scrapperd 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +18 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +54 -0
- data/Rakefile +8 -0
- data/lib/scrapperd.rb +6 -0
- data/lib/scrapperd/activity.rb +41 -0
- data/lib/scrapperd/base.rb +21 -0
- data/lib/scrapperd/error.rb +9 -0
- data/lib/scrapperd/version.rb +3 -0
- data/scrapperd.gemspec +29 -0
- data/test/activity_test.rb +21 -0
- data/test/test_helper.rb +4 -0
- metadata +135 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 227704fb9f04229706b060e558decb3a22c70ba7
|
4
|
+
data.tar.gz: 8f3b6972e1d9c9f0dc0b01b0fc75a03fa438283c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: d0c4697138145a3d3fc3f3a1fc189a38e06a0994db1e973f1416f0d7b82002987c9e9d29d5e1ae7201f975fa13ff8e1791d5b06517f02460441e1fde54208fb5
|
7
|
+
data.tar.gz: 735e9924e5cff405ec933a4c640b5e9c504172b27766b1b8ac50cf7b05aba410df2891207f41ef2117e03708a041e1f8235aa45b8396837fc1afb271c77bf0d1
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Victor
|
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 +1,54 @@
|
|
1
|
+
# Scrapperd
|
2
|
+
|
3
|
+
Scrapperd is a very simple scrapper for the public user activity RSS in [Letterboxd](http://letterboxd.com). It relies in OpenStruct to build objects.
|
4
|
+
|
5
|
+
|
6
|
+
## Installation
|
7
|
+
|
8
|
+
To get the latest stable:
|
9
|
+
|
10
|
+
gem 'scrapperd'
|
11
|
+
|
12
|
+
To get the latest code:
|
13
|
+
|
14
|
+
gem 'scrapperd', git: https://github.com/eltercero/scrapperd
|
15
|
+
|
16
|
+
And then execute:
|
17
|
+
|
18
|
+
$ bundle
|
19
|
+
|
20
|
+
## Usage
|
21
|
+
|
22
|
+
```ruby
|
23
|
+
>> require 'scrapperd'
|
24
|
+
|
25
|
+
>> client = Scrapperd::Base.new
|
26
|
+
|
27
|
+
# Example
|
28
|
+
#####################################################
|
29
|
+
# Return the RSS for a username
|
30
|
+
>> activities = client.fetch('eltercero')
|
31
|
+
=> [#<Scrapperd::Activity ...]
|
32
|
+
>> film = activities.first
|
33
|
+
=> #<Scrapperd::Activity title="Porco Rosso, 1992", score=8, link="http://letterboxd.com/eltercero/film/porco-rosso/", film_link="http://letterboxd.com/film/porco-rosso/", watched_at=2015-03-13 00:00:00 +0100, added_at=2015-03-13 22:52:18 +0100, original_response=#<Hashie::Mash dc_creator="V\xC3\xADctor" description="<p><img src=\"http://zardoz.cf.letterboxd.com/resized/film-poster/4/5/1/3/0/45130-porco-rosso-0-150-0-222-crop.jpg\"/></p> <p>Watched on Friday March 13, 2015.</p>" guid="letterboxd-watch-7901161" link="http://letterboxd.com/eltercero/film/porco-rosso/" pubDate=2015-03-13 22:52:18 +0100 title="Porco Rosso, 1992 - \xE2\x98\x85\xE2\x98\x85\xE2\x98\x85\xE2\x98\x85">>
|
34
|
+
>> film.title
|
35
|
+
=> "Porco Rosso, 1992"
|
36
|
+
>> film.score
|
37
|
+
=> 8
|
38
|
+
>> film.watched_at
|
39
|
+
=> 2015-03-13 00:00:00 +0100
|
40
|
+
```
|
41
|
+
|
42
|
+
## Contributing
|
43
|
+
|
44
|
+
Please, be my guest!
|
45
|
+
|
46
|
+
1. Fork it ( http://github.com/eltercero/scrapperd/fork )
|
47
|
+
2. Create your feature branch (`git checkout -b sequels-can-be-good`). Don't forget to test your changes!
|
48
|
+
3. Commit your changes (`git commit -am 'Remember Godfather 2!'`)
|
49
|
+
4. Push to the branch (`git push origin sequels-can-be-good`)
|
50
|
+
5. Create new Pull Request
|
51
|
+
|
52
|
+
## License
|
53
|
+
|
54
|
+
Released under the [MIT License](http://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/lib/scrapperd.rb
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
require 'simple-rss'
|
2
|
+
require 'ostruct'
|
3
|
+
require 'pry'
|
4
|
+
|
5
|
+
module Scrapperd
|
6
|
+
class Activity < ::OpenStruct
|
7
|
+
|
8
|
+
def initialize(item)
|
9
|
+
super(Hashie::Mash.new({
|
10
|
+
title: title_from_title(item[:title]),
|
11
|
+
score: score_from_title(item[:title]),
|
12
|
+
link: item[:link].force_encoding("UTF-8"),
|
13
|
+
film_link: "http://letterboxd.com/film/#{nicetitle_from_url(item[:link])}/".force_encoding("UTF-8"),
|
14
|
+
watched_at: watched_at_from_description(item[:description]),
|
15
|
+
added_at: item[:pubDate],
|
16
|
+
original_response: item
|
17
|
+
})
|
18
|
+
)
|
19
|
+
end
|
20
|
+
|
21
|
+
def nicetitle_from_url(url)
|
22
|
+
url.split('/').last
|
23
|
+
end
|
24
|
+
|
25
|
+
def watched_at_from_description(description)
|
26
|
+
string_date = description.match(/<p>Watched on (.*)<\/p>/)[1]
|
27
|
+
Time.parse string_date
|
28
|
+
end
|
29
|
+
|
30
|
+
def title_from_title(title)
|
31
|
+
title.split(' - ')[0..-2].join(' - ').force_encoding("UTF-8")
|
32
|
+
end
|
33
|
+
|
34
|
+
def score_from_title(title)
|
35
|
+
html_score = title.split(' - ').last
|
36
|
+
html_score.force_encoding("UTF-8")
|
37
|
+
html_score.split(//).map{|ind_score| ind_score == "★" ? 2 : 1 }.inject{|sum,x| sum + x }
|
38
|
+
end
|
39
|
+
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'simple-rss'
|
2
|
+
require 'open-uri'
|
3
|
+
require 'pry'
|
4
|
+
|
5
|
+
require 'scrapperd/activity'
|
6
|
+
require 'scrapperd/error'
|
7
|
+
|
8
|
+
module Scrapperd
|
9
|
+
class Base
|
10
|
+
|
11
|
+
BASE_URL = "http://letterboxd.com/"
|
12
|
+
|
13
|
+
def fetch(username)
|
14
|
+
raise Scrapperd::Error::BadRequest.new('options must be in a Hash') unless username
|
15
|
+
|
16
|
+
rss = SimpleRSS.parse(open("#{BASE_URL}#{username}/rss"))
|
17
|
+
rss.items.map{|item| Scrapperd::Activity.new(item)}
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
21
|
+
end
|
data/scrapperd.gemspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'scrapperd/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "scrapperd"
|
8
|
+
spec.version = Scrapperd::VERSION
|
9
|
+
spec.authors = ["Víctor Martín"]
|
10
|
+
spec.email = ["victor.martin84@gmail.com"]
|
11
|
+
spec.summary = %q{Scrapper for Letterboxd user's activity}
|
12
|
+
spec.description = %q{Scrapper for Letterboxd user's activity using public user RSS}
|
13
|
+
spec.homepage = "https://github.com/eltercero/scrapperd"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
18
|
+
|
19
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
20
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
21
|
+
spec.require_paths = ["lib"]
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.5"
|
24
|
+
spec.add_development_dependency "rake", '~> 10.1'
|
25
|
+
|
26
|
+
spec.add_development_dependency 'minitest', '~>5.2'
|
27
|
+
spec.add_dependency 'simple-rss','~> 1.3', '>= 1.3.1'
|
28
|
+
spec.add_dependency 'hashie', '~>2.0'
|
29
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'test_helper'
|
2
|
+
|
3
|
+
class ActivityTest < MiniTest::Unit::TestCase
|
4
|
+
def test_activity_conversion
|
5
|
+
item = { :title => "Nausica\xC3\xA4 of the Valley of the Wind, 1984 - \xE2\x98\x85\xE2\x98\x85\xE2\x98\x85\xC2\xBD",
|
6
|
+
:link => "http://letterboxd.com/eltercero/film/nausicaa-of-the-valley-of-the-wind/",
|
7
|
+
:description => "<p><img src=\"http://primer.cf.letterboxd.com/resized/film-poster/5/1/9/6/9/51969-nausicaa-of-the-valley-of-the-wind-0-150-0-222-crop.jpg\"/></p> <p>Watched on Saturday March 14, 2015.</p>",
|
8
|
+
:pubDate => Time.new('2015-03-14 19:45:50 +0100'),
|
9
|
+
:guid => "letterboxd-watch-7911516",
|
10
|
+
:dc_creator => "V\xC3\xADctor"}
|
11
|
+
|
12
|
+
activity = Scrapperd::Activity.new(item)
|
13
|
+
|
14
|
+
assert_equal activity.title, "Nausica\xC3\xA4 of the Valley of the Wind, 1984"
|
15
|
+
assert_equal activity.score, 7
|
16
|
+
assert_equal activity.link, "http://letterboxd.com/eltercero/film/nausicaa-of-the-valley-of-the-wind/"
|
17
|
+
assert_equal activity.film_link, "http://letterboxd.com/film/nausicaa-of-the-valley-of-the-wind/"
|
18
|
+
assert_equal activity.watched_at, Time.parse("Saturday March 14, 2015.")
|
19
|
+
assert_equal activity.added_at, Time.new('2015-03-14 19:45:50 +0100')
|
20
|
+
end
|
21
|
+
end
|
data/test/test_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,135 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: scrapperd
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Víctor Martín
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-03-14 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.5'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.5'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.1'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.1'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: minitest
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '5.2'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '5.2'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: simple-rss
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.3'
|
62
|
+
- - ">="
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: 1.3.1
|
65
|
+
type: :runtime
|
66
|
+
prerelease: false
|
67
|
+
version_requirements: !ruby/object:Gem::Requirement
|
68
|
+
requirements:
|
69
|
+
- - "~>"
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: '1.3'
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: 1.3.1
|
75
|
+
- !ruby/object:Gem::Dependency
|
76
|
+
name: hashie
|
77
|
+
requirement: !ruby/object:Gem::Requirement
|
78
|
+
requirements:
|
79
|
+
- - "~>"
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '2.0'
|
82
|
+
type: :runtime
|
83
|
+
prerelease: false
|
84
|
+
version_requirements: !ruby/object:Gem::Requirement
|
85
|
+
requirements:
|
86
|
+
- - "~>"
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '2.0'
|
89
|
+
description: Scrapper for Letterboxd user's activity using public user RSS
|
90
|
+
email:
|
91
|
+
- victor.martin84@gmail.com
|
92
|
+
executables: []
|
93
|
+
extensions: []
|
94
|
+
extra_rdoc_files: []
|
95
|
+
files:
|
96
|
+
- ".gitignore"
|
97
|
+
- Gemfile
|
98
|
+
- LICENSE.txt
|
99
|
+
- README.md
|
100
|
+
- Rakefile
|
101
|
+
- lib/scrapperd.rb
|
102
|
+
- lib/scrapperd/activity.rb
|
103
|
+
- lib/scrapperd/base.rb
|
104
|
+
- lib/scrapperd/error.rb
|
105
|
+
- lib/scrapperd/version.rb
|
106
|
+
- scrapperd.gemspec
|
107
|
+
- test/activity_test.rb
|
108
|
+
- test/test_helper.rb
|
109
|
+
homepage: https://github.com/eltercero/scrapperd
|
110
|
+
licenses:
|
111
|
+
- MIT
|
112
|
+
metadata: {}
|
113
|
+
post_install_message:
|
114
|
+
rdoc_options: []
|
115
|
+
require_paths:
|
116
|
+
- lib
|
117
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
118
|
+
requirements:
|
119
|
+
- - ">="
|
120
|
+
- !ruby/object:Gem::Version
|
121
|
+
version: '0'
|
122
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
123
|
+
requirements:
|
124
|
+
- - ">="
|
125
|
+
- !ruby/object:Gem::Version
|
126
|
+
version: '0'
|
127
|
+
requirements: []
|
128
|
+
rubyforge_project:
|
129
|
+
rubygems_version: 2.2.2
|
130
|
+
signing_key:
|
131
|
+
specification_version: 4
|
132
|
+
summary: Scrapper for Letterboxd user's activity
|
133
|
+
test_files:
|
134
|
+
- test/activity_test.rb
|
135
|
+
- test/test_helper.rb
|