image_scraper 0.1.1 → 0.1.2
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/VERSION +1 -1
- data/image_scraper.gemspec +2 -2
- data/lib/image_scraper.rb +0 -1
- data/lib/image_scraper/client.rb +4 -2
- data/lib/image_scraper/util.rb +4 -0
- data/test/test_image_scraper.rb +13 -0
- metadata +4 -4
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.1.
|
1
|
+
0.1.2
|
data/image_scraper.gemspec
CHANGED
@@ -5,11 +5,11 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{image_scraper}
|
8
|
-
s.version = "0.1.
|
8
|
+
s.version = "0.1.2"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["John McAliley"]
|
12
|
-
s.date = %q{2011-06-
|
12
|
+
s.date = %q{2011-06-03}
|
13
13
|
s.description = %q{Simple utility to pull image urls from web page}
|
14
14
|
s.email = %q{john.mcaliley@gmail.com}
|
15
15
|
s.extra_rdoc_files = [
|
data/lib/image_scraper.rb
CHANGED
data/lib/image_scraper/client.rb
CHANGED
@@ -34,10 +34,12 @@ module ImageScraper
|
|
34
34
|
css = file.string rescue IO.read(file)
|
35
35
|
|
36
36
|
images += css.scan(/url\((.*?)\)/).collect do |image_url|
|
37
|
+
image_url = image_url[0]
|
37
38
|
if image_url.include?("data:image") and @include_css_data_images
|
38
|
-
image_url
|
39
|
+
image_url
|
39
40
|
else
|
40
|
-
|
41
|
+
image_url = ImageScraper::Util.strip_quotes(image_url)
|
42
|
+
@convert_to_absolute_url ? ImageScraper::Util.absolute_url(url,image_url) : image_url
|
41
43
|
end
|
42
44
|
end
|
43
45
|
end
|
data/lib/image_scraper/util.rb
CHANGED
data/test/test_image_scraper.rb
CHANGED
@@ -44,4 +44,17 @@ class TestImageScraper < Test::Unit::TestCase
|
|
44
44
|
scraper = ImageScraper::Client.new("http://local.couponshack.com")
|
45
45
|
assert scraper.stylesheet_images.include? ("http://local.couponshack.com/images/bg.png")
|
46
46
|
end
|
47
|
+
|
48
|
+
should "strip quotes from a url" do
|
49
|
+
assert_equal "/images/test.png", ImageScraper::Util.strip_quotes("'/images/test.png'")
|
50
|
+
assert_equal "http://www.somsite.com/images/test.png", ImageScraper::Util.strip_quotes("'http://www.somsite.com/images/test.png'")
|
51
|
+
assert_equal "/images/test.png", ImageScraper::Util.strip_quotes('"/images/test.png"')
|
52
|
+
end
|
53
|
+
|
54
|
+
should "return domain section from a url" do
|
55
|
+
assert_equal "http://ug.ly", ImageScraper::Util.domain("http://ug.ly/what/is/this.html")
|
56
|
+
assert_equal "http://ug.ly", ImageScraper::Util.domain("http://ug.ly/what/is/this/")
|
57
|
+
assert_equal "http://ug.ly", ImageScraper::Util.domain("http://ug.ly/what")
|
58
|
+
assert_equal "http://www.ug.ly", ImageScraper::Util.domain("http://www.ug.ly/what/is/this/")
|
59
|
+
end
|
47
60
|
end
|
metadata
CHANGED
@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
|
|
5
5
|
segments:
|
6
6
|
- 0
|
7
7
|
- 1
|
8
|
-
-
|
9
|
-
version: 0.1.
|
8
|
+
- 2
|
9
|
+
version: 0.1.2
|
10
10
|
platform: ruby
|
11
11
|
authors:
|
12
12
|
- John McAliley
|
@@ -14,7 +14,7 @@ autorequire:
|
|
14
14
|
bindir: bin
|
15
15
|
cert_chain: []
|
16
16
|
|
17
|
-
date: 2011-06-
|
17
|
+
date: 2011-06-03 00:00:00 -04:00
|
18
18
|
default_executable:
|
19
19
|
dependencies:
|
20
20
|
- !ruby/object:Gem::Dependency
|
@@ -175,7 +175,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
175
175
|
requirements:
|
176
176
|
- - ">="
|
177
177
|
- !ruby/object:Gem::Version
|
178
|
-
hash:
|
178
|
+
hash: -738762267344225369
|
179
179
|
segments:
|
180
180
|
- 0
|
181
181
|
version: "0"
|