coolCrawler 0.3.0 → 0.4.0
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/coolCrawler/version.rb +1 -1
- data/lib/cool_crawler.rb +5 -4
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 7aecaddb63af3eb7a621f2cd75472291e0376ca57ef30ec229edcbe274bc704b
|
|
4
|
+
data.tar.gz: f42a0b9230a6886169cc7dd35f25f03dcb8b1f6d53ec5515c32ed647e2249ee5
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 36442036c64c324adf090c7ccb4b6cc474875471ac1dc54ead21604e9de8209036c608e18d0b83bf97e37281720c66cf5b4a8084fb97ed7d81aa7aa1f58e7387
|
|
7
|
+
data.tar.gz: 38a40361a3ee2d1b34efbf21e482fa4663f89d20731490e1ebd2e6e014cd66537cd95e0da9fdef14ec33d02f59d0aa054fcca383e158e2ed9fbe544501771ce6
|
data/lib/coolCrawler/version.rb
CHANGED
data/lib/cool_crawler.rb
CHANGED
|
@@ -35,8 +35,8 @@ module CoolCrawler
|
|
|
35
35
|
end
|
|
36
36
|
end
|
|
37
37
|
|
|
38
|
-
def after(page, links)
|
|
39
|
-
callback.call(page, links) unless callback.nil?
|
|
38
|
+
def after(page, links, body)
|
|
39
|
+
callback.call(page, links, body) unless callback.nil?
|
|
40
40
|
end
|
|
41
41
|
|
|
42
42
|
def send_crawlers
|
|
@@ -49,8 +49,9 @@ module CoolCrawler
|
|
|
49
49
|
pages.each do |page|
|
|
50
50
|
barrier.async do
|
|
51
51
|
response = internet.get URI.join(@site, page).to_s
|
|
52
|
-
|
|
53
|
-
|
|
52
|
+
body = response.read
|
|
53
|
+
links = gather_links_uri(body, URI.join(uri, page))
|
|
54
|
+
after(page, links, body)
|
|
54
55
|
links.each do |link|
|
|
55
56
|
enqueue(link)
|
|
56
57
|
add_to_visited(link)
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: coolCrawler
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.4.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- William Wright
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2022-10-
|
|
11
|
+
date: 2022-10-14 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: rspec
|