mechanizer 1.11 → 1.12
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/README.md +10 -10
- data/Rakefile +3 -3
- data/lib/mechanizer/noko.rb +4 -4
- data/lib/mechanizer/version.rb +1 -1
- data/mechanizer.gemspec +1 -1
- metadata +3 -3
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: bf5e0126c5a9c8e0dbf5eeb4a99e2c0f241ce95348abbdd0b70ce646aefe8063
|
|
4
|
+
data.tar.gz: 1fdd68e34f4abec9a7f97eb1fd1b71b74bdee20c4915c0157ca013110e67dc94
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 5848e452bd1054800b47265699979c87d6dd44300d9f4614dd9f4181933365149e9e6e05906ba19f044db155098e600a81d7842b4996a1d2722da2d32bc271c5
|
|
7
|
+
data.tar.gz: 8061245ddedef9f9cc718808a541797f271ae45f12d944e86792e12f9c5cf97306cbfaa1d87f97d5c5f194ccdaa306854528a7dfb77cb138e14e6edc82a21a31
|
data/README.md
CHANGED
|
@@ -58,20 +58,20 @@ noko_hash = noko.scrape(args)
|
|
|
58
58
|
```
|
|
59
59
|
err_msg = noko_hash[:err_msg]
|
|
60
60
|
page = noko_hash[:page]
|
|
61
|
-
|
|
61
|
+
texts_and_paths = noko_hash[:texts_and_paths]
|
|
62
62
|
```
|
|
63
63
|
|
|
64
|
-
### 4. Example Texts &
|
|
64
|
+
### 4. Example Texts & paths:
|
|
65
65
|
|
|
66
66
|
```
|
|
67
|
-
|
|
68
|
-
{:text=>"english 5 675 000+ articles", :
|
|
69
|
-
{:text=>"日本語 1 111 000+ 記事", :
|
|
70
|
-
{:text=>"español 1 427 000+ artículos", :
|
|
71
|
-
{:text=>"deutsch 2 195 000+ artikel", :
|
|
72
|
-
{:text=>"русский 1 481 000+ статей", :
|
|
73
|
-
{:text=>"français 1 997 000+ articles", :
|
|
74
|
-
{:text=>"italiano 1 446 000+ voci", :
|
|
67
|
+
texts_and_paths = [
|
|
68
|
+
{:text=>"english 5 675 000+ articles", :path=>"//en.wikipedia.org/"},
|
|
69
|
+
{:text=>"日本語 1 111 000+ 記事", :path=>"//ja.wikipedia.org/"},
|
|
70
|
+
{:text=>"español 1 427 000+ artículos", :path=>"//es.wikipedia.org/"},
|
|
71
|
+
{:text=>"deutsch 2 195 000+ artikel", :path=>"//de.wikipedia.org/"},
|
|
72
|
+
{:text=>"русский 1 481 000+ статей", :path=>"//ru.wikipedia.org/"},
|
|
73
|
+
{:text=>"français 1 997 000+ articles", :path=>"//fr.wikipedia.org/"},
|
|
74
|
+
{:text=>"italiano 1 446 000+ voci", :path=>"//it.wikipedia.org/"}
|
|
75
75
|
]
|
|
76
76
|
```
|
|
77
77
|
|
data/Rakefile
CHANGED
|
@@ -16,8 +16,8 @@ task :console do
|
|
|
16
16
|
require "active_support/all"
|
|
17
17
|
ARGV.clear
|
|
18
18
|
|
|
19
|
-
noko_page_hash = run_mechanizer
|
|
20
|
-
binding.pry
|
|
19
|
+
# noko_page_hash = run_mechanizer
|
|
20
|
+
# binding.pry
|
|
21
21
|
|
|
22
22
|
IRB.start
|
|
23
23
|
end
|
|
@@ -31,7 +31,7 @@ def run_mechanizer
|
|
|
31
31
|
|
|
32
32
|
err_msg = noko_hash[:err_msg]
|
|
33
33
|
page = noko_hash[:page]
|
|
34
|
-
|
|
34
|
+
texts_and_paths = noko_hash[:texts_and_paths]
|
|
35
35
|
|
|
36
36
|
other_projects = page.css('.other-project')&.text
|
|
37
37
|
other_projects = other_projects.split("\n").reject(&:blank?)
|
data/lib/mechanizer/noko.rb
CHANGED
|
@@ -18,7 +18,7 @@ module Mechanizer
|
|
|
18
18
|
def scrape(args)
|
|
19
19
|
@timeout = args.fetch(:timeout, 60)
|
|
20
20
|
url = args.fetch(:url)
|
|
21
|
-
noko_hash = { url: url, err_msg: nil,
|
|
21
|
+
noko_hash = { url: url, err_msg: nil, texts_and_paths: {}, page: nil }
|
|
22
22
|
noko_hash = start_noko(noko_hash)
|
|
23
23
|
noko_hash = extract_links(noko_hash)
|
|
24
24
|
noko_hash
|
|
@@ -27,10 +27,10 @@ module Mechanizer
|
|
|
27
27
|
def extract_links(noko_hash)
|
|
28
28
|
links = noko_hash[:page]&.links
|
|
29
29
|
unless noko_hash[:err_msg].present? || !links.present?
|
|
30
|
-
noko_hash[:
|
|
30
|
+
noko_hash[:texts_and_paths] = links.map do |link|
|
|
31
31
|
text = link.text&.downcase&.gsub(/\s+/, ' ')&.strip
|
|
32
|
-
|
|
33
|
-
|
|
32
|
+
path = link&.href&.downcase&.strip
|
|
33
|
+
text_and_path = {text: text, path: path}
|
|
34
34
|
end
|
|
35
35
|
end
|
|
36
36
|
noko_hash
|
data/lib/mechanizer/version.rb
CHANGED
data/mechanizer.gemspec
CHANGED
|
@@ -33,7 +33,7 @@ Gem::Specification.new do |spec|
|
|
|
33
33
|
spec.required_ruby_version = '~> 2.5.1'
|
|
34
34
|
spec.add_dependency 'activesupport', '~> 5.2'
|
|
35
35
|
spec.add_dependency 'utf8_sanitizer', '~> 2.16'
|
|
36
|
-
spec.add_dependency 'crm_formatter', '~> 2.
|
|
36
|
+
spec.add_dependency 'crm_formatter', '~> 2.64'
|
|
37
37
|
spec.add_dependency 'mechanize', '~> 2.7', '>= 2.7.6'
|
|
38
38
|
|
|
39
39
|
# spec.add_dependency "activesupport-inflector", ['~> 0.1.0']
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: mechanizer
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: '1.
|
|
4
|
+
version: '1.12'
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Adam Booth
|
|
@@ -44,14 +44,14 @@ dependencies:
|
|
|
44
44
|
requirements:
|
|
45
45
|
- - "~>"
|
|
46
46
|
- !ruby/object:Gem::Version
|
|
47
|
-
version: '2.
|
|
47
|
+
version: '2.64'
|
|
48
48
|
type: :runtime
|
|
49
49
|
prerelease: false
|
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
|
51
51
|
requirements:
|
|
52
52
|
- - "~>"
|
|
53
53
|
- !ruby/object:Gem::Version
|
|
54
|
-
version: '2.
|
|
54
|
+
version: '2.64'
|
|
55
55
|
- !ruby/object:Gem::Dependency
|
|
56
56
|
name: mechanize
|
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|