makasi 0.1.6 → 0.1.8
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 +4 -4
- data/Gemfile.lock +6 -6
- data/lib/makasi/search_index.rb +13 -10
- data/lib/makasi/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: ba3ee3d8a76ad5be96cc44382b12e1ca9f50dbfa
|
|
4
|
+
data.tar.gz: a89d9a578714529867a900eea92dac758ecf49c9
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 44029a653a50c6f7af3799787be1b955af98289f5d4844b6165f33c714502004ee2e06a96a837040029a9cbbe9891b292467c4f936f3cc4ad944b89ecd6f6a05
|
|
7
|
+
data.tar.gz: 3bba581a0a3a9a91f2ed0963d8ac24631f3066f8c6bda468285375ef3770f1264d85e3803a886fa550cf7f7bca37c2409fb553988f7fdc20afca0f4fbd6df160
|
data/Gemfile.lock
CHANGED
|
@@ -1,23 +1,23 @@
|
|
|
1
1
|
PATH
|
|
2
2
|
remote: .
|
|
3
3
|
specs:
|
|
4
|
-
makasi (0.1.
|
|
5
|
-
asari
|
|
4
|
+
makasi (0.1.8)
|
|
5
|
+
asari (= 0.10.4)
|
|
6
6
|
sitemap_generator
|
|
7
7
|
|
|
8
8
|
GEM
|
|
9
9
|
remote: https://rubygems.org/
|
|
10
10
|
specs:
|
|
11
|
-
asari (0.
|
|
11
|
+
asari (0.10.4)
|
|
12
12
|
httparty
|
|
13
13
|
builder (3.2.2)
|
|
14
|
-
httparty (0.13.
|
|
14
|
+
httparty (0.13.7)
|
|
15
15
|
json (~> 1.8)
|
|
16
16
|
multi_xml (>= 0.5.2)
|
|
17
17
|
json (1.8.3)
|
|
18
18
|
multi_xml (0.5.5)
|
|
19
19
|
rake (10.4.2)
|
|
20
|
-
sitemap_generator (5.0
|
|
20
|
+
sitemap_generator (5.1.0)
|
|
21
21
|
builder
|
|
22
22
|
|
|
23
23
|
PLATFORMS
|
|
@@ -29,4 +29,4 @@ DEPENDENCIES
|
|
|
29
29
|
rake (~> 10.0)
|
|
30
30
|
|
|
31
31
|
BUNDLED WITH
|
|
32
|
-
1.10.
|
|
32
|
+
1.10.6
|
data/lib/makasi/search_index.rb
CHANGED
|
@@ -5,7 +5,7 @@ module Makasi
|
|
|
5
5
|
|
|
6
6
|
def reindex
|
|
7
7
|
sync_db_with_sitemap
|
|
8
|
-
|
|
8
|
+
puts "End Sync, starting parse and uploading pages"
|
|
9
9
|
CloudSearchDocument.desc(:reindexed_at).each do |cloudsearch_doc|
|
|
10
10
|
html_content = load_page(cloudsearch_doc.url)
|
|
11
11
|
html_doc = Nokogiri::HTML(html_content)
|
|
@@ -23,7 +23,7 @@ module Makasi
|
|
|
23
23
|
"\n\tRESOURCE_ID: " + meta_tag_for(html_doc, "resource_id") +
|
|
24
24
|
"\n"
|
|
25
25
|
end
|
|
26
|
-
|
|
26
|
+
puts cloudsearch_doc.url
|
|
27
27
|
add_item_to_cloudsearch(cloudsearch_doc, html_doc)
|
|
28
28
|
|
|
29
29
|
cloudsearch_doc.update_attributes(reindexed_at: DateTime.now)
|
|
@@ -68,15 +68,18 @@ module Makasi
|
|
|
68
68
|
return ""
|
|
69
69
|
end
|
|
70
70
|
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
71
|
+
url += "/" unless url.ends_with?("/")
|
|
72
|
+
if url.start_with?('https') then
|
|
73
|
+
parsed_url = URI.parse(url)
|
|
74
|
+
http = Net::HTTP.new(parsed_url.host, parsed_url.port)
|
|
75
|
+
http.use_ssl = true
|
|
76
|
+
request = Net::HTTP::Get.new(url)
|
|
77
|
+
response = http.start { |http| http.request(request) }
|
|
78
|
+
else
|
|
79
|
+
parsed_url = URI.parse(url)
|
|
80
|
+
request = Net::HTTP::Get.new(url)
|
|
81
|
+
response = Net::HTTP.start(parsed_url.host, parsed_url.port) { |http| http.request(request) }
|
|
75
82
|
end
|
|
76
|
-
|
|
77
|
-
parsed_url = URI.parse(url)
|
|
78
|
-
request = Net::HTTP::Get.new(url)
|
|
79
|
-
response = Net::HTTP.start(parsed_url.host, parsed_url.port) { |http| http.request(request) }
|
|
80
83
|
case response
|
|
81
84
|
when Net::HTTPSuccess then response.body
|
|
82
85
|
when Net::HTTPRedirection then load_page(response['location'], limit - 1)
|
data/lib/makasi/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: makasi
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.8
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Nataliia Kumeiko
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2015-
|
|
11
|
+
date: 2015-11-04 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|