arachnid 0.2.2 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/arachnid.rb +13 -4
- metadata +70 -58
data/lib/arachnid.rb
CHANGED
@@ -47,7 +47,7 @@ class Arachnid
|
|
47
47
|
links = Nokogiri::HTML.parse(response.body).xpath('.//a/@href')
|
48
48
|
|
49
49
|
links.each do |link|
|
50
|
-
if(internal_link?(link) && !@global_visited.include?(split_url_at_hash(link)) && no_hash_in_url?(link) && no_image_in_url?(link))
|
50
|
+
if(internal_link?(link, response.effective_url) && !@global_visited.include?(split_url_at_hash(link)) && no_hash_in_url?(link) && no_image_in_url?(link))
|
51
51
|
|
52
52
|
sanitized_link = sanitize_link(split_url_at_hash(link))
|
53
53
|
if(sanitized_link)
|
@@ -83,15 +83,23 @@ class Arachnid
|
|
83
83
|
|
84
84
|
begin
|
85
85
|
parsed_domain = Domainatrix.parse(url)
|
86
|
-
|
86
|
+
|
87
|
+
if(parsed_domain.subdomain != "")
|
88
|
+
parsed_domain.subdomain + '.' + parsed_domain.domain + '.' + parsed_domain.public_suffix
|
89
|
+
else
|
90
|
+
parsed_domain.domain + '.' + parsed_domain.public_suffix
|
91
|
+
end
|
87
92
|
rescue NoMethodError, Addressable::URI::InvalidURIError => e
|
88
93
|
puts "URL Parsing Exception (#{url}): #{e}" if @debug == true
|
89
94
|
return nil
|
90
95
|
end
|
91
96
|
end
|
92
97
|
|
93
|
-
def internal_link?(url)
|
94
|
-
|
98
|
+
def internal_link?(url, effective_url)
|
99
|
+
|
100
|
+
absolute_url = make_absolute(url, effective_url)
|
101
|
+
|
102
|
+
parsed_url = parse_domain(absolute_url)
|
95
103
|
if(@domain == parsed_url)
|
96
104
|
return true
|
97
105
|
else
|
@@ -117,6 +125,7 @@ class Arachnid
|
|
117
125
|
end
|
118
126
|
|
119
127
|
def no_image_in_url?(url)
|
128
|
+
return true if url.to_s.length == 0
|
120
129
|
return true unless @exclude_urls_with_images
|
121
130
|
|
122
131
|
extensions = ['.jpg', '.gif', '.png', '.jpeg']
|
metadata
CHANGED
@@ -1,99 +1,111 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: arachnid
|
3
|
-
version: !ruby/object:Gem::Version
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.3.0
|
4
5
|
prerelease:
|
5
|
-
version: 0.2.2
|
6
6
|
platform: ruby
|
7
|
-
authors:
|
7
|
+
authors:
|
8
8
|
- dchuk
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
dependencies:
|
16
|
-
- !ruby/object:Gem::Dependency
|
12
|
+
date: 2014-01-16 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
17
15
|
name: typhoeus
|
18
|
-
|
19
|
-
requirement: &id001 !ruby/object:Gem::Requirement
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
20
17
|
none: false
|
21
|
-
requirements:
|
22
|
-
- -
|
23
|
-
- !ruby/object:Gem::Version
|
18
|
+
requirements:
|
19
|
+
- - '='
|
20
|
+
- !ruby/object:Gem::Version
|
24
21
|
version: 0.3.2
|
25
22
|
type: :runtime
|
26
|
-
version_requirements: *id001
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
name: bloomfilter-rb
|
29
23
|
prerelease: false
|
30
|
-
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - '='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 0.3.2
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: bloomfilter-rb
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
31
33
|
none: false
|
32
|
-
requirements:
|
33
|
-
- -
|
34
|
-
- !ruby/object:Gem::Version
|
34
|
+
requirements:
|
35
|
+
- - '='
|
36
|
+
- !ruby/object:Gem::Version
|
35
37
|
version: 2.1.1
|
36
38
|
type: :runtime
|
37
|
-
version_requirements: *id002
|
38
|
-
- !ruby/object:Gem::Dependency
|
39
|
-
name: nokogiri
|
40
39
|
prerelease: false
|
41
|
-
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - '='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: 2.1.1
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: nokogiri
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
42
49
|
none: false
|
43
|
-
requirements:
|
44
|
-
- -
|
45
|
-
- !ruby/object:Gem::Version
|
50
|
+
requirements:
|
51
|
+
- - '='
|
52
|
+
- !ruby/object:Gem::Version
|
46
53
|
version: 1.5.0
|
47
54
|
type: :runtime
|
48
|
-
version_requirements: *id003
|
49
|
-
- !ruby/object:Gem::Dependency
|
50
|
-
name: domainatrix
|
51
55
|
prerelease: false
|
52
|
-
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - '='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 1.5.0
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: domainatrix
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
53
65
|
none: false
|
54
|
-
requirements:
|
55
|
-
- -
|
56
|
-
- !ruby/object:Gem::Version
|
66
|
+
requirements:
|
67
|
+
- - '='
|
68
|
+
- !ruby/object:Gem::Version
|
57
69
|
version: 0.0.10
|
58
70
|
type: :runtime
|
59
|
-
|
60
|
-
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - '='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: 0.0.10
|
78
|
+
description: Arachnid is a web crawler that relies on Bloom Filters to efficiently
|
79
|
+
store visited urls and Typhoeus to avoid the overhead of Mechanize when crawling
|
80
|
+
every page on a domain.
|
61
81
|
email: me@dchuk.com
|
62
82
|
executables: []
|
63
|
-
|
64
83
|
extensions: []
|
65
|
-
|
66
84
|
extra_rdoc_files: []
|
67
|
-
|
68
|
-
files:
|
85
|
+
files:
|
69
86
|
- lib/arachnid.rb
|
70
|
-
has_rdoc: true
|
71
87
|
homepage: https://github.com/dchuk/Arachnid
|
72
88
|
licenses: []
|
73
|
-
|
74
89
|
post_install_message:
|
75
90
|
rdoc_options: []
|
76
|
-
|
77
|
-
require_paths:
|
91
|
+
require_paths:
|
78
92
|
- lib
|
79
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
93
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
80
94
|
none: false
|
81
|
-
requirements:
|
82
|
-
- -
|
83
|
-
- !ruby/object:Gem::Version
|
84
|
-
version:
|
85
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
95
|
+
requirements:
|
96
|
+
- - ! '>='
|
97
|
+
- !ruby/object:Gem::Version
|
98
|
+
version: '0'
|
99
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
100
|
none: false
|
87
|
-
requirements:
|
88
|
-
- -
|
89
|
-
- !ruby/object:Gem::Version
|
90
|
-
version:
|
101
|
+
requirements:
|
102
|
+
- - ! '>='
|
103
|
+
- !ruby/object:Gem::Version
|
104
|
+
version: '0'
|
91
105
|
requirements: []
|
92
|
-
|
93
106
|
rubyforge_project:
|
94
|
-
rubygems_version: 1.
|
107
|
+
rubygems_version: 1.8.23
|
95
108
|
signing_key:
|
96
109
|
specification_version: 3
|
97
110
|
summary: Extremely fast and efficient domain spider
|
98
111
|
test_files: []
|
99
|
-
|