true_url 0.0.3 → 0.0.4
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.
- checksums.yaml +4 -4
- data/lib/true_url/fetch.rb +38 -0
- data/lib/true_url/version.rb +1 -1
- metadata +2 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: fe4a8259bda1a0227d7c85cebd88661f208bd4ce
|
|
4
|
+
data.tar.gz: 14b26af3018b5d04472c06a0cbb6a925cf06332a
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: b6a37a1a3087e12d242949196983b3d65da44c76f7c82c17f7e1e3058c28cc398b0ed87dbd80a8d2ada9895c22490e04a8bef1d3aeae3be0031a950bf064cfe3
|
|
7
|
+
data.tar.gz: 6770fdfb57aff9f0a471986bc61e980c6a15400f0ec15b841c325f0def08202c24f6b00da25d9ceb7c21082a21587a11d2115fe9629bb65c96e6f40eb0f04653
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
require 'http'
|
|
2
|
+
require 'nokogiri'
|
|
3
|
+
|
|
4
|
+
class TrueURL
|
|
5
|
+
module Fetch
|
|
6
|
+
extend self
|
|
7
|
+
|
|
8
|
+
def execute(context)
|
|
9
|
+
starting_url = context.working_url
|
|
10
|
+
|
|
11
|
+
response = HTTP.follow
|
|
12
|
+
.get(starting_url)
|
|
13
|
+
|
|
14
|
+
canonical_url = find_canonical_header(response.headers) || find_canonical_url(response.to_s) || response.uri
|
|
15
|
+
context.set_working_url(canonical_url, starting_url)
|
|
16
|
+
end
|
|
17
|
+
|
|
18
|
+
def find_canonical_header(headers)
|
|
19
|
+
return if headers['Link'].nil?
|
|
20
|
+
|
|
21
|
+
links = headers['Link'].is_a?(String) ? [headers['Link']] : headers['Link']
|
|
22
|
+
links.each { |link| return link.split(/[<>;]/)[1] if link.end_with?('rel="canonical"') }
|
|
23
|
+
nil
|
|
24
|
+
end
|
|
25
|
+
|
|
26
|
+
def find_canonical_url(html)
|
|
27
|
+
doc = Nokogiri::HTML(html)
|
|
28
|
+
|
|
29
|
+
elem = doc.at('link[rel="canonical"]')
|
|
30
|
+
canonical_url = elem['href'] unless elem.nil?
|
|
31
|
+
|
|
32
|
+
elem = doc.at('meta[property="og:url"]')
|
|
33
|
+
og_url = elem['content'] unless elem.nil?
|
|
34
|
+
|
|
35
|
+
canonical_url || og_url
|
|
36
|
+
end
|
|
37
|
+
end
|
|
38
|
+
end
|
data/lib/true_url/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: true_url
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Jonathan Wong
|
|
@@ -116,6 +116,7 @@ files:
|
|
|
116
116
|
- Rakefile
|
|
117
117
|
- lib/true_url.rb
|
|
118
118
|
- lib/true_url/context.rb
|
|
119
|
+
- lib/true_url/fetch.rb
|
|
119
120
|
- lib/true_url/strategy.rb
|
|
120
121
|
- lib/true_url/strategy/dailymotion.rb
|
|
121
122
|
- lib/true_url/strategy/nicovideo.rb
|