ngpod_scraper 0.1.1
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.
- data/.gitignore +9 -0
- data/Gemfile +4 -0
- data/LICENSE +20 -0
- data/README.markdown +46 -0
- data/Rakefile +1 -0
- data/VERSION +1 -0
- data/bin/ngpod_scraper +6 -0
- data/lib/ngpod_scraper/client.rb +42 -0
- data/lib/ngpod_scraper/ngpod_scraper.rb +9 -0
- data/lib/ngpod_scraper/photo.rb +87 -0
- data/lib/ngpod_scraper/photo_page.rb +25 -0
- data/lib/ngpod_scraper/version.rb +3 -0
- data/lib/ngpod_scraper.rb +12 -0
- data/ngpod_scraper.gemspec +29 -0
- data/spec/fixtures/config.yml +8 -0
- data/spec/fixtures/test.html +2698 -0
- data/spec/fixtures/test.jpg +0 -0
- data/spec/ngpod_scraper/client_spec.rb +81 -0
- data/spec/ngpod_scraper/ngpod_scraper_spec.rb +17 -0
- data/spec/ngpod_scraper/photo_page_spec.rb +39 -0
- data/spec/ngpod_scraper/photo_spec.rb +129 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +16 -0
- metadata +183 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 George Mendoza
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.markdown
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
README
|
2
|
+
========================================================================
|
3
|
+
|
4
|
+
Download the photo of the day from the National Geographic website
|
5
|
+
and save it as a desktop wallpaper.
|
6
|
+
|
7
|
+
Installation
|
8
|
+
------------------------------------------------------------------------
|
9
|
+
|
10
|
+
gem install ngpod_scraper
|
11
|
+
|
12
|
+
Requirements
|
13
|
+
------------------------------------------------------------------------
|
14
|
+
|
15
|
+
* nokogiri
|
16
|
+
* pow
|
17
|
+
* rmagick
|
18
|
+
* valuable
|
19
|
+
|
20
|
+
Usage
|
21
|
+
------------------------------------------------------------------------
|
22
|
+
|
23
|
+
ngpod_scaper path/to/config.yml
|
24
|
+
|
25
|
+
Sample config.yml
|
26
|
+
------------------------------------------------------------------------
|
27
|
+
|
28
|
+
url: http://photography.nationalgeographic.com/photography/photo-of-the-day
|
29
|
+
show_logs: true
|
30
|
+
photo:
|
31
|
+
path_format: '/home/gsmendoza/Pictures/national-geographic/#{year}-#{month}/#{name}'
|
32
|
+
wallpaper_path_format: '/home/gsmendoza/Pictures/national-geographic/photo-of-the-day.jpg'
|
33
|
+
wallpaper_width: 1280
|
34
|
+
wallpaper_height: 800
|
35
|
+
wallpaper_background_color: black
|
36
|
+
|
37
|
+
`path_format` and `wallpaper_path_format` are evaluated as strings.
|
38
|
+
For convenience, the following values are provided:
|
39
|
+
|
40
|
+
* time, year, month, day, hour - based on `Time.now`
|
41
|
+
* name - the filename of the photo
|
42
|
+
|
43
|
+
Displaying the photos as your screensaver
|
44
|
+
------------------------------------------------------------------------
|
45
|
+
|
46
|
+
In Ubuntu, you'll need to do [this](http://cro.alienpants.com/index.php/2008/01/04/customising-the-pictures-folder-screensaver-in-ubuntu-gutsy/).
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
data/bin/ngpod_scraper
ADDED
@@ -0,0 +1,42 @@
|
|
1
|
+
module NgpodScraper
|
2
|
+
class Client
|
3
|
+
attr_reader :config
|
4
|
+
|
5
|
+
def initialize(config)
|
6
|
+
@config = symbolize_keys(config)
|
7
|
+
end
|
8
|
+
|
9
|
+
def get_photo
|
10
|
+
PhotoPage.new(config[:url], config).photo
|
11
|
+
end
|
12
|
+
|
13
|
+
def log(message)
|
14
|
+
if config[:show_logs]
|
15
|
+
puts message
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
def run
|
20
|
+
photo = get_photo
|
21
|
+
if photo.exists?
|
22
|
+
log "Wasn't able to download the photo of the day. Maybe the photo has already been downloaded."
|
23
|
+
else
|
24
|
+
photo.save
|
25
|
+
photo.save_wallpaper
|
26
|
+
log "Downloaded #{photo.path}"
|
27
|
+
end
|
28
|
+
photo
|
29
|
+
end
|
30
|
+
|
31
|
+
private
|
32
|
+
|
33
|
+
def symbolize_keys(hash)
|
34
|
+
result = {}
|
35
|
+
hash.each do |key, value|
|
36
|
+
value = symbolize_keys(value) if value.is_a?(Hash)
|
37
|
+
result[key.to_sym] = value
|
38
|
+
end
|
39
|
+
result
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,87 @@
|
|
1
|
+
module NgpodScraper
|
2
|
+
class Photo < Valuable
|
3
|
+
has_value :file
|
4
|
+
has_value :path_format
|
5
|
+
has_value :url
|
6
|
+
has_value :wallpaper_background_color
|
7
|
+
has_value :wallpaper_height
|
8
|
+
has_value :wallpaper_width
|
9
|
+
has_value :wallpaper_path_format
|
10
|
+
|
11
|
+
def exists?
|
12
|
+
Pow(path).exists?
|
13
|
+
end
|
14
|
+
|
15
|
+
def image
|
16
|
+
@image ||= Magick::ImageList.new(path)
|
17
|
+
end
|
18
|
+
|
19
|
+
def path
|
20
|
+
return @path if defined?(@path)
|
21
|
+
path_format_in_a_string = %Q{"#{path_format}"}
|
22
|
+
@path = Pow(eval(path_format_in_a_string)).to_s
|
23
|
+
end
|
24
|
+
|
25
|
+
def save
|
26
|
+
Pow(path).create "w" do |f|
|
27
|
+
f.write file.read
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
def save_wallpaper
|
32
|
+
Pow(wallpaper_path).parent.create
|
33
|
+
wallpaper.write(wallpaper_path)
|
34
|
+
end
|
35
|
+
|
36
|
+
def wallpaper
|
37
|
+
scale = wallpaper_scale
|
38
|
+
resized_image = image.resize(scale * image.columns, scale * image.rows)
|
39
|
+
|
40
|
+
background_color = wallpaper_background_color
|
41
|
+
background = Magick::Image.new(wallpaper_width, wallpaper_height){
|
42
|
+
self.background_color = background_color
|
43
|
+
}
|
44
|
+
|
45
|
+
background.composite(resized_image,
|
46
|
+
(wallpaper_width - resized_image.columns)/2,
|
47
|
+
(wallpaper_height - resized_image.rows)/2,
|
48
|
+
Magick::OverCompositeOp)
|
49
|
+
end
|
50
|
+
|
51
|
+
def wallpaper_path
|
52
|
+
return @wallpaper_path if defined?(@wallpaper_path)
|
53
|
+
wallpaper_path_format_in_a_string = %Q{"#{wallpaper_path_format}"}
|
54
|
+
@wallpaper_path = Pow(eval(wallpaper_path_format_in_a_string)).to_s
|
55
|
+
end
|
56
|
+
|
57
|
+
def wallpaper_scale
|
58
|
+
[wallpaper_height.to_f/image.rows, wallpaper_width.to_f/image.columns, 1].min
|
59
|
+
end
|
60
|
+
|
61
|
+
private
|
62
|
+
|
63
|
+
def day
|
64
|
+
time.strftime('%d')
|
65
|
+
end
|
66
|
+
|
67
|
+
def hour
|
68
|
+
time.strftime('%H')
|
69
|
+
end
|
70
|
+
|
71
|
+
def month
|
72
|
+
time.strftime('%m')
|
73
|
+
end
|
74
|
+
|
75
|
+
def name
|
76
|
+
Pow(url).name
|
77
|
+
end
|
78
|
+
|
79
|
+
def time
|
80
|
+
Time.now
|
81
|
+
end
|
82
|
+
|
83
|
+
def year
|
84
|
+
time.strftime('%Y')
|
85
|
+
end
|
86
|
+
end
|
87
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module NgpodScraper
|
2
|
+
class PhotoPage
|
3
|
+
attr_reader :config, :url
|
4
|
+
|
5
|
+
def initialize(url, config = {})
|
6
|
+
@url = url
|
7
|
+
@config = config
|
8
|
+
end
|
9
|
+
|
10
|
+
def photo
|
11
|
+
url = photo_url
|
12
|
+
attributes = (config[:photo] || {}).merge(:url => url, :file => open(photo_url))
|
13
|
+
return Photo.new(attributes)
|
14
|
+
end
|
15
|
+
|
16
|
+
def photo_url
|
17
|
+
page = Nokogiri::HTML(open(url))
|
18
|
+
begin
|
19
|
+
page.search(".primary_photo img").attr('src').value
|
20
|
+
rescue Exception => e
|
21
|
+
raise MissingPhotoUrl, "Cannot find the photo url: #{e.message}"
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,12 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'open-uri'
|
3
|
+
require 'pow'
|
4
|
+
require 'RMagick'
|
5
|
+
require 'valuable'
|
6
|
+
require 'yaml'
|
7
|
+
|
8
|
+
require "ngpod_scraper/version"
|
9
|
+
require 'ngpod_scraper/ngpod_scraper'
|
10
|
+
require 'ngpod_scraper/client'
|
11
|
+
require 'ngpod_scraper/photo'
|
12
|
+
require 'ngpod_scraper/photo_page'
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "ngpod_scraper/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "ngpod_scraper"
|
7
|
+
s.version = NgpodScraper::VERSION
|
8
|
+
s.authors = ["George Mendoza"]
|
9
|
+
s.email = ["gsmendoza@gmail.com"]
|
10
|
+
s.homepage = "http://github.com/gsmendoza/ngpod_scraper"
|
11
|
+
s.summary = %q{National Geographic Photo of the Day Screen Scraper}
|
12
|
+
s.description = %q{A tool for scraping National Geographic's Photo of the Day}
|
13
|
+
|
14
|
+
s.rubyforge_project = "ngpod_scraper"
|
15
|
+
|
16
|
+
s.files = `git ls-files`.split("\n")
|
17
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
18
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
19
|
+
s.require_paths = ["lib"]
|
20
|
+
|
21
|
+
# specify any dependencies here; for example:
|
22
|
+
s.add_development_dependency "fakeweb", "~> 1.2.8"
|
23
|
+
s.add_development_dependency "rspec", "~> 1.3.0"
|
24
|
+
|
25
|
+
s.add_runtime_dependency "nokogiri", ">= 1.4.2"
|
26
|
+
s.add_runtime_dependency "pow", ">= 0.2.3"
|
27
|
+
s.add_runtime_dependency "rmagick", ">= 2.13.1"
|
28
|
+
s.add_runtime_dependency "valuable", ">= 0.8.2"
|
29
|
+
end
|
@@ -0,0 +1,8 @@
|
|
1
|
+
url: http://photography.nationalgeographic.com/photography/photo-of-the-day
|
2
|
+
show_logs: false
|
3
|
+
photo:
|
4
|
+
path_format: 'tmp/#{year}-#{month}/#{name}'
|
5
|
+
wallpaper_path_format: 'tmp/photo-of-the-day.jpg'
|
6
|
+
wallpaper_width: 1280
|
7
|
+
wallpaper_height: 800
|
8
|
+
wallpaper_background_color: black
|