nthuevent 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +53 -0
- data/.rubocop.yml +7 -0
- data/Gemfile +5 -0
- data/Gemfile.lock +29 -0
- data/LICENSE +21 -0
- data/bin/nthuevent +21 -0
- data/lib/crawl.rb +23 -0
- data/lib/nthu_event.rb +4 -0
- data/lib/nthuevent/event.rb +30 -0
- data/lib/nthuevent/nthu_event_api.rb +71 -0
- data/lib/nthuevent/version.rb +5 -0
- data/nthuevent.gemspec +32 -0
- metadata +199 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 7c73ab820a67a71b30aa865d86d127e92d3c36e0
|
4
|
+
data.tar.gz: 672fd8ebd74712b3837f336cfa405fb1588ed0bd
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: be1466d9dfa7ff8b297838ea56416043a9c827a2d6e72b0c0b90bdb3f351438ea9f549d329967de26c0699cad1830d9801849f7ebd589c89b713fb22d93bbc73
|
7
|
+
data.tar.gz: 47b6dbcd9ac4cf98f8727b12f51cc175b17077a40f0cd86cae54ce4dd9a6175342b6d3a8ca5245693117f5bc308aaad88a9c654017a66e01437b9b2fda71188a
|
data/.gitignore
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
*.gem
|
2
|
+
*.rbc
|
3
|
+
/.config
|
4
|
+
/coverage/
|
5
|
+
/InstalledFiles
|
6
|
+
/pkg/
|
7
|
+
/spec/reports/
|
8
|
+
/spec/examples.txt
|
9
|
+
/test/tmp/
|
10
|
+
/test/version_tmp/
|
11
|
+
/tmp/
|
12
|
+
|
13
|
+
# Used by dotenv library to load environment variables.
|
14
|
+
# .env
|
15
|
+
|
16
|
+
## Specific to RubyMotion:
|
17
|
+
.dat*
|
18
|
+
.repl_history
|
19
|
+
build/
|
20
|
+
*.bridgesupport
|
21
|
+
build-iPhoneOS/
|
22
|
+
build-iPhoneSimulator/
|
23
|
+
|
24
|
+
## Specific to RubyMotion (use of CocoaPods):
|
25
|
+
#
|
26
|
+
# We recommend against adding the Pods directory to your .gitignore. However
|
27
|
+
# you should judge for yourself, the pros and cons are mentioned at:
|
28
|
+
# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
|
29
|
+
#
|
30
|
+
# vendor/Pods/
|
31
|
+
|
32
|
+
## Documentation cache and generated files:
|
33
|
+
/.yardoc/
|
34
|
+
/_yardoc/
|
35
|
+
/doc/
|
36
|
+
/rdoc/
|
37
|
+
|
38
|
+
## Environment normalization:
|
39
|
+
/.bundle/
|
40
|
+
/vendor/bundle
|
41
|
+
/lib/bundler/man/
|
42
|
+
|
43
|
+
# for a library or gem, you might want to ignore these files since the code is
|
44
|
+
# intended to run in multiple environments; otherwise, check them in:
|
45
|
+
# Gemfile.lock
|
46
|
+
# .ruby-version
|
47
|
+
# .ruby-gemset
|
48
|
+
|
49
|
+
# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
|
50
|
+
.rvmrc
|
51
|
+
|
52
|
+
# macOS file system
|
53
|
+
.DS_Store
|
data/.rubocop.yml
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
GEM
|
2
|
+
remote: https://rubygems.org/
|
3
|
+
specs:
|
4
|
+
ast (2.3.0)
|
5
|
+
mini_portile2 (2.1.0)
|
6
|
+
nokogiri (1.6.8.1)
|
7
|
+
mini_portile2 (~> 2.1.0)
|
8
|
+
parser (2.3.2.0)
|
9
|
+
ast (~> 2.2)
|
10
|
+
powerpack (0.1.1)
|
11
|
+
rainbow (2.1.0)
|
12
|
+
rubocop (0.45.0)
|
13
|
+
parser (>= 2.3.1.1, < 3.0)
|
14
|
+
powerpack (~> 0.1)
|
15
|
+
rainbow (>= 1.99.1, < 3.0)
|
16
|
+
ruby-progressbar (~> 1.7)
|
17
|
+
unicode-display_width (~> 1.0, >= 1.0.1)
|
18
|
+
ruby-progressbar (1.8.1)
|
19
|
+
unicode-display_width (1.1.1)
|
20
|
+
|
21
|
+
PLATFORMS
|
22
|
+
ruby
|
23
|
+
|
24
|
+
DEPENDENCIES
|
25
|
+
nokogiri
|
26
|
+
rubocop
|
27
|
+
|
28
|
+
BUNDLED WITH
|
29
|
+
1.13.6
|
data/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
MIT LICENSE
|
2
|
+
|
3
|
+
Copyright (c)
|
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/bin/nthuevent
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
$LOAD_PATH.unshift File.join(File.dirname(__FILE__), '..', 'lib')
|
4
|
+
require 'nthu_event'
|
5
|
+
|
6
|
+
event_type = ARGV[0] || 'admin'
|
7
|
+
# unless event_type
|
8
|
+
# puts 'USAGE: nthuevent [org_id]'
|
9
|
+
# exit(1)
|
10
|
+
# end
|
11
|
+
|
12
|
+
events = NthuEvent::Event.find(type: event_type, page: 1)
|
13
|
+
|
14
|
+
unless events.nil?
|
15
|
+
events.first(3).each.with_index(1) do |event, index|
|
16
|
+
print "#{index}: "
|
17
|
+
puts "#{event.title} (#{event.date})"
|
18
|
+
puts event.content
|
19
|
+
puts
|
20
|
+
end
|
21
|
+
end
|
data/lib/crawl.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'uri'
|
4
|
+
|
5
|
+
admin_board_uri = 'http://bulletin.web.nthu.edu.tw/files/40-1912-5074-1.php?Lang=zh-tw'
|
6
|
+
|
7
|
+
doc = Nokogiri::HTML(open(admin_board_uri))
|
8
|
+
|
9
|
+
events = doc.css('div.h5').map do |node|
|
10
|
+
date = node.css('.date').text.gsub(/[\[\]\s]+/, '')
|
11
|
+
event_node = node.css('.ptname a')
|
12
|
+
link = URI.join(admin_board_uri, event_node.attr('href').value)
|
13
|
+
|
14
|
+
title = event_node.attr('title').value
|
15
|
+
content_doc = Nokogiri::HTML(open(link))
|
16
|
+
content = content_doc.css('.ptcontent').text.strip
|
17
|
+
|
18
|
+
{ title: title, content: content, link: link, date: date }
|
19
|
+
end
|
20
|
+
|
21
|
+
events.each do |event|
|
22
|
+
puts event
|
23
|
+
end
|
data/lib/nthu_event.rb
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
require_relative 'nthu_event_api'
|
3
|
+
|
4
|
+
module NthuEvent
|
5
|
+
# Single event on organiztion's feed
|
6
|
+
class Event
|
7
|
+
attr_reader :title, :content, :url, :date
|
8
|
+
|
9
|
+
def initialize(event_data)
|
10
|
+
load_data(event_data)
|
11
|
+
end
|
12
|
+
|
13
|
+
def self.find(type: nil, page: nil)
|
14
|
+
events_data = NthuEvent::NthuEventApi.events(type: type, page: page)
|
15
|
+
events = events_data.map do |event_data|
|
16
|
+
new(event_data)
|
17
|
+
end
|
18
|
+
events
|
19
|
+
end
|
20
|
+
|
21
|
+
private
|
22
|
+
|
23
|
+
def load_data(event_data)
|
24
|
+
@title = event_data[:title]
|
25
|
+
@content = event_data[:content]
|
26
|
+
@url = event_data[:url]
|
27
|
+
@date = event_data[:date]
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
@@ -0,0 +1,71 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
require 'open-uri'
|
3
|
+
require 'nokogiri'
|
4
|
+
require 'uri'
|
5
|
+
|
6
|
+
module NthuEvent
|
7
|
+
# Service for all FB API calls
|
8
|
+
class NthuEventApi
|
9
|
+
BASE_URL = 'http://bulletin.web.nthu.edu.tw/files/'
|
10
|
+
EVENT_TYPE_URL = {
|
11
|
+
admin: '40-1912-5074',
|
12
|
+
recruit_internal: '40-1912-5075',
|
13
|
+
recruit_external: '40-1912-5081',
|
14
|
+
admission: '40-1912-5082',
|
15
|
+
art: '40-1912-5083',
|
16
|
+
academic: '40-1912-5084',
|
17
|
+
student: '40-1912-5085',
|
18
|
+
others: '40-1912-5086'
|
19
|
+
}.freeze
|
20
|
+
|
21
|
+
def self.events(type: :admin, page: 0)
|
22
|
+
type = EVENT_TYPE_URL[type.to_sym]
|
23
|
+
events, totalpage = get_event_list("#{BASE_URL}#{type}-#{page}.php")
|
24
|
+
return events if page.positive?
|
25
|
+
|
26
|
+
# get all pages if page is zero
|
27
|
+
(2..totalpage).each do |p|
|
28
|
+
evnts, _total = get_event_list("#{BASE_URL}#{type}-#{p}.php")
|
29
|
+
events += evnts
|
30
|
+
end
|
31
|
+
events
|
32
|
+
end
|
33
|
+
|
34
|
+
private_class_method
|
35
|
+
|
36
|
+
def self.get_event_list(url)
|
37
|
+
doc = Nokogiri::HTML(open(url))
|
38
|
+
events = doc.css('div.h5').map do |node|
|
39
|
+
date, link, title = parse_event_metadata(node)
|
40
|
+
content = get_event_content(link)
|
41
|
+
|
42
|
+
{ title: title, content: content, url: link, date: date }
|
43
|
+
end
|
44
|
+
|
45
|
+
# get total page
|
46
|
+
totalpage = get_pagenum_from_url(doc.css('#navigate a.pagenum').attr('href').value)
|
47
|
+
[events, totalpage]
|
48
|
+
end
|
49
|
+
|
50
|
+
def self.parse_event_metadata(node)
|
51
|
+
date = node.css('.date').text.gsub(/[\[\]\s]+/, '')
|
52
|
+
event_node = node.css('.ptname a')
|
53
|
+
link = URI.join(BASE_URL, event_node.attr('href').value)
|
54
|
+
title = event_node.attr('title').value
|
55
|
+
[date, link, title]
|
56
|
+
end
|
57
|
+
|
58
|
+
def self.get_event_content(url)
|
59
|
+
content_doc = Nokogiri::HTML(open(url))
|
60
|
+
content = content_doc.css('.ptcontent').text.strip
|
61
|
+
content
|
62
|
+
end
|
63
|
+
|
64
|
+
private_class_method
|
65
|
+
|
66
|
+
def self.get_pagenum_from_url(url)
|
67
|
+
match_data = url.match('-(\d+)\.php')
|
68
|
+
Integer(match_data.captures[0])
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
data/nthuevent.gemspec
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
$LOAD_PATH.push File.expand_path('../lib', __FILE__)
|
3
|
+
require 'nthuevent/version'
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = 'nthuevent'
|
7
|
+
s.version = NthuEvent::VERSION
|
8
|
+
|
9
|
+
s.summary = 'Gets event content from NTHU bulletin'
|
10
|
+
s.description = 'Extracts the title, content, and other informaiton of an event'
|
11
|
+
s.authors = ['JJC', 'Rollee Chen', 'shannywu']
|
12
|
+
s.email = ['jjc@nlplab.cc']
|
13
|
+
|
14
|
+
s.files = `git ls-files`.split("\n")
|
15
|
+
s.test_files = `git ls-files -- spec/*`.split("\n")
|
16
|
+
s.executables << 'nthuevent'
|
17
|
+
|
18
|
+
s.add_runtime_dependency 'nokogiri', '~> 1.6'
|
19
|
+
|
20
|
+
s.add_development_dependency 'minitest', '~> 5.9'
|
21
|
+
s.add_development_dependency 'minitest-rg', '~> 5.2'
|
22
|
+
s.add_development_dependency 'rake', '~> 11.3'
|
23
|
+
s.add_development_dependency 'vcr', '~> 3.0'
|
24
|
+
s.add_development_dependency 'webmock', '~> 2.1'
|
25
|
+
s.add_development_dependency 'simplecov', '~> 0.12'
|
26
|
+
s.add_development_dependency 'flog', '~> 4.4'
|
27
|
+
s.add_development_dependency 'flay', '~> 2.8'
|
28
|
+
s.add_development_dependency 'rubocop', '~> 0.42'
|
29
|
+
|
30
|
+
s.homepage = 'https://github.com/twentyfour7/nthu-event'
|
31
|
+
s.license = 'MIT'
|
32
|
+
end
|
metadata
ADDED
@@ -0,0 +1,199 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: nthuevent
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- JJC
|
8
|
+
- Rollee Chen
|
9
|
+
- shannywu
|
10
|
+
autorequire:
|
11
|
+
bindir: bin
|
12
|
+
cert_chain: []
|
13
|
+
date: 2017-01-06 00:00:00.000000000 Z
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: nokogiri
|
17
|
+
requirement: !ruby/object:Gem::Requirement
|
18
|
+
requirements:
|
19
|
+
- - "~>"
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '1.6'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
requirements:
|
26
|
+
- - "~>"
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
version: '1.6'
|
29
|
+
- !ruby/object:Gem::Dependency
|
30
|
+
name: minitest
|
31
|
+
requirement: !ruby/object:Gem::Requirement
|
32
|
+
requirements:
|
33
|
+
- - "~>"
|
34
|
+
- !ruby/object:Gem::Version
|
35
|
+
version: '5.9'
|
36
|
+
type: :development
|
37
|
+
prerelease: false
|
38
|
+
version_requirements: !ruby/object:Gem::Requirement
|
39
|
+
requirements:
|
40
|
+
- - "~>"
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: '5.9'
|
43
|
+
- !ruby/object:Gem::Dependency
|
44
|
+
name: minitest-rg
|
45
|
+
requirement: !ruby/object:Gem::Requirement
|
46
|
+
requirements:
|
47
|
+
- - "~>"
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: '5.2'
|
50
|
+
type: :development
|
51
|
+
prerelease: false
|
52
|
+
version_requirements: !ruby/object:Gem::Requirement
|
53
|
+
requirements:
|
54
|
+
- - "~>"
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '5.2'
|
57
|
+
- !ruby/object:Gem::Dependency
|
58
|
+
name: rake
|
59
|
+
requirement: !ruby/object:Gem::Requirement
|
60
|
+
requirements:
|
61
|
+
- - "~>"
|
62
|
+
- !ruby/object:Gem::Version
|
63
|
+
version: '11.3'
|
64
|
+
type: :development
|
65
|
+
prerelease: false
|
66
|
+
version_requirements: !ruby/object:Gem::Requirement
|
67
|
+
requirements:
|
68
|
+
- - "~>"
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: '11.3'
|
71
|
+
- !ruby/object:Gem::Dependency
|
72
|
+
name: vcr
|
73
|
+
requirement: !ruby/object:Gem::Requirement
|
74
|
+
requirements:
|
75
|
+
- - "~>"
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '3.0'
|
78
|
+
type: :development
|
79
|
+
prerelease: false
|
80
|
+
version_requirements: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - "~>"
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: '3.0'
|
85
|
+
- !ruby/object:Gem::Dependency
|
86
|
+
name: webmock
|
87
|
+
requirement: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - "~>"
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: '2.1'
|
92
|
+
type: :development
|
93
|
+
prerelease: false
|
94
|
+
version_requirements: !ruby/object:Gem::Requirement
|
95
|
+
requirements:
|
96
|
+
- - "~>"
|
97
|
+
- !ruby/object:Gem::Version
|
98
|
+
version: '2.1'
|
99
|
+
- !ruby/object:Gem::Dependency
|
100
|
+
name: simplecov
|
101
|
+
requirement: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- - "~>"
|
104
|
+
- !ruby/object:Gem::Version
|
105
|
+
version: '0.12'
|
106
|
+
type: :development
|
107
|
+
prerelease: false
|
108
|
+
version_requirements: !ruby/object:Gem::Requirement
|
109
|
+
requirements:
|
110
|
+
- - "~>"
|
111
|
+
- !ruby/object:Gem::Version
|
112
|
+
version: '0.12'
|
113
|
+
- !ruby/object:Gem::Dependency
|
114
|
+
name: flog
|
115
|
+
requirement: !ruby/object:Gem::Requirement
|
116
|
+
requirements:
|
117
|
+
- - "~>"
|
118
|
+
- !ruby/object:Gem::Version
|
119
|
+
version: '4.4'
|
120
|
+
type: :development
|
121
|
+
prerelease: false
|
122
|
+
version_requirements: !ruby/object:Gem::Requirement
|
123
|
+
requirements:
|
124
|
+
- - "~>"
|
125
|
+
- !ruby/object:Gem::Version
|
126
|
+
version: '4.4'
|
127
|
+
- !ruby/object:Gem::Dependency
|
128
|
+
name: flay
|
129
|
+
requirement: !ruby/object:Gem::Requirement
|
130
|
+
requirements:
|
131
|
+
- - "~>"
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '2.8'
|
134
|
+
type: :development
|
135
|
+
prerelease: false
|
136
|
+
version_requirements: !ruby/object:Gem::Requirement
|
137
|
+
requirements:
|
138
|
+
- - "~>"
|
139
|
+
- !ruby/object:Gem::Version
|
140
|
+
version: '2.8'
|
141
|
+
- !ruby/object:Gem::Dependency
|
142
|
+
name: rubocop
|
143
|
+
requirement: !ruby/object:Gem::Requirement
|
144
|
+
requirements:
|
145
|
+
- - "~>"
|
146
|
+
- !ruby/object:Gem::Version
|
147
|
+
version: '0.42'
|
148
|
+
type: :development
|
149
|
+
prerelease: false
|
150
|
+
version_requirements: !ruby/object:Gem::Requirement
|
151
|
+
requirements:
|
152
|
+
- - "~>"
|
153
|
+
- !ruby/object:Gem::Version
|
154
|
+
version: '0.42'
|
155
|
+
description: Extracts the title, content, and other informaiton of an event
|
156
|
+
email:
|
157
|
+
- jjc@nlplab.cc
|
158
|
+
executables:
|
159
|
+
- nthuevent
|
160
|
+
extensions: []
|
161
|
+
extra_rdoc_files: []
|
162
|
+
files:
|
163
|
+
- ".gitignore"
|
164
|
+
- ".rubocop.yml"
|
165
|
+
- Gemfile
|
166
|
+
- Gemfile.lock
|
167
|
+
- LICENSE
|
168
|
+
- bin/nthuevent
|
169
|
+
- lib/crawl.rb
|
170
|
+
- lib/nthu_event.rb
|
171
|
+
- lib/nthuevent/event.rb
|
172
|
+
- lib/nthuevent/nthu_event_api.rb
|
173
|
+
- lib/nthuevent/version.rb
|
174
|
+
- nthuevent.gemspec
|
175
|
+
homepage: https://github.com/twentyfour7/nthu-event
|
176
|
+
licenses:
|
177
|
+
- MIT
|
178
|
+
metadata: {}
|
179
|
+
post_install_message:
|
180
|
+
rdoc_options: []
|
181
|
+
require_paths:
|
182
|
+
- lib
|
183
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
184
|
+
requirements:
|
185
|
+
- - ">="
|
186
|
+
- !ruby/object:Gem::Version
|
187
|
+
version: '0'
|
188
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
189
|
+
requirements:
|
190
|
+
- - ">="
|
191
|
+
- !ruby/object:Gem::Version
|
192
|
+
version: '0'
|
193
|
+
requirements: []
|
194
|
+
rubyforge_project:
|
195
|
+
rubygems_version: 2.5.1
|
196
|
+
signing_key:
|
197
|
+
specification_version: 4
|
198
|
+
summary: Gets event content from NTHU bulletin
|
199
|
+
test_files: []
|