broken_link_finder 0.12.2 → 0.12.3
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/CHANGELOG.md +11 -1
- data/Gemfile.lock +28 -24
- data/broken_link_finder.gemspec +1 -1
- data/lib/broken_link_finder/finder.rb +5 -2
- data/lib/broken_link_finder/version.rb +1 -1
- data/lib/broken_link_finder/wgit_extensions.rb +7 -0
- metadata +5 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 4e60e87e2f9f1ae05d4ebe58066169e389994fba88ea3393a9dc5c3d04df20b6
|
4
|
+
data.tar.gz: 8019a1671fb811d6bf67feefb044f77be18dc04b0904b1b4e43cb258ee0d5fa3
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6b16be9cbbd35ea468ff879a833b8a20cc6557b6bf1f2c0c79ae7243fc8a75d0f1b2d19ff9030dc112816871b232f85cbe49e344ee0ada405062b731961912a8
|
7
|
+
data.tar.gz: cf4f43c4d5369f218e1700b941fd5a4b3681aaafc8131e1394b734b72d343b6ee743690f15c115f711ccf5e133fe91777224fd943b04ae89e46e3ca06f09e424
|
data/CHANGELOG.md
CHANGED
@@ -9,9 +9,19 @@
|
|
9
9
|
- ...
|
10
10
|
---
|
11
11
|
|
12
|
+
## v0.12.3
|
13
|
+
### Added
|
14
|
+
- Added `BrokenLinkFinder::Finder#manager` getter method.
|
15
|
+
### Changed/Removed
|
16
|
+
- Updated production dependencies including `wgit` (to `v0.12.0`).
|
17
|
+
- Updated `Wgit::Url`s to look like Strings when inspected.
|
18
|
+
### Fixed
|
19
|
+
- ...
|
20
|
+
---
|
21
|
+
|
12
22
|
## v0.12.2
|
13
23
|
### Added
|
14
|
-
- Updated to Ruby 3.3 and updated production dependencies including Wgit (v0.11)
|
24
|
+
- Updated to Ruby 3.3 and updated production dependencies including Wgit (v0.11.0)
|
15
25
|
- Added `--js` and `--js-delay` flag options to the executable. This allows JS parsing to update a page's DOM before it get crawled.
|
16
26
|
### Changed/Removed
|
17
27
|
- ...
|
data/Gemfile.lock
CHANGED
@@ -1,62 +1,66 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
broken_link_finder (0.12.
|
4
|
+
broken_link_finder (0.12.3)
|
5
5
|
thor (~> 1.3)
|
6
6
|
thread (~> 0.2)
|
7
|
-
wgit (~> 0.
|
7
|
+
wgit (~> 0.12)
|
8
8
|
|
9
9
|
GEM
|
10
10
|
remote: https://rubygems.org/
|
11
11
|
specs:
|
12
|
-
addressable (2.8.
|
13
|
-
public_suffix (>= 2.0.2, <
|
14
|
-
|
12
|
+
addressable (2.8.7)
|
13
|
+
public_suffix (>= 2.0.2, < 7.0)
|
14
|
+
base64 (0.2.0)
|
15
|
+
bigdecimal (3.1.8)
|
16
|
+
bson (5.0.1)
|
15
17
|
byebug (11.1.3)
|
16
18
|
coderay (1.1.3)
|
17
|
-
concurrent-ruby (1.
|
18
|
-
crack (0.
|
19
|
+
concurrent-ruby (1.3.4)
|
20
|
+
crack (1.0.0)
|
21
|
+
bigdecimal
|
19
22
|
rexml
|
20
23
|
ethon (0.16.0)
|
21
24
|
ffi (>= 1.15.0)
|
22
|
-
ferrum (0.
|
25
|
+
ferrum (0.15)
|
23
26
|
addressable (~> 2.5)
|
24
27
|
concurrent-ruby (~> 1.1)
|
25
28
|
webrick (~> 1.7)
|
26
|
-
websocket-driver (
|
27
|
-
ffi (1.
|
28
|
-
hashdiff (1.1.
|
29
|
+
websocket-driver (~> 0.7)
|
30
|
+
ffi (1.17.0)
|
31
|
+
hashdiff (1.1.1)
|
29
32
|
maxitest (3.7.0)
|
30
33
|
minitest (>= 5.0.0, < 5.15.0)
|
31
|
-
method_source (1.
|
32
|
-
mini_portile2 (2.8.
|
34
|
+
method_source (1.1.0)
|
35
|
+
mini_portile2 (2.8.7)
|
33
36
|
minitest (5.14.4)
|
34
|
-
mongo (2.
|
35
|
-
bson (>= 4.14.1, <
|
36
|
-
nokogiri (1.16.
|
37
|
+
mongo (2.21.0)
|
38
|
+
bson (>= 4.14.1, < 6.0.0)
|
39
|
+
nokogiri (1.16.7)
|
37
40
|
mini_portile2 (~> 2.8.2)
|
38
41
|
racc (~> 1.4)
|
39
42
|
pry (0.14.2)
|
40
43
|
coderay (~> 1.1)
|
41
44
|
method_source (~> 1.0)
|
42
|
-
public_suffix (
|
43
|
-
racc (1.
|
44
|
-
rake (13.1
|
45
|
-
rexml (3.
|
46
|
-
thor (1.3.
|
45
|
+
public_suffix (6.0.1)
|
46
|
+
racc (1.8.1)
|
47
|
+
rake (13.2.1)
|
48
|
+
rexml (3.3.9)
|
49
|
+
thor (1.3.2)
|
47
50
|
thread (0.2.2)
|
48
51
|
typhoeus (1.4.1)
|
49
52
|
ethon (>= 0.9.0)
|
50
|
-
webmock (3.
|
53
|
+
webmock (3.24.0)
|
51
54
|
addressable (>= 2.8.0)
|
52
55
|
crack (>= 0.3.2)
|
53
56
|
hashdiff (>= 0.4.0, < 2.0.0)
|
54
|
-
webrick (1.8.
|
57
|
+
webrick (1.8.2)
|
55
58
|
websocket-driver (0.7.6)
|
56
59
|
websocket-extensions (>= 0.1.0)
|
57
60
|
websocket-extensions (0.1.5)
|
58
|
-
wgit (0.
|
61
|
+
wgit (0.12.0)
|
59
62
|
addressable (~> 2.8)
|
63
|
+
base64 (~> 0.2)
|
60
64
|
ferrum (~> 0.14)
|
61
65
|
mongo (~> 2.19)
|
62
66
|
nokogiri (~> 1.15)
|
data/broken_link_finder.gemspec
CHANGED
@@ -20,6 +20,9 @@ module BrokenLinkFinder
|
|
20
20
|
# The underlying Wgit::Crawler used by this instance of Finder.
|
21
21
|
attr_reader :crawler
|
22
22
|
|
23
|
+
# The underlying link manager used by this instance of Finder.
|
24
|
+
attr_reader :manager
|
25
|
+
|
23
26
|
# Returns a new Finder instance.
|
24
27
|
def initialize(sort: :page, max_threads: DEFAULT_MAX_THREADS, &block)
|
25
28
|
raise "Sort by either :page or :link, not #{sort}" \
|
@@ -61,7 +64,7 @@ module BrokenLinkFinder
|
|
61
64
|
doc = @crawler.crawl(url.dup)
|
62
65
|
|
63
66
|
# Ensure the given page url is valid.
|
64
|
-
raise "Invalid or broken URL: #{url}"
|
67
|
+
raise "Invalid or broken URL: #{url}" if doc.empty?
|
65
68
|
|
66
69
|
# Get all page links and determine which are broken.
|
67
70
|
find_broken_links(doc)
|
@@ -212,7 +215,7 @@ module BrokenLinkFinder
|
|
212
215
|
|
213
216
|
# Return if the crawled link is broken or not.
|
214
217
|
def link_broken?(doc)
|
215
|
-
doc.
|
218
|
+
doc.empty? || @crawler.last_response.not_found? || has_broken_anchor(doc)
|
216
219
|
end
|
217
220
|
|
218
221
|
# Returns true if the link is/contains a broken anchor/fragment.
|
@@ -1,5 +1,12 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
+
# Make Wgit::Urls look like Strings when inspected.
|
4
|
+
class Wgit::Url
|
5
|
+
def inspect
|
6
|
+
to_s.inspect
|
7
|
+
end
|
8
|
+
end
|
9
|
+
|
3
10
|
# Define a method on each doc for recording unparsable links.
|
4
11
|
# Unparsable links are recorded as broken links by Finder.
|
5
12
|
class Wgit::Document
|
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: 0.12.
|
4
|
+
version: 0.12.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Michael Telford
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-
|
11
|
+
date: 2024-10-30 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -128,14 +128,14 @@ dependencies:
|
|
128
128
|
requirements:
|
129
129
|
- - "~>"
|
130
130
|
- !ruby/object:Gem::Version
|
131
|
-
version: '0.
|
131
|
+
version: '0.12'
|
132
132
|
type: :runtime
|
133
133
|
prerelease: false
|
134
134
|
version_requirements: !ruby/object:Gem::Requirement
|
135
135
|
requirements:
|
136
136
|
- - "~>"
|
137
137
|
- !ruby/object:Gem::Version
|
138
|
-
version: '0.
|
138
|
+
version: '0.12'
|
139
139
|
description: Finds a website's broken links using the 'wgit' gem and reports back
|
140
140
|
to you with a summary.
|
141
141
|
email: michael.telford@live.com
|
@@ -194,7 +194,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
194
194
|
- !ruby/object:Gem::Version
|
195
195
|
version: '0'
|
196
196
|
requirements: []
|
197
|
-
rubygems_version: 3.5.
|
197
|
+
rubygems_version: 3.5.22
|
198
198
|
signing_key:
|
199
199
|
specification_version: 4
|
200
200
|
summary: Finds a website's broken links and reports back to you with a summary.
|