grucrawler 0.0.3 → 0.0.5
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/README.md +2 -0
- data/lib/grucrawler/queue.rb +3 -1
- data/lib/grucrawler/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 2f9257639bf846e766fbbba96ff192b70eb787f5
|
4
|
+
data.tar.gz: 761f391b0f3015b67acfef7d2dda40160f58859e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b92f0d90252eacca1c0125035678fa93a5f4cdd35f8ea8eab38212e570a211e9136616a725d834fe0af1b64e0b2cd3c61e6c1cdd751b81f387d36417c509fd1e
|
7
|
+
data.tar.gz: 6263c707c3838423916716e45231391f087ab67fb826661f0e57ba20aae9a04610b9a387301b8f968b8bede8097470493d014f68df668659614b0ebb50cf95b0
|
data/README.md
CHANGED
@@ -29,6 +29,8 @@ class ItalianCrawler
|
|
29
29
|
end
|
30
30
|
|
31
31
|
def follow_link(target_url, typhoeus_response, nokogiri_html)
|
32
|
+
return false if target_url.match(/\.(jpg|png|js|css|pdf|exe|dmg|zip|doc|rtf|rar|swf|bmp|swf|mp3|wav|mp4|mpg|flv|wma)$/)
|
33
|
+
|
32
34
|
return true if target_url.include? '.it'
|
33
35
|
|
34
36
|
false
|
data/lib/grucrawler/queue.rb
CHANGED
@@ -113,7 +113,9 @@ class GruCrawler
|
|
113
113
|
return nil if uri.host.nil?
|
114
114
|
host = uri.host.downcase
|
115
115
|
host = host.start_with?('www.') ? host[4..-1] : host
|
116
|
-
host.match(/\w+\.\w+$/)
|
116
|
+
match = [host.match(/\w+\.\w+$/)]
|
117
|
+
return nil unless match
|
118
|
+
match[0]
|
117
119
|
end
|
118
120
|
end
|
119
121
|
end
|
data/lib/grucrawler/version.rb
CHANGED