crawl 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- data/README +8 -0
- data/lib/crawl/engine.rb +1 -1
- data/lib/crawl/version.rb +1 -1
- metadata +9 -8
data/README
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
1
|
+
Crawl pages witin a domain, reporting any page that returns a bad response code
|
|
2
|
+
Usage: crawl [options] domain
|
|
3
|
+
-s, --start /home,/about Starting path(s), defaults to /
|
|
4
|
+
-u, --username username Basic auth username
|
|
5
|
+
-p, --password password Basic auth password
|
|
6
|
+
-c, --ci Output files for CI integration
|
|
7
|
+
-v, --verbose Give details when crawling
|
|
8
|
+
-h, --help Show this message
|
data/lib/crawl/engine.rb
CHANGED
|
@@ -132,7 +132,7 @@ private
|
|
|
132
132
|
test_suite.finish
|
|
133
133
|
@report_manager.write_report(test_suite) if options[:ci]
|
|
134
134
|
return response
|
|
135
|
-
rescue RestClient::InternalServerError => e
|
|
135
|
+
rescue RestClient::InternalServerError, RestClient::ResourceNotFound => e
|
|
136
136
|
@errors << Result.new(link, "Error whilst retrieving page: #{e.message}")
|
|
137
137
|
@invalid_links << link
|
|
138
138
|
return nil
|
data/lib/crawl/version.rb
CHANGED
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: 0.0.
|
|
4
|
+
version: 0.0.4
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,11 +9,11 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2011-11-
|
|
12
|
+
date: 2011-11-10 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: nokogiri
|
|
16
|
-
requirement: &
|
|
16
|
+
requirement: &70243809291280 !ruby/object:Gem::Requirement
|
|
17
17
|
none: false
|
|
18
18
|
requirements:
|
|
19
19
|
- - ! '>='
|
|
@@ -21,10 +21,10 @@ dependencies:
|
|
|
21
21
|
version: '0'
|
|
22
22
|
type: :runtime
|
|
23
23
|
prerelease: false
|
|
24
|
-
version_requirements: *
|
|
24
|
+
version_requirements: *70243809291280
|
|
25
25
|
- !ruby/object:Gem::Dependency
|
|
26
26
|
name: rest-client
|
|
27
|
-
requirement: &
|
|
27
|
+
requirement: &70243809290740 !ruby/object:Gem::Requirement
|
|
28
28
|
none: false
|
|
29
29
|
requirements:
|
|
30
30
|
- - ! '>='
|
|
@@ -32,10 +32,10 @@ dependencies:
|
|
|
32
32
|
version: '0'
|
|
33
33
|
type: :runtime
|
|
34
34
|
prerelease: false
|
|
35
|
-
version_requirements: *
|
|
35
|
+
version_requirements: *70243809290740
|
|
36
36
|
- !ruby/object:Gem::Dependency
|
|
37
37
|
name: ci_reporter
|
|
38
|
-
requirement: &
|
|
38
|
+
requirement: &70243809290140 !ruby/object:Gem::Requirement
|
|
39
39
|
none: false
|
|
40
40
|
requirements:
|
|
41
41
|
- - ! '>='
|
|
@@ -43,7 +43,7 @@ dependencies:
|
|
|
43
43
|
version: '0'
|
|
44
44
|
type: :runtime
|
|
45
45
|
prerelease: false
|
|
46
|
-
version_requirements: *
|
|
46
|
+
version_requirements: *70243809290140
|
|
47
47
|
description: Crawl all pages on a domain, checking for errors
|
|
48
48
|
email:
|
|
49
49
|
- tor@alphasights.com
|
|
@@ -54,6 +54,7 @@ extra_rdoc_files: []
|
|
|
54
54
|
files:
|
|
55
55
|
- .gitignore
|
|
56
56
|
- Gemfile
|
|
57
|
+
- README
|
|
57
58
|
- Rakefile
|
|
58
59
|
- bin/crawl
|
|
59
60
|
- crawl.gemspec
|