coolCrawler 0.4.2 → 0.4.4
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 +13 -9
- 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: 79059c4a0ef1c026082b3ef2b25ee13c2310984a2049be4345f0345b226d2e99
|
|
4
|
+
data.tar.gz: 32d02d444ef3553df02c2764073b1d9f5cbdabea272ee1d2b3eb9e80a5a29434
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 56d89149672219eb082eb188d2d79fde2d97931efe8295983719a5693c5b96c07e607a309d03690e8a739a2a3018f73c7d0fbd18da6003cbafa7969633890b2e
|
|
7
|
+
data.tar.gz: f37a6061b4b318cb19423ab4de961a98b625d1e17e6f85eb78524794a967a2f5dda4bceaa5c5414b2df33a359c9c0fd5a8e8a7bfe22c4f872e41a9e9c5f46d48
|
data/lib/coolCrawler/version.rb
CHANGED
data/lib/cool_crawler.rb
CHANGED
|
@@ -31,7 +31,7 @@ module CoolCrawler
|
|
|
31
31
|
end
|
|
32
32
|
|
|
33
33
|
def run
|
|
34
|
-
until queue.empty?
|
|
34
|
+
until queue.empty? || @visited_pages >= @max_pages
|
|
35
35
|
send_crawlers
|
|
36
36
|
sleep(delay)
|
|
37
37
|
end
|
|
@@ -43,7 +43,10 @@ module CoolCrawler
|
|
|
43
43
|
|
|
44
44
|
def send_crawlers
|
|
45
45
|
pages = []
|
|
46
|
-
|
|
46
|
+
until queue.empty? || pages.size >= max_connections || @visited_pages >= @max_pages
|
|
47
|
+
pages << queue.pop
|
|
48
|
+
@visited_pages += 1
|
|
49
|
+
end
|
|
47
50
|
Async do
|
|
48
51
|
internet = Async::HTTP::Internet.new
|
|
49
52
|
barrier = Async::Barrier.new
|
|
@@ -51,12 +54,14 @@ module CoolCrawler
|
|
|
51
54
|
pages.each do |page|
|
|
52
55
|
barrier.async do
|
|
53
56
|
response = internet.get URI.join(@site, page).to_s
|
|
54
|
-
body = response.read
|
|
55
|
-
|
|
56
|
-
|
|
57
|
+
body = Nokogiri::HTML(response.read)
|
|
58
|
+
body.search('//img').remove
|
|
59
|
+
body.search('//style').remove
|
|
60
|
+
body.search('//script').remove
|
|
61
|
+
links = gather_links_uri(body.to_s, URI.join(uri, page))
|
|
62
|
+
after(page, links, body.to_s)
|
|
57
63
|
links.each do |link|
|
|
58
64
|
enqueue(link)
|
|
59
|
-
@visited_pages += 1
|
|
60
65
|
add_to_visited(link)
|
|
61
66
|
end
|
|
62
67
|
end
|
|
@@ -74,7 +79,7 @@ module CoolCrawler
|
|
|
74
79
|
next if a["href"].nil?
|
|
75
80
|
uri_a = URI(a["href"].strip.split('#')[0].sub(/\\|(\s+$)/, ""))
|
|
76
81
|
begin
|
|
77
|
-
|
|
82
|
+
links << URI.join(page, uri_a).path if (uri_a.host == uri.host || uri_a.host.nil?) && uri_a.path
|
|
78
83
|
rescue
|
|
79
84
|
# do nothing
|
|
80
85
|
end
|
|
@@ -107,9 +112,8 @@ module CoolCrawler
|
|
|
107
112
|
end
|
|
108
113
|
|
|
109
114
|
def enqueue(path)
|
|
110
|
-
unless visited.include?(path)
|
|
115
|
+
unless visited.include?(path)
|
|
111
116
|
queue << path
|
|
112
|
-
p queue.size
|
|
113
117
|
end
|
|
114
118
|
end
|
|
115
119
|
|
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.
|
|
4
|
+
version: 0.4.4
|
|
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-
|
|
11
|
+
date: 2022-11-01 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: rspec
|