crawler_sample 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +30 -0
- data/Rakefile +1 -0
- data/crawler_sample.gemspec +24 -0
- data/lib/crawler_sample.rb +80 -0
- data/lib/crawler_sample/string.rb +14 -0
- data/lib/crawler_sample/url.rb +19 -0
- data/lib/crawler_sample/version.rb +3 -0
- metadata +67 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
ZTEyODc4NDZlMmE3MWYyYzM5YzUyYmQ5ZjlkMmEwZTAxNGQ3NWMwMQ==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
ZGE0ZTA0NzdhNTkwNGM5OWY4ZmE5NDU5ZWY5MjJmZjQzNWFjNjBjNw==
|
7
|
+
!binary "U0hBNTEy":
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
MGZmYmZlZTRkYmUxYWU5NjNlMjcyMGNmNTZhOWI4YjcxZmVkNzBlOThlNTFm
|
10
|
+
OTU1ZWUyYzY3MWE5MGU1ZmQyYTA3YWNlMTAyMTc0ODIzZTJjZTZmNjNlNWNj
|
11
|
+
MDJjNDY5ODFjZGFhN2NiZjc5YzQxOTNkMmU4OGY4NGUxNGMzYzk=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
NTI3ZWMxMTJkOWU1MzNhNDUzYTA2NzFmOWFlNTNlY2JjNjBkMjA0OWY5YjM1
|
14
|
+
NzMwMDE4YTI4MjVhOTgyN2ZkYTdjZjQ5YTg2Y2ZmNDAzMWM5ZTBlM2YzNzY3
|
15
|
+
YWVkMDc5YWJlZDRmMTc2MjVhZmFhN2ExYjViNTRjZmQ1MDJmN2I=
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Shigeki Doumae
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
# CrawlerSample
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'crawler_sample'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install crawler_sample
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
This gem is a web crawler sample code.
|
22
|
+
So I do not reccmmend that you use.
|
23
|
+
|
24
|
+
## Contributing
|
25
|
+
|
26
|
+
1. Fork it
|
27
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
28
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
29
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
30
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'crawler_sample/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "crawler_sample"
|
8
|
+
gem.version = CrawlerSample::VERSION
|
9
|
+
gem.authors = ["Shigeki Doumae"]
|
10
|
+
gem.email = ["shigeki.doumae@gmail.com"]
|
11
|
+
gem.description = %q{This gem is a web crawler sample code.So I don't reccmmend that you use.}
|
12
|
+
gem.summary = %q{This gem is a web crawler sample code.So I don't reccmmend that you use.}
|
13
|
+
gem.homepage = ""
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
|
20
|
+
gem.add_dependency "nokogiri", "~>1.5.6"
|
21
|
+
#gem.add_dependency "open-uri"
|
22
|
+
#gem.add_dependency "kconv"
|
23
|
+
|
24
|
+
end
|
@@ -0,0 +1,80 @@
|
|
1
|
+
require "crawler_sample/version"
|
2
|
+
require 'crawler_sample/url'
|
3
|
+
require 'crawler_sample/string'
|
4
|
+
require "nokogiri"
|
5
|
+
require "open-uri"
|
6
|
+
require 'kconv'
|
7
|
+
module CrawlerSample
|
8
|
+
# Your code goes here...
|
9
|
+
attr_accessor :top_url, :target_urls, :exclude_urls, :deep_flg, :delay, :stop_flg, :crawl_stop_count
|
10
|
+
|
11
|
+
def crawl(url=nil)
|
12
|
+
raise "URL is Blank" if url.nil?
|
13
|
+
self.target_urls=[url]
|
14
|
+
self.exclude_urls=[]
|
15
|
+
target_scheme=URI.parse(url).scheme
|
16
|
+
target_host=URI.parse(url).host
|
17
|
+
error_cnt=0
|
18
|
+
crawl_page_cnt=0
|
19
|
+
self.crawl_stop_count = 1000 if self.crawl_stop_count.to_i <= 0
|
20
|
+
loop do
|
21
|
+
begin
|
22
|
+
break if self.target_urls.empty? || self.stop_flg==true
|
23
|
+
url = self.target_urls.pop
|
24
|
+
self.exclude_urls << url
|
25
|
+
begin
|
26
|
+
p "SuccessURL #{url}"
|
27
|
+
site_contents = self.scrape(url)
|
28
|
+
crawl_page_cnt += 1
|
29
|
+
rescue
|
30
|
+
p "ErrorURL #{url}"
|
31
|
+
end
|
32
|
+
site_contents.search("a").each do|anc|
|
33
|
+
#ホスト名がtargetのホストと違う場合はクロール対象外にする
|
34
|
+
begin; URI.parse(anc["href"]).host; rescue; next; end
|
35
|
+
next unless anc["href"].scan(/\.(jpg|jpeg|png|gif|bmp|zip|exe|pdf|lzh)/i).empty?
|
36
|
+
next if URI.parse(anc["href"]).host && target_host!=URI.parse(anc["href"]).host
|
37
|
+
anc["href"] = URI.parse(anc["href"]).path if URI.parse(anc["href"]).host
|
38
|
+
anc["href"] = anc["href"].gsub(/\/\.{1,2}/,"")
|
39
|
+
anc["href"] = "/#{anc["href"]}" if anc["href"][0] != "/"
|
40
|
+
self.target_urls << "#{target_scheme}://#{target_host}#{anc["href"]}".gsub(/\/\.{1,2}/,"")
|
41
|
+
self.target_urls = (self.target_urls - self.exclude_urls).uniq
|
42
|
+
end
|
43
|
+
yield site_contents
|
44
|
+
rescue => e
|
45
|
+
error_cnt +=1
|
46
|
+
p "error #{error_cnt} #{e}"
|
47
|
+
next
|
48
|
+
end
|
49
|
+
crawl_is_force_stop if error_cnt > 200 || crawl_page_cnt > self.crawl_stop_count
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def crawl_is_force_stop
|
54
|
+
self.stop_flg=true
|
55
|
+
end
|
56
|
+
|
57
|
+
def crawl_from_url(url=nil)
|
58
|
+
raise "URL is Blank" if url.nil?
|
59
|
+
site_contents = self.scrape(url)
|
60
|
+
return if site_contents.nil?
|
61
|
+
yield site_contents
|
62
|
+
end
|
63
|
+
|
64
|
+
def crawl_delay=(delay=nil)
|
65
|
+
self.delay= delay.nil? ? 1 : delay
|
66
|
+
end
|
67
|
+
|
68
|
+
def crawl_delay
|
69
|
+
return self.delay.nil? ? 1 : self.delay
|
70
|
+
end
|
71
|
+
|
72
|
+
def scrape(url, option={})
|
73
|
+
#self.delay = option[:delay].present? ? option[:delay] : 1
|
74
|
+
sleep self.crawl_delay #delay
|
75
|
+
html=open(url,"r:binary","User-Agent"=>"Blue Field 0.5.0.1" ).read
|
76
|
+
return Nokogiri::HTML(html.toutf8, nil, 'utf-8')
|
77
|
+
rescue
|
78
|
+
raise FaildScrape
|
79
|
+
end
|
80
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
class Url
|
2
|
+
attr_accessor :scheme, :host, :value
|
3
|
+
def initialize(values = {})
|
4
|
+
values.each do |k, v|
|
5
|
+
self.send("#{k}=", v)
|
6
|
+
end
|
7
|
+
end
|
8
|
+
|
9
|
+
def valid?
|
10
|
+
begin
|
11
|
+
uri = URI.parse(self.value)
|
12
|
+
resp = uri.kind_of?(URI::HTTP)
|
13
|
+
return resp
|
14
|
+
rescue URI::InvalidURIError
|
15
|
+
return false
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
end
|
metadata
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: crawler_sample
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Shigeki Doumae
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-06-11 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nokogiri
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 1.5.6
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 1.5.6
|
27
|
+
description: This gem is a web crawler sample code.So I don't reccmmend that you use.
|
28
|
+
email:
|
29
|
+
- shigeki.doumae@gmail.com
|
30
|
+
executables: []
|
31
|
+
extensions: []
|
32
|
+
extra_rdoc_files: []
|
33
|
+
files:
|
34
|
+
- .gitignore
|
35
|
+
- Gemfile
|
36
|
+
- LICENSE.txt
|
37
|
+
- README.md
|
38
|
+
- Rakefile
|
39
|
+
- crawler_sample.gemspec
|
40
|
+
- lib/crawler_sample.rb
|
41
|
+
- lib/crawler_sample/string.rb
|
42
|
+
- lib/crawler_sample/url.rb
|
43
|
+
- lib/crawler_sample/version.rb
|
44
|
+
homepage: ''
|
45
|
+
licenses: []
|
46
|
+
metadata: {}
|
47
|
+
post_install_message:
|
48
|
+
rdoc_options: []
|
49
|
+
require_paths:
|
50
|
+
- lib
|
51
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
52
|
+
requirements:
|
53
|
+
- - ! '>='
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: '0'
|
56
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - ! '>='
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '0'
|
61
|
+
requirements: []
|
62
|
+
rubyforge_project:
|
63
|
+
rubygems_version: 2.0.3
|
64
|
+
signing_key:
|
65
|
+
specification_version: 4
|
66
|
+
summary: This gem is a web crawler sample code.So I don't reccmmend that you use.
|
67
|
+
test_files: []
|