scrapey 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +29 -0
- data/Rakefile +2 -0
- data/lib/scrapey.rb +95 -0
- data/lib/scrapey/version.rb +3 -0
- data/scrapey.gemspec +21 -0
- metadata +53 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 P Guardiario
|
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 +1,29 @@
|
|
1
|
+
# Scrapey
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'scrapey'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install scrapey
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/lib/scrapey.rb
ADDED
@@ -0,0 +1,95 @@
|
|
1
|
+
require "scrapey/version"
|
2
|
+
require "scrapey/src/cache"
|
3
|
+
require "scrapey/src/database"
|
4
|
+
|
5
|
+
module Scrapey
|
6
|
+
BASEDIR = File.expand_path(File.dirname($0)).gsub(/\/src$/,'')
|
7
|
+
|
8
|
+
def get_or_post method, url, options={}, *args
|
9
|
+
agent = method == 'goto' ? @browser : @agent
|
10
|
+
_retries = options.delete :retries
|
11
|
+
_sleep = options.delete :sleep
|
12
|
+
begin
|
13
|
+
new_args = method, url
|
14
|
+
unless options.empty? && args.empty?
|
15
|
+
new_args << options
|
16
|
+
args.each{|arg| new_args << arg}
|
17
|
+
end
|
18
|
+
|
19
|
+
doc = load_cache(url) if @use_cache
|
20
|
+
return doc if doc
|
21
|
+
|
22
|
+
page = agent.send *new_args
|
23
|
+
save_cache(url, page.body) if @use_cache
|
24
|
+
|
25
|
+
#exit if Object.const_defined? :Ocra
|
26
|
+
page
|
27
|
+
rescue Exception => e
|
28
|
+
case
|
29
|
+
when defined? on_error
|
30
|
+
on_error e
|
31
|
+
get_or_post method, url, options, *args
|
32
|
+
when _retries && _retries > 0
|
33
|
+
puts "Error. Retries remaining: #{options[:retries]}"
|
34
|
+
sleep _sleep if _sleep
|
35
|
+
get_or_post method, url, options.merge({:retries => _retries - 1, :sleep => _sleep}), *args
|
36
|
+
else raise e
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
def get *args; get_or_post 'get', *args; end
|
42
|
+
def post *args; get_or_post 'post', *args; end
|
43
|
+
def head *args; get_or_post 'head', *args; end
|
44
|
+
def goto *args; get_or_post 'goto', *args; end
|
45
|
+
|
46
|
+
def set_proxy *args
|
47
|
+
@agent.set_proxy *args
|
48
|
+
end
|
49
|
+
|
50
|
+
def fields *args
|
51
|
+
@fields = args
|
52
|
+
end
|
53
|
+
|
54
|
+
def save item
|
55
|
+
unless @csv && !@csv.closed?
|
56
|
+
@csv = CSV.open @output, 'w'
|
57
|
+
@csv << @fields if @fields
|
58
|
+
end
|
59
|
+
case
|
60
|
+
when item.is_a?(Array) then @csv << item
|
61
|
+
when item.is_a?(Hash) then @csv << @fields.map{|f| item[f]}
|
62
|
+
else raise "unsupported type: #{item.class}"
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
def visited? url
|
67
|
+
@visited ||= []
|
68
|
+
return true if @visited.include? url
|
69
|
+
@visited << url
|
70
|
+
false
|
71
|
+
end
|
72
|
+
|
73
|
+
def ts
|
74
|
+
Time.now.to_i.to_s
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
include Scrapey
|
79
|
+
|
80
|
+
# some defaults that I like
|
81
|
+
@agent ||= Mechanize.new{|a| a.history.max_size = 10}
|
82
|
+
@agent.user_agent = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.56 Safari/536.5'
|
83
|
+
|
84
|
+
# defaulkt output file
|
85
|
+
@output = Time.now.strftime("#{BASEDIR}/Output/output_%Y_%m_%d_%H_%M_%S.csv")
|
86
|
+
|
87
|
+
# read config file
|
88
|
+
config_file = "#{BASEDIR}/config/config.yml"
|
89
|
+
@config = File.exists?(config_file) ? YAML::load(File.open(config_file)) : {}
|
90
|
+
|
91
|
+
if @config['database']
|
92
|
+
['active_record', @config['database']['adapter'], 'tzinfo', 'active_support/multibyte'].each{|lib| require lib}
|
93
|
+
ActiveRecord::Base.establish_connection(@config['database'])
|
94
|
+
end
|
95
|
+
|
data/scrapey.gemspec
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/scrapey/version', __FILE__)
|
3
|
+
|
4
|
+
gem 'mechanize'
|
5
|
+
gem 'json'
|
6
|
+
|
7
|
+
Gem::Specification.new do |gem|
|
8
|
+
gem.authors = ["P Guardiario"]
|
9
|
+
gem.email = ["pguardiario@gmail.com"]
|
10
|
+
gem.description = %q{A simple scraping framework}
|
11
|
+
gem.summary = %q{A simple scraping framework}
|
12
|
+
gem.homepage = ""
|
13
|
+
|
14
|
+
gem.files = `git ls-files`.split($\)
|
15
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
16
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
17
|
+
gem.name = "scrapey"
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
gem.version = Scrapey::VERSION
|
20
|
+
end
|
21
|
+
|
metadata
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: scrapey
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- P Guardiario
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-07-22 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: A simple scraping framework
|
15
|
+
email:
|
16
|
+
- pguardiario@gmail.com
|
17
|
+
executables: []
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- .gitignore
|
22
|
+
- Gemfile
|
23
|
+
- LICENSE
|
24
|
+
- README.md
|
25
|
+
- Rakefile
|
26
|
+
- lib/scrapey.rb
|
27
|
+
- lib/scrapey/version.rb
|
28
|
+
- scrapey.gemspec
|
29
|
+
homepage: ''
|
30
|
+
licenses: []
|
31
|
+
post_install_message:
|
32
|
+
rdoc_options: []
|
33
|
+
require_paths:
|
34
|
+
- lib
|
35
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
36
|
+
none: false
|
37
|
+
requirements:
|
38
|
+
- - ! '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
42
|
+
none: false
|
43
|
+
requirements:
|
44
|
+
- - ! '>='
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: '0'
|
47
|
+
requirements: []
|
48
|
+
rubyforge_project:
|
49
|
+
rubygems_version: 1.8.11
|
50
|
+
signing_key:
|
51
|
+
specification_version: 3
|
52
|
+
summary: A simple scraping framework
|
53
|
+
test_files: []
|