vore 0.2.4-arm64-linux → 0.2.5-arm64-linux
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/vore/crawler.rb +6 -4
- data/lib/vore/version.rb +1 -1
- 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: 23dad8fc88f81cb3583c080a4a606af50ebb6357100a469c13286f7834b326f6
|
|
4
|
+
data.tar.gz: 2ccb300c34fca54a2488fb31cefe3814058d13a564509bd49e6da459a74d6b13
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ab68468943157d4c4f878a111c043fa45c437c23a37787cdf26f1cf9e99d8fe8bb53872f46273872bd9e97efb130b78a293a83175f517b1e0c067c3ebe1b5a41
|
|
7
|
+
data.tar.gz: 2bddbd68a4dce6c5e4a8664f6c53798543e8ef1fec4cd257cdc0255ed24772fe09afca3ddf38b3887454ffa50faa3d99f8564190f30bb84c5c18ca2170f76be2
|
data/lib/vore/crawler.rb
CHANGED
|
@@ -31,7 +31,7 @@ module Vore
|
|
|
31
31
|
|
|
32
32
|
output = %x(#{@executable} \
|
|
33
33
|
--user-agent #{user_agent} \
|
|
34
|
-
--delay
|
|
34
|
+
--delay 3500 \
|
|
35
35
|
--url #{website} \
|
|
36
36
|
download \
|
|
37
37
|
-t \
|
|
@@ -48,16 +48,18 @@ module Vore
|
|
|
48
48
|
Dir.glob(File.join(output_dir, "**", "*")).each do |path|
|
|
49
49
|
next unless File.file?(path)
|
|
50
50
|
|
|
51
|
+
results[:pages_visited] += 1
|
|
52
|
+
|
|
51
53
|
html_file = File.read(path).force_encoding("UTF-8")
|
|
52
|
-
rewritten_html_file = @selma.rewrite(html_file)
|
|
53
54
|
|
|
54
|
-
|
|
55
|
-
if rewritten_html_file.empty?
|
|
55
|
+
if html_file.empty?
|
|
56
56
|
results[:pages_unprocessed] += 1
|
|
57
57
|
results[:unprocessed_pages] << path
|
|
58
58
|
next
|
|
59
59
|
end
|
|
60
60
|
|
|
61
|
+
rewritten_html_file = @selma.rewrite(html_file)
|
|
62
|
+
|
|
61
63
|
# drops the first 3 parts of the path, which are "tmp", "vore", and the site name
|
|
62
64
|
url_path = path.split(FILE_SEPERATOR)[3..].join("/")
|
|
63
65
|
|
data/lib/vore/version.rb
CHANGED