scry 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/LICENSE.txt +21 -0
- data/README.md +123 -0
- data/bin/console +14 -0
- data/bin/monitor +8 -0
- data/bin/scrape_blackboard +6 -0
- data/lib/scry.rb +57 -0
- data/lib/scry/course.rb +194 -0
- data/lib/scry/export_failed.rb +7 -0
- data/lib/scry/helpers.rb +19 -0
- data/lib/scry/scraper.rb +62 -0
- data/lib/scry/sidekiq/config.ru +8 -0
- data/lib/scry/sidekiq/workers/export_downloader.rb +39 -0
- data/lib/scry/sidekiq/workers/export_generator.rb +45 -0
- data/lib/scry/sidekiq/workers/log_writer.rb +22 -0
- data/lib/scry/tasks.rb +32 -0
- data/lib/scry/version.rb +3 -0
- data/lib/scry/workers.rb +4 -0
- metadata +196 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 8498f89f31168881c6697f7cdc1a9425096f1162
|
4
|
+
data.tar.gz: f4edcdd786e68962a9edf92ab98c0b12d5731386
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 71cb018b167abfd16e0375392791665c30d9ec1deef82a8cbf57f8c3eaf24f83e5e901108e149d32e9f28e549d5c1000dd172b857c6b64417847504591cc156a
|
7
|
+
data.tar.gz: db13dd81f55baeee873b7344b168b1c8db14765019c42b26eea2202c7bec2873c391dd08588238e80395e7cf44689052f74b93a42ef7e78bb4b6d05d9c7ad1b6
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 AtomicJolt
|
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 +1,123 @@
|
|
1
|
+
# Scry [![Build Status](https://travis-ci.org/atomicjolt/scry.svg?branch=master)](https://travis-ci.org/atomicjolt/scry)
|
2
|
+
|
3
|
+
Scrapes courses from blackboard.
|
4
|
+
|
5
|
+
## Dependencies
|
6
|
+
ruby >= 2.2.2
|
7
|
+
|
8
|
+
redis-server >= 3.0.7
|
9
|
+
|
10
|
+
## Installation
|
11
|
+
|
12
|
+
Add this line to your application's Gemfile:
|
13
|
+
|
14
|
+
```ruby
|
15
|
+
gem "scry"
|
16
|
+
```
|
17
|
+
|
18
|
+
And then execute:
|
19
|
+
```sh
|
20
|
+
$ bundle
|
21
|
+
```
|
22
|
+
|
23
|
+
Or install it yourself as:
|
24
|
+
```sh
|
25
|
+
$ gem install scry
|
26
|
+
```
|
27
|
+
|
28
|
+
Create a ruby file `workers.rb` and add
|
29
|
+
```ruby
|
30
|
+
require "scry/workers"
|
31
|
+
```
|
32
|
+
|
33
|
+
Create a `Rakefile` and add
|
34
|
+
```ruby
|
35
|
+
require "scry/tasks"
|
36
|
+
Scry::Tasks.install_tasks
|
37
|
+
```
|
38
|
+
|
39
|
+
Create a `sidekiq.yml` file and add
|
40
|
+
```yml
|
41
|
+
:concurrency: 20
|
42
|
+
|
43
|
+
:queues:
|
44
|
+
- [scry_export_generator, 1]
|
45
|
+
- [scry_export_downloader, 1]
|
46
|
+
- [scry_log_writer, 1]
|
47
|
+
|
48
|
+
:limits:
|
49
|
+
scry_export_generator: 5
|
50
|
+
scry_export_downloader: 15
|
51
|
+
scry_log_writer: 1
|
52
|
+
```
|
53
|
+
_note: limits is available through the [sidekiq-limit_fetch](https://github.com/brainopia/sidekiq-limit_fetch) gem_
|
54
|
+
|
55
|
+
Create a "scry.yml" file and add
|
56
|
+
```yml
|
57
|
+
:url: https://<blackboard_url>/
|
58
|
+
:login: <user_name>
|
59
|
+
:passwd: <user_password>
|
60
|
+
```
|
61
|
+
|
62
|
+
### Optional
|
63
|
+
If different log file names are desired, in the `scry.yml` add the file names.
|
64
|
+
This is the default configuration:
|
65
|
+
```yml
|
66
|
+
:export_generation_good: export_generation_good.txt
|
67
|
+
:export_generation_bad: export_generation_bad.txt
|
68
|
+
:export_download_good: export_download_good.txt
|
69
|
+
:export_download_bad: export_download_bad.txt
|
70
|
+
:export_generation_no_export_button: export_generation_no_export_button.txt
|
71
|
+
```
|
72
|
+
And if a different export folder is desired:
|
73
|
+
```yml
|
74
|
+
:default_dir: blackboard_exports
|
75
|
+
```
|
76
|
+
|
77
|
+
## Usage
|
78
|
+
|
79
|
+
Start up sidekiq
|
80
|
+
```sh
|
81
|
+
bundle exec sidekiq -r ./workers.rb -C sidekiq.yml
|
82
|
+
```
|
83
|
+
|
84
|
+
Run the rake task to download all the courses.
|
85
|
+
```sh
|
86
|
+
bundle exec rake scry:scrape
|
87
|
+
```
|
88
|
+
This will download each cartridge zip into the default directory `blackboard_exports`
|
89
|
+
|
90
|
+
Delete entire default blackboard_exports folder
|
91
|
+
```sh
|
92
|
+
bundle exec rake scry:clean
|
93
|
+
```
|
94
|
+
|
95
|
+
Monitor sidekiq
|
96
|
+
```sh
|
97
|
+
bundle exec monitor
|
98
|
+
```
|
99
|
+
|
100
|
+
# Development
|
101
|
+
|
102
|
+
After checking out the repo, run `bundle install` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
103
|
+
|
104
|
+
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).
|
105
|
+
|
106
|
+
## Running sidekiq
|
107
|
+
|
108
|
+
Need redis running first: `redis-server`
|
109
|
+
|
110
|
+
Run `bundle exec sidekiq -r ./lib/scry/workers.rb -C sidekiq.yml`
|
111
|
+
|
112
|
+
To get access to the workers in code require "lib/scry/sidekiq/boot.rb"
|
113
|
+
|
114
|
+
To monitor sidekiq using the web UI, run `bin/monitor`
|
115
|
+
|
116
|
+
## Contributing
|
117
|
+
|
118
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/scry. 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.
|
119
|
+
|
120
|
+
|
121
|
+
## License
|
122
|
+
|
123
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "scry"
|
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/monitor
ADDED
data/lib/scry.rb
ADDED
@@ -0,0 +1,57 @@
|
|
1
|
+
require "scry/scraper"
|
2
|
+
|
3
|
+
EXPORT_GENERATION_GOOD = "export_generation_good.txt".freeze
|
4
|
+
EXPORT_GENERATION_BAD = "export_generation_bad.txt".freeze
|
5
|
+
EXPORT_DOWNLOAD_GOOD = "export_download_good.txt".freeze
|
6
|
+
EXPORT_DOWNLOAD_BAD = "export_download_bad.txt".freeze
|
7
|
+
EXPORT_GENERATION_NO_EXPORT_BUTTON =
|
8
|
+
"export_generation_no_export_button.txt".freeze
|
9
|
+
|
10
|
+
DEFAULT_DIR = "blackboard_exports".freeze
|
11
|
+
|
12
|
+
module Scry
|
13
|
+
def self.config
|
14
|
+
if File.exists? "scry.yml"
|
15
|
+
YAML::load(File.read("scry.yml"))
|
16
|
+
else
|
17
|
+
{}
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
def self.url
|
22
|
+
Scry.config[:url]
|
23
|
+
end
|
24
|
+
|
25
|
+
def self.login
|
26
|
+
Scry.config[:login]
|
27
|
+
end
|
28
|
+
|
29
|
+
def self.passwd
|
30
|
+
Scry.config[:passwd]
|
31
|
+
end
|
32
|
+
|
33
|
+
def self.default_dir
|
34
|
+
Scry.config[:default_dir] || DEFAULT_DIR
|
35
|
+
end
|
36
|
+
|
37
|
+
def self.export_generation_good
|
38
|
+
Scry.config[:export_generation_good] || EXPORT_GENERATION_GOOD
|
39
|
+
end
|
40
|
+
|
41
|
+
def self.export_generation_bad
|
42
|
+
Scry.config[:export_generation_bad] || EXPORT_GENERATION_BAD
|
43
|
+
end
|
44
|
+
|
45
|
+
def self.export_download_good
|
46
|
+
Scry.config[:export_download_good] || EXPORT_DOWNLOAD_GOOD
|
47
|
+
end
|
48
|
+
|
49
|
+
def self.export_download_bad
|
50
|
+
Scry.config[:export_download_bad] || EXPORT_DOWNLOAD_BAD
|
51
|
+
end
|
52
|
+
|
53
|
+
def self.export_generation_no_export_button
|
54
|
+
Scry.config[:export_generation_no_export_button] ||
|
55
|
+
EXPORT_GENERATION_NO_EXPORT_BUTTON
|
56
|
+
end
|
57
|
+
end
|
data/lib/scry/course.rb
ADDED
@@ -0,0 +1,194 @@
|
|
1
|
+
require "mechanize"
|
2
|
+
require "scry"
|
3
|
+
require "scry/helpers"
|
4
|
+
require "scry/export_failed"
|
5
|
+
|
6
|
+
TWO_HOURS = 7200
|
7
|
+
|
8
|
+
module Scry
|
9
|
+
##
|
10
|
+
# This class represents a course for which we are extracting data
|
11
|
+
##
|
12
|
+
class Course
|
13
|
+
include Scry::Helpers
|
14
|
+
|
15
|
+
##
|
16
|
+
# A new course accepts a Mechanize Agent
|
17
|
+
# and a Mechanize::Page::Link object for a course link
|
18
|
+
##
|
19
|
+
def initialize(agent, course_link)
|
20
|
+
@agent = agent
|
21
|
+
@course_link = course_link
|
22
|
+
end
|
23
|
+
|
24
|
+
##
|
25
|
+
# Creates a new instance of a course
|
26
|
+
# from given cookies so the user is signed in
|
27
|
+
##
|
28
|
+
def self.from_cookies(cookie_crumbs, course_url)
|
29
|
+
agent = Mechanize.new
|
30
|
+
agent.cookie_jar = YAML::load(cookie_crumbs)
|
31
|
+
course_link = Mechanize::Page::Link.new(
|
32
|
+
{
|
33
|
+
"href" => course_url,
|
34
|
+
},
|
35
|
+
agent,
|
36
|
+
nil,
|
37
|
+
)
|
38
|
+
Course.new(agent, course_link)
|
39
|
+
end
|
40
|
+
|
41
|
+
##
|
42
|
+
# Creates an export file for the course
|
43
|
+
#
|
44
|
+
# Navigates from the course page to the export course page
|
45
|
+
# and creates an export for the course.
|
46
|
+
#
|
47
|
+
# First it all existing exports, then attempts to create a new export.
|
48
|
+
#
|
49
|
+
# It will wait a specified amount of time for the export to be created.
|
50
|
+
##
|
51
|
+
def create_export
|
52
|
+
course_page = @agent.click(@course_link)
|
53
|
+
package_links = course_page.links_with(
|
54
|
+
text: /Packages & Utilities Overview Page/,
|
55
|
+
)
|
56
|
+
if package_links.any?
|
57
|
+
utilities_page = click_link(
|
58
|
+
agent: @agent,
|
59
|
+
page: course_page,
|
60
|
+
text: /Packages & Utilities Overview Page/,
|
61
|
+
)
|
62
|
+
exports_page = click_link(
|
63
|
+
agent: @agent,
|
64
|
+
page: utilities_page,
|
65
|
+
text: /Export\/Archive Course/,
|
66
|
+
)
|
67
|
+
export_button_link = exports_page.links_with(
|
68
|
+
text: /Export Package/,
|
69
|
+
)
|
70
|
+
if export_button_link.any?
|
71
|
+
course_id =
|
72
|
+
exports_page.form_with(name: "selectFileToDelete")["courseId"]
|
73
|
+
_delete_existing_exports(exports_page, course_id, nil)
|
74
|
+
export_page = click_link(
|
75
|
+
agent: @agent,
|
76
|
+
page: exports_page,
|
77
|
+
text: /Export Package/,
|
78
|
+
)
|
79
|
+
exports_page = _process_export_form(export_page)
|
80
|
+
exports = exports_page.links_with(
|
81
|
+
text: "View Basic Log",
|
82
|
+
)
|
83
|
+
_wait_for_export(exports, utilities_page, exports_page, course_id)
|
84
|
+
else
|
85
|
+
write_log(
|
86
|
+
Scry.export_generation_no_export_button,
|
87
|
+
@course_link.href.strip,
|
88
|
+
)
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
92
|
+
|
93
|
+
##
|
94
|
+
# Opens the log for an export and checks if it was successful.
|
95
|
+
##
|
96
|
+
def validate_export(exports_page)
|
97
|
+
links = exports_page.links_with(text: "View Basic Log")
|
98
|
+
if links.empty?
|
99
|
+
raise Scry::ExportFailed, "Links empty #{exports_page.uri}"
|
100
|
+
end
|
101
|
+
url = links.last.attributes["onclick"][/'(.*)'/, 1]
|
102
|
+
log_page = @agent.get(url)
|
103
|
+
text = Nokogiri::HTML(log_page.body).css("div#containerdiv").text
|
104
|
+
!text.match(/error/i)
|
105
|
+
end
|
106
|
+
|
107
|
+
##
|
108
|
+
# Extracts the download URL for an export
|
109
|
+
##
|
110
|
+
def download_url(page)
|
111
|
+
download_link = page.links_with(text: "Open").last
|
112
|
+
download_link.href
|
113
|
+
end
|
114
|
+
|
115
|
+
##
|
116
|
+
# Downloads the export into the given directory.
|
117
|
+
##
|
118
|
+
def download_export(url)
|
119
|
+
puts "Start downloading #{url}"
|
120
|
+
time = Time.now
|
121
|
+
@agent.pluggable_parser["application/zip"] = Mechanize::Download
|
122
|
+
filename = File.basename(URI.parse(url).path)
|
123
|
+
@agent.get(url).save(File.join(Scry.default_dir, filename))
|
124
|
+
elapsed = Time.now - time
|
125
|
+
puts "Done downloading #{url} took #{elapsed} seconds"
|
126
|
+
end
|
127
|
+
|
128
|
+
##
|
129
|
+
# :nodoc:
|
130
|
+
# Fills out the export form and submits it.
|
131
|
+
##
|
132
|
+
def _process_export_form(export_page)
|
133
|
+
export_page.form_with(name: "selectCourse") do |export_form|
|
134
|
+
export_form.radiobutton_with(
|
135
|
+
id: "copyLinkToCourseFilesAndCopiesOfContent",
|
136
|
+
).check
|
137
|
+
export_form.radiobutton_with(
|
138
|
+
id: "copyLinkToExternalCourseFilesAndCopiesOfContent",
|
139
|
+
).check
|
140
|
+
export_form.checkboxes.each(&:check)
|
141
|
+
end.submit
|
142
|
+
end
|
143
|
+
|
144
|
+
##
|
145
|
+
# :nodoc:
|
146
|
+
# Waits a specified amount of time for an export
|
147
|
+
# to show up on the exports page.
|
148
|
+
##
|
149
|
+
def _wait_for_export(exports, utilities_page, exports_page, course_id)
|
150
|
+
time = Time.now
|
151
|
+
elapsed = 0
|
152
|
+
puts "Begin waiting for export link for #{course_id}"
|
153
|
+
while exports.count.zero? && elapsed < TWO_HOURS
|
154
|
+
sleep 30
|
155
|
+
exports_page = click_link(
|
156
|
+
agent: @agent,
|
157
|
+
page: utilities_page,
|
158
|
+
text: /Export\/Archive Course/,
|
159
|
+
)
|
160
|
+
exports = exports_page.links_with(
|
161
|
+
text: "View Basic Log",
|
162
|
+
)
|
163
|
+
elapsed = Time.now - time
|
164
|
+
puts "#{course_id} waited #{elapsed.to_i} seconds for link"
|
165
|
+
end
|
166
|
+
if elapsed >= TWO_HOURS
|
167
|
+
raise Scry::ExportFailed, "Export timeout for #{course_id}"
|
168
|
+
end
|
169
|
+
puts "#{course_id} done after #{(Time.now - time).to_i} seconds"
|
170
|
+
exports_page
|
171
|
+
end
|
172
|
+
|
173
|
+
##
|
174
|
+
# :nodoc:
|
175
|
+
# Deletes all existing exports from a page.
|
176
|
+
##
|
177
|
+
def _delete_existing_exports(page, course_id, links)
|
178
|
+
links ||= page.links_with(text: "Delete")
|
179
|
+
puts "#{course_id} Deleting exports... #{links.count} remaining"
|
180
|
+
if links.any?
|
181
|
+
filename = links.last.href[/'(.*)'\,/, 1]
|
182
|
+
|
183
|
+
page = page.form_with(name: "selectFileToDelete") do |form|
|
184
|
+
form.field_with(name: "filename").value = filename
|
185
|
+
end.submit
|
186
|
+
|
187
|
+
links = page.links_with(text: "Delete")
|
188
|
+
if links.any?
|
189
|
+
_delete_existing_exports(page, course_id, links)
|
190
|
+
end
|
191
|
+
end
|
192
|
+
end
|
193
|
+
end
|
194
|
+
end
|
data/lib/scry/helpers.rb
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
require "scry/sidekiq/workers/log_writer"
|
2
|
+
|
3
|
+
module Scry
|
4
|
+
module Helpers
|
5
|
+
##
|
6
|
+
# Clicks a link with the given text.
|
7
|
+
##
|
8
|
+
def click_link(agent:, page:, text:)
|
9
|
+
agent.click(page.link_with(text: text))
|
10
|
+
end
|
11
|
+
|
12
|
+
##
|
13
|
+
# Enqueues data to be written to a log file.
|
14
|
+
##
|
15
|
+
def write_log(log, data)
|
16
|
+
Scry::LogWriter.perform_async(log, data)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
data/lib/scry/scraper.rb
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
require "rubygems"
|
2
|
+
require "mechanize"
|
3
|
+
require "scry"
|
4
|
+
require "scry/sidekiq/workers/export_generator"
|
5
|
+
require "scry/helpers"
|
6
|
+
require "scry/course"
|
7
|
+
|
8
|
+
module Scry
|
9
|
+
extend Scry::Helpers
|
10
|
+
|
11
|
+
##
|
12
|
+
# Creates sidekiq jobs for each course to generate an export.
|
13
|
+
#
|
14
|
+
# Logs in the user and goes over every course
|
15
|
+
# and creates a sidekiq to generate an export for it.
|
16
|
+
##
|
17
|
+
def self.scrape
|
18
|
+
url = Scry.url
|
19
|
+
login = Scry.login
|
20
|
+
passwd = Scry.passwd
|
21
|
+
|
22
|
+
agent = Mechanize.new do |secret_agent_man|
|
23
|
+
secret_agent_man.follow_meta_refresh = true
|
24
|
+
end
|
25
|
+
|
26
|
+
agent.get(url) do |home_page|
|
27
|
+
index_page = home_page.form_with(name: "login") do |form|
|
28
|
+
form["user_id"] = login
|
29
|
+
form["password"] = passwd
|
30
|
+
end.submit
|
31
|
+
courses_page = click_link(
|
32
|
+
agent: agent,
|
33
|
+
page: index_page,
|
34
|
+
text: /Open Bb Course List/,
|
35
|
+
)
|
36
|
+
|
37
|
+
courses_downloaded = Scry.courses_downloaded
|
38
|
+
|
39
|
+
# It is currently unknown if the links on the courses_page are paginated
|
40
|
+
# This gets them as if they are not.
|
41
|
+
course_links = courses_page.links_with(href: /type=Course/)
|
42
|
+
course_links.each do |course_link|
|
43
|
+
course_url = course_link.href.strip
|
44
|
+
if !courses_downloaded.include? course_url
|
45
|
+
cookie_crumbs = agent.cookie_jar.to_yaml
|
46
|
+
Scry::ExportGenerator.perform_async(
|
47
|
+
cookie_crumbs,
|
48
|
+
File.join(url, course_url),
|
49
|
+
)
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
def self.courses_downloaded
|
56
|
+
if File.exists?(Scry.export_download_good)
|
57
|
+
File.read(Scry.export_download_good)
|
58
|
+
else
|
59
|
+
""
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
@@ -0,0 +1,39 @@
|
|
1
|
+
require "mechanize"
|
2
|
+
require "sidekiq"
|
3
|
+
require "scry"
|
4
|
+
require "scry/course"
|
5
|
+
require "scry/export_failed"
|
6
|
+
require "scry/helpers"
|
7
|
+
|
8
|
+
module Scry
|
9
|
+
##
|
10
|
+
# Works on downloading an export.
|
11
|
+
#
|
12
|
+
# Will attempt 5 times before giving up.
|
13
|
+
##
|
14
|
+
class ExportDownloader
|
15
|
+
include Sidekiq::Worker
|
16
|
+
include Scry::Helpers
|
17
|
+
sidekiq_options queue: :scry_export_downloader, retry: 5
|
18
|
+
|
19
|
+
##
|
20
|
+
# Instigates downloading an export.
|
21
|
+
#
|
22
|
+
# Creates a course from the cookies,
|
23
|
+
# then starts downloading the export.
|
24
|
+
##
|
25
|
+
def perform(cookie_crumbs, course_url, download_url)
|
26
|
+
course = Course.from_cookies(cookie_crumbs, course_url)
|
27
|
+
uri = URI.parse(course_url)
|
28
|
+
uri.path = download_url
|
29
|
+
course.download_export(uri.to_s)
|
30
|
+
write_log(Scry.export_download_good, course_url)
|
31
|
+
rescue SocketError, Mechanize::Error, Net::HTTPClientError => e
|
32
|
+
write_log(
|
33
|
+
Scry.export_download_bad,
|
34
|
+
"#{course_url} #{e.class} #{e.message}",
|
35
|
+
)
|
36
|
+
raise
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
@@ -0,0 +1,45 @@
|
|
1
|
+
require "sidekiq"
|
2
|
+
require "scry"
|
3
|
+
require "scry/course"
|
4
|
+
require "scry/export_failed"
|
5
|
+
require "scry/helpers"
|
6
|
+
require "scry/sidekiq/workers/export_downloader"
|
7
|
+
|
8
|
+
##
|
9
|
+
# Works on generating the export.
|
10
|
+
#
|
11
|
+
# Will attempt 5 times before giving up.
|
12
|
+
##
|
13
|
+
module Scry
|
14
|
+
class ExportGenerator
|
15
|
+
include Sidekiq::Worker
|
16
|
+
include Scry::Helpers
|
17
|
+
sidekiq_options queue: :scry_export_generator, retry: 5
|
18
|
+
|
19
|
+
##
|
20
|
+
# Instigates generating an export.
|
21
|
+
#
|
22
|
+
# Creates a course from the cookies,
|
23
|
+
# then starts generating the export.
|
24
|
+
##
|
25
|
+
def perform(cookie_crumbs, course_url)
|
26
|
+
course = Course.from_cookies(cookie_crumbs, course_url)
|
27
|
+
exports_page = course.create_export
|
28
|
+
if exports_page.is_a? Mechanize::Page
|
29
|
+
valid = course.validate_export(exports_page)
|
30
|
+
if valid
|
31
|
+
write_log(Scry.export_generation_good, course_url)
|
32
|
+
download_url = course.download_url(exports_page)
|
33
|
+
Scry::ExportDownloader.perform_async(
|
34
|
+
cookie_crumbs,
|
35
|
+
course_url,
|
36
|
+
download_url,
|
37
|
+
)
|
38
|
+
else
|
39
|
+
write_log(Scry.export_generation_bad, course_url)
|
40
|
+
raise Scry::ExportFailed, "Something failed"
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
require "sidekiq"
|
2
|
+
|
3
|
+
##
|
4
|
+
# Writes log files
|
5
|
+
#
|
6
|
+
# Will attempt 5 times before giving up.
|
7
|
+
##
|
8
|
+
module Scry
|
9
|
+
class LogWriter
|
10
|
+
include Sidekiq::Worker
|
11
|
+
sidekiq_options queue: :scry_log_writer, retry: 5
|
12
|
+
|
13
|
+
##
|
14
|
+
# Writes data to the given log file
|
15
|
+
##
|
16
|
+
def perform(log, data)
|
17
|
+
File.open(log, "a") do |file|
|
18
|
+
file.puts data
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
data/lib/scry/tasks.rb
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
require "rake/clean"
|
2
|
+
require "scry"
|
3
|
+
|
4
|
+
module Scry
|
5
|
+
class Tasks
|
6
|
+
extend Rake::DSL if defined? Rake::DSL
|
7
|
+
|
8
|
+
##
|
9
|
+
# Creates rake tasks that can be ran from the gem.
|
10
|
+
#
|
11
|
+
# Add this to your Rakefile
|
12
|
+
#
|
13
|
+
# require "scry/tasks"
|
14
|
+
# Scry::Tasks.install_tasks
|
15
|
+
#
|
16
|
+
##
|
17
|
+
def self.install_tasks
|
18
|
+
namespace :scry do
|
19
|
+
desc "Scrape the configured url for course data"
|
20
|
+
task :scrape do
|
21
|
+
mkdir_p Scry.default_dir
|
22
|
+
Scry.scrape
|
23
|
+
end
|
24
|
+
|
25
|
+
desc "Completely delete all downloaded files"
|
26
|
+
task :clean do
|
27
|
+
rm_rf Scry.default_dir
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
data/lib/scry/version.rb
ADDED
data/lib/scry/workers.rb
ADDED
metadata
ADDED
@@ -0,0 +1,196 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: scry
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Atomic Jolt
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-12-07 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: pry-byebug
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '3.4'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '3.4'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rspec
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '3.5'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '3.5'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: webmock
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.1'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.1'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '11.3'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '11.3'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: mechanize
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '2.7'
|
76
|
+
- - ">="
|
77
|
+
- !ruby/object:Gem::Version
|
78
|
+
version: 2.7.5
|
79
|
+
type: :runtime
|
80
|
+
prerelease: false
|
81
|
+
version_requirements: !ruby/object:Gem::Requirement
|
82
|
+
requirements:
|
83
|
+
- - "~>"
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '2.7'
|
86
|
+
- - ">="
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: 2.7.5
|
89
|
+
- !ruby/object:Gem::Dependency
|
90
|
+
name: fileutils
|
91
|
+
requirement: !ruby/object:Gem::Requirement
|
92
|
+
requirements:
|
93
|
+
- - "~>"
|
94
|
+
- !ruby/object:Gem::Version
|
95
|
+
version: '0.7'
|
96
|
+
type: :runtime
|
97
|
+
prerelease: false
|
98
|
+
version_requirements: !ruby/object:Gem::Requirement
|
99
|
+
requirements:
|
100
|
+
- - "~>"
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
version: '0.7'
|
103
|
+
- !ruby/object:Gem::Dependency
|
104
|
+
name: sidekiq
|
105
|
+
requirement: !ruby/object:Gem::Requirement
|
106
|
+
requirements:
|
107
|
+
- - "~>"
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '4.2'
|
110
|
+
type: :runtime
|
111
|
+
prerelease: false
|
112
|
+
version_requirements: !ruby/object:Gem::Requirement
|
113
|
+
requirements:
|
114
|
+
- - "~>"
|
115
|
+
- !ruby/object:Gem::Version
|
116
|
+
version: '4.2'
|
117
|
+
- !ruby/object:Gem::Dependency
|
118
|
+
name: sidekiq-limit_fetch
|
119
|
+
requirement: !ruby/object:Gem::Requirement
|
120
|
+
requirements:
|
121
|
+
- - "~>"
|
122
|
+
- !ruby/object:Gem::Version
|
123
|
+
version: '3.4'
|
124
|
+
type: :runtime
|
125
|
+
prerelease: false
|
126
|
+
version_requirements: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - "~>"
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '3.4'
|
131
|
+
- !ruby/object:Gem::Dependency
|
132
|
+
name: thin
|
133
|
+
requirement: !ruby/object:Gem::Requirement
|
134
|
+
requirements:
|
135
|
+
- - "~>"
|
136
|
+
- !ruby/object:Gem::Version
|
137
|
+
version: '1.7'
|
138
|
+
type: :runtime
|
139
|
+
prerelease: false
|
140
|
+
version_requirements: !ruby/object:Gem::Requirement
|
141
|
+
requirements:
|
142
|
+
- - "~>"
|
143
|
+
- !ruby/object:Gem::Version
|
144
|
+
version: '1.7'
|
145
|
+
description: Commandline tool that downloads blackboard cartridges
|
146
|
+
email: joel@atomicjolt.com
|
147
|
+
executables:
|
148
|
+
- console
|
149
|
+
- monitor
|
150
|
+
- scrape_blackboard
|
151
|
+
extensions: []
|
152
|
+
extra_rdoc_files:
|
153
|
+
- README.md
|
154
|
+
files:
|
155
|
+
- LICENSE.txt
|
156
|
+
- README.md
|
157
|
+
- bin/console
|
158
|
+
- bin/monitor
|
159
|
+
- bin/scrape_blackboard
|
160
|
+
- lib/scry.rb
|
161
|
+
- lib/scry/course.rb
|
162
|
+
- lib/scry/export_failed.rb
|
163
|
+
- lib/scry/helpers.rb
|
164
|
+
- lib/scry/scraper.rb
|
165
|
+
- lib/scry/sidekiq/config.ru
|
166
|
+
- lib/scry/sidekiq/workers/export_downloader.rb
|
167
|
+
- lib/scry/sidekiq/workers/export_generator.rb
|
168
|
+
- lib/scry/sidekiq/workers/log_writer.rb
|
169
|
+
- lib/scry/tasks.rb
|
170
|
+
- lib/scry/version.rb
|
171
|
+
- lib/scry/workers.rb
|
172
|
+
homepage: https://github.com/atomicjolt/scry
|
173
|
+
licenses:
|
174
|
+
- MIT
|
175
|
+
metadata: {}
|
176
|
+
post_install_message:
|
177
|
+
rdoc_options: []
|
178
|
+
require_paths:
|
179
|
+
- lib
|
180
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
181
|
+
requirements:
|
182
|
+
- - ">="
|
183
|
+
- !ruby/object:Gem::Version
|
184
|
+
version: '0'
|
185
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
186
|
+
requirements:
|
187
|
+
- - ">="
|
188
|
+
- !ruby/object:Gem::Version
|
189
|
+
version: '0'
|
190
|
+
requirements: []
|
191
|
+
rubyforge_project:
|
192
|
+
rubygems_version: 2.5.1
|
193
|
+
signing_key:
|
194
|
+
specification_version: 4
|
195
|
+
summary: Downloads Blackboard Cartridges
|
196
|
+
test_files: []
|