url_scrubber 0.8.7 → 0.8.8
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 +8 -8
- data/lib/url_scrubber/version.rb +1 -1
- data/lib/url_scrubber.rb +7 -0
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,15 +1,15 @@
|
|
|
1
1
|
---
|
|
2
2
|
!binary "U0hBMQ==":
|
|
3
3
|
metadata.gz: !binary |-
|
|
4
|
-
|
|
4
|
+
OTg0Y2U4MGIxODA2ODYyNDYzMDUyMGZjYmY4MWYwNTlmNGI3YjI3Mg==
|
|
5
5
|
data.tar.gz: !binary |-
|
|
6
|
-
|
|
6
|
+
NTM3YWVhMzFkMDc0ZDI0NTdlYjQyZmIyYmEwYWU5ZDI5YzQ3ZWY5Nw==
|
|
7
7
|
SHA512:
|
|
8
8
|
metadata.gz: !binary |-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
9
|
+
NDVmZDhjYjllZTNkOWIyNjIyMTIxMWIyYjAyZjAzM2M4NTRlMTA1MDczM2M0
|
|
10
|
+
MjJkMjJiOTYyZmNkNmMxODE2YmIxYjVkYmFmY2QwZDgxZjgyNGMwZGVhNjRi
|
|
11
|
+
NzdkNGM3YmFmZjFhOTFjNTI0YjZiMjlmNTc4YzcxOWZjZmI3YTI=
|
|
12
12
|
data.tar.gz: !binary |-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
13
|
+
YjczOTUwYjQyNzI3MDVjOTQxNTVmMjhlMTkyZjNjNjQzYzgwOTMxYTA2YzBk
|
|
14
|
+
MzY1ODgzYjE1ZDFmYmNhNWQ2OWNlODhhNDc4ZDIyMDI4MTA5NTdkYjRiM2Q1
|
|
15
|
+
MGRkZjA3MGY1ZmU0MDdiNjk1MDM2YWQxNTIwMWJjZDcxN2YxZDc=
|
data/lib/url_scrubber/version.rb
CHANGED
data/lib/url_scrubber.rb
CHANGED
|
@@ -7,6 +7,7 @@ USER_AGENT = 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-us) AppleWebK
|
|
|
7
7
|
module UrlScrubber
|
|
8
8
|
|
|
9
9
|
def self.scrub(url)
|
|
10
|
+
return url if url.blank?
|
|
10
11
|
url = url.clone # don't modify the original argument
|
|
11
12
|
|
|
12
13
|
m = url.match(/(htt?ps?:\/\/\S*)/i)
|
|
@@ -285,6 +286,12 @@ module UrlScrubber
|
|
|
285
286
|
regex3 = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/(?<uname>[^\?\/]*))($|\/$|\/(about|timeline|info|app_.*)?)/i
|
|
286
287
|
regex4 = /^(?<url>(https?:\/\/)((www|business)\.)?facebook\.com\/)(?<php>home.php\?([#!]+\/)*)(?<uname>.*)/i
|
|
287
288
|
|
|
289
|
+
# If the user gives us a path to a Post, "http://facebook.com/LoansByJanet/posts/1691075027771418"
|
|
290
|
+
# then drop the post part, "/posts/1691075027771418" to get the base url, "http://facebook.com/LoansByJanet/"
|
|
291
|
+
if mdata = /^(?<base_url>.+)\/posts\/(?<postid>[0-9]+).*$/.match(url)
|
|
292
|
+
url = mdata[:base_url]
|
|
293
|
+
end
|
|
294
|
+
|
|
288
295
|
if url.match("/media/albums") || url.match("/media/set")
|
|
289
296
|
# puts "media"
|
|
290
297
|
url = url.match('\&') ? url.split('&',2)[0] : url
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: url_scrubber
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.8.
|
|
4
|
+
version: 0.8.8
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Colin Langton
|
|
@@ -11,7 +11,7 @@ authors:
|
|
|
11
11
|
autorequire:
|
|
12
12
|
bindir: bin
|
|
13
13
|
cert_chain: []
|
|
14
|
-
date:
|
|
14
|
+
date: 2017-09-13 00:00:00.000000000 Z
|
|
15
15
|
dependencies:
|
|
16
16
|
- !ruby/object:Gem::Dependency
|
|
17
17
|
name: rspec
|