krawler 1.0.4 → 1.0.5
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/krawler/version.rb +1 -1
- data/lib/krawler.rb +4 -1
- metadata +4 -4
data/lib/krawler/version.rb
CHANGED
data/lib/krawler.rb
CHANGED
|
@@ -3,7 +3,7 @@ require 'mechanize'
|
|
|
3
3
|
require 'timeout'
|
|
4
4
|
require 'uri'
|
|
5
5
|
require 'thread'
|
|
6
|
-
|
|
6
|
+
require 'pry'
|
|
7
7
|
module Krawler
|
|
8
8
|
|
|
9
9
|
class Base
|
|
@@ -67,6 +67,9 @@ module Krawler
|
|
|
67
67
|
end
|
|
68
68
|
|
|
69
69
|
def crawl_page(link, agent)
|
|
70
|
+
link = link.to_s.gsub(/per_page=36/, '')
|
|
71
|
+
link = link =~ /(.*)(page=\d)/ ? "#{$1}per_page=36&#{$2}" : "#{link}?per_page=36&page=1"
|
|
72
|
+
|
|
70
73
|
@crawled_links << link
|
|
71
74
|
|
|
72
75
|
begin
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: krawler
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.0.
|
|
4
|
+
version: 1.0.5
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,11 +9,11 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2012-07-
|
|
12
|
+
date: 2012-07-27 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: mechanize
|
|
16
|
-
requirement: &
|
|
16
|
+
requirement: &70180957485360 !ruby/object:Gem::Requirement
|
|
17
17
|
none: false
|
|
18
18
|
requirements:
|
|
19
19
|
- - ~>
|
|
@@ -21,7 +21,7 @@ dependencies:
|
|
|
21
21
|
version: 2.5.0
|
|
22
22
|
type: :runtime
|
|
23
23
|
prerelease: false
|
|
24
|
-
version_requirements: *
|
|
24
|
+
version_requirements: *70180957485360
|
|
25
25
|
description: Simple little website crawler.
|
|
26
26
|
email:
|
|
27
27
|
- mike@urlgonomics.com
|