ecfs 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/.travis.yml +3 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +54 -0
- data/Rakefile +11 -0
- data/ecfs.gemspec +26 -0
- data/lib/ecfs.rb +5 -0
- data/lib/ecfs/proceedings_query.rb +100 -0
- data/lib/ecfs/version.rb +3 -0
- data/test/helper.rb +17 -0
- data/test/test_proceedings_query.rb +53 -0
- metadata +126 -0
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Alan deLevie
|
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 +1,54 @@
|
|
1
|
+
# ECFS
|
2
|
+
|
3
|
+
ECFS helps you download and parse filings from the FCC's Electronic Comment Filing System.
|
4
|
+
|
5
|
+
[![Build Status](https://travis-ci.org/adelevie/ecfs.png?branch=master)](https://travis-ci.org/adelevie/ecfs)
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'ecfs'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
```sh
|
18
|
+
$ bundle
|
19
|
+
```
|
20
|
+
|
21
|
+
Or install it yourself as:
|
22
|
+
|
23
|
+
```sh
|
24
|
+
$ gem install ecfs
|
25
|
+
```
|
26
|
+
|
27
|
+
## Usage
|
28
|
+
|
29
|
+
```ruby
|
30
|
+
|
31
|
+
# get info about a specific proceeding
|
32
|
+
proceeding = ECFS::ProceedingsQuery.new.tap do |q|
|
33
|
+
q.eq("proceeding_number", "12-375")
|
34
|
+
end.get
|
35
|
+
#=>
|
36
|
+
{
|
37
|
+
"bureau_name" => "Wireline Competition Bureau",
|
38
|
+
"subject" =>
|
39
|
+
"Implementation of the Pay Telephone Reclassification and Compensation Provisions of the Telecommunications Act of 1996 et al.",
|
40
|
+
"prepared_by" => "Aleta.Bowers",
|
41
|
+
"date_created" => "12/26/2012",
|
42
|
+
"status" => "Open",
|
43
|
+
"total_filings" => "292",
|
44
|
+
"filings_in_last_30_days" => "58"
|
45
|
+
}
|
46
|
+
```
|
47
|
+
|
48
|
+
## Contributing
|
49
|
+
|
50
|
+
1. Fork it
|
51
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
52
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
53
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
54
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/ecfs.gemspec
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'ecfs/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "ecfs"
|
8
|
+
spec.version = ECFS::VERSION
|
9
|
+
spec.authors = ["Alan deLevie"]
|
10
|
+
spec.email = ["adelevie@gmail.com"]
|
11
|
+
spec.description = %q{ECFS provides a set of utilities for scraping FCC rulemakings}
|
12
|
+
spec.summary = %q{ECFS helps you obtain comments and other filings from the FCC's Electronic Comment Filing System}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
|
24
|
+
spec.add_dependency "mechanize"
|
25
|
+
spec.add_dependency "pry"
|
26
|
+
end
|
data/lib/ecfs.rb
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
require "mechanize"
|
2
|
+
|
3
|
+
module ECFS
|
4
|
+
|
5
|
+
class ProceedingsQuery
|
6
|
+
attr_reader :constraints
|
7
|
+
|
8
|
+
def initialize
|
9
|
+
@constraints = {}
|
10
|
+
end
|
11
|
+
|
12
|
+
def eq(field, value)
|
13
|
+
@constraints[field] = value
|
14
|
+
self
|
15
|
+
end
|
16
|
+
|
17
|
+
def constraints_dictionary
|
18
|
+
{
|
19
|
+
"docket_number" => "name",
|
20
|
+
"bureau_code" => "bureauCode",
|
21
|
+
"subject" => "subject",
|
22
|
+
"bureau_id" => "bureauIdentificationNumber",
|
23
|
+
"applicant" => "application",
|
24
|
+
"filed_by" => "filedBy",
|
25
|
+
"recent_filings" => "__checkbox_recentFilingsRequired",
|
26
|
+
"open_status" => "openStatus",
|
27
|
+
"created_after" => "created.minDate",
|
28
|
+
"created_before" => "created.maxDate",
|
29
|
+
"closed_after" => "closed.minDate",
|
30
|
+
"closed_before" => "closed.maxDate",
|
31
|
+
"callsign" => "callsign",
|
32
|
+
"channel" => "channel",
|
33
|
+
"rule_section" => "ruleSection",
|
34
|
+
"page_number" => "pageNumber"
|
35
|
+
}
|
36
|
+
end
|
37
|
+
|
38
|
+
def format_constraint(constraint)
|
39
|
+
constraints_dictionary[constraint]
|
40
|
+
end
|
41
|
+
|
42
|
+
def query_string
|
43
|
+
@constraints.keys.map do |constraint|
|
44
|
+
format_constraint(constraint) + "=" + @constraints[constraint]
|
45
|
+
end.join("&")
|
46
|
+
end
|
47
|
+
|
48
|
+
def url
|
49
|
+
base = "http://apps.fcc.gov/ecfs/proceeding_search/execute"
|
50
|
+
|
51
|
+
"#{base}?#{query_string}"
|
52
|
+
end
|
53
|
+
|
54
|
+
def get
|
55
|
+
if @constraints["docket_number"]
|
56
|
+
scrape_proceedings_page
|
57
|
+
else
|
58
|
+
scrape_results_page
|
59
|
+
end
|
60
|
+
end
|
61
|
+
|
62
|
+
private
|
63
|
+
|
64
|
+
def scrape_proceedings_page
|
65
|
+
agent = Mechanize.new
|
66
|
+
page = agent.get(url)
|
67
|
+
container = []
|
68
|
+
page.search("div").select do |d|
|
69
|
+
d.attributes["class"].nil? == false
|
70
|
+
end.select do |d|
|
71
|
+
d.attributes["class"].text == "wwgrp"
|
72
|
+
end.each do |node|
|
73
|
+
node.search("span").each do |span|
|
74
|
+
search = span.search("label")
|
75
|
+
pair = []
|
76
|
+
if search.length > 0
|
77
|
+
key = search.first.children.first.text.lstrip.rstrip.split(":")[0].gsub(" ", "_").downcase
|
78
|
+
pair << key
|
79
|
+
else
|
80
|
+
value = span.text.lstrip.rstrip
|
81
|
+
value.gsub!(",", "") if value.is_a?(String)
|
82
|
+
pair << value
|
83
|
+
end
|
84
|
+
container << pair
|
85
|
+
end
|
86
|
+
end
|
87
|
+
hash = {}
|
88
|
+
container.each_slice(2) do |chunk|
|
89
|
+
hash.merge!({chunk[0][0] => chunk[1][0]})
|
90
|
+
end
|
91
|
+
|
92
|
+
hash
|
93
|
+
end
|
94
|
+
|
95
|
+
def scrape_results_page
|
96
|
+
raise "Parsing result pages is not yet supported."
|
97
|
+
end
|
98
|
+
|
99
|
+
end
|
100
|
+
end
|
data/lib/ecfs/version.rb
ADDED
data/test/helper.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'bundler'
|
3
|
+
begin
|
4
|
+
Bundler.setup(:default, :development)
|
5
|
+
rescue Bundler::BundlerError => e
|
6
|
+
$stderr.puts e.message
|
7
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
8
|
+
exit e.status_code
|
9
|
+
end
|
10
|
+
|
11
|
+
|
12
|
+
require 'test/unit'
|
13
|
+
|
14
|
+
|
15
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
16
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
17
|
+
require 'ecfs'
|
@@ -0,0 +1,53 @@
|
|
1
|
+
require "helper"
|
2
|
+
require "pp"
|
3
|
+
|
4
|
+
class TestProceedingsQuery < Test::Unit::TestCase
|
5
|
+
def test_add_constraint
|
6
|
+
proceedings_query = ECFS::ProceedingsQuery.new
|
7
|
+
proceedings_query.eq("docket_number", "12-375")
|
8
|
+
proceedings_query.constraints
|
9
|
+
end
|
10
|
+
|
11
|
+
def test_constraints_dictionary
|
12
|
+
proceedings_query = ECFS::ProceedingsQuery.new
|
13
|
+
dictionary = proceedings_query.constraints_dictionary
|
14
|
+
assert_equal Hash, dictionary.class
|
15
|
+
end
|
16
|
+
|
17
|
+
def test_query_string
|
18
|
+
proceedings_query = ECFS::ProceedingsQuery.new
|
19
|
+
proceedings_query.eq("docket_number", "12-375")
|
20
|
+
proceedings_query.eq("subject", "phones")
|
21
|
+
assert_equal proceedings_query.query_string, "name=12-375&subject=phones"
|
22
|
+
end
|
23
|
+
|
24
|
+
def test_url
|
25
|
+
proceedings_query = ECFS::ProceedingsQuery.new
|
26
|
+
proceedings_query.eq("bureau_code", "WC")
|
27
|
+
proceedings_query.eq("subject", "phones")
|
28
|
+
url = "http://apps.fcc.gov/ecfs/proceeding_search/execute?bureauCode=WC&subject=phones"
|
29
|
+
assert_equal proceedings_query.url, url
|
30
|
+
end
|
31
|
+
|
32
|
+
def test_get_proceeding_info
|
33
|
+
proceedings_query = ECFS::ProceedingsQuery.new
|
34
|
+
proceedings_query.eq("docket_number", "12-375")
|
35
|
+
results = proceedings_query.get
|
36
|
+
%w[
|
37
|
+
bureau_name subject date_created status
|
38
|
+
total_filings filings_in_last_30_days
|
39
|
+
].each do |key|
|
40
|
+
assert results.keys.include?(key)
|
41
|
+
end
|
42
|
+
pp results
|
43
|
+
end
|
44
|
+
|
45
|
+
# TODO: Implement proceeding search result pages
|
46
|
+
def test_get_proceeding_search_results
|
47
|
+
proceedings_query = ECFS::ProceedingsQuery.new
|
48
|
+
proceedings_query.eq("bureau_code", "WB")
|
49
|
+
assert_raise RuntimeError do
|
50
|
+
proceedings_query.get
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
metadata
ADDED
@@ -0,0 +1,126 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ecfs
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Alan deLevie
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-05-13 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: bundler
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '1.3'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '1.3'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rake
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: mechanize
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :runtime
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: pry
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :runtime
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
description: ECFS provides a set of utilities for scraping FCC rulemakings
|
79
|
+
email:
|
80
|
+
- adelevie@gmail.com
|
81
|
+
executables: []
|
82
|
+
extensions: []
|
83
|
+
extra_rdoc_files: []
|
84
|
+
files:
|
85
|
+
- .gitignore
|
86
|
+
- .travis.yml
|
87
|
+
- Gemfile
|
88
|
+
- LICENSE.txt
|
89
|
+
- README.md
|
90
|
+
- Rakefile
|
91
|
+
- ecfs.gemspec
|
92
|
+
- lib/ecfs.rb
|
93
|
+
- lib/ecfs/proceedings_query.rb
|
94
|
+
- lib/ecfs/version.rb
|
95
|
+
- test/helper.rb
|
96
|
+
- test/test_proceedings_query.rb
|
97
|
+
homepage: ''
|
98
|
+
licenses:
|
99
|
+
- MIT
|
100
|
+
post_install_message:
|
101
|
+
rdoc_options: []
|
102
|
+
require_paths:
|
103
|
+
- lib
|
104
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
105
|
+
none: false
|
106
|
+
requirements:
|
107
|
+
- - ! '>='
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
110
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
111
|
+
none: false
|
112
|
+
requirements:
|
113
|
+
- - ! '>='
|
114
|
+
- !ruby/object:Gem::Version
|
115
|
+
version: '0'
|
116
|
+
requirements: []
|
117
|
+
rubyforge_project:
|
118
|
+
rubygems_version: 1.8.24
|
119
|
+
signing_key:
|
120
|
+
specification_version: 3
|
121
|
+
summary: ECFS helps you obtain comments and other filings from the FCC's Electronic
|
122
|
+
Comment Filing System
|
123
|
+
test_files:
|
124
|
+
- test/helper.rb
|
125
|
+
- test/test_proceedings_query.rb
|
126
|
+
has_rdoc:
|