deadfinder 1.2.1 → 1.2.2
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 +36 -30
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: e1e747b78068c1590c88f49acc42ca917a3c26684564c4465449181d5fea4125
|
|
4
|
+
data.tar.gz: 19f6a77d77bb0b3e2daba04ec364b1626eebbe30ec9973753fb75c1cb78ffc2e
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ddc7a3974fcbf62d78ce739862f1686b070bfea6f26ae534c5fe18b49fb48432f7483567ab109ef4b97d40916460be1b08524dc8615d5f537564555df817c781
|
|
7
|
+
data.tar.gz: b676e1009517b67da7cff2dc10f26a50f6635d1abfeab6e036092d2b63eff55fa758c3cb0ee2b63ec34157901f00708a2d0f4282e99e5fc61057f70ad939e23f
|
data/lib/deadfinder/logger.rb
CHANGED
data/lib/deadfinder/version.rb
CHANGED
data/lib/deadfinder.rb
CHANGED
|
@@ -19,38 +19,42 @@ Output = {}
|
|
|
19
19
|
|
|
20
20
|
class DeadFinderRunner
|
|
21
21
|
def run(target, options)
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
22
|
+
begin
|
|
23
|
+
page = Nokogiri::HTML(URI.open(target))
|
|
24
|
+
|
|
25
|
+
nodeset_a = page.css('a')
|
|
26
|
+
link_a = nodeset_a.map { |element| element['href'] }.compact
|
|
27
|
+
nodeset_script = page.css('script')
|
|
28
|
+
link_script = nodeset_script.map { |element| element['src'] }.compact
|
|
29
|
+
nodeset_link = page.css('link')
|
|
30
|
+
link_link = nodeset_link.map { |element| element['href'] }.compact
|
|
31
|
+
|
|
32
|
+
link_merged = []
|
|
33
|
+
link_merged.concat link_a, link_script, link_link
|
|
34
|
+
|
|
35
|
+
Logger.target target
|
|
36
|
+
Logger.sub_info "Found #{link_merged.length} point. [a:#{link_a.length}/s:#{link_script.length}/l:#{link_link.length}]"
|
|
37
|
+
Logger.sub_info 'Checking'
|
|
38
|
+
jobs = Channel.new(buffer: :buffered, capacity: 1000)
|
|
39
|
+
results = Channel.new(buffer: :buffered, capacity: 1000)
|
|
40
|
+
|
|
41
|
+
(1..options['concurrency']).each do |w|
|
|
42
|
+
Channel.go { worker(w, jobs, results, target, options) }
|
|
43
|
+
end
|
|
43
44
|
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
45
|
+
link_merged.uniq.each do |node|
|
|
46
|
+
result = generate_url node, target
|
|
47
|
+
jobs << result
|
|
48
|
+
end
|
|
49
|
+
jobs.close
|
|
49
50
|
|
|
50
|
-
|
|
51
|
-
|
|
51
|
+
(1..link_merged.uniq.length).each do
|
|
52
|
+
~results
|
|
53
|
+
end
|
|
54
|
+
Logger.sub_done 'Done'
|
|
55
|
+
rescue => e
|
|
56
|
+
Logger.error "[#{e}] #{target}"
|
|
52
57
|
end
|
|
53
|
-
Logger.sub_done 'Done'
|
|
54
58
|
end
|
|
55
59
|
|
|
56
60
|
def worker(_id, jobs, results, target, options)
|
|
@@ -102,9 +106,11 @@ end
|
|
|
102
106
|
|
|
103
107
|
def run_sitemap(sitemap_url, options)
|
|
104
108
|
app = DeadFinderRunner.new
|
|
109
|
+
base_uri = URI(sitemap_url)
|
|
105
110
|
sitemap = SitemapParser.new sitemap_url, { recurse: true }
|
|
106
111
|
sitemap.to_a.each do |url|
|
|
107
|
-
|
|
112
|
+
turl = generate_url url, base_uri
|
|
113
|
+
app.run turl, options
|
|
108
114
|
end
|
|
109
115
|
gen_output
|
|
110
116
|
end
|