rfsp 0.9.0
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 +17 -0
- data/.rspec +2 -0
- data/Gemfile +2 -0
- data/LICENSE.txt +22 -0
- data/README.md +37 -0
- data/Rakefile +8 -0
- data/lib/rfsp.rb +10 -0
- data/lib/rfsp/client.rb +18 -0
- data/lib/rfsp/fl.rb +46 -0
- data/lib/rfsp/freelansim.rb +51 -0
- data/lib/rfsp/version.rb +3 -0
- data/lib/rfsp/weblancer.rb +46 -0
- data/rfsp.gemspec +32 -0
- data/spec/rfsp/fl_spec.rb +19 -0
- data/spec/spec_helper.rb +8 -0
- metadata +201 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 7de216178f224cec07a036bc0cd0acfc73c137cd
|
4
|
+
data.tar.gz: a1bf51d69f55ed977601bf2796f54ed9971cb42b
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b20aa78fc5213162cdfc3042e5dc51f3626cbc2067eed32547ebd8cf41d7a0a2eb152b1f62ceca3d87a737e5a983443e3776196990a29d584d232b3dc3db210f
|
7
|
+
data.tar.gz: 33ba15273b3b6a6850e4d960fb928b4deabe8538c3d57d037fc47a2de22340187eec755a93a4905f388558f32f6d6bf1cd4561050e6d04c2593ac02e612732aa
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Leonid
|
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 +1,37 @@
|
|
1
|
+
# RFSP
|
2
|
+
|
3
|
+
Loads RSS from www.fl.ru, www.weblancer.net, freelansim.ru and normalize project info.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
$ gem install rfsp
|
8
|
+
|
9
|
+
## Usage
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
|
13
|
+
projects = RFSP::Fl.parse_rss
|
14
|
+
projects = RFSP::Weblancer.parse_rss
|
15
|
+
projects = RFSP::Freelansim.parse_rss
|
16
|
+
```
|
17
|
+
|
18
|
+
Project contains info:
|
19
|
+
|
20
|
+
1. `uri`
|
21
|
+
1. `id`
|
22
|
+
1. `published`
|
23
|
+
1. `title`
|
24
|
+
1. `body`
|
25
|
+
1. `category` - ex. `Дизайн / Логотипы, Дизайн / Фирменный стиль`, not availiable for freelansim.ru
|
26
|
+
1. `budget`
|
27
|
+
1. `origin` - originally parsed string
|
28
|
+
2. `amount` - integer
|
29
|
+
3. `currency` - ex. 'rur, 'usd'
|
30
|
+
1. `tags` - only for freelansim.ru
|
31
|
+
|
32
|
+
For freelansim to get budget and tags you should call `RFSP::Freelansim.parse_page project` - it'll get info from project page.
|
33
|
+
|
34
|
+
Each class have methods:
|
35
|
+
|
36
|
+
* `::feed` - returns feed parsed by Feedjira
|
37
|
+
* `::update` - reloads cached feed
|
data/Rakefile
ADDED
data/lib/rfsp.rb
ADDED
data/lib/rfsp/client.rb
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
require 'rest_client'
|
3
|
+
require 'open-uri'
|
4
|
+
require 'feedjira'
|
5
|
+
|
6
|
+
class RFSP::Client
|
7
|
+
UA = 'Mozilla/5.0 (Windows NT 5.1; rv:31.0) Gecko/20100101 Firefox/31.0'
|
8
|
+
|
9
|
+
def self.get uri
|
10
|
+
# response = RestClient.get(uri, user_agent: UA)
|
11
|
+
# raise "Response code is #{response.code}" if response.code != 200
|
12
|
+
Nokogiri::HTML open(uri, "User-Agent" => UA)
|
13
|
+
end
|
14
|
+
|
15
|
+
def self.feed uri
|
16
|
+
Feedjira::Feed.fetch_and_parse uri, user_agent: UA
|
17
|
+
end
|
18
|
+
end
|
data/lib/rfsp/fl.rb
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
require_relative 'client'
|
2
|
+
require 'ostruct'
|
3
|
+
|
4
|
+
class RFSP::Fl
|
5
|
+
RSS_URI = 'https://www.fl.ru/rss/all.xml'
|
6
|
+
|
7
|
+
class << self
|
8
|
+
|
9
|
+
def parse_rss
|
10
|
+
projects = []
|
11
|
+
feed.entries.each do |e|
|
12
|
+
p = OpenStruct.new
|
13
|
+
p.uri = e.url
|
14
|
+
p.id = e.url.match(/(\d+)/)[1].to_i
|
15
|
+
p.published = e.published
|
16
|
+
p.body = e.summary
|
17
|
+
p.title = e.title
|
18
|
+
p.site = 'fl'
|
19
|
+
p.category = e.categories.map{|c| c.gsub(/<\/?.+?>/, '')}.join ', '
|
20
|
+
budget_regexp = / \(Бюджет: (\d+) +(руб|\$)\.?\)\Z/
|
21
|
+
if m = p.title.match(budget_regexp)
|
22
|
+
budget = OpenStruct.new
|
23
|
+
budget.origin = m[0]
|
24
|
+
budget.origin[' ('] = ''
|
25
|
+
budget.origin[')'] = ''
|
26
|
+
budget.amount = m[1].to_i
|
27
|
+
budget.currency = m[2] == '$' ? 'usd' : m[2] == 'руб' ? 'rur' : nil
|
28
|
+
p.budget = budget
|
29
|
+
p.title.sub! budget_regexp, ''
|
30
|
+
end
|
31
|
+
projects << p
|
32
|
+
end
|
33
|
+
projects
|
34
|
+
end
|
35
|
+
|
36
|
+
def feed
|
37
|
+
@@feed ||= update
|
38
|
+
end
|
39
|
+
|
40
|
+
def update
|
41
|
+
@@feed = RFSP::Client.feed RSS_URI
|
42
|
+
end
|
43
|
+
|
44
|
+
end
|
45
|
+
|
46
|
+
end
|
@@ -0,0 +1,51 @@
|
|
1
|
+
require_relative 'client'
|
2
|
+
require 'ostruct'
|
3
|
+
|
4
|
+
class RFSP::Freelansim
|
5
|
+
RSS_URI = 'http://freelansim.ru/rss/tasks'
|
6
|
+
|
7
|
+
class << self
|
8
|
+
|
9
|
+
def parse_rss
|
10
|
+
projects = []
|
11
|
+
feed.entries.each do |e|
|
12
|
+
p = OpenStruct.new
|
13
|
+
p.uri = e.url
|
14
|
+
p.id = e.url.match(/(\d+)/)[1].to_i
|
15
|
+
p.published = e.published
|
16
|
+
p.body = e.summary
|
17
|
+
p.title = e.title
|
18
|
+
p.site = 'freelansim'
|
19
|
+
projects << p
|
20
|
+
end
|
21
|
+
projects
|
22
|
+
end
|
23
|
+
|
24
|
+
|
25
|
+
def parse_budget_and_tags project
|
26
|
+
doc = RFSP::Client.get project.uri
|
27
|
+
price = doc.search('.task__price .count').first
|
28
|
+
if price
|
29
|
+
budget = OpenStruct.new
|
30
|
+
budget.origin = price.text
|
31
|
+
budget.amount = budget.origin.match(/([\d ]+)/)[1].gsub(' ', '').to_i
|
32
|
+
budget.currency = 'rur' if budget.origin['руб.']
|
33
|
+
end
|
34
|
+
project.budget = budget
|
35
|
+
project.tags = doc.search('.tags a').map(&:text).join ', '
|
36
|
+
project
|
37
|
+
end
|
38
|
+
|
39
|
+
alias :parse_page :parse_budget_and_tags
|
40
|
+
|
41
|
+
def feed
|
42
|
+
@@feed ||= update
|
43
|
+
end
|
44
|
+
|
45
|
+
def update
|
46
|
+
@@feed = RFSP::Client.feed RSS_URI
|
47
|
+
end
|
48
|
+
|
49
|
+
end
|
50
|
+
|
51
|
+
end
|
data/lib/rfsp/version.rb
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
require_relative 'client'
|
2
|
+
require 'ostruct'
|
3
|
+
require 'nokogiri'
|
4
|
+
|
5
|
+
class RFSP::Weblancer
|
6
|
+
RSS_URI = 'http://www.weblancer.net/rss/projects.rss'
|
7
|
+
|
8
|
+
class << self
|
9
|
+
|
10
|
+
def parse_rss
|
11
|
+
projects = []
|
12
|
+
feed.entries.each do |e|
|
13
|
+
p = OpenStruct.new
|
14
|
+
p.site = 'weblancer'
|
15
|
+
p.uri = e.url
|
16
|
+
p.id = e.url.match(/(\d+)/)[1].to_i
|
17
|
+
p.published = e.published
|
18
|
+
p.body = e.summary
|
19
|
+
p.title = e.title
|
20
|
+
body_doc = Nokogiri::HTML p.body
|
21
|
+
p.category = body_doc.search('a').select{|c| c.attr('href')['projects/?category_id=']}.map(&:text).join ', '
|
22
|
+
if amount2 = body_doc.search('.amount_2').first
|
23
|
+
budget = OpenStruct.new
|
24
|
+
budget.origin = amount2.text
|
25
|
+
m = budget.origin.match(/(\d+) (\w+)/)
|
26
|
+
budget.amount = m[1].to_i
|
27
|
+
budget.currency = m[2].downcase
|
28
|
+
p.budget = budget
|
29
|
+
end
|
30
|
+
p.body.sub!(/\n.+<br \/><br \/>/, '')
|
31
|
+
projects << p
|
32
|
+
end
|
33
|
+
projects
|
34
|
+
end
|
35
|
+
|
36
|
+
def feed
|
37
|
+
@@feed ||= update
|
38
|
+
end
|
39
|
+
|
40
|
+
def update
|
41
|
+
@@feed = RFSP::Client.feed RSS_URI
|
42
|
+
end
|
43
|
+
|
44
|
+
end
|
45
|
+
|
46
|
+
end
|
data/rfsp.gemspec
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'rfsp/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'rfsp'
|
8
|
+
spec.version = RFSP::VERSION
|
9
|
+
spec.authors = ['Ibrahim Ivanko']
|
10
|
+
spec.email = ['ibrahim-ivanko@mdtlpr.com']
|
11
|
+
spec.summary = %q{Russian Freelance Site Parser}
|
12
|
+
spec.description = %q{Get projects from www.fl.ru www.weblancer.net freelansim.ru}
|
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_runtime_dependency 'rest_client', '~> 1.0'
|
22
|
+
spec.add_runtime_dependency 'nokogiri', '~> 1.0'
|
23
|
+
spec.add_runtime_dependency 'feedjira', '~> 1.0'
|
24
|
+
|
25
|
+
spec.add_development_dependency 'bundler', '~> 1.5'
|
26
|
+
spec.add_development_dependency 'rake'
|
27
|
+
spec.add_development_dependency 'pry'
|
28
|
+
spec.add_development_dependency 'rspec-core', '~> 3.0'
|
29
|
+
spec.add_development_dependency 'rspec-mocks'
|
30
|
+
spec.add_development_dependency 'rspec-expectations', '~> 3.0'
|
31
|
+
spec.add_development_dependency 'rr', '~> 1.0'
|
32
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe RFSP::Fl do
|
4
|
+
|
5
|
+
describe 'projects' do
|
6
|
+
let(:projects){RFSP::Fl.parse_rss}
|
7
|
+
it 'loads 30 projects from rss' do
|
8
|
+
expect(projects.count).to eq 60
|
9
|
+
end
|
10
|
+
|
11
|
+
it 'initilize id and uri of projects' do
|
12
|
+
expect(projects[0].id.class).to eq Fixnum
|
13
|
+
expect(projects[0].uri.class).to eq String
|
14
|
+
expect(projects[0].uri).to_not be_empty
|
15
|
+
expect(projects[0].id).to be > 0
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,201 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rfsp
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.9.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ibrahim Ivanko
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-07-24 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rest_client
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: nokogiri
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: feedjira
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: bundler
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.5'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.5'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rake
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: pry
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: rspec-core
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '3.0'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '3.0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: rspec-mocks
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ">="
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ">="
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '0'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: rspec-expectations
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - "~>"
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '3.0'
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - "~>"
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '3.0'
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: rr
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - "~>"
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '1.0'
|
146
|
+
type: :development
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - "~>"
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '1.0'
|
153
|
+
description: Get projects from www.fl.ru www.weblancer.net freelansim.ru
|
154
|
+
email:
|
155
|
+
- ibrahim-ivanko@mdtlpr.com
|
156
|
+
executables: []
|
157
|
+
extensions: []
|
158
|
+
extra_rdoc_files: []
|
159
|
+
files:
|
160
|
+
- ".gitignore"
|
161
|
+
- ".rspec"
|
162
|
+
- Gemfile
|
163
|
+
- LICENSE.txt
|
164
|
+
- README.md
|
165
|
+
- Rakefile
|
166
|
+
- lib/rfsp.rb
|
167
|
+
- lib/rfsp/client.rb
|
168
|
+
- lib/rfsp/fl.rb
|
169
|
+
- lib/rfsp/freelansim.rb
|
170
|
+
- lib/rfsp/version.rb
|
171
|
+
- lib/rfsp/weblancer.rb
|
172
|
+
- rfsp.gemspec
|
173
|
+
- spec/rfsp/fl_spec.rb
|
174
|
+
- spec/spec_helper.rb
|
175
|
+
homepage: ''
|
176
|
+
licenses:
|
177
|
+
- MIT
|
178
|
+
metadata: {}
|
179
|
+
post_install_message:
|
180
|
+
rdoc_options: []
|
181
|
+
require_paths:
|
182
|
+
- lib
|
183
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
184
|
+
requirements:
|
185
|
+
- - ">="
|
186
|
+
- !ruby/object:Gem::Version
|
187
|
+
version: '0'
|
188
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
189
|
+
requirements:
|
190
|
+
- - ">="
|
191
|
+
- !ruby/object:Gem::Version
|
192
|
+
version: '0'
|
193
|
+
requirements: []
|
194
|
+
rubyforge_project:
|
195
|
+
rubygems_version: 2.2.2
|
196
|
+
signing_key:
|
197
|
+
specification_version: 4
|
198
|
+
summary: Russian Freelance Site Parser
|
199
|
+
test_files:
|
200
|
+
- spec/rfsp/fl_spec.rb
|
201
|
+
- spec/spec_helper.rb
|