crawl 1.1.3 → 1.1.4
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/.gitignore +2 -0
- data/.rspec +2 -0
- data/Gemfile +9 -0
- data/README.md +3 -0
- data/circle.yml +3 -0
- data/lib/crawl/page.rb +6 -2
- data/lib/crawl/version.rb +1 -1
- data/spec/lib/crawl/page_spec.rb +0 -0
- data/spec/page_spec.rb +11 -0
- data/spec/spec_helper.rb +17 -0
- metadata +12 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 103da22dba2987ec6ec5bbf700473cb243170fc5
|
4
|
+
data.tar.gz: 8197231448106e4fe0b198b53e734110eb1748a9
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 206ff34e285a074b7dad8ebb68453295df14d67b95b3a4755d823a0d4bd2a3bae92859ff02fe52dee6b134c02966c7f4d9c61e52e1938c3815d56fc7debf7387
|
7
|
+
data.tar.gz: 2f8f655862a28cd4772317866b72ca31c392c7c63997226bac8c2ceccfe15fca203501189a4a0b9db0ebe002555fc9932265a016cd63c247b85b355398434592
|
data/.gitignore
CHANGED
data/.rspec
ADDED
data/Gemfile
CHANGED
data/README.md
CHANGED
@@ -1,5 +1,8 @@
|
|
1
1
|
# Crawl
|
2
2
|
|
3
|
+
[](https://circleci.com/gh/alphasights/crawl/tree/master)
|
4
|
+
|
5
|
+
|
3
6
|
Crawl pages within a domain, reporting any page that returns a bad response code
|
4
7
|
|
5
8
|
Usage:
|
data/circle.yml
ADDED
data/lib/crawl/page.rb
CHANGED
@@ -17,10 +17,14 @@ class Page
|
|
17
17
|
if url.start_with?('/')
|
18
18
|
url
|
19
19
|
else
|
20
|
-
"#{
|
20
|
+
"#{source_directory}/#{url}"
|
21
21
|
end
|
22
22
|
end
|
23
23
|
|
24
|
+
def source_directory
|
25
|
+
File.split(source).first.sub(/^\./, '').sub(/\/$/, '')
|
26
|
+
end
|
27
|
+
|
24
28
|
def <=>(other)
|
25
29
|
url <=> other.url
|
26
30
|
end
|
@@ -58,4 +62,4 @@ class Page
|
|
58
62
|
def to_s
|
59
63
|
"#{url} found on #{source} - #{error || 'OK'}"
|
60
64
|
end
|
61
|
-
end
|
65
|
+
end
|
data/lib/crawl/version.rb
CHANGED
File without changes
|
data/spec/page_spec.rb
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
require './lib/crawl/page'
|
2
|
+
|
3
|
+
RSpec.describe Page do
|
4
|
+
describe "#relative_url" do
|
5
|
+
specify { expect(Page.new(:register, "/", "/").relative_url).to eq "/" }
|
6
|
+
specify { expect(Page.new(:register, "page.html", "").relative_url).to eq "/page.html" }
|
7
|
+
specify { expect(Page.new(:register, "/interview", "/").relative_url).to eq "/interview" }
|
8
|
+
specify { expect(Page.new(:register, "overview.html", "/").relative_url).to eq "/overview.html" }
|
9
|
+
specify { expect(Page.new(:register, "post-5.html", "/posts/index.html").relative_url).to eq "/posts/post-5.html" }
|
10
|
+
end
|
11
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
RSpec.configure do |config|
|
2
|
+
config.expect_with :rspec do |expectations|
|
3
|
+
expectations.include_chain_clauses_in_custom_matcher_descriptions = true
|
4
|
+
end
|
5
|
+
|
6
|
+
if config.files_to_run.one?
|
7
|
+
config.default_formatter = 'doc'
|
8
|
+
end
|
9
|
+
|
10
|
+
config.shared_context_metadata_behavior = :apply_to_host_groups
|
11
|
+
config.filter_run_when_matching :focus
|
12
|
+
config.example_status_persistence_file_path = "spec/examples.txt"
|
13
|
+
config.disable_monkey_patching!
|
14
|
+
config.warnings = true
|
15
|
+
config.order = :random
|
16
|
+
Kernel.srand config.seed
|
17
|
+
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crawl
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.1.
|
4
|
+
version: 1.1.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Tor Erik Linnerud
|
@@ -10,7 +10,7 @@ authors:
|
|
10
10
|
autorequire:
|
11
11
|
bindir: bin
|
12
12
|
cert_chain: []
|
13
|
-
date:
|
13
|
+
date: 2016-09-07 00:00:00.000000000 Z
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
16
16
|
name: nokogiri
|
@@ -79,11 +79,13 @@ extensions: []
|
|
79
79
|
extra_rdoc_files: []
|
80
80
|
files:
|
81
81
|
- ".gitignore"
|
82
|
+
- ".rspec"
|
82
83
|
- Gemfile
|
83
84
|
- LICENSE.txt
|
84
85
|
- README.md
|
85
86
|
- Rakefile
|
86
87
|
- bin/crawl
|
88
|
+
- circle.yml
|
87
89
|
- crawl.gemspec
|
88
90
|
- lib/crawl.rb
|
89
91
|
- lib/crawl/engine.rb
|
@@ -92,6 +94,9 @@ files:
|
|
92
94
|
- lib/crawl/register.rb
|
93
95
|
- lib/crawl/string.rb
|
94
96
|
- lib/crawl/version.rb
|
97
|
+
- spec/lib/crawl/page_spec.rb
|
98
|
+
- spec/page_spec.rb
|
99
|
+
- spec/spec_helper.rb
|
95
100
|
homepage: http://github.com/alphasights/crawl
|
96
101
|
licenses:
|
97
102
|
- MIT
|
@@ -112,10 +117,12 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
112
117
|
version: '0'
|
113
118
|
requirements: []
|
114
119
|
rubyforge_project:
|
115
|
-
rubygems_version: 2.
|
120
|
+
rubygems_version: 2.5.1
|
116
121
|
signing_key:
|
117
122
|
specification_version: 4
|
118
123
|
summary: Crawl pages witin a domain, reporting any page that returns a bad response
|
119
124
|
code
|
120
|
-
test_files:
|
121
|
-
|
125
|
+
test_files:
|
126
|
+
- spec/lib/crawl/page_spec.rb
|
127
|
+
- spec/page_spec.rb
|
128
|
+
- spec/spec_helper.rb
|