deadfinder 1.1.1 → 1.2.0
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/logger.rb +4 -0
- data/lib/deadfinder/version.rb +1 -1
- data/lib/deadfinder.rb +47 -12
- metadata +29 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 694fc6108a1fde665a3e8b265071409ac483434b093c94e3eebb25324e4bb300
|
4
|
+
data.tar.gz: 1bd04447be853ff381263915fe2ddcaca3418699828d5e97feb674623c41c8ba
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 42eb575191bc6fa72cca03b0a94a8f20db82242c19a93bc0fcc9dfe8872c03c2cfe1accf68c480b0432f7c73df4ee0b1782ad08906d1e4bdea35dfc268d837b3
|
7
|
+
data.tar.gz: 39d5838080f9afd84cf3272f85a4cc6e26cf663da10b76a7e9fcfe1f63ac1b41ca973a21e454743fbc1011f9955b3c9ec488e0a586df94bdaca5e01f2ea5bec2
|
data/lib/deadfinder/logger.rb
CHANGED
data/lib/deadfinder/version.rb
CHANGED
data/lib/deadfinder.rb
CHANGED
@@ -9,22 +9,36 @@ require 'deadfinder/logger'
|
|
9
9
|
require 'deadfinder/version'
|
10
10
|
require 'concurrent-edge'
|
11
11
|
require 'sitemap-parser'
|
12
|
+
require 'set'
|
13
|
+
require 'json'
|
12
14
|
|
13
15
|
Channel = Concurrent::Channel
|
16
|
+
CacheSet = Set.new
|
17
|
+
CacheQue = {}
|
18
|
+
Output = {}
|
14
19
|
|
15
20
|
class DeadFinderRunner
|
16
21
|
def run(target, options)
|
17
22
|
page = Nokogiri::HTML(URI.open(target))
|
18
|
-
|
19
|
-
|
23
|
+
|
24
|
+
nodeset_a = page.css('a')
|
25
|
+
link_a = nodeset_a.map { |element| element['href'] }.compact
|
26
|
+
nodeset_script = page.css('script')
|
27
|
+
link_script = nodeset_script.map { |element| element['src'] }.compact
|
28
|
+
nodeset_link = page.css('link')
|
29
|
+
link_link = nodeset_link.map { |element| element['href'] }.compact
|
30
|
+
|
31
|
+
link_merged = []
|
32
|
+
link_merged.concat link_a, link_script, link_link
|
33
|
+
|
20
34
|
Logger.target target
|
21
|
-
Logger.sub_info "Found #{
|
35
|
+
Logger.sub_info "Found #{link_merged.length} point. [a:#{link_a.length}/s:#{link_script.length}/l:#{link_link.length}]"
|
22
36
|
Logger.sub_info 'Checking'
|
23
|
-
jobs = Channel.new(buffer: :buffered, capacity:
|
24
|
-
results = Channel.new(buffer: :buffered, capacity:
|
37
|
+
jobs = Channel.new(buffer: :buffered, capacity: 1000)
|
38
|
+
results = Channel.new(buffer: :buffered, capacity: 1000)
|
25
39
|
|
26
40
|
(1..options['concurrency']).each do |w|
|
27
|
-
Channel.go { worker(w, jobs, results) }
|
41
|
+
Channel.go { worker(w, jobs, results, target, options) }
|
28
42
|
end
|
29
43
|
|
30
44
|
link_a.uniq.each do |node|
|
@@ -36,15 +50,26 @@ class DeadFinderRunner
|
|
36
50
|
(1..link_a.uniq.length).each do
|
37
51
|
~results
|
38
52
|
end
|
39
|
-
Logger.
|
53
|
+
Logger.sub_done 'Done'
|
40
54
|
end
|
41
55
|
|
42
|
-
def worker(_id, jobs, results)
|
56
|
+
def worker(_id, jobs, results, target, options)
|
43
57
|
jobs.each do |j|
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
58
|
+
if !CacheSet.include? j
|
59
|
+
CacheSet.add j
|
60
|
+
begin
|
61
|
+
CacheQue[j] = true
|
62
|
+
URI.open(j, read_timeout: options['timeout'])
|
63
|
+
rescue StandardError => e
|
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
|
70
|
+
end
|
71
|
+
elsif !CacheQue[j]
|
72
|
+
Logger.found "[404 Not Found] #{j}"
|
48
73
|
end
|
49
74
|
results << j
|
50
75
|
end
|
@@ -57,6 +82,7 @@ def run_pipe(options)
|
|
57
82
|
target = $LAST_READ_LINE.gsub("\n", '')
|
58
83
|
app.run target, options
|
59
84
|
end
|
85
|
+
gen_output
|
60
86
|
end
|
61
87
|
|
62
88
|
def run_file(filename, options)
|
@@ -65,11 +91,13 @@ def run_file(filename, options)
|
|
65
91
|
target = line.gsub("\n", '')
|
66
92
|
app.run target, options
|
67
93
|
end
|
94
|
+
gen_output
|
68
95
|
end
|
69
96
|
|
70
97
|
def run_url(url, options)
|
71
98
|
app = DeadFinderRunner.new
|
72
99
|
app.run url, options
|
100
|
+
gen_output
|
73
101
|
end
|
74
102
|
|
75
103
|
def run_sitemap(sitemap_url, options)
|
@@ -78,10 +106,17 @@ def run_sitemap(sitemap_url, options)
|
|
78
106
|
sitemap.to_a.each do |url|
|
79
107
|
app.run url, options
|
80
108
|
end
|
109
|
+
gen_output
|
110
|
+
end
|
111
|
+
|
112
|
+
def gen_output
|
113
|
+
File.write options['output'], Output.to_json if options['output'] != ''
|
81
114
|
end
|
82
115
|
|
83
116
|
class DeadFinder < Thor
|
84
117
|
class_option :concurrency, aliases: :c, default: 20, type: :numeric
|
118
|
+
class_option :timeout, aliases: :t, default: 10, type: :numeric
|
119
|
+
class_option :output, aliases: :o, default: '', type: :string, desc: 'Save JSON Result'
|
85
120
|
|
86
121
|
desc 'pipe', 'Scan the URLs from STDIN. (e.g cat urls.txt | deadfinder pipe)'
|
87
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.
|
4
|
+
version: 1.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- hahwul
|
@@ -94,6 +94,34 @@ dependencies:
|
|
94
94
|
- - "~>"
|
95
95
|
- !ruby/object:Gem::Version
|
96
96
|
version: 1.2.0
|
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
|
97
125
|
description: Dead link (broken link) means a link within a web page that cannot be
|
98
126
|
connected. These links can have a security negative impact with SEO. This tool makes
|
99
127
|
it easy to identify and modify.
|