
|
+
signing_key:
|
115
|
+
specification_version: 4
|
116
|
+
summary: A mechanize-driven client to scrape info about your account from NYPL
|
117
|
+
test_files: []
|