nvd_feed_api 0.0.3 → 0.3.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.gitignore +1 -1
- data/.gitlab-ci.yml +25 -10
- data/.rubocop.yml +12 -5
- data/.tool-versions +1 -0
- data/Gemfile.lock +67 -0
- data/README.md +2 -1
- data/lib/nvd_feed_api.rb +44 -456
- data/lib/nvd_feed_api/feed.rb +410 -0
- data/lib/nvd_feed_api/meta.rb +116 -0
- data/lib/nvd_feed_api/version.rb +1 -1
- data/nvd_feed_api.gemspec +12 -12
- data/pages/CHANGELOG.md +50 -4
- data/pages/EXAMPLES.md +3 -5
- data/pages/INSTALL.md +2 -9
- data/renovate.json +15 -0
- data/test/test_nvd_feed_api.rb +89 -56
- metadata +39 -29
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 158649a33021b95393055afc6861185443aeae4665cc6acd86814f29a866d8f0
|
4
|
+
data.tar.gz: 75ca47cdcece6352581ed8ddfe9339ce393e48199ba4c895e6e49e05e959b08b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 66c08b3167c12da6168331f84caa557d945ebb16c76e565cefa6ac44c7960e5eb8bae840a2231c16d2cc9ef982bd13eb9b68289dff66dbee4af0c115a45e20f4
|
7
|
+
data.tar.gz: 2729e066d04f9f29e9fd3fbd76c88cb3c208c2a82eab331e3202fca9a42a7f658d7645f7d3c17f5df770c54b1eb8e084b611f6e23eefab90c7e4cada90e114f0
|
data/.gitignore
CHANGED
data/.gitlab-ci.yml
CHANGED
@@ -1,36 +1,51 @@
|
|
1
1
|
# Official language image. Look for the different tagged releases at:
|
2
2
|
# https://hub.docker.com/r/library/ruby/tags/
|
3
|
-
image: ruby:2.4-alpine
|
4
3
|
|
4
|
+
# Caching: https://docs.gitlab.com/ee/ci/caching/#caching-ruby-dependencies
|
5
5
|
cache:
|
6
|
+
key: ${CI_COMMIT_REF_SLUG}
|
6
7
|
paths:
|
7
8
|
- vendor/ruby # cache gems in between builds
|
8
9
|
|
9
10
|
before_script:
|
10
11
|
- ruby -v # Print out ruby version for debugging
|
11
|
-
- gem install bundler
|
12
|
+
- gem install bundler --no-document # Bundler is not installed with the image
|
12
13
|
# install nproc (coreutils) for bundle -j
|
13
14
|
# install git for building the gemspec
|
14
15
|
# install make, gcc for building gem native extension (commonmarker)
|
15
16
|
# libc-dev for musl-dev dependency (stdlib.h) needed by gcc
|
16
17
|
- apk --no-cache add coreutils git make gcc libc-dev
|
17
18
|
- bundle install -j $(nproc) --path vendor # Install dependencies into ./vendor/ruby
|
18
|
-
- rake install # install the gem
|
19
|
+
- bundle exec rake install # install the gem
|
19
20
|
|
20
|
-
|
21
|
+
# Anchors: https://docs.gitlab.com/ee/ci/yaml/README.html#anchors
|
22
|
+
.test_template: &job_definition
|
21
23
|
stage: test
|
22
24
|
script:
|
23
|
-
|
25
|
+
- bundle exec rubocop
|
26
|
+
- bundle exec rake test
|
24
27
|
|
25
|
-
test:
|
26
|
-
|
27
|
-
|
28
|
-
|
28
|
+
test:2.4:
|
29
|
+
<<: *job_definition
|
30
|
+
image: ruby:2.4-alpine
|
31
|
+
|
32
|
+
test:2.5:
|
33
|
+
<<: *job_definition
|
34
|
+
image: ruby:2.5-alpine
|
35
|
+
|
36
|
+
test:2.6:
|
37
|
+
<<: *job_definition
|
38
|
+
image: ruby:2.6-alpine
|
39
|
+
|
40
|
+
test:2.7:
|
41
|
+
<<: *job_definition
|
42
|
+
image: ruby:2.7-alpine
|
29
43
|
|
30
44
|
pages:
|
31
45
|
stage: deploy
|
46
|
+
image: ruby:2.4-alpine
|
32
47
|
script:
|
33
|
-
- yard doc
|
48
|
+
- bundle exec yard doc
|
34
49
|
- mkdir public
|
35
50
|
- mv doc/* public/
|
36
51
|
artifacts:
|
data/.rubocop.yml
CHANGED
@@ -1,5 +1,12 @@
|
|
1
1
|
AllCops:
|
2
|
-
TargetRubyVersion: 2.
|
2
|
+
TargetRubyVersion: 2.7
|
3
|
+
NewCops: enable
|
4
|
+
|
5
|
+
Layout/HashAlignment:
|
6
|
+
EnforcedHashRocketStyle: table
|
7
|
+
|
8
|
+
Layout/LineLength:
|
9
|
+
Enabled: false
|
3
10
|
|
4
11
|
# Rubocop is too stupid too see that the variable is used
|
5
12
|
Lint/UselessAssignment:
|
@@ -18,10 +25,7 @@ Metrics/ClassLength:
|
|
18
25
|
Enabled: false
|
19
26
|
|
20
27
|
Metrics/CyclomaticComplexity:
|
21
|
-
Max:
|
22
|
-
|
23
|
-
Metrics/LineLength:
|
24
|
-
Enabled: false
|
28
|
+
Max: 20
|
25
29
|
|
26
30
|
Metrics/MethodLength:
|
27
31
|
Max: 100
|
@@ -44,3 +48,6 @@ Style/PerlBackrefs:
|
|
44
48
|
# Allow explicit return
|
45
49
|
Style/RedundantReturn:
|
46
50
|
Enabled: false
|
51
|
+
|
52
|
+
Style/WordArray:
|
53
|
+
EnforcedStyle: brackets
|
data/.tool-versions
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
ruby 2.7.1
|
data/Gemfile.lock
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
nvd_feed_api (0.3.1)
|
5
|
+
archive-zip (~> 0.11)
|
6
|
+
nokogiri (~> 1.10)
|
7
|
+
oj (>= 3.7.8, < 4)
|
8
|
+
|
9
|
+
GEM
|
10
|
+
remote: https://rubygems.org/
|
11
|
+
specs:
|
12
|
+
archive-zip (0.12.0)
|
13
|
+
io-like (~> 0.3.0)
|
14
|
+
ast (2.4.1)
|
15
|
+
commonmarker (0.21.0)
|
16
|
+
ruby-enum (~> 0.5)
|
17
|
+
concurrent-ruby (1.1.7)
|
18
|
+
github-markup (3.0.4)
|
19
|
+
i18n (1.8.5)
|
20
|
+
concurrent-ruby (~> 1.0)
|
21
|
+
io-like (0.3.1)
|
22
|
+
mini_portile2 (2.4.0)
|
23
|
+
minitest (5.14.2)
|
24
|
+
nokogiri (1.10.10)
|
25
|
+
mini_portile2 (~> 2.4.0)
|
26
|
+
oj (3.10.14)
|
27
|
+
parallel (1.19.2)
|
28
|
+
parser (2.7.1.5)
|
29
|
+
ast (~> 2.4.1)
|
30
|
+
rainbow (3.0.0)
|
31
|
+
rake (13.0.1)
|
32
|
+
redcarpet (3.5.0)
|
33
|
+
regexp_parser (1.8.1)
|
34
|
+
rexml (3.2.4)
|
35
|
+
rubocop (0.92.0)
|
36
|
+
parallel (~> 1.10)
|
37
|
+
parser (>= 2.7.1.5)
|
38
|
+
rainbow (>= 2.2.2, < 4.0)
|
39
|
+
regexp_parser (>= 1.7)
|
40
|
+
rexml
|
41
|
+
rubocop-ast (>= 0.5.0)
|
42
|
+
ruby-progressbar (~> 1.7)
|
43
|
+
unicode-display_width (>= 1.4.0, < 2.0)
|
44
|
+
rubocop-ast (0.7.1)
|
45
|
+
parser (>= 2.7.1.5)
|
46
|
+
ruby-enum (0.8.0)
|
47
|
+
i18n
|
48
|
+
ruby-progressbar (1.10.1)
|
49
|
+
unicode-display_width (1.7.0)
|
50
|
+
yard (0.9.25)
|
51
|
+
|
52
|
+
PLATFORMS
|
53
|
+
ruby
|
54
|
+
|
55
|
+
DEPENDENCIES
|
56
|
+
bundler (~> 2.1)
|
57
|
+
commonmarker (~> 0.21)
|
58
|
+
github-markup (~> 3.0)
|
59
|
+
minitest (~> 5.14)
|
60
|
+
nvd_feed_api!
|
61
|
+
rake (~> 13.0)
|
62
|
+
redcarpet (~> 3.5)
|
63
|
+
rubocop (~> 0.92)
|
64
|
+
yard (~> 0.9)
|
65
|
+
|
66
|
+
BUNDLED WITH
|
67
|
+
2.1.4
|
data/README.md
CHANGED
@@ -5,6 +5,7 @@
|
|
5
5
|
[![Gem stable](https://img.shields.io/gem/dv/nvd_feed_api/stable.svg)][rubygems]
|
6
6
|
[![Gem latest](https://img.shields.io/gem/dtv/nvd_feed_api.svg)][rubygems]
|
7
7
|
[![Gem total download](https://img.shields.io/gem/dt/nvd_feed_api.svg)][rubygems]
|
8
|
+
[![Rawsec's CyberSecurity Inventory](https://inventory.rawsec.ml/img/badges/Rawsec-inventoried-FF5050_flat.svg)](https://inventory.rawsec.ml/tools.html#nvd_feed_api)
|
8
9
|
|
9
10
|
[rubygems]:https://rubygems.org/gems/nvd_feed_api/
|
10
11
|
|
@@ -12,7 +13,7 @@
|
|
12
13
|
|
13
14
|
**nvd_feed_api** is a simple ruby API for NVD CVE feeds.
|
14
15
|
|
15
|
-
The API will help you to download and manage NVD Data Feeds, search for CVEs, build your
|
16
|
+
The API will help you to download and manage NVD Data Feeds, search for CVEs, build your vulnerability assessment platform or vulnerability database.
|
16
17
|
|
17
18
|
Name | Link
|
18
19
|
--- | ---
|
data/lib/nvd_feed_api.rb
CHANGED
@@ -1,15 +1,13 @@
|
|
1
1
|
# @author Alexandre ZANNI <alexandre.zanni@engineer.com>
|
2
2
|
|
3
3
|
# Ruby internal
|
4
|
-
require 'digest'
|
5
4
|
require 'net/https'
|
6
5
|
require 'set'
|
7
6
|
# External
|
8
|
-
require 'archive/zip'
|
9
7
|
require 'nokogiri'
|
10
|
-
require 'oj'
|
11
8
|
# Project internal
|
12
9
|
require 'nvd_feed_api/version'
|
10
|
+
require 'nvd_feed_api/feed'
|
13
11
|
|
14
12
|
# The class that parse NVD website to get information.
|
15
13
|
# @example Initialize a NVDFeedScraper object, get the feeds and see them:
|
@@ -20,332 +18,12 @@ require 'nvd_feed_api/version'
|
|
20
18
|
# scraper.feeds("CVE-2007")
|
21
19
|
# cve2007, cve2015 = scraper.feeds("CVE-2007", "CVE-2015")
|
22
20
|
class NVDFeedScraper
|
21
|
+
BASE = 'https://nvd.nist.gov'.freeze
|
23
22
|
# The NVD url where is located the data feeds.
|
24
|
-
URL =
|
23
|
+
URL = "#{BASE}/vuln/data-feeds".freeze
|
25
24
|
# Load constants
|
26
25
|
include NvdFeedApi
|
27
26
|
|
28
|
-
# Feed object.
|
29
|
-
class Feed
|
30
|
-
class << self
|
31
|
-
# Get / set default feed storage location, where will be stored JSON feeds and archives by default.
|
32
|
-
# @return [String] default feed storage location. Default to +/tmp/+.
|
33
|
-
# @example
|
34
|
-
# NVDFeedScraper::Feed.default_storage_location = '/srv/downloads/'
|
35
|
-
attr_accessor :default_storage_location
|
36
|
-
end
|
37
|
-
@default_storage_location = '/tmp/'
|
38
|
-
|
39
|
-
# @return [String] the name of the feed.
|
40
|
-
# @example
|
41
|
-
# 'CVE-2007'
|
42
|
-
attr_reader :name
|
43
|
-
|
44
|
-
# @return [String] the last update date of the feed information on the NVD website.
|
45
|
-
# @example
|
46
|
-
# '10/19/2017 3:27:02 AM -04:00'
|
47
|
-
attr_reader :updated
|
48
|
-
|
49
|
-
# @return [String] the URL of the metadata file of the feed.
|
50
|
-
# @example
|
51
|
-
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.meta'
|
52
|
-
attr_reader :meta_url
|
53
|
-
|
54
|
-
# @return [String] the URL of the gz archive of the feed.
|
55
|
-
# @example
|
56
|
-
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.json.gz'
|
57
|
-
attr_reader :gz_url
|
58
|
-
|
59
|
-
# @return [String] the URL of the zip archive of the feed.
|
60
|
-
# @example
|
61
|
-
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.json.zip'
|
62
|
-
attr_reader :zip_url
|
63
|
-
|
64
|
-
# @return [Meta] the {Meta} object of the feed.
|
65
|
-
# @note
|
66
|
-
# Return nil if not previously loaded by {#meta_pull}.
|
67
|
-
# Note that {#json_pull} also calls {#meta_pull}.
|
68
|
-
# @example
|
69
|
-
# s = NVDFeedScraper.new
|
70
|
-
# s.scrap
|
71
|
-
# f = s.feeds("CVE-2014")
|
72
|
-
# f.meta # => nil
|
73
|
-
# f.meta_pull
|
74
|
-
# f.meta # => #<NVDFeedScraper::Meta:0x00555b53027570 ... >
|
75
|
-
attr_reader :meta
|
76
|
-
|
77
|
-
# @return [String] the path of the saved JSON file.
|
78
|
-
# @note Return nil if not previously loaded by {#json_pull}.
|
79
|
-
# @example
|
80
|
-
# s = NVDFeedScraper.new
|
81
|
-
# s.scrap
|
82
|
-
# f = s.feeds("CVE-2014")
|
83
|
-
# f.json_file # => nil
|
84
|
-
# f.json_pull
|
85
|
-
# f.json_file # => "/tmp/nvdcve-1.0-2014.json"
|
86
|
-
attr_reader :json_file
|
87
|
-
|
88
|
-
# A new instance of Feed.
|
89
|
-
# @param name [String] see {#name}.
|
90
|
-
# @param updated [String] see {#updated}.
|
91
|
-
# @param meta_url [String] see {#meta_url}.
|
92
|
-
# @param gz_url [String] see {#gz_url}.
|
93
|
-
# @param zip_url [String] see {#zip_url}.
|
94
|
-
def initialize(name, updated, meta_url, gz_url, zip_url)
|
95
|
-
@name = name
|
96
|
-
@updated = updated
|
97
|
-
@meta_url = meta_url
|
98
|
-
@gz_url = gz_url
|
99
|
-
@zip_url = zip_url
|
100
|
-
# do not pull meta and json automatically for speed and memory footprint
|
101
|
-
@meta = nil
|
102
|
-
@json_file = nil
|
103
|
-
end
|
104
|
-
|
105
|
-
# Create or update the {Meta} object (fill the attribute).
|
106
|
-
# @return [Meta] the updated {Meta} object of the feed.
|
107
|
-
# @see #meta
|
108
|
-
def meta_pull
|
109
|
-
meta_content = NVDFeedScraper::Meta.new(@meta_url)
|
110
|
-
meta_content.parse
|
111
|
-
# update @meta
|
112
|
-
@meta = meta_content
|
113
|
-
end
|
114
|
-
|
115
|
-
# Download the gz archive of the feed.
|
116
|
-
# @param opts [Hash] see {#download_file}.
|
117
|
-
# @return [String] the saved gz file path.
|
118
|
-
# @example
|
119
|
-
# afeed.download_gz
|
120
|
-
# afeed.download_gz(destination_path: '/srv/save/')
|
121
|
-
def download_gz(opts = {})
|
122
|
-
download_file(@gz_url, opts)
|
123
|
-
end
|
124
|
-
|
125
|
-
# Download the zip archive of the feed.
|
126
|
-
# @param opts [Hash] see {#download_file}.
|
127
|
-
# @return [String] the saved zip file path.
|
128
|
-
# @example
|
129
|
-
# afeed.download_zip
|
130
|
-
# afeed.download_zip(destination_path: '/srv/save/')
|
131
|
-
def download_zip(opts = {})
|
132
|
-
download_file(@zip_url, opts)
|
133
|
-
end
|
134
|
-
|
135
|
-
# Download the JSON feed and fill the attribute.
|
136
|
-
# @param opts [Hash] see {#download_file}.
|
137
|
-
# @return [String] the path of the saved JSON file. Default use {Feed#default_storage_location}.
|
138
|
-
# @note Will downlaod and save the zip of the JSON file, unzip and save it. This massively consume time.
|
139
|
-
# @see #json_file
|
140
|
-
def json_pull(opts = {})
|
141
|
-
opts[:destination_path] ||= Feed.default_storage_location
|
142
|
-
|
143
|
-
skip_download = false
|
144
|
-
destination_path = opts[:destination_path]
|
145
|
-
destination_path += '/' unless destination_path[-1] == '/'
|
146
|
-
filename = URI(@zip_url).path.split('/').last.chomp('.zip')
|
147
|
-
# do not use @json_file for destination_file because of offline loading
|
148
|
-
destination_file = destination_path + filename
|
149
|
-
meta_pull
|
150
|
-
if File.file?(destination_file)
|
151
|
-
# Verify hash to see if it is the latest
|
152
|
-
computed_h = Digest::SHA256.file(destination_file)
|
153
|
-
skip_download = true if meta.sha256.casecmp(computed_h.hexdigest).zero?
|
154
|
-
end
|
155
|
-
if skip_download
|
156
|
-
@json_file = destination_file
|
157
|
-
else
|
158
|
-
zip_path = download_zip(opts)
|
159
|
-
Archive::Zip.open(zip_path) do |z|
|
160
|
-
z.extract(destination_path, flatten: true)
|
161
|
-
end
|
162
|
-
@json_file = zip_path.chomp('.zip')
|
163
|
-
# Verify hash integrity
|
164
|
-
computed_h = Digest::SHA256.file(@json_file)
|
165
|
-
raise "File corruption: #{@json_file}" unless meta.sha256.casecmp(computed_h.hexdigest).zero?
|
166
|
-
end
|
167
|
-
return @json_file
|
168
|
-
end
|
169
|
-
|
170
|
-
# Search for CVE in the feed.
|
171
|
-
# @overload cve(cve)
|
172
|
-
# One CVE.
|
173
|
-
# @param cve [String] CVE ID, case insensitive.
|
174
|
-
# @return [Hash] a Ruby Hash corresponding to the CVE.
|
175
|
-
# @overload cve(cve_arr)
|
176
|
-
# An array of CVEs.
|
177
|
-
# @param cve_arr [Array<String>] Array of CVE ID, case insensitive.
|
178
|
-
# @return [Array] an Array of CVE, each CVE is a Ruby Hash. May not be in the same order as provided.
|
179
|
-
# @overload cve(cve, *)
|
180
|
-
# Multiple CVEs.
|
181
|
-
# @param cve [String] CVE ID, case insensitive.
|
182
|
-
# @param * [String] As many CVE ID as you want.
|
183
|
-
# @return [Array] an Array of CVE, each CVE is a Ruby Hash. May not be in the same order as provided.
|
184
|
-
# @note {#json_pull} is needed before using this method. Remember you're searching only in the current feed.
|
185
|
-
# @todo implement a CVE Class instead of returning a Hash.
|
186
|
-
# @see https://scap.nist.gov/schema/nvd/feed/0.1/nvd_cve_feed_json_0.1_beta.schema
|
187
|
-
# @see https://scap.nist.gov/schema/nvd/feed/0.1/CVE_JSON_4.0_min.schema
|
188
|
-
# @example
|
189
|
-
# s = NVDFeedScraper.new
|
190
|
-
# s.scrap
|
191
|
-
# f = s.feeds("CVE-2014")
|
192
|
-
# f.json_pull
|
193
|
-
# f.cve("CVE-2014-0002", "cve-2014-0001")
|
194
|
-
def cve(*arg_cve)
|
195
|
-
raise 'json_file is nil, it needs to be populated with json_pull' if @json_file.nil?
|
196
|
-
raise "json_file (#{@json_file}) doesn't exist" unless File.file?(@json_file)
|
197
|
-
return_value = nil
|
198
|
-
raise 'no argument provided, 1 or more expected' if arg_cve.empty?
|
199
|
-
if arg_cve.length == 1
|
200
|
-
if arg_cve[0].is_a?(String)
|
201
|
-
raise "bad CVE name (#{arg_cve[0]})" unless /^CVE-[0-9]{4}-[0-9]{4,}$/i.match?(arg_cve[0])
|
202
|
-
doc = Oj::Doc.open(File.read(@json_file))
|
203
|
-
# Quicker than doc.fetch('/CVE_Items').size
|
204
|
-
doc_size = doc.fetch('/CVE_data_numberOfCVEs').to_i
|
205
|
-
(1..doc_size).each do |i|
|
206
|
-
if arg_cve[0].upcase == doc.fetch("/CVE_Items/#{i}/cve/CVE_data_meta/ID")
|
207
|
-
return_value = doc.fetch("/CVE_Items/#{i}")
|
208
|
-
break
|
209
|
-
end
|
210
|
-
end
|
211
|
-
doc.close
|
212
|
-
elsif arg_cve[0].is_a?(Array)
|
213
|
-
return_value = []
|
214
|
-
# Sorting CVE can allow us to parse quicker
|
215
|
-
# Upcase to be sure include? works
|
216
|
-
cves_to_find = arg_cve[0].map(&:upcase).sort
|
217
|
-
raise 'one of the provided arguments is not a String' unless cves_to_find.all? { |x| x.is_a?(String) }
|
218
|
-
raise 'bad CVE name' unless cves_to_find.all? { |x| /^CVE-[0-9]{4}-[0-9]{4,}$/i.match?(x) }
|
219
|
-
doc = Oj::Doc.open(File.read(@json_file))
|
220
|
-
# Quicker than doc.fetch('/CVE_Items').size
|
221
|
-
doc_size = doc.fetch('/CVE_data_numberOfCVEs').to_i
|
222
|
-
(1..doc_size).each do |i|
|
223
|
-
doc.move("/CVE_Items/#{i}")
|
224
|
-
cve_id = doc.fetch('cve/CVE_data_meta/ID')
|
225
|
-
if cves_to_find.include?(cve_id)
|
226
|
-
return_value.push(doc.fetch)
|
227
|
-
cves_to_find.delete(cve_id)
|
228
|
-
elsif cves_to_find.empty?
|
229
|
-
break
|
230
|
-
end
|
231
|
-
end
|
232
|
-
raise "#{cves_to_find.join(', ')} are unexisting CVEs in this feed" unless cves_to_find.empty?
|
233
|
-
else
|
234
|
-
raise "the provided argument (#{arg_cve[0]}) is nor a String or an Array"
|
235
|
-
end
|
236
|
-
else
|
237
|
-
# Overloading a list of arguments as one array argument
|
238
|
-
return_value = cve(arg_cve)
|
239
|
-
end
|
240
|
-
return return_value
|
241
|
-
end
|
242
|
-
|
243
|
-
# Return a list with the name of all available CVEs in the feed.
|
244
|
-
# Can only be called after {#json_pull}.
|
245
|
-
# @return [Array<String>] List with the name of all available CVEs. May return thousands CVEs.
|
246
|
-
def available_cves
|
247
|
-
raise 'json_file is nil, it needs to be populated with json_pull' if @json_file.nil?
|
248
|
-
raise "json_file (#{@json_file}) doesn't exist" unless File.file?(@json_file)
|
249
|
-
doc = Oj::Doc.open(File.read(@json_file))
|
250
|
-
# Quicker than doc.fetch('/CVE_Items').size
|
251
|
-
doc_size = doc.fetch('/CVE_data_numberOfCVEs').to_i
|
252
|
-
cve_names = []
|
253
|
-
(1..doc_size).each do |i|
|
254
|
-
doc.move("/CVE_Items/#{i}")
|
255
|
-
cve_names.push(doc.fetch('cve/CVE_data_meta/ID'))
|
256
|
-
end
|
257
|
-
doc.close
|
258
|
-
return cve_names
|
259
|
-
end
|
260
|
-
|
261
|
-
protected
|
262
|
-
|
263
|
-
# @param arg_name [String] the new name of the feed.
|
264
|
-
# @return [String] the new name of the feed.
|
265
|
-
# @example
|
266
|
-
# 'CVE-2007'
|
267
|
-
def name=(arg_name)
|
268
|
-
raise "name (#{arg_name}) is not a string" unless arg_name.is_a(String)
|
269
|
-
@name = arg_name
|
270
|
-
end
|
271
|
-
|
272
|
-
# @param arg_updated [String] the last update date of the feed information on the NVD website.
|
273
|
-
# @return [String] the new date.
|
274
|
-
# @example
|
275
|
-
# '10/19/2017 3:27:02 AM -04:00'
|
276
|
-
def updated=(arg_updated)
|
277
|
-
raise "updated date (#{arg_updated}) is not a string" unless arg_updated.is_a(String)
|
278
|
-
@updated = arg_updated
|
279
|
-
end
|
280
|
-
|
281
|
-
# @param arg_meta_url [String] the new URL of the metadata file of the feed.
|
282
|
-
# @return [String] the new URL of the metadata file of the feed.
|
283
|
-
# @example
|
284
|
-
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.meta'
|
285
|
-
def meta_url=(arg_meta_url)
|
286
|
-
raise "meta_url (#{arg_meta_url}) is not a string" unless arg_meta_url.is_a(String)
|
287
|
-
@meta_url = arg_meta_url
|
288
|
-
end
|
289
|
-
|
290
|
-
# @param arg_gz_url [String] the new URL of the gz archive of the feed.
|
291
|
-
# @return [String] the new URL of the gz archive of the feed.
|
292
|
-
# @example
|
293
|
-
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.json.gz'
|
294
|
-
def gz_url=(arg_gz_url)
|
295
|
-
raise "gz_url (#{arg_gz_url}) is not a string" unless arg_gz_url.is_a(String)
|
296
|
-
@gz_url = arg_gz_url
|
297
|
-
end
|
298
|
-
|
299
|
-
# @param arg_zip_url [String] the new URL of the zip archive of the feed.
|
300
|
-
# @return [String] the new URL of the zip archive of the feed.
|
301
|
-
# @example
|
302
|
-
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.json.zip'
|
303
|
-
def zip_url=(arg_zip_url)
|
304
|
-
raise "zip_url (#{arg_zip_url}) is not a string" unless arg_zip_url.is_a(String)
|
305
|
-
@zip_url = arg_zip_url
|
306
|
-
end
|
307
|
-
|
308
|
-
# Download a file.
|
309
|
-
# @param file_url [String] the URL of the file.
|
310
|
-
# @param opts [Hash] the optional downlaod parameters.
|
311
|
-
# @option opts [String] :destination_path the destination path (may
|
312
|
-
# overwrite existing file).
|
313
|
-
# Default use {Feed#default_storage_location}.
|
314
|
-
# @option opts [String] :sha256 the SHA256 hash to check, if the file
|
315
|
-
# already exist and the hash matches then the download will be skipped.
|
316
|
-
# @return [String] the saved file path.
|
317
|
-
# @example
|
318
|
-
# download_file('https://example.org/example.zip') # => '/tmp/example.zip'
|
319
|
-
# download_file('https://example.org/example.zip', destination_path: '/srv/save/') # => '/srv/save/example.zip'
|
320
|
-
# download_file('https://example.org/example.zip', {destination_path: '/srv/save/', sha256: '70d6ea136d5036b6ce771921a949357216866c6442f44cea8497f0528c54642d'}) # => '/srv/save/example.zip'
|
321
|
-
def download_file(file_url, opts = {})
|
322
|
-
opts[:destination_path] ||= Feed.default_storage_location
|
323
|
-
opts[:sha256] ||= nil
|
324
|
-
|
325
|
-
destination_path = opts[:destination_path]
|
326
|
-
destination_path += '/' unless destination_path[-1] == '/'
|
327
|
-
skip_download = false
|
328
|
-
uri = URI(file_url)
|
329
|
-
filename = uri.path.split('/').last
|
330
|
-
destination_file = destination_path + filename
|
331
|
-
unless opts[:sha256].nil?
|
332
|
-
if File.file?(destination_file)
|
333
|
-
# Verify hash to see if it is the latest
|
334
|
-
computed_h = Digest::SHA256.file(destination_file)
|
335
|
-
skip_download = true if opts[:sha256].casecmp(computed_h.hexdigest).zero?
|
336
|
-
end
|
337
|
-
end
|
338
|
-
unless skip_download
|
339
|
-
res = Net::HTTP.get_response(uri)
|
340
|
-
raise "#{file_url} ended with #{res.code} #{res.message}" unless res.is_a?(Net::HTTPSuccess)
|
341
|
-
open(destination_file, 'wb') do |file|
|
342
|
-
file.write(res.body)
|
343
|
-
end
|
344
|
-
end
|
345
|
-
return destination_file
|
346
|
-
end
|
347
|
-
end
|
348
|
-
|
349
27
|
# Initialize the scraper
|
350
28
|
def initialize
|
351
29
|
@url = URL
|
@@ -354,21 +32,33 @@ class NVDFeedScraper
|
|
354
32
|
|
355
33
|
# Scrap / parse the website to get the feeds and fill the {#feeds} attribute.
|
356
34
|
# @note {#scrap} need to be called only once but can be called again to update if the NVD feed page changed.
|
357
|
-
# @return [Integer]
|
35
|
+
# @return [Integer] Number of scrapped feeds.
|
358
36
|
def scrap
|
359
37
|
uri = URI(@url)
|
360
38
|
html = Net::HTTP.get(uri)
|
361
39
|
|
362
40
|
doc = Nokogiri::HTML(html)
|
363
41
|
@feeds = []
|
364
|
-
|
365
|
-
|
366
|
-
|
367
|
-
|
368
|
-
|
369
|
-
|
370
|
-
|
42
|
+
tmp_feeds = {}
|
43
|
+
doc.css('#vuln-feed-table table.xml-feed-table tr[data-testid]').each do |tr|
|
44
|
+
num, type = tr.attr('data-testid')[13..].split('-')
|
45
|
+
if type == 'meta'
|
46
|
+
tmp_feeds[num] = {}
|
47
|
+
tmp_feeds[num][:name] = tr.css('td')[0].text
|
48
|
+
tmp_feeds[num][:updated] = tr.css('td')[1].text
|
49
|
+
tmp_feeds[num][:meta] = BASE + tr.css('td')[2].css('> a').attr('href').value
|
50
|
+
elsif type == 'gz'
|
51
|
+
tmp_feeds[num][:gz] = BASE + tr.css('td > a').attr('href').value
|
52
|
+
elsif type == 'zip'
|
53
|
+
tmp_feeds[num][:zip] = BASE + tr.css('td > a').attr('href').value
|
54
|
+
@feeds.push(Feed.new(tmp_feeds[num][:name],
|
55
|
+
tmp_feeds[num][:updated],
|
56
|
+
tmp_feeds[num][:meta],
|
57
|
+
tmp_feeds[num][:gz],
|
58
|
+
tmp_feeds[num][:zip]))
|
59
|
+
end
|
371
60
|
end
|
61
|
+
return @feeds.size
|
372
62
|
end
|
373
63
|
|
374
64
|
# Return feeds. Can only be called after {#scrap}.
|
@@ -395,6 +85,7 @@ class NVDFeedScraper
|
|
395
85
|
# @see https://nvd.nist.gov/vuln/data-feeds
|
396
86
|
def feeds(*arg_feeds)
|
397
87
|
raise 'call scrap method before using feeds method' if @feeds.nil?
|
88
|
+
|
398
89
|
return_value = nil
|
399
90
|
if arg_feeds.empty?
|
400
91
|
return_value = @feeds
|
@@ -406,6 +97,7 @@ class NVDFeedScraper
|
|
406
97
|
# if nothing found return nil
|
407
98
|
elsif arg_feeds[0].is_a?(Array)
|
408
99
|
raise 'one of the provided arguments is not a String' unless arg_feeds[0].all? { |x| x.is_a?(String) }
|
100
|
+
|
409
101
|
# Sorting CVE can allow us to parse quicker
|
410
102
|
# Upcase to be sure include? works
|
411
103
|
# Does not use map(&:upcase) to preserve CVE-Recent and CVE-Modified
|
@@ -437,6 +129,7 @@ class NVDFeedScraper
|
|
437
129
|
# scraper.available_feeds => ["CVE-Modified", "CVE-Recent", "CVE-2017", "CVE-2016", "CVE-2015", "CVE-2014", "CVE-2013", "CVE-2012", "CVE-2011", "CVE-2010", "CVE-2009", "CVE-2008", "CVE-2007", "CVE-2006", "CVE-2005", "CVE-2004", "CVE-2003", "CVE-2002"]
|
438
130
|
def available_feeds
|
439
131
|
raise 'call scrap method before using available_feeds method' if @feeds.nil?
|
132
|
+
|
440
133
|
feed_names = []
|
441
134
|
@feeds.each do |feed| # feed is an objet
|
442
135
|
feed_names.push(feed.name)
|
@@ -469,9 +162,11 @@ class NVDFeedScraper
|
|
469
162
|
def cve(*arg_cve)
|
470
163
|
return_value = nil
|
471
164
|
raise 'no argument provided, 1 or more expected' if arg_cve.empty?
|
165
|
+
|
472
166
|
if arg_cve.length == 1
|
473
167
|
if arg_cve[0].is_a?(String)
|
474
168
|
raise 'bad CVE name' unless /^CVE-[0-9]{4}-[0-9]{4,}$/i.match?(arg_cve[0])
|
169
|
+
|
475
170
|
year = /^CVE-([0-9]{4})-[0-9]{4,}$/i.match(arg_cve[0]).captures[0]
|
476
171
|
matched_feed = nil
|
477
172
|
feed_names = available_feeds
|
@@ -483,13 +178,17 @@ class NVDFeedScraper
|
|
483
178
|
break
|
484
179
|
end
|
485
180
|
end
|
181
|
+
# CVE-2002 feed (the 1st one) contains CVE from 1999 to 2002
|
182
|
+
matched_feed = 'CVE-2002' if matched_feed.nil? && ('1999'..'2001').to_a.include?(year)
|
486
183
|
raise "bad CVE year in #{arg_cve}" if matched_feed.nil?
|
184
|
+
|
487
185
|
f = feeds(matched_feed)
|
488
186
|
f.json_pull
|
489
187
|
return_value = f.cve(arg_cve[0])
|
490
188
|
elsif arg_cve[0].is_a?(Array)
|
491
189
|
raise 'one of the provided arguments is not a String' unless arg_cve[0].all? { |x| x.is_a?(String) }
|
492
190
|
raise 'bad CVE name' unless arg_cve[0].all? { |x| /^CVE-[0-9]{4}-[0-9]{4,}$/i.match?(x) }
|
191
|
+
|
493
192
|
return_value = []
|
494
193
|
# Sorting CVE can allow us to parse quicker
|
495
194
|
# Upcase to be sure include? works
|
@@ -501,8 +200,18 @@ class NVDFeedScraper
|
|
501
200
|
feed_names = available_feeds.to_set
|
502
201
|
feed_names.delete('CVE-Modified')
|
503
202
|
feed_names.delete('CVE-Recent')
|
203
|
+
# CVE-2002 feed (the 1st one) contains CVE from 1999 to 2002
|
204
|
+
virtual_feeds = ['CVE-1999', 'CVE-2000', 'CVE-2001']
|
205
|
+
# So virtually add those feed...
|
206
|
+
feed_names.merge(virtual_feeds)
|
504
207
|
raise 'unexisting CVE year was provided in some CVE' unless feeds_to_match.subset?(feed_names)
|
208
|
+
|
505
209
|
matched_feeds = feeds_to_match.intersection(feed_names)
|
210
|
+
# and now that the intersection is done remove those virtual feeds and add CVE-2002 instead if needed
|
211
|
+
unless matched_feeds.intersection(virtual_feeds.to_set).empty?
|
212
|
+
matched_feeds.subtract(virtual_feeds)
|
213
|
+
matched_feeds.add('CVE-2002')
|
214
|
+
end
|
506
215
|
feeds_arr = feeds(matched_feeds.to_a)
|
507
216
|
feeds_arr.each do |feed|
|
508
217
|
feed.json_pull
|
@@ -547,23 +256,13 @@ class NVDFeedScraper
|
|
547
256
|
def update_feeds(*arg_feed)
|
548
257
|
return_value = false
|
549
258
|
raise 'no argument provided, 1 or more expected' if arg_feed.empty?
|
259
|
+
|
550
260
|
scrap
|
551
261
|
if arg_feed.length == 1
|
552
262
|
if arg_feed[0].is_a?(Feed)
|
553
263
|
new_feed = feeds(arg_feed[0].name)
|
554
264
|
# update attributes
|
555
|
-
|
556
|
-
arg_feed[0].name = new_feed.name
|
557
|
-
arg_feed[0].updated = new_feed.updated
|
558
|
-
arg_feed[0].meta_url = new_feed.meta_url
|
559
|
-
arg_feed[0].gz_url = new_feed.gz_url
|
560
|
-
arg_feed[0].zip_url = new_feed.zip_url
|
561
|
-
# update if @meta was set
|
562
|
-
arg_feed[0].meta_pull unless feed.meta.nil?
|
563
|
-
# update if @json_file was set
|
564
|
-
arg_feed[0].json_pull unless feed.json_file.nil?
|
565
|
-
return_value = true
|
566
|
-
end
|
265
|
+
return_value = arg_feed[0].update!(new_feed)
|
567
266
|
elsif arg_feed[0].is_a?(Array)
|
568
267
|
return_value = []
|
569
268
|
arg_feed[0].each do |f|
|
@@ -597,115 +296,4 @@ class NVDFeedScraper
|
|
597
296
|
end
|
598
297
|
return cve_names
|
599
298
|
end
|
600
|
-
|
601
|
-
# Manage the meta file from a feed.
|
602
|
-
#
|
603
|
-
# == Usage
|
604
|
-
#
|
605
|
-
# @example
|
606
|
-
# s = NVDFeedScraper.new
|
607
|
-
# s.scrap
|
608
|
-
# metaUrl = s.feeds("CVE-2014").meta_url
|
609
|
-
# m = NVDFeedScraper::Meta.new
|
610
|
-
# m.url = metaUrl
|
611
|
-
# m.parse
|
612
|
-
# m.sha256
|
613
|
-
#
|
614
|
-
# Several ways to set the url:
|
615
|
-
#
|
616
|
-
# m = NVDFeedScraper::Meta.new(metaUrl)
|
617
|
-
# m.parse
|
618
|
-
# # or
|
619
|
-
# m = NVDFeedScraper::Meta.new
|
620
|
-
# m.url = metaUrl
|
621
|
-
# m.parse
|
622
|
-
# # or
|
623
|
-
# m = NVDFeedScraper::Meta.new
|
624
|
-
# m.parse(metaUrl)
|
625
|
-
class Meta
|
626
|
-
# {Meta} last modified date getter
|
627
|
-
# @return [String] the last modified date and time.
|
628
|
-
# @example
|
629
|
-
# '2017-10-19T03:27:02-04:00'
|
630
|
-
attr_reader :last_modified_date
|
631
|
-
|
632
|
-
# {Meta} JSON size getter
|
633
|
-
# @return [String] the size of the JSON file uncompressed.
|
634
|
-
# @example
|
635
|
-
# '29443314'
|
636
|
-
attr_reader :size
|
637
|
-
|
638
|
-
# {Meta} zip size getter
|
639
|
-
# @return [String] the size of the zip file.
|
640
|
-
# @example
|
641
|
-
# '2008493'
|
642
|
-
attr_reader :zip_size
|
643
|
-
|
644
|
-
# {Meta} gz size getter
|
645
|
-
# @return [String] the size of the gz file.
|
646
|
-
# @example
|
647
|
-
# '2008357'
|
648
|
-
attr_reader :gz_size
|
649
|
-
|
650
|
-
# {Meta} JSON sha256 getter
|
651
|
-
# @return [String] the SHA256 value of the uncompressed JSON file.
|
652
|
-
# @example
|
653
|
-
# '33ED52D451692596D644F23742ED42B4E350258B11ACB900F969F148FCE3777B'
|
654
|
-
attr_reader :sha256
|
655
|
-
|
656
|
-
# @param url [String, nil] see {Feed#meta_url}.
|
657
|
-
def initialize(url = nil)
|
658
|
-
@url = url
|
659
|
-
end
|
660
|
-
|
661
|
-
# {Meta} URL getter.
|
662
|
-
# @return [String] The URL of the meta file of the feed.
|
663
|
-
attr_reader :url
|
664
|
-
|
665
|
-
# {Meta} URL setter.
|
666
|
-
# @param url [String] see {Feed#meta_url}.
|
667
|
-
def url=(url)
|
668
|
-
@url = url
|
669
|
-
@last_modified_date = @size = @zip_size = @gz_size = @sha256 = nil
|
670
|
-
end
|
671
|
-
|
672
|
-
# Parse the meta file from the URL and set the attributes.
|
673
|
-
# @overload parse
|
674
|
-
# Parse the meta file from the URL and set the attributes.
|
675
|
-
# @return [Integer] Returns +0+ when there is no error.
|
676
|
-
# @overload parse(url)
|
677
|
-
# Set the URL of the meta file of the feed and
|
678
|
-
# parse the meta file from the URL and set the attributes.
|
679
|
-
# @param url [String] see {Feed.meta_url}
|
680
|
-
# @return [Integer] Returns +0+ when there is no error.
|
681
|
-
def parse(*arg)
|
682
|
-
if arg.empty?
|
683
|
-
elsif arg.length == 1 # arg = url
|
684
|
-
self.url = arg[0]
|
685
|
-
else
|
686
|
-
raise 'Too much arguments'
|
687
|
-
end
|
688
|
-
|
689
|
-
raise "Can't parse if the URL is empty" if @url.nil?
|
690
|
-
uri = URI(@url)
|
691
|
-
|
692
|
-
meta = Net::HTTP.get(uri)
|
693
|
-
|
694
|
-
meta = Hash[meta.split.map { |x| x.split(':', 2) }]
|
695
|
-
|
696
|
-
raise 'no lastModifiedDate attribute found' unless meta['lastModifiedDate']
|
697
|
-
raise 'no valid size attribute found' unless /[0-9]+/.match?(meta['size'])
|
698
|
-
raise 'no valid zipSize attribute found' unless /[0-9]+/.match?(meta['zipSize'])
|
699
|
-
raise 'no valid gzSize attribute found' unless /[0-9]+/.match?(meta['gzSize'])
|
700
|
-
raise 'no valid sha256 attribute found' unless /[0-9A-F]{64}/.match?(meta['sha256'])
|
701
|
-
|
702
|
-
@last_modified_date = meta['lastModifiedDate']
|
703
|
-
@size = meta['size']
|
704
|
-
@zip_size = meta['zipSize']
|
705
|
-
@gz_size = meta['gzSize']
|
706
|
-
@sha256 = meta['sha256']
|
707
|
-
|
708
|
-
0
|
709
|
-
end
|
710
|
-
end
|
711
299
|
end
|