links_crawler 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/links_crawler.rb +24 -0
- data/lib/links_crawler/model_instance_methods.rb +72 -0
- data/lib/links_crawler/version.rb +3 -0
- data/links_crawler.gemspec +20 -0
- metadata +48 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: c07bea8f84cb2543c550fb14f3d8482d7a960918
|
4
|
+
data.tar.gz: 11e05b8107486dfa22b004c97b867bd938ffffa7
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: d0bceaa69b62924ff60f1cb180d6b56b4c1df58b74fee4f635302471cc4fb6b6d35e90cbde94ad9c1af80e101c9bfe3cadd823aa8b97ac9cb83e240f6fbb4c39
|
7
|
+
data.tar.gz: 7a012812983be0597d5787547fc75ed4a6b63e63955dd13de5b51f92ca8c9b904224766e0751132e193fe038669f6a2dd68192aaeab739136130dfd1db5a94e7
|
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
|
3
|
+
module LinksCrawler #products list, feedbacks list
|
4
|
+
def self.included(recipient)
|
5
|
+
recipient.class_eval do
|
6
|
+
include ModelInstanceMethods
|
7
|
+
end
|
8
|
+
end
|
9
|
+
|
10
|
+
module ModelInstanceMethods
|
11
|
+
def import(target, importer)
|
12
|
+
case importer.origin
|
13
|
+
when "eBay"
|
14
|
+
extend Ebay::Importer
|
15
|
+
target_at_and_for target, importer
|
16
|
+
when "iOffer"
|
17
|
+
extend Ioffer::Importer
|
18
|
+
target_at_and_for target, importer
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end# instance methods
|
22
|
+
end
|
23
|
+
|
24
|
+
|
@@ -0,0 +1,72 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
|
3
|
+
module LinksCrawler
|
4
|
+
module ModelInstanceMethods
|
5
|
+
|
6
|
+
def fetch_links(dname,path)
|
7
|
+
uri = "http://#{dname}#{path}" unless dname.include?("http")
|
8
|
+
uri = URI(uri)
|
9
|
+
|
10
|
+
Net::HTTP.start(uri.host, uri.port) do |http|
|
11
|
+
request = Net::HTTP::Get.new uri
|
12
|
+
res = http.request request
|
13
|
+
str_body = res.body # proper argument
|
14
|
+
|
15
|
+
relative_links = str_body.scan(/href="[^(http|\.\.|#)].*?"/)
|
16
|
+
relative_links_path = relative_links.collect do |relative_link|
|
17
|
+
relative_link.delete("\"")[5..-1]
|
18
|
+
end
|
19
|
+
|
20
|
+
abs_links = str_body.scan(/href="http.*?"/).select do |href|
|
21
|
+
href.include? dname
|
22
|
+
end
|
23
|
+
abs_links_path = abs_links.collect do |abs_href|
|
24
|
+
URI(abs_href.delete("\"")[5..-1]).path
|
25
|
+
end
|
26
|
+
|
27
|
+
mixed_links = (relative_links_path + abs_links_path).uniq
|
28
|
+
mixed_links.each do |k|
|
29
|
+
tmp = k #.delete("\"")[5..-1]
|
30
|
+
if path == '/'
|
31
|
+
@arr_links << tmp
|
32
|
+
else
|
33
|
+
@arr_links.unshift tmp if is_valid_path?(tmp)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
def is_valid_path?(tmp)
|
40
|
+
!@arr_links.include?(tmp) && !tmp.include?("javascript") && !tmp.match(/css$/)
|
41
|
+
end
|
42
|
+
|
43
|
+
def traverse(dname)
|
44
|
+
root = '/'
|
45
|
+
fetch_links(dname,root)
|
46
|
+
#debugger
|
47
|
+
while link = @arr_links.shift
|
48
|
+
if !@traversed.include? link
|
49
|
+
@traversed << link
|
50
|
+
puts "dname #{dname} link #{link}"
|
51
|
+
begin
|
52
|
+
fetch_links(dname,link)
|
53
|
+
@arr_links.delete(link) # remove the link that having been traversed
|
54
|
+
rescue
|
55
|
+
@arr_links.delete(link) # remove the link that having been traversed
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
|
62
|
+
def search(dname)
|
63
|
+
@arr_links = []
|
64
|
+
@traversed = []
|
65
|
+
traverse(dname)
|
66
|
+
@traversed.each do |i|
|
67
|
+
puts "http://#{dname}" + i
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
end
|
72
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
#-*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "links_crawler/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "links_crawler"
|
7
|
+
s.version = LinksCrawler::VERSION
|
8
|
+
s.platform = Gem::Platform::RUBY
|
9
|
+
s.authors = ["wenbo"]
|
10
|
+
s.email = ["yiyun6674@hotmail.com"]
|
11
|
+
s.homepage = ""
|
12
|
+
s.summary = %q{check how many links are available inside the website}
|
13
|
+
s.description = <<-EOF
|
14
|
+
check how many links are available inside the website
|
15
|
+
EOF
|
16
|
+
|
17
|
+
s.files = `git ls-files`.split("\n")
|
18
|
+
s.test_files = `git ls-files -- {test}/*`.split("\n")
|
19
|
+
s.require_paths = ["lib"]
|
20
|
+
end
|
metadata
ADDED
@@ -0,0 +1,48 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: links_crawler
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- wenbo
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-06-02 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: |2
|
14
|
+
check how many links are available inside the website
|
15
|
+
email:
|
16
|
+
- yiyun6674@hotmail.com
|
17
|
+
executables: []
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- lib/links_crawler.rb
|
22
|
+
- lib/links_crawler/model_instance_methods.rb
|
23
|
+
- lib/links_crawler/version.rb
|
24
|
+
- links_crawler.gemspec
|
25
|
+
homepage: ''
|
26
|
+
licenses: []
|
27
|
+
metadata: {}
|
28
|
+
post_install_message:
|
29
|
+
rdoc_options: []
|
30
|
+
require_paths:
|
31
|
+
- lib
|
32
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
33
|
+
requirements:
|
34
|
+
- - '>='
|
35
|
+
- !ruby/object:Gem::Version
|
36
|
+
version: '0'
|
37
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - '>='
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '0'
|
42
|
+
requirements: []
|
43
|
+
rubyforge_project:
|
44
|
+
rubygems_version: 2.2.2
|
45
|
+
signing_key:
|
46
|
+
specification_version: 4
|
47
|
+
summary: check how many links are available inside the website
|
48
|
+
test_files: []
|