tiny_http_parser 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +22 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +40 -0
- data/Rakefile +2 -0
- data/lib/tiny_http_parser/fetcher_base.rb +54 -0
- data/lib/tiny_http_parser/fetcher_from_enum.rb +17 -0
- data/lib/tiny_http_parser/proxy_circular_list.rb +19 -0
- data/lib/tiny_http_parser/version.rb +3 -0
- data/lib/tiny_http_parser.rb +8 -0
- data/tiny_http_parser.gemspec +25 -0
- metadata +112 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 940dd59c3555a0a4df74ae5c8cd09c02aeb0dc14
|
4
|
+
data.tar.gz: 2d6e590dbc9498efce67a99fb9dd4d80754cb5a8
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: f4e01eae1592b96d23f6d1213537304d5941c4ff71b1c84a1201f6080a004b7a81687fdd1d8778e162df9a1598b2d4ed324dfc9133df86c6067123f42f493791
|
7
|
+
data.tar.gz: bb463c1506930fe1f9ca86813673121cb210d562af995001753f55bd7989e47114049dfefbfddb464f09cafe71f9059dcb55f440d3f1487bb0d709cff453b1d2
|
data/.gitignore
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
*.gem
|
2
|
+
*.rbc
|
3
|
+
.bundle
|
4
|
+
.config
|
5
|
+
.yardoc
|
6
|
+
Gemfile.lock
|
7
|
+
InstalledFiles
|
8
|
+
_yardoc
|
9
|
+
coverage
|
10
|
+
doc/
|
11
|
+
lib/bundler/man
|
12
|
+
pkg
|
13
|
+
rdoc
|
14
|
+
spec/reports
|
15
|
+
test/tmp
|
16
|
+
test/version_tmp
|
17
|
+
tmp
|
18
|
+
*.bundle
|
19
|
+
*.so
|
20
|
+
*.o
|
21
|
+
*.a
|
22
|
+
mkmf.log
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2015 gingray
|
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 +1,40 @@
|
|
1
|
+
# TinyHttpParser
|
2
|
+
|
3
|
+
Simple tool for fetching urls over internet
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'tiny_http_parser'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install tiny_http_parser
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
require 'tiny_parser'
|
22
|
+
|
23
|
+
fetcher = FetcherFromEnum.new ['http://ya.ru','http://google.com']
|
24
|
+
fetcher.on_content_get do |content|
|
25
|
+
puts '[+]'+ content.slice(0, 10)
|
26
|
+
end
|
27
|
+
|
28
|
+
fetcher.on_exception_raised do |e|
|
29
|
+
puts e
|
30
|
+
end
|
31
|
+
|
32
|
+
fetcher.perform
|
33
|
+
|
34
|
+
## Contributing
|
35
|
+
|
36
|
+
1. Fork it ( https://github.com/[my-github-username]/tiny_http_parser/fork )
|
37
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
38
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
39
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
40
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
require 'httpclient'
|
2
|
+
class FetcherBase
|
3
|
+
|
4
|
+
def initialize
|
5
|
+
raise 'abstract class'
|
6
|
+
end
|
7
|
+
|
8
|
+
def set_proxy &block
|
9
|
+
@proxy_block = block if block_given?
|
10
|
+
end
|
11
|
+
|
12
|
+
def proxy_set?
|
13
|
+
@proxy_block != nil
|
14
|
+
end
|
15
|
+
|
16
|
+
def get_proxy
|
17
|
+
@proxy_block.call
|
18
|
+
end
|
19
|
+
|
20
|
+
def parse_url
|
21
|
+
raise 'abstract method called exception'
|
22
|
+
end
|
23
|
+
|
24
|
+
def on_content_get &block
|
25
|
+
@content_block = block if block_given?
|
26
|
+
end
|
27
|
+
|
28
|
+
def configure &block
|
29
|
+
@configure_block = block if block_given?
|
30
|
+
end
|
31
|
+
|
32
|
+
def on_exception_raised &block
|
33
|
+
@exception_raised_block = block if block_given?
|
34
|
+
end
|
35
|
+
|
36
|
+
def perform
|
37
|
+
raise 'no on_content_get block given' unless @content_block
|
38
|
+
http_client = HTTPClient.new
|
39
|
+
http_client = HTTPClient.new(get_proxy) if proxy_set?
|
40
|
+
while true do
|
41
|
+
url = parse_url
|
42
|
+
break unless url
|
43
|
+
content_block.call(http_client) if @configure_block
|
44
|
+
begin
|
45
|
+
content = http_client.get_content url
|
46
|
+
rescue Exception => e
|
47
|
+
@exception_raised_block.call(e,url,http_client) if @exception_raised_block
|
48
|
+
else
|
49
|
+
@content_block.call content
|
50
|
+
end
|
51
|
+
http_client = HTTPClient.new(get_proxy) if proxy_set?
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
require_relative 'fetcher_base'
|
2
|
+
|
3
|
+
class FetcherFromEnum < FetcherBase
|
4
|
+
|
5
|
+
def initialize enumerable
|
6
|
+
@enumerable = enumerable.to_a
|
7
|
+
@counter = 0
|
8
|
+
end
|
9
|
+
|
10
|
+
def parse_url
|
11
|
+
return nil if @counter >= @enumerable.length
|
12
|
+
result = @enumerable[@counter]
|
13
|
+
@counter += 1
|
14
|
+
result
|
15
|
+
end
|
16
|
+
|
17
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
class ProxyCircularList
|
2
|
+
def initialize proxy_enum
|
3
|
+
@proxy_enum = proxy_enum.to_a
|
4
|
+
@counter = 0
|
5
|
+
end
|
6
|
+
|
7
|
+
def fetch
|
8
|
+
raise 'empty proxy list given' if @proxy_enum.length == 0
|
9
|
+
@counter = 0 if @counter >= @proxy_enum.length
|
10
|
+
result = @proxy_enum[@counter]
|
11
|
+
@counter +=1
|
12
|
+
puts result
|
13
|
+
result
|
14
|
+
end
|
15
|
+
|
16
|
+
def to_proc
|
17
|
+
Proc.new { fetch }
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'tiny_http_parser/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "tiny_http_parser"
|
8
|
+
spec.version = TinyHttpParser::VERSION
|
9
|
+
spec.authors = ["gingray"]
|
10
|
+
spec.email = ["gingray.dev@gmail.com"]
|
11
|
+
spec.summary = %q{simple tool to fecth data over internet}
|
12
|
+
spec.description = %q{if you have a lot of urls and you need pretty straight forward parsing this tool for you ;)}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.6"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
spec.add_development_dependency "rspec"
|
24
|
+
spec.add_dependency "httpclient"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,112 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: tiny_http_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- gingray
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-01-15 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: '1.6'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.6'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
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: httpclient
|
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
|
+
description: if you have a lot of urls and you need pretty straight forward parsing
|
70
|
+
this tool for you ;)
|
71
|
+
email:
|
72
|
+
- gingray.dev@gmail.com
|
73
|
+
executables: []
|
74
|
+
extensions: []
|
75
|
+
extra_rdoc_files: []
|
76
|
+
files:
|
77
|
+
- ".gitignore"
|
78
|
+
- Gemfile
|
79
|
+
- LICENSE.txt
|
80
|
+
- README.md
|
81
|
+
- Rakefile
|
82
|
+
- lib/tiny_http_parser.rb
|
83
|
+
- lib/tiny_http_parser/fetcher_base.rb
|
84
|
+
- lib/tiny_http_parser/fetcher_from_enum.rb
|
85
|
+
- lib/tiny_http_parser/proxy_circular_list.rb
|
86
|
+
- lib/tiny_http_parser/version.rb
|
87
|
+
- tiny_http_parser.gemspec
|
88
|
+
homepage: ''
|
89
|
+
licenses:
|
90
|
+
- MIT
|
91
|
+
metadata: {}
|
92
|
+
post_install_message:
|
93
|
+
rdoc_options: []
|
94
|
+
require_paths:
|
95
|
+
- lib
|
96
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
97
|
+
requirements:
|
98
|
+
- - ">="
|
99
|
+
- !ruby/object:Gem::Version
|
100
|
+
version: '0'
|
101
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- - ">="
|
104
|
+
- !ruby/object:Gem::Version
|
105
|
+
version: '0'
|
106
|
+
requirements: []
|
107
|
+
rubyforge_project:
|
108
|
+
rubygems_version: 2.4.5
|
109
|
+
signing_key:
|
110
|
+
specification_version: 4
|
111
|
+
summary: simple tool to fecth data over internet
|
112
|
+
test_files: []
|