rcrawl 0.4.5 → 0.4.6
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.
- data/Rakefile +1 -1
- data/lib/rcrawl/crawler.rb +4 -0
- data/lib/rcrawl/version.rb +1 -1
- metadata +1 -1
data/Rakefile
CHANGED
data/lib/rcrawl/crawler.rb
CHANGED
|
@@ -27,6 +27,10 @@ module Rcrawl
|
|
|
27
27
|
# Get link
|
|
28
28
|
url_server
|
|
29
29
|
next unless robot_safe? @url
|
|
30
|
+
if @url.include? '#'
|
|
31
|
+
print "... Anchor link found, skipping..."
|
|
32
|
+
next
|
|
33
|
+
end
|
|
30
34
|
# Parse robots.txt, then download document if robot_safe
|
|
31
35
|
fetch_http(@url)
|
|
32
36
|
# Store raw HTML in variable to read/reread as needed
|
data/lib/rcrawl/version.rb
CHANGED