arb-bs 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/Gemfile +4 -0
- data/README.md +36 -0
- data/Rakefile +2 -0
- data/arb-bs.gemspec +27 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/exe/bs_pic +33 -0
- data/lib/arb/bs/version.rb +5 -0
- data/lib/arb/bs.rb +1 -0
- metadata +96 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 2a8da1d3d085af9aefaf5bb70c7815c8595e65dc
|
4
|
+
data.tar.gz: 086af94724d0d41d008d0d72237822ee74c9afd0
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 2c9ceaa9dd4f344fdc0f0c798bbe0c9f911b21beec3ebef63d91b852cc7007fe62dec050c840cf9d6d2b31b4142cee3af8fb93c50913444f7d3fb57db1368b07
|
7
|
+
data.tar.gz: 6eff3825d92b1d6d681fd0bcdb2cba4851777563fab715946afc802b2a20fd5960c6df08e790f98e6da6611e1829abbc82776c282457289d33c85541a19e3ec5
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
# Arb::Bs
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/arb/bs`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'arb-bs'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install arb-bs
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/arybin/arb-bs.
|
36
|
+
|
data/Rakefile
ADDED
data/arb-bs.gemspec
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'arb/bs/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "arb-bs"
|
8
|
+
spec.version = Arb::Bs::VERSION
|
9
|
+
spec.authors = ["arybin"]
|
10
|
+
spec.email = ["arybin@163.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{A demo of Web Crawler using arb-crawler}
|
13
|
+
spec.description = %q{A demo of Web Crawler using arb-crawler}
|
14
|
+
spec.homepage = "https://github.com/arybin-cn/arb-bs"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
17
|
+
f.match(%r{^(test|spec|features)/})
|
18
|
+
end
|
19
|
+
spec.bindir = "exe"
|
20
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
21
|
+
spec.require_paths = ["lib"]
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.14"
|
24
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
25
|
+
spec.add_dependency "arb-crawler"
|
26
|
+
|
27
|
+
end
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "arb/bs"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/exe/bs_pic
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'arb/crawler'
|
4
|
+
|
5
|
+
include Arb
|
6
|
+
|
7
|
+
domain='www.budejie.com'
|
8
|
+
map_file='map.txt'
|
9
|
+
max_page=ARGV.first || 50
|
10
|
+
|
11
|
+
File.open(map_file,'w+') unless File.exists? map_file
|
12
|
+
|
13
|
+
loop do
|
14
|
+
"http://#{domain}/pic/?".enum('?',1..max_page.to_i).each_with_index do |url,index|
|
15
|
+
Crawler.get_by_css(url,"div.j-r-list-c-img a img").each do |hash|
|
16
|
+
url_file=Crawler.filename_of_url(hash[:"data-original"])
|
17
|
+
unless File.readlines(map_file).find{|line| line.to_s.include? url_file}
|
18
|
+
if Crawler.download(hash[:"data-original"],url_file)
|
19
|
+
puts "#{hash[:'data-original']}\n#{hash[:title]}",''
|
20
|
+
File.open map_file,'a' do |file|
|
21
|
+
file.puts "#{url_file}:#{hash[:title]}"
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
tmp=1+rand(5)
|
27
|
+
puts "Page round finished for page #{index+1}, next action in #{tmp} seconds later."
|
28
|
+
sleep tmp
|
29
|
+
end
|
30
|
+
tmp=30+rand(30)
|
31
|
+
puts "Complete round finished, next action in #{tmp} seconds later."
|
32
|
+
sleep tmp
|
33
|
+
end
|
data/lib/arb/bs.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "arb/bs/version"
|
metadata
ADDED
@@ -0,0 +1,96 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: arb-bs
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- arybin
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-02-13 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.14'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.14'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: arb-crawler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
description: A demo of Web Crawler using arb-crawler
|
56
|
+
email:
|
57
|
+
- arybin@163.com
|
58
|
+
executables:
|
59
|
+
- bs_pic
|
60
|
+
extensions: []
|
61
|
+
extra_rdoc_files: []
|
62
|
+
files:
|
63
|
+
- ".gitignore"
|
64
|
+
- Gemfile
|
65
|
+
- README.md
|
66
|
+
- Rakefile
|
67
|
+
- arb-bs.gemspec
|
68
|
+
- bin/console
|
69
|
+
- bin/setup
|
70
|
+
- exe/bs_pic
|
71
|
+
- lib/arb/bs.rb
|
72
|
+
- lib/arb/bs/version.rb
|
73
|
+
homepage: https://github.com/arybin-cn/arb-bs
|
74
|
+
licenses: []
|
75
|
+
metadata: {}
|
76
|
+
post_install_message:
|
77
|
+
rdoc_options: []
|
78
|
+
require_paths:
|
79
|
+
- lib
|
80
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: '0'
|
85
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
requirements: []
|
91
|
+
rubyforge_project:
|
92
|
+
rubygems_version: 2.4.8
|
93
|
+
signing_key:
|
94
|
+
specification_version: 4
|
95
|
+
summary: A demo of Web Crawler using arb-crawler
|
96
|
+
test_files: []
|