pba_crawler 0.0.7 → 0.0.8
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/lib/pba_crawler/generic.rb +6 -2
- data/lib/pba_crawler/version.rb +1 -1
- metadata +2 -2
data/lib/pba_crawler/generic.rb
CHANGED
|
@@ -12,12 +12,16 @@ module PbaCrawler
|
|
|
12
12
|
end
|
|
13
13
|
|
|
14
14
|
def crawl_url(url)
|
|
15
|
+
@@proxy = @@proxies.fetch(@@cursor)
|
|
16
|
+
|
|
17
|
+
p "#{url}|#{@@proxy.address}|#{@@proxy.port}"
|
|
18
|
+
|
|
15
19
|
agent = Mechanize.new { |a|
|
|
16
20
|
a.html_parser = Nokogiri::HTML
|
|
17
21
|
a.open_timeout = 20
|
|
18
22
|
a.read_timeout = 20
|
|
19
23
|
}
|
|
20
|
-
|
|
24
|
+
|
|
21
25
|
agent.set_proxy(@@proxy.address,@@proxy.port)
|
|
22
26
|
agent.user_agent = 'Mozilla/5.0 (Windows; U; Windows NT 6.1; nl; rv:1.9.2.13) Gecko/20101203 Firefox/3.6.13'
|
|
23
27
|
|
|
@@ -40,9 +44,9 @@ module PbaCrawler
|
|
|
40
44
|
|
|
41
45
|
def rescue_get_url(agent,url)
|
|
42
46
|
if @@cursor + 1 < @@proxies.size
|
|
43
|
-
p "#{agent.proxy_addr} #{agent.proxy_port}"
|
|
44
47
|
@@cursor = @@cursor + 1
|
|
45
48
|
@@proxy = @@proxies.fetch(@@cursor)
|
|
49
|
+
p "#{url}|#{@@proxy.address}|#{@@proxy.port}"
|
|
46
50
|
agent.set_proxy(@@proxy.address,@@proxy.port)
|
|
47
51
|
response = get_url(agent,url)
|
|
48
52
|
end
|
data/lib/pba_crawler/version.rb
CHANGED
metadata
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: pba_crawler
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
4
|
prerelease:
|
|
5
|
-
version: 0.0.
|
|
5
|
+
version: 0.0.8
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
8
8
|
- Pierre BASILE
|
|
@@ -10,7 +10,7 @@ autorequire:
|
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
12
|
|
|
13
|
-
date: 2011-
|
|
13
|
+
date: 2011-04-19 00:00:00 +02:00
|
|
14
14
|
default_executable:
|
|
15
15
|
dependencies:
|
|
16
16
|
- !ruby/object:Gem::Dependency
|