broken_link_finder 0.9.1 → 0.9.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +9 -0
- data/Gemfile +2 -0
- data/Gemfile.lock +24 -21
- data/README.md +3 -1
- data/benchmark.rb +0 -1
- data/bin/console +13 -22
- data/broken_link_finder.gemspec +5 -7
- data/lib/broken_link_finder/finder.rb +25 -16
- data/lib/broken_link_finder/reporter.rb +4 -4
- data/lib/broken_link_finder/version.rb +1 -1
- data/lib/broken_link_finder/wgit_extensions.rb +1 -1
- metadata +17 -45
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 110068a5db9454d69709454f50ade3f667c0e63dad6d101c23bf991a04f770eb
|
4
|
+
data.tar.gz: 0fd46fed486bf382935d68020fcae9391c288b5d5742ce19ba61d2896e2eebe7
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: c9c744045ee462b8981ab418a5c3acdb9162c36e14c8603391c1f79e9247872de877a83ce2a7dd5f8779d8774a044562054445410666a5af518d11f5fded3f22
|
7
|
+
data.tar.gz: e4e0e2b2d19596493564a361fef0a98afdddcefb395309dba139df6bd508a12385ca16e47004bd503c585954454d9608449995b4ed6009926e0b856d11962181
|
data/CHANGELOG.md
CHANGED
@@ -9,6 +9,15 @@
|
|
9
9
|
- ...
|
10
10
|
---
|
11
11
|
|
12
|
+
## v0.9.2
|
13
|
+
### Added
|
14
|
+
- ...
|
15
|
+
### Changed/Removed
|
16
|
+
- Updated `wgit` gem to version 0.4.0 which brings a speed boost to crawls.
|
17
|
+
### Fixed
|
18
|
+
- ...
|
19
|
+
---
|
20
|
+
|
12
21
|
## v0.9.1
|
13
22
|
### Added
|
14
23
|
- `BrokenLinkFinder::Finder.crawl_site` alias: `crawl_r`.
|
data/Gemfile
CHANGED
data/Gemfile.lock
CHANGED
@@ -1,10 +1,10 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
broken_link_finder (0.9.
|
5
|
-
thor (
|
6
|
-
thread (
|
7
|
-
wgit (
|
4
|
+
broken_link_finder (0.9.2)
|
5
|
+
thor (~> 0.20.3)
|
6
|
+
thread (~> 0.2.0)
|
7
|
+
wgit (~> 0.4.0)
|
8
8
|
|
9
9
|
GEM
|
10
10
|
remote: https://rubygems.org/
|
@@ -16,15 +16,16 @@ GEM
|
|
16
16
|
coderay (1.1.2)
|
17
17
|
crack (0.4.3)
|
18
18
|
safe_yaml (~> 1.0.0)
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
19
|
+
ethon (0.12.0)
|
20
|
+
ffi (>= 1.3.0)
|
21
|
+
ffi (1.11.1)
|
22
|
+
hashdiff (1.0.0)
|
23
|
+
maxitest (3.4.0)
|
24
|
+
minitest (>= 5.0.0, < 5.13.0)
|
24
25
|
method_source (0.9.2)
|
25
26
|
mini_portile2 (2.4.0)
|
26
|
-
minitest (5.
|
27
|
-
mongo (2.9.
|
27
|
+
minitest (5.12.2)
|
28
|
+
mongo (2.9.2)
|
28
29
|
bson (>= 4.4.2, < 5.0.0)
|
29
30
|
nokogiri (1.10.4)
|
30
31
|
mini_portile2 (~> 2.4.0)
|
@@ -32,20 +33,21 @@ GEM
|
|
32
33
|
coderay (~> 1.1.0)
|
33
34
|
method_source (~> 0.9.0)
|
34
35
|
public_suffix (3.1.0)
|
35
|
-
rack (2.0.7)
|
36
|
-
rainbow (3.0.0)
|
37
36
|
rake (10.5.0)
|
38
37
|
safe_yaml (1.0.5)
|
39
38
|
thor (0.20.3)
|
40
|
-
thread (0.2.
|
41
|
-
|
39
|
+
thread (0.2.2)
|
40
|
+
typhoeus (1.3.1)
|
41
|
+
ethon (>= 0.9.0)
|
42
|
+
webmock (3.7.6)
|
42
43
|
addressable (>= 2.3.6)
|
43
44
|
crack (>= 0.3.2)
|
44
|
-
hashdiff
|
45
|
-
wgit (0.
|
45
|
+
hashdiff (>= 0.4.0, < 2.0.0)
|
46
|
+
wgit (0.4.0)
|
46
47
|
addressable (~> 2.6.0)
|
47
48
|
mongo (~> 2.9.0)
|
48
49
|
nokogiri (~> 1.10.3)
|
50
|
+
typhoeus (~> 1.3.1)
|
49
51
|
|
50
52
|
PLATFORMS
|
51
53
|
ruby
|
@@ -54,12 +56,13 @@ DEPENDENCIES
|
|
54
56
|
broken_link_finder!
|
55
57
|
bundler (~> 2.0)
|
56
58
|
byebug (~> 11.0)
|
57
|
-
|
58
|
-
memory_profiler (~> 0.9)
|
59
|
-
minitest (~> 5.0)
|
59
|
+
maxitest (~> 3.3)
|
60
60
|
pry (~> 0.12)
|
61
61
|
rake (~> 10.0)
|
62
|
-
webmock (~> 3.
|
62
|
+
webmock (~> 3.6)
|
63
|
+
|
64
|
+
RUBY VERSION
|
65
|
+
ruby 2.5.3p105
|
63
66
|
|
64
67
|
BUNDLED WITH
|
65
68
|
2.0.1
|
data/README.md
CHANGED
@@ -19,9 +19,11 @@ In a nutshell, only HTTP(S) based links can be successfully verified by `broken_
|
|
19
19
|
|
20
20
|
See the [usage](#Usage) section below on how to check which links have been ignored during a crawl.
|
21
21
|
|
22
|
+
With that said, the usual array of HTTP URL features are supported including anchors/fragments, query strings and IRI's (non ASCII based URL's).
|
23
|
+
|
22
24
|
## Made Possible By
|
23
25
|
|
24
|
-
`broken_link_finder` relies heavily on the `wgit` Ruby gem. See its [repository](https://github.com/michaeltelford/wgit) for more details.
|
26
|
+
`broken_link_finder` relies heavily on the `wgit` Ruby gem by the same author. See its [repository](https://github.com/michaeltelford/wgit) for more details.
|
25
27
|
|
26
28
|
## Installation
|
27
29
|
|
data/benchmark.rb
CHANGED
data/bin/console
CHANGED
@@ -4,30 +4,20 @@
|
|
4
4
|
require 'bundler/setup'
|
5
5
|
require 'pry'
|
6
6
|
require 'byebug'
|
7
|
-
require 'logger'
|
8
|
-
require 'httplog'
|
9
7
|
require 'broken_link_finder'
|
10
8
|
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
config.log_headers = false
|
24
|
-
config.log_data = false
|
25
|
-
config.log_status = true
|
26
|
-
config.log_response = false
|
27
|
-
config.log_benchmark = false
|
28
|
-
|
29
|
-
config.compact_log = false
|
30
|
-
config.json_log = false
|
9
|
+
# Monkey patch and log all HTTP requests made during the console.
|
10
|
+
module Typhoeus
|
11
|
+
singleton_class.class_eval do
|
12
|
+
alias_method :orig_get, :get
|
13
|
+
end
|
14
|
+
|
15
|
+
def self.get(base_url, options = {})
|
16
|
+
puts "[typhoeus] Sending GET: #{base_url}"
|
17
|
+
resp = orig_get(base_url, options)
|
18
|
+
puts "[typhoeus] Status: #{resp.code} (#{resp.body.length} bytes in #{resp.total_time} seconds)"
|
19
|
+
resp
|
20
|
+
end
|
31
21
|
end
|
32
22
|
|
33
23
|
# Call reload to load all recent code changes.
|
@@ -48,6 +38,7 @@ by_page = Finder.new
|
|
48
38
|
by_link = Finder.new sort: :link
|
49
39
|
finder = by_page
|
50
40
|
|
41
|
+
# Start the console.
|
51
42
|
puts "\nbroken_link_finder v#{BrokenLinkFinder::VERSION}"
|
52
43
|
|
53
44
|
binding.pry
|
data/broken_link_finder.gemspec
CHANGED
@@ -39,14 +39,12 @@ Gem::Specification.new do |spec|
|
|
39
39
|
|
40
40
|
spec.add_development_dependency 'bundler', '~> 2.0'
|
41
41
|
spec.add_development_dependency 'byebug', '~> 11.0'
|
42
|
-
spec.add_development_dependency '
|
43
|
-
spec.add_development_dependency 'memory_profiler', '~> 0.9'
|
44
|
-
spec.add_development_dependency 'minitest', '~> 5.0'
|
42
|
+
spec.add_development_dependency 'maxitest', '~> 3.3'
|
45
43
|
spec.add_development_dependency 'pry', '~> 0.12'
|
46
44
|
spec.add_development_dependency 'rake', '~> 10.0'
|
47
|
-
spec.add_development_dependency 'webmock', '~> 3.
|
45
|
+
spec.add_development_dependency 'webmock', '~> 3.6'
|
48
46
|
|
49
|
-
spec.add_runtime_dependency 'thor', '0.20.3'
|
50
|
-
spec.add_runtime_dependency 'thread', '0.2'
|
51
|
-
spec.add_runtime_dependency 'wgit', '0.
|
47
|
+
spec.add_runtime_dependency 'thor', '~> 0.20.3'
|
48
|
+
spec.add_runtime_dependency 'thread', '~> 0.2.0'
|
49
|
+
spec.add_runtime_dependency 'wgit', '~> 0.4.0'
|
52
50
|
end
|
@@ -39,7 +39,7 @@ module BrokenLinkFinder
|
|
39
39
|
|
40
40
|
# Finds broken links within a single page and appends them to the
|
41
41
|
# @broken_links array. Returns true if at least one broken link was found.
|
42
|
-
# Access the broken links with Finder#broken_links.
|
42
|
+
# Access the broken links afterwards with Finder#broken_links.
|
43
43
|
def crawl_url(url)
|
44
44
|
clear_links
|
45
45
|
|
@@ -61,7 +61,7 @@ module BrokenLinkFinder
|
|
61
61
|
# Finds broken links within an entire site and appends them to the
|
62
62
|
# @broken_links array. Returns a tuple containing a Boolean of true if
|
63
63
|
# at least one broken link was found and an Array of all pages crawled.
|
64
|
-
# Access the broken links with Finder#broken_links.
|
64
|
+
# Access the broken links afterwards with Finder#broken_links.
|
65
65
|
def crawl_site(url)
|
66
66
|
clear_links
|
67
67
|
|
@@ -70,7 +70,7 @@ module BrokenLinkFinder
|
|
70
70
|
crawled_pages = []
|
71
71
|
|
72
72
|
# Crawl the site's HTML web pages looking for links.
|
73
|
-
|
73
|
+
externals = @crawler.crawl_site(url) do |doc|
|
74
74
|
crawled_pages << doc.url
|
75
75
|
next unless doc
|
76
76
|
|
@@ -79,7 +79,7 @@ module BrokenLinkFinder
|
|
79
79
|
end
|
80
80
|
|
81
81
|
# Ensure the given website url is valid.
|
82
|
-
raise "Invalid or broken URL: #{url}"
|
82
|
+
raise "Invalid or broken URL: #{url}" unless externals
|
83
83
|
|
84
84
|
# Wait for all threads to finish.
|
85
85
|
pool.shutdown
|
@@ -113,15 +113,7 @@ module BrokenLinkFinder
|
|
113
113
|
|
114
114
|
# Finds which links are unsupported or broken and records the details.
|
115
115
|
def find_broken_links(doc)
|
116
|
-
|
117
|
-
links = doc.all_links
|
118
|
-
.reject do |link|
|
119
|
-
if link.is_absolute? && !link.start_with?('http')
|
120
|
-
append_ignored_link(doc.url, link)
|
121
|
-
true
|
122
|
-
end
|
123
|
-
end
|
124
|
-
.uniq
|
116
|
+
links = get_supported_links(doc)
|
125
117
|
|
126
118
|
# Iterate over the supported links checking if they're broken or not.
|
127
119
|
links.each do |link|
|
@@ -134,11 +126,10 @@ module BrokenLinkFinder
|
|
134
126
|
end
|
135
127
|
|
136
128
|
# The link hasn't been processed before so we crawl it.
|
137
|
-
|
138
|
-
link_doc = @crawler.crawl_url(link_url)
|
129
|
+
link_doc = crawl_link(doc, link)
|
139
130
|
|
140
131
|
# Determine if the crawled link is broken or not.
|
141
|
-
if @crawler.last_response.
|
132
|
+
if @crawler.last_response.code == 404 ||
|
142
133
|
link_doc.nil? ||
|
143
134
|
has_broken_anchor(link_doc)
|
144
135
|
append_broken_link(doc.url, link)
|
@@ -150,6 +141,24 @@ module BrokenLinkFinder
|
|
150
141
|
nil
|
151
142
|
end
|
152
143
|
|
144
|
+
# Report and reject any non supported links. Any link that is absolute and
|
145
|
+
# doesn't start with 'http' is unsupported e.g. 'mailto:blah' etc.
|
146
|
+
def get_supported_links(doc)
|
147
|
+
doc.all_links
|
148
|
+
.reject do |link|
|
149
|
+
if link.is_absolute? && !link.start_with?('http')
|
150
|
+
append_ignored_link(doc.url, link)
|
151
|
+
true
|
152
|
+
end
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
# Makes the link absolute and crawls it, returning its Wgit::Document.
|
157
|
+
def crawl_link(doc, link)
|
158
|
+
link = get_absolute_link(doc, link)
|
159
|
+
@crawler.crawl_url(link)
|
160
|
+
end
|
161
|
+
|
153
162
|
# Returns the link in absolute form so it can be crawled.
|
154
163
|
def get_absolute_link(doc, link)
|
155
164
|
link.is_relative? ? doc.base_url(link: link).concat(link) : link
|
@@ -12,10 +12,10 @@ module BrokenLinkFinder
|
|
12
12
|
raise "sort by either :page or :link, not #{sort}" \
|
13
13
|
unless %i[page link].include?(sort)
|
14
14
|
|
15
|
-
@stream
|
16
|
-
@sort
|
17
|
-
@broken_links
|
18
|
-
@ignored_links
|
15
|
+
@stream = stream
|
16
|
+
@sort = sort
|
17
|
+
@broken_links = broken_links
|
18
|
+
@ignored_links = ignored_links
|
19
19
|
end
|
20
20
|
|
21
21
|
# Pretty print a report detailing the link summary.
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: broken_link_finder
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.9.
|
4
|
+
version: 0.9.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Michael Telford
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-
|
11
|
+
date: 2019-10-18 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -39,47 +39,19 @@ dependencies:
|
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '11.0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
|
-
name:
|
42
|
+
name: maxitest
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
45
|
- - "~>"
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
47
|
+
version: '3.3'
|
48
48
|
type: :development
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
52
|
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
55
|
-
- !ruby/object:Gem::Dependency
|
56
|
-
name: memory_profiler
|
57
|
-
requirement: !ruby/object:Gem::Requirement
|
58
|
-
requirements:
|
59
|
-
- - "~>"
|
60
|
-
- !ruby/object:Gem::Version
|
61
|
-
version: '0.9'
|
62
|
-
type: :development
|
63
|
-
prerelease: false
|
64
|
-
version_requirements: !ruby/object:Gem::Requirement
|
65
|
-
requirements:
|
66
|
-
- - "~>"
|
67
|
-
- !ruby/object:Gem::Version
|
68
|
-
version: '0.9'
|
69
|
-
- !ruby/object:Gem::Dependency
|
70
|
-
name: minitest
|
71
|
-
requirement: !ruby/object:Gem::Requirement
|
72
|
-
requirements:
|
73
|
-
- - "~>"
|
74
|
-
- !ruby/object:Gem::Version
|
75
|
-
version: '5.0'
|
76
|
-
type: :development
|
77
|
-
prerelease: false
|
78
|
-
version_requirements: !ruby/object:Gem::Requirement
|
79
|
-
requirements:
|
80
|
-
- - "~>"
|
81
|
-
- !ruby/object:Gem::Version
|
82
|
-
version: '5.0'
|
54
|
+
version: '3.3'
|
83
55
|
- !ruby/object:Gem::Dependency
|
84
56
|
name: pry
|
85
57
|
requirement: !ruby/object:Gem::Requirement
|
@@ -114,56 +86,56 @@ dependencies:
|
|
114
86
|
requirements:
|
115
87
|
- - "~>"
|
116
88
|
- !ruby/object:Gem::Version
|
117
|
-
version: '3.
|
89
|
+
version: '3.6'
|
118
90
|
type: :development
|
119
91
|
prerelease: false
|
120
92
|
version_requirements: !ruby/object:Gem::Requirement
|
121
93
|
requirements:
|
122
94
|
- - "~>"
|
123
95
|
- !ruby/object:Gem::Version
|
124
|
-
version: '3.
|
96
|
+
version: '3.6'
|
125
97
|
- !ruby/object:Gem::Dependency
|
126
98
|
name: thor
|
127
99
|
requirement: !ruby/object:Gem::Requirement
|
128
100
|
requirements:
|
129
|
-
- -
|
101
|
+
- - "~>"
|
130
102
|
- !ruby/object:Gem::Version
|
131
103
|
version: 0.20.3
|
132
104
|
type: :runtime
|
133
105
|
prerelease: false
|
134
106
|
version_requirements: !ruby/object:Gem::Requirement
|
135
107
|
requirements:
|
136
|
-
- -
|
108
|
+
- - "~>"
|
137
109
|
- !ruby/object:Gem::Version
|
138
110
|
version: 0.20.3
|
139
111
|
- !ruby/object:Gem::Dependency
|
140
112
|
name: thread
|
141
113
|
requirement: !ruby/object:Gem::Requirement
|
142
114
|
requirements:
|
143
|
-
- -
|
115
|
+
- - "~>"
|
144
116
|
- !ruby/object:Gem::Version
|
145
|
-
version:
|
117
|
+
version: 0.2.0
|
146
118
|
type: :runtime
|
147
119
|
prerelease: false
|
148
120
|
version_requirements: !ruby/object:Gem::Requirement
|
149
121
|
requirements:
|
150
|
-
- -
|
122
|
+
- - "~>"
|
151
123
|
- !ruby/object:Gem::Version
|
152
|
-
version:
|
124
|
+
version: 0.2.0
|
153
125
|
- !ruby/object:Gem::Dependency
|
154
126
|
name: wgit
|
155
127
|
requirement: !ruby/object:Gem::Requirement
|
156
128
|
requirements:
|
157
|
-
- -
|
129
|
+
- - "~>"
|
158
130
|
- !ruby/object:Gem::Version
|
159
|
-
version: 0.
|
131
|
+
version: 0.4.0
|
160
132
|
type: :runtime
|
161
133
|
prerelease: false
|
162
134
|
version_requirements: !ruby/object:Gem::Requirement
|
163
135
|
requirements:
|
164
|
-
- -
|
136
|
+
- - "~>"
|
165
137
|
- !ruby/object:Gem::Version
|
166
|
-
version: 0.
|
138
|
+
version: 0.4.0
|
167
139
|
description: Finds a website's broken links using the 'wgit' gem and reports back
|
168
140
|
to you with a summary.
|
169
141
|
email: michael.telford@live.com
|