deadfinder 1.1.2 → 1.2.1
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/lib/deadfinder/version.rb +1 -1
- data/lib/deadfinder.rb +26 -14
- metadata +32 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: cccf1eac41e7cb13f5391bd8191931b6225f3b16dd23a2e4432816d93730be2e
|
4
|
+
data.tar.gz: dddb0d51bc6b00507ae8622945114d373e7366714a74ebc4ede95057db1224f2
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d273d3d94cce7a98185dfda1713b43ddf632b19b11bff3f93c1c68bdbf3306c65825411b95f2b4ab3a517bfb88ca3db2f888a4b4a84814058a030b7c62098a0c
|
7
|
+
data.tar.gz: ca7d125f5c7a89275672418546e6913af1765bdc0eaaa8ce324be94c24e4b84989df9ec4fae371d6a4a7a160c97be47db2633b8de04be0eb98dfdc4ea2009978
|
data/lib/deadfinder/version.rb
CHANGED
data/lib/deadfinder.rb
CHANGED
@@ -10,10 +10,12 @@ require 'deadfinder/version'
|
|
10
10
|
require 'concurrent-edge'
|
11
11
|
require 'sitemap-parser'
|
12
12
|
require 'set'
|
13
|
+
require 'json'
|
13
14
|
|
14
15
|
Channel = Concurrent::Channel
|
15
16
|
CacheSet = Set.new
|
16
17
|
CacheQue = {}
|
18
|
+
Output = {}
|
17
19
|
|
18
20
|
class DeadFinderRunner
|
19
21
|
def run(target, options)
|
@@ -27,7 +29,7 @@ class DeadFinderRunner
|
|
27
29
|
link_link = nodeset_link.map { |element| element['href'] }.compact
|
28
30
|
|
29
31
|
link_merged = []
|
30
|
-
link_merged
|
32
|
+
link_merged.concat link_a, link_script, link_link
|
31
33
|
|
32
34
|
Logger.target target
|
33
35
|
Logger.sub_info "Found #{link_merged.length} point. [a:#{link_a.length}/s:#{link_script.length}/l:#{link_link.length}]"
|
@@ -36,7 +38,7 @@ class DeadFinderRunner
|
|
36
38
|
results = Channel.new(buffer: :buffered, capacity: 1000)
|
37
39
|
|
38
40
|
(1..options['concurrency']).each do |w|
|
39
|
-
Channel.go { worker(w, jobs, results, options) }
|
41
|
+
Channel.go { worker(w, jobs, results, target, options) }
|
40
42
|
end
|
41
43
|
|
42
44
|
link_a.uniq.each do |node|
|
@@ -51,24 +53,25 @@ class DeadFinderRunner
|
|
51
53
|
Logger.sub_done 'Done'
|
52
54
|
end
|
53
55
|
|
54
|
-
def worker(_id, jobs, results, options)
|
56
|
+
def worker(_id, jobs, results, target, options)
|
55
57
|
jobs.each do |j|
|
56
58
|
if !CacheSet.include? j
|
57
59
|
CacheSet.add j
|
58
60
|
begin
|
59
61
|
CacheQue[j] = true
|
60
|
-
URI.open(j, :
|
62
|
+
URI.open(j, read_timeout: options['timeout'])
|
61
63
|
rescue StandardError => e
|
62
|
-
|
63
|
-
|
64
|
+
if e.to_s.include? '404 Not Found'
|
65
|
+
Logger.found "[#{e}] #{j}"
|
66
|
+
CacheQue[j] = false
|
67
|
+
Output[target] = [] if Output[target].nil?
|
68
|
+
Output[target].push j
|
69
|
+
end
|
64
70
|
end
|
65
|
-
|
66
|
-
|
67
|
-
if !CacheQue[j]
|
68
|
-
Logger.found "[404 Not Found] #{j}"
|
69
|
-
end
|
70
|
-
results << j
|
71
|
+
elsif !CacheQue[j]
|
72
|
+
Logger.found "[404 Not Found] #{j}"
|
71
73
|
end
|
74
|
+
results << j
|
72
75
|
end
|
73
76
|
end
|
74
77
|
end
|
@@ -79,6 +82,7 @@ def run_pipe(options)
|
|
79
82
|
target = $LAST_READ_LINE.gsub("\n", '')
|
80
83
|
app.run target, options
|
81
84
|
end
|
85
|
+
gen_output
|
82
86
|
end
|
83
87
|
|
84
88
|
def run_file(filename, options)
|
@@ -87,11 +91,13 @@ def run_file(filename, options)
|
|
87
91
|
target = line.gsub("\n", '')
|
88
92
|
app.run target, options
|
89
93
|
end
|
94
|
+
gen_output
|
90
95
|
end
|
91
96
|
|
92
97
|
def run_url(url, options)
|
93
98
|
app = DeadFinderRunner.new
|
94
99
|
app.run url, options
|
100
|
+
gen_output
|
95
101
|
end
|
96
102
|
|
97
103
|
def run_sitemap(sitemap_url, options)
|
@@ -100,11 +106,17 @@ def run_sitemap(sitemap_url, options)
|
|
100
106
|
sitemap.to_a.each do |url|
|
101
107
|
app.run url, options
|
102
108
|
end
|
109
|
+
gen_output
|
110
|
+
end
|
111
|
+
|
112
|
+
def gen_output
|
113
|
+
File.write options['output'], Output.to_json if options['output'] != ''
|
103
114
|
end
|
104
115
|
|
105
116
|
class DeadFinder < Thor
|
106
|
-
class_option :concurrency, aliases: :c, default: 20, type: :numeric
|
107
|
-
class_option :timeout, aliases: :t, default: 10, type: :numeric
|
117
|
+
class_option :concurrency, aliases: :c, default: 20, type: :numeric, desc: 'Set Concurrncy'
|
118
|
+
class_option :timeout, aliases: :t, default: 10, type: :numeric, desc: 'Set HTTP Timeout'
|
119
|
+
class_option :output, aliases: :o, default: '', type: :string, desc: 'Save JSON Result'
|
108
120
|
|
109
121
|
desc 'pipe', 'Scan the URLs from STDIN. (e.g cat urls.txt | deadfinder pipe)'
|
110
122
|
def pipe
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: deadfinder
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.1
|
4
|
+
version: 1.2.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- hahwul
|
@@ -94,9 +94,37 @@ dependencies:
|
|
94
94
|
- - "~>"
|
95
95
|
- !ruby/object:Gem::Version
|
96
96
|
version: 1.2.0
|
97
|
-
|
98
|
-
|
99
|
-
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: set
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: 1.0.0
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 1.0.0
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: json
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: 2.6.0
|
118
|
+
type: :runtime
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: 2.6.0
|
125
|
+
description: Find dead-links (broken links). Dead link (broken link) means a link
|
126
|
+
within a web page that cannot be connected. These links can have a negative impact
|
127
|
+
to SEO and Security. This tool makes it easy to identify and modify.
|
100
128
|
email: hahwul@gmail.com
|
101
129
|
executables:
|
102
130
|
- deadfinder
|