indexable 0.1.0 → 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.
- checksums.yaml +4 -4
- data/lib/indexable/indexable.rb +53 -0
- 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: 0a6d2c79c0eb8d268fba3a60b0300c8ac464f32b
|
4
|
+
data.tar.gz: 795a31d66d9acfe8cc83e9dcf43d269886ae5833
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5bf720013d32fff089bdd6cece00eccc345592eb6def5c5d31670c7eb29af7d7398e8a1c51f898ee2427ccb1f2091bdd629938a006a2ac816a36a40b9dbd67f0
|
7
|
+
data.tar.gz: c76f9a4f1065c82c01a93d7c80c8ce8a71caf283b4f844d3b50b42d6041304c4bc8e1dd7358df0199cda77e98adaebf80837d4dbc59154c486365ef7accb1b3d
|
@@ -0,0 +1,53 @@
|
|
1
|
+
require 'rack/request'
|
2
|
+
require 'indexable/phantomjs'
|
3
|
+
|
4
|
+
module Indexable
|
5
|
+
class Middleware
|
6
|
+
CRAWLER_USER_AGENTS = [
|
7
|
+
/^Twitterbot/, /^curl/, /Googlebot/, /Mediapartners/, /Adsbot-Google/,
|
8
|
+
/\(.*http(s|\(s\))?:\/\/.*\)/
|
9
|
+
]
|
10
|
+
|
11
|
+
def initialize(app)
|
12
|
+
@app = app
|
13
|
+
end
|
14
|
+
|
15
|
+
# Detect whether the current request comes from a bot. Based on the logic used
|
16
|
+
# by Bustle.com (https://www.dropbox.com/s/s4oibqsxqpo3hll/bustle%20slizzle.pdf)
|
17
|
+
def request_from_crawler?(env)
|
18
|
+
user_agent = env["HTTP_USER_AGENT"]
|
19
|
+
params = Rack::Request.new(env).params
|
20
|
+
return false unless user_agent
|
21
|
+
return true if CRAWLER_USER_AGENTS.any? {|s| user_agent.match(s) }
|
22
|
+
return true if params.has_key?('_escaped_fragment_')
|
23
|
+
params['nojs'].eql?('true')
|
24
|
+
end
|
25
|
+
|
26
|
+
def call(env)
|
27
|
+
status, headers, content = *@app.call(env)
|
28
|
+
|
29
|
+
if status == 200 and headers['Content-Type'].match(/^text\/html/) and request_from_crawler?(env)
|
30
|
+
script = ::File.dirname(__FILE__) + "/render_page.js"
|
31
|
+
file = Tempfile.new(['indexable', '.html'])
|
32
|
+
|
33
|
+
if content.respond_to? :body
|
34
|
+
html = content.body
|
35
|
+
else
|
36
|
+
html = content.join('')
|
37
|
+
end
|
38
|
+
|
39
|
+
file.write html
|
40
|
+
file.close
|
41
|
+
begin
|
42
|
+
url = Rack::Request.new(env).url
|
43
|
+
content = [Phantomjs.new(script, file.path, url).run]
|
44
|
+
status = 500 if content[0] == "Couldn't render page... orz."
|
45
|
+
ensure
|
46
|
+
file.unlink
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
[status, headers, content]
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: indexable
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Vikhyat Korrapati
|
@@ -31,6 +31,7 @@ extensions: []
|
|
31
31
|
extra_rdoc_files: []
|
32
32
|
files:
|
33
33
|
- lib/indexable.rb
|
34
|
+
- lib/indexable/indexable.rb
|
34
35
|
- lib/indexable/render_page.js
|
35
36
|
- lib/indexable/phantomjs.rb
|
36
37
|
- lib/indexable/railtie.rb
|