grucrawler 0.0.2 → 0.0.3
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/README.md +2 -1
- data/lib/grucrawler/version.rb +1 -1
- data/lib/grucrawler.rb +5 -0
- 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: ed98643e2c2212bb044726cf3dda3af19a06ba8d
|
|
4
|
+
data.tar.gz: 70fadbce9333a32831ba5c5150916cecfeda5bf6
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 778c8ae783b46a8cb82448156da1741c4780d10148a673702071fe53ff896e587106dc66c54df52c642b8f29d5d69d16060cd20e2f6df466c6deece3cf0d8a0f
|
|
7
|
+
data.tar.gz: fcfb89156687d864a66f955d9c309b5ccbc0b2cd0a88a4b94802a1d5cab52d34399f73071f1783ca930f4df510e5dba617d25e30272d5d257c4e8dc522eb2f87
|
data/README.md
CHANGED
|
@@ -10,7 +10,8 @@ class ItalianCrawler
|
|
|
10
10
|
visit_urls_only_once: true,
|
|
11
11
|
follow_redirects: true,
|
|
12
12
|
concurrency: 5,
|
|
13
|
-
domain_wait: 20 # seconds between visits to the same domain
|
|
13
|
+
domain_wait: 20, # seconds between visits to the same domain
|
|
14
|
+
max_page_size: 1000000
|
|
14
15
|
}
|
|
15
16
|
end
|
|
16
17
|
|
data/lib/grucrawler/version.rb
CHANGED
data/lib/grucrawler.rb
CHANGED
|
@@ -56,6 +56,11 @@ class GruCrawler
|
|
|
56
56
|
|
|
57
57
|
crawl_more()
|
|
58
58
|
|
|
59
|
+
if response.body.length > (@options[:max_page_size] || 1000*1000*1000)
|
|
60
|
+
@crawler.debug("URL response size too big: #{response.body.length} from #{response.request.url}")
|
|
61
|
+
return
|
|
62
|
+
end
|
|
63
|
+
|
|
59
64
|
nokogiri = Nokogiri::HTML(response.body)
|
|
60
65
|
|
|
61
66
|
begin
|