arb-crawler 1.0.0
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-crawler.gemspec +29 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/arb/crawler/version.rb +5 -0
- data/lib/arb/crawler.rb +67 -0
- metadata +122 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 1edbf13a9ded81eb25cf49a3d8f42abf38d86f0f
|
4
|
+
data.tar.gz: fef12e014d16904d3b5c7b99bdbfc30125985b22
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 6938b1e9a8b5270dd7068e9d5c541548905c9ce63259d3b32b80b0a924da79e804c03f155915657d1f8d83eb0ecb25c11a9179397cf6fe53361e89dbc57b7def
|
7
|
+
data.tar.gz: f603f483c106a317df770b49bd14ca6d08163ae73208cfb82b23aa58798a6f9647dc05b2ff257a3b4550f2689e11d34b0b695fa028b5fd08dc306bc581bfd428
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
# Arb::Crawler
|
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/crawler`. 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-crawler'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install arb-crawler
|
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-crawler.
|
36
|
+
|
data/Rakefile
ADDED
data/arb-crawler.gemspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'arb/crawler/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "arb-crawler"
|
8
|
+
spec.version = Arb::Crawler::VERSION
|
9
|
+
spec.authors = ["arybin"]
|
10
|
+
spec.email = ["arybin@163.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Web page crawler.}
|
13
|
+
spec.description = %q{Web page crawler.}
|
14
|
+
spec.homepage = "https://github.com/arybin-cn/arb-crawler"
|
15
|
+
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
18
|
+
f.match(%r{^(test|spec|features)/})
|
19
|
+
end
|
20
|
+
spec.bindir = "exe"
|
21
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
22
|
+
spec.require_paths = ["lib"]
|
23
|
+
|
24
|
+
spec.add_development_dependency "bundler", "~> 1.14"
|
25
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
26
|
+
spec.add_dependency "arb-str"
|
27
|
+
spec.add_dependency "nokogiri"
|
28
|
+
spec.add_dependency "httpclient"
|
29
|
+
end
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "arb/crawler"
|
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/lib/arb/crawler.rb
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
require "arb/crawler/version"
|
2
|
+
|
3
|
+
require 'nokogiri'
|
4
|
+
require 'httpclient'
|
5
|
+
require 'arb/str'
|
6
|
+
|
7
|
+
module Arb
|
8
|
+
module Crawler
|
9
|
+
class << self
|
10
|
+
client=HTTPClient.new
|
11
|
+
methods=%w{delete get post put}
|
12
|
+
ways=%w{css xpath}
|
13
|
+
|
14
|
+
define_method :default_client do
|
15
|
+
client
|
16
|
+
end
|
17
|
+
|
18
|
+
define_method :filename_of_url do |url|
|
19
|
+
url && url[url.rindex('/')+1..-1]
|
20
|
+
end
|
21
|
+
|
22
|
+
define_method :download do |url,file|
|
23
|
+
begin
|
24
|
+
File.open file,'wb+' do |file|
|
25
|
+
file<<client.get(url).body
|
26
|
+
end
|
27
|
+
rescue Exception=>e
|
28
|
+
$stderr.puts e
|
29
|
+
false
|
30
|
+
end
|
31
|
+
true
|
32
|
+
end
|
33
|
+
|
34
|
+
methods.each do |method|
|
35
|
+
ways.each do |way|
|
36
|
+
define_method "#{method}_by_#{way}_raw" do |url,css_or_xpath,&blk|
|
37
|
+
::Nokogiri.parse(client.send(method,url).body).send(way,css_or_xpath).tap do |res|
|
38
|
+
if blk
|
39
|
+
res.each do |e|
|
40
|
+
blk[e]
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
define_method "#{method}_by_#{way}" do |url,css_or_xpath,&blk|
|
47
|
+
[].tap do |arr|
|
48
|
+
send("#{method}_by_#{way}_raw",url,css_or_xpath).each do |nokogiri_element|
|
49
|
+
arr<<Hash.new.tap do |hash|
|
50
|
+
nokogiri_element.attributes.keys.each do |key|
|
51
|
+
hash[key.to_sym]=nokogiri_element.attribute(key).value
|
52
|
+
end
|
53
|
+
hash.singleton_class.send :define_method, :text do
|
54
|
+
nokogiri_element.text
|
55
|
+
end
|
56
|
+
blk[e] if blk
|
57
|
+
end
|
58
|
+
end
|
59
|
+
end
|
60
|
+
end
|
61
|
+
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
end
|
67
|
+
end
|
metadata
ADDED
@@ -0,0 +1,122 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: arb-crawler
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- arybin
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-02-12 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-str
|
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
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: nokogiri
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: httpclient
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
description: Web page crawler.
|
84
|
+
email:
|
85
|
+
- arybin@163.com
|
86
|
+
executables: []
|
87
|
+
extensions: []
|
88
|
+
extra_rdoc_files: []
|
89
|
+
files:
|
90
|
+
- ".gitignore"
|
91
|
+
- Gemfile
|
92
|
+
- README.md
|
93
|
+
- Rakefile
|
94
|
+
- arb-crawler.gemspec
|
95
|
+
- bin/console
|
96
|
+
- bin/setup
|
97
|
+
- lib/arb/crawler.rb
|
98
|
+
- lib/arb/crawler/version.rb
|
99
|
+
homepage: https://github.com/arybin-cn/arb-crawler
|
100
|
+
licenses: []
|
101
|
+
metadata: {}
|
102
|
+
post_install_message:
|
103
|
+
rdoc_options: []
|
104
|
+
require_paths:
|
105
|
+
- lib
|
106
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
112
|
+
requirements:
|
113
|
+
- - ">="
|
114
|
+
- !ruby/object:Gem::Version
|
115
|
+
version: '0'
|
116
|
+
requirements: []
|
117
|
+
rubyforge_project:
|
118
|
+
rubygems_version: 2.4.8
|
119
|
+
signing_key:
|
120
|
+
specification_version: 4
|
121
|
+
summary: Web page crawler.
|
122
|
+
test_files: []
|