nvd_feed_api 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/nvd_feed_api.rb +2 -447
- data/lib/nvd_feed_api/feed.rb +397 -0
- data/lib/nvd_feed_api/meta.rb +115 -0
- data/lib/nvd_feed_api/version.rb +1 -1
- data/pages/CHANGELOG.md +14 -0
- data/test/test_nvd_feed_api.rb +39 -6
- metadata +3 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 38ab69d805d125729995fc9ea26d79e0b324414f
|
4
|
+
data.tar.gz: 7c9838e134a5f503d21979a5915db3cd9d9e823b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: eda8d75faf07c0189cf6fdf9bbea8296fce70f0aaf380e8af2a3af83d1216f6ae360319cd01e727659f4cac527cd284ac9e9555dfb1dc79f1982f93309940129
|
7
|
+
data.tar.gz: eb9eb999eee1ef44b3b64de314f3fb37b0cc857df67a7ae580ed6f71ef51e827f3ec93de5b5fdfdd0205a0f280f6825e673a858e67248c9a684dc77a1342adea
|
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:
|
@@ -25,327 +23,6 @@ class NVDFeedScraper
|
|
25
23
|
# Load constants
|
26
24
|
include NvdFeedApi
|
27
25
|
|
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
26
|
# Initialize the scraper
|
350
27
|
def initialize
|
351
28
|
@url = URL
|
@@ -563,18 +240,7 @@ class NVDFeedScraper
|
|
563
240
|
if arg_feed[0].is_a?(Feed)
|
564
241
|
new_feed = feeds(arg_feed[0].name)
|
565
242
|
# update attributes
|
566
|
-
|
567
|
-
arg_feed[0].name = new_feed.name
|
568
|
-
arg_feed[0].updated = new_feed.updated
|
569
|
-
arg_feed[0].meta_url = new_feed.meta_url
|
570
|
-
arg_feed[0].gz_url = new_feed.gz_url
|
571
|
-
arg_feed[0].zip_url = new_feed.zip_url
|
572
|
-
# update if @meta was set
|
573
|
-
arg_feed[0].meta_pull unless feed.meta.nil?
|
574
|
-
# update if @json_file was set
|
575
|
-
arg_feed[0].json_pull unless feed.json_file.nil?
|
576
|
-
return_value = true
|
577
|
-
end
|
243
|
+
return_value = arg_feed[0].update!(new_feed)
|
578
244
|
elsif arg_feed[0].is_a?(Array)
|
579
245
|
return_value = []
|
580
246
|
arg_feed[0].each do |f|
|
@@ -608,115 +274,4 @@ class NVDFeedScraper
|
|
608
274
|
end
|
609
275
|
return cve_names
|
610
276
|
end
|
611
|
-
|
612
|
-
# Manage the meta file from a feed.
|
613
|
-
#
|
614
|
-
# == Usage
|
615
|
-
#
|
616
|
-
# @example
|
617
|
-
# s = NVDFeedScraper.new
|
618
|
-
# s.scrap
|
619
|
-
# metaUrl = s.feeds("CVE-2014").meta_url
|
620
|
-
# m = NVDFeedScraper::Meta.new
|
621
|
-
# m.url = metaUrl
|
622
|
-
# m.parse
|
623
|
-
# m.sha256
|
624
|
-
#
|
625
|
-
# Several ways to set the url:
|
626
|
-
#
|
627
|
-
# m = NVDFeedScraper::Meta.new(metaUrl)
|
628
|
-
# m.parse
|
629
|
-
# # or
|
630
|
-
# m = NVDFeedScraper::Meta.new
|
631
|
-
# m.url = metaUrl
|
632
|
-
# m.parse
|
633
|
-
# # or
|
634
|
-
# m = NVDFeedScraper::Meta.new
|
635
|
-
# m.parse(metaUrl)
|
636
|
-
class Meta
|
637
|
-
# {Meta} last modified date getter
|
638
|
-
# @return [String] the last modified date and time.
|
639
|
-
# @example
|
640
|
-
# '2017-10-19T03:27:02-04:00'
|
641
|
-
attr_reader :last_modified_date
|
642
|
-
|
643
|
-
# {Meta} JSON size getter
|
644
|
-
# @return [String] the size of the JSON file uncompressed.
|
645
|
-
# @example
|
646
|
-
# '29443314'
|
647
|
-
attr_reader :size
|
648
|
-
|
649
|
-
# {Meta} zip size getter
|
650
|
-
# @return [String] the size of the zip file.
|
651
|
-
# @example
|
652
|
-
# '2008493'
|
653
|
-
attr_reader :zip_size
|
654
|
-
|
655
|
-
# {Meta} gz size getter
|
656
|
-
# @return [String] the size of the gz file.
|
657
|
-
# @example
|
658
|
-
# '2008357'
|
659
|
-
attr_reader :gz_size
|
660
|
-
|
661
|
-
# {Meta} JSON sha256 getter
|
662
|
-
# @return [String] the SHA256 value of the uncompressed JSON file.
|
663
|
-
# @example
|
664
|
-
# '33ED52D451692596D644F23742ED42B4E350258B11ACB900F969F148FCE3777B'
|
665
|
-
attr_reader :sha256
|
666
|
-
|
667
|
-
# @param url [String, nil] see {Feed#meta_url}.
|
668
|
-
def initialize(url = nil)
|
669
|
-
@url = url
|
670
|
-
end
|
671
|
-
|
672
|
-
# {Meta} URL getter.
|
673
|
-
# @return [String] The URL of the meta file of the feed.
|
674
|
-
attr_reader :url
|
675
|
-
|
676
|
-
# {Meta} URL setter.
|
677
|
-
# @param url [String] see {Feed#meta_url}.
|
678
|
-
def url=(url)
|
679
|
-
@url = url
|
680
|
-
@last_modified_date = @size = @zip_size = @gz_size = @sha256 = nil
|
681
|
-
end
|
682
|
-
|
683
|
-
# Parse the meta file from the URL and set the attributes.
|
684
|
-
# @overload parse
|
685
|
-
# Parse the meta file from the URL and set the attributes.
|
686
|
-
# @return [Integer] Returns +0+ when there is no error.
|
687
|
-
# @overload parse(url)
|
688
|
-
# Set the URL of the meta file of the feed and
|
689
|
-
# parse the meta file from the URL and set the attributes.
|
690
|
-
# @param url [String] see {Feed.meta_url}
|
691
|
-
# @return [Integer] Returns +0+ when there is no error.
|
692
|
-
def parse(*arg)
|
693
|
-
if arg.empty?
|
694
|
-
elsif arg.length == 1 # arg = url
|
695
|
-
self.url = arg[0]
|
696
|
-
else
|
697
|
-
raise 'Too much arguments'
|
698
|
-
end
|
699
|
-
|
700
|
-
raise "Can't parse if the URL is empty" if @url.nil?
|
701
|
-
uri = URI(@url)
|
702
|
-
|
703
|
-
meta = Net::HTTP.get(uri)
|
704
|
-
|
705
|
-
meta = Hash[meta.split.map { |x| x.split(':', 2) }]
|
706
|
-
|
707
|
-
raise 'no lastModifiedDate attribute found' unless meta['lastModifiedDate']
|
708
|
-
raise 'no valid size attribute found' unless /[0-9]+/.match?(meta['size'])
|
709
|
-
raise 'no valid zipSize attribute found' unless /[0-9]+/.match?(meta['zipSize'])
|
710
|
-
raise 'no valid gzSize attribute found' unless /[0-9]+/.match?(meta['gzSize'])
|
711
|
-
raise 'no valid sha256 attribute found' unless /[0-9A-F]{64}/.match?(meta['sha256'])
|
712
|
-
|
713
|
-
@last_modified_date = meta['lastModifiedDate']
|
714
|
-
@size = meta['size']
|
715
|
-
@zip_size = meta['zipSize']
|
716
|
-
@gz_size = meta['gzSize']
|
717
|
-
@sha256 = meta['sha256']
|
718
|
-
|
719
|
-
0
|
720
|
-
end
|
721
|
-
end
|
722
277
|
end
|
@@ -0,0 +1,397 @@
|
|
1
|
+
# Ruby internal
|
2
|
+
require 'digest'
|
3
|
+
require 'net/https'
|
4
|
+
require 'date'
|
5
|
+
# External
|
6
|
+
require 'archive/zip'
|
7
|
+
require 'oj'
|
8
|
+
# Project internal
|
9
|
+
require 'nvd_feed_api/meta'
|
10
|
+
|
11
|
+
class NVDFeedScraper
|
12
|
+
# Feed object.
|
13
|
+
class Feed
|
14
|
+
class << self
|
15
|
+
# Get / set default feed storage location, where will be stored JSON feeds and archives by default.
|
16
|
+
# @return [String] default feed storage location. Default to +/tmp/+.
|
17
|
+
# @example
|
18
|
+
# NVDFeedScraper::Feed.default_storage_location = '/srv/downloads/'
|
19
|
+
attr_accessor :default_storage_location
|
20
|
+
end
|
21
|
+
@default_storage_location = '/tmp/'
|
22
|
+
|
23
|
+
# @return [String] the name of the feed.
|
24
|
+
# @example
|
25
|
+
# 'CVE-2007'
|
26
|
+
attr_reader :name
|
27
|
+
|
28
|
+
# @return [String] the last update date of the feed information on the NVD website.
|
29
|
+
# @example
|
30
|
+
# '10/19/2017 3:27:02 AM -04:00'
|
31
|
+
attr_reader :updated
|
32
|
+
|
33
|
+
# @return [String] the URL of the metadata file of the feed.
|
34
|
+
# @example
|
35
|
+
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.meta'
|
36
|
+
attr_reader :meta_url
|
37
|
+
|
38
|
+
# @return [String] the URL of the gz archive of the feed.
|
39
|
+
# @example
|
40
|
+
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.json.gz'
|
41
|
+
attr_reader :gz_url
|
42
|
+
|
43
|
+
# @return [String] the URL of the zip archive of the feed.
|
44
|
+
# @example
|
45
|
+
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.json.zip'
|
46
|
+
attr_reader :zip_url
|
47
|
+
|
48
|
+
# @return [Meta] the {Meta} object of the feed.
|
49
|
+
# @note
|
50
|
+
# Return nil if not previously loaded by {#meta_pull}.
|
51
|
+
# Note that {#json_pull} also calls {#meta_pull}.
|
52
|
+
# @example
|
53
|
+
# s = NVDFeedScraper.new
|
54
|
+
# s.scrap
|
55
|
+
# f = s.feeds("CVE-2014")
|
56
|
+
# f.meta # => nil
|
57
|
+
# f.meta_pull
|
58
|
+
# f.meta # => #<NVDFeedScraper::Meta:0x00555b53027570 ... >
|
59
|
+
attr_reader :meta
|
60
|
+
|
61
|
+
# @return [String] the path of the saved JSON file.
|
62
|
+
# @note Return nil if not previously loaded by {#json_pull}.
|
63
|
+
# @example
|
64
|
+
# s = NVDFeedScraper.new
|
65
|
+
# s.scrap
|
66
|
+
# f = s.feeds("CVE-2014")
|
67
|
+
# f.json_file # => nil
|
68
|
+
# f.json_pull
|
69
|
+
# f.json_file # => "/tmp/nvdcve-1.0-2014.json"
|
70
|
+
attr_reader :json_file
|
71
|
+
|
72
|
+
# @return [String] the type of the feed, should always be +CVE+.
|
73
|
+
# @note Return nil if not previously loaded by {#json_pull}.
|
74
|
+
attr_reader :data_type
|
75
|
+
|
76
|
+
# @return [String] the format of the feed, should always be +MITRE+.
|
77
|
+
# @note Return nil if not previously loaded by {#json_pull}.
|
78
|
+
attr_reader :data_format
|
79
|
+
|
80
|
+
# @return [Float] the version of the JSON schema of the feed.
|
81
|
+
# @note Return nil if not previously loaded by {#json_pull}.
|
82
|
+
attr_reader :data_version
|
83
|
+
|
84
|
+
# @return [Integer] the number of CVEs of in the feed.
|
85
|
+
# @note Return nil if not previously loaded by {#json_pull}.
|
86
|
+
attr_reader :data_number_of_cves
|
87
|
+
|
88
|
+
# @return [Date] the date of the last update of the feed by the NVD.
|
89
|
+
# @note Return nil if not previously loaded by {#json_pull}.
|
90
|
+
attr_reader :data_timestamp
|
91
|
+
|
92
|
+
# A new instance of Feed.
|
93
|
+
# @param name [String] see {#name}.
|
94
|
+
# @param updated [String] see {#updated}.
|
95
|
+
# @param meta_url [String] see {#meta_url}.
|
96
|
+
# @param gz_url [String] see {#gz_url}.
|
97
|
+
# @param zip_url [String] see {#zip_url}.
|
98
|
+
def initialize(name, updated, meta_url, gz_url, zip_url)
|
99
|
+
# Frome meta file
|
100
|
+
@name = name
|
101
|
+
@updated = updated
|
102
|
+
@meta_url = meta_url
|
103
|
+
@gz_url = gz_url
|
104
|
+
@zip_url = zip_url
|
105
|
+
# do not pull meta and json automatically for speed and memory footprint
|
106
|
+
@meta = nil
|
107
|
+
@json_file = nil
|
108
|
+
# feed data
|
109
|
+
@data_type = nil
|
110
|
+
@data_format = nil
|
111
|
+
@data_version = nil
|
112
|
+
@data_number_of_cves = nil
|
113
|
+
@data_timestamp = nil
|
114
|
+
end
|
115
|
+
|
116
|
+
# Create or update the {Meta} object (fill the attribute).
|
117
|
+
# @return [Meta] the updated {Meta} object of the feed.
|
118
|
+
# @see #meta
|
119
|
+
def meta_pull
|
120
|
+
meta_content = NVDFeedScraper::Meta.new(@meta_url)
|
121
|
+
meta_content.parse
|
122
|
+
# update @meta
|
123
|
+
@meta = meta_content
|
124
|
+
end
|
125
|
+
|
126
|
+
# Download the gz archive of the feed.
|
127
|
+
# @param opts [Hash] see {#download_file}.
|
128
|
+
# @return [String] the saved gz file path.
|
129
|
+
# @example
|
130
|
+
# afeed.download_gz
|
131
|
+
# afeed.download_gz(destination_path: '/srv/save/')
|
132
|
+
def download_gz(opts = {})
|
133
|
+
download_file(@gz_url, opts)
|
134
|
+
end
|
135
|
+
|
136
|
+
# Download the zip archive of the feed.
|
137
|
+
# @param opts [Hash] see {#download_file}.
|
138
|
+
# @return [String] the saved zip file path.
|
139
|
+
# @example
|
140
|
+
# afeed.download_zip
|
141
|
+
# afeed.download_zip(destination_path: '/srv/save/')
|
142
|
+
def download_zip(opts = {})
|
143
|
+
download_file(@zip_url, opts)
|
144
|
+
end
|
145
|
+
|
146
|
+
# Download the JSON feed and fill the attribute.
|
147
|
+
# @param opts [Hash] see {#download_file}.
|
148
|
+
# @return [String] the path of the saved JSON file. Default use {Feed#default_storage_location}.
|
149
|
+
# @note Will downlaod and save the zip of the JSON file, unzip and save it. This massively consume time.
|
150
|
+
# @see #json_file
|
151
|
+
def json_pull(opts = {})
|
152
|
+
opts[:destination_path] ||= Feed.default_storage_location
|
153
|
+
|
154
|
+
skip_download = false
|
155
|
+
destination_path = opts[:destination_path]
|
156
|
+
destination_path += '/' unless destination_path[-1] == '/'
|
157
|
+
filename = URI(@zip_url).path.split('/').last.chomp('.zip')
|
158
|
+
# do not use @json_file for destination_file because of offline loading
|
159
|
+
destination_file = destination_path + filename
|
160
|
+
meta_pull
|
161
|
+
if File.file?(destination_file)
|
162
|
+
# Verify hash to see if it is the latest
|
163
|
+
computed_h = Digest::SHA256.file(destination_file)
|
164
|
+
skip_download = true if meta.sha256.casecmp(computed_h.hexdigest).zero?
|
165
|
+
end
|
166
|
+
if skip_download
|
167
|
+
@json_file = destination_file
|
168
|
+
# Set data
|
169
|
+
if @data_type.nil?
|
170
|
+
doc = Oj::Doc.open(File.read(@json_file))
|
171
|
+
@data_type = doc.fetch('/CVE_data_type')
|
172
|
+
@data_format = doc.fetch('/CVE_data_format')
|
173
|
+
@data_version = doc.fetch('/CVE_data_version').to_f
|
174
|
+
@data_number_of_cves = doc.fetch('/CVE_data_numberOfCVEs').to_i
|
175
|
+
@data_timestamp = Date.strptime(doc.fetch('/CVE_data_timestamp'), '%FT%RZ')
|
176
|
+
doc.close
|
177
|
+
end
|
178
|
+
else
|
179
|
+
zip_path = download_zip(opts)
|
180
|
+
Archive::Zip.open(zip_path) do |z|
|
181
|
+
z.extract(destination_path, flatten: true)
|
182
|
+
end
|
183
|
+
@json_file = zip_path.chomp('.zip')
|
184
|
+
# Verify hash integrity
|
185
|
+
computed_h = Digest::SHA256.file(@json_file)
|
186
|
+
raise "File corruption: #{@json_file}" unless meta.sha256.casecmp(computed_h.hexdigest).zero?
|
187
|
+
# update data
|
188
|
+
doc = Oj::Doc.open(File.read(@json_file))
|
189
|
+
@data_type = doc.fetch('/CVE_data_type')
|
190
|
+
@data_format = doc.fetch('/CVE_data_format')
|
191
|
+
@data_version = doc.fetch('/CVE_data_version').to_f
|
192
|
+
@data_number_of_cves = doc.fetch('/CVE_data_numberOfCVEs').to_i
|
193
|
+
@data_timestamp = Date.strptime(doc.fetch('/CVE_data_timestamp'), '%FT%RZ')
|
194
|
+
doc.close
|
195
|
+
end
|
196
|
+
return @json_file
|
197
|
+
end
|
198
|
+
|
199
|
+
# Search for CVE in the feed.
|
200
|
+
# @overload cve(cve)
|
201
|
+
# One CVE.
|
202
|
+
# @param cve [String] CVE ID, case insensitive.
|
203
|
+
# @return [Hash] a Ruby Hash corresponding to the CVE.
|
204
|
+
# @overload cve(cve_arr)
|
205
|
+
# An array of CVEs.
|
206
|
+
# @param cve_arr [Array<String>] Array of CVE ID, case insensitive.
|
207
|
+
# @return [Array] an Array of CVE, each CVE is a Ruby Hash. May not be in the same order as provided.
|
208
|
+
# @overload cve(cve, *)
|
209
|
+
# Multiple CVEs.
|
210
|
+
# @param cve [String] CVE ID, case insensitive.
|
211
|
+
# @param * [String] As many CVE ID as you want.
|
212
|
+
# @return [Array] an Array of CVE, each CVE is a Ruby Hash. May not be in the same order as provided.
|
213
|
+
# @note {#json_pull} is needed before using this method. Remember you're searching only in the current feed.
|
214
|
+
# @todo implement a CVE Class instead of returning a Hash.
|
215
|
+
# @see https://scap.nist.gov/schema/nvd/feed/0.1/nvd_cve_feed_json_0.1_beta.schema
|
216
|
+
# @see https://scap.nist.gov/schema/nvd/feed/0.1/CVE_JSON_4.0_min.schema
|
217
|
+
# @example
|
218
|
+
# s = NVDFeedScraper.new
|
219
|
+
# s.scrap
|
220
|
+
# f = s.feeds("CVE-2014")
|
221
|
+
# f.json_pull
|
222
|
+
# f.cve("CVE-2014-0002", "cve-2014-0001")
|
223
|
+
def cve(*arg_cve)
|
224
|
+
raise 'json_file is nil, it needs to be populated with json_pull' if @json_file.nil?
|
225
|
+
raise "json_file (#{@json_file}) doesn't exist" unless File.file?(@json_file)
|
226
|
+
return_value = nil
|
227
|
+
raise 'no argument provided, 1 or more expected' if arg_cve.empty?
|
228
|
+
if arg_cve.length == 1
|
229
|
+
if arg_cve[0].is_a?(String)
|
230
|
+
raise "bad CVE name (#{arg_cve[0]})" unless /^CVE-[0-9]{4}-[0-9]{4,}$/i.match?(arg_cve[0])
|
231
|
+
doc = Oj::Doc.open(File.read(@json_file))
|
232
|
+
# Quicker than doc.fetch('/CVE_Items').size
|
233
|
+
(1..@data_number_of_cves).each do |i|
|
234
|
+
if arg_cve[0].upcase == doc.fetch("/CVE_Items/#{i}/cve/CVE_data_meta/ID")
|
235
|
+
return_value = doc.fetch("/CVE_Items/#{i}")
|
236
|
+
break
|
237
|
+
end
|
238
|
+
end
|
239
|
+
doc.close
|
240
|
+
elsif arg_cve[0].is_a?(Array)
|
241
|
+
return_value = []
|
242
|
+
# Sorting CVE can allow us to parse quicker
|
243
|
+
# Upcase to be sure include? works
|
244
|
+
cves_to_find = arg_cve[0].map(&:upcase).sort
|
245
|
+
raise 'one of the provided arguments is not a String' unless cves_to_find.all? { |x| x.is_a?(String) }
|
246
|
+
raise 'bad CVE name' unless cves_to_find.all? { |x| /^CVE-[0-9]{4}-[0-9]{4,}$/i.match?(x) }
|
247
|
+
doc = Oj::Doc.open(File.read(@json_file))
|
248
|
+
# Quicker than doc.fetch('/CVE_Items').size
|
249
|
+
(1..@data_number_of_cves).each do |i|
|
250
|
+
doc.move("/CVE_Items/#{i}")
|
251
|
+
cve_id = doc.fetch('cve/CVE_data_meta/ID')
|
252
|
+
if cves_to_find.include?(cve_id)
|
253
|
+
return_value.push(doc.fetch)
|
254
|
+
cves_to_find.delete(cve_id)
|
255
|
+
elsif cves_to_find.empty?
|
256
|
+
break
|
257
|
+
end
|
258
|
+
end
|
259
|
+
raise "#{cves_to_find.join(', ')} are unexisting CVEs in this feed" unless cves_to_find.empty?
|
260
|
+
else
|
261
|
+
raise "the provided argument (#{arg_cve[0]}) is nor a String or an Array"
|
262
|
+
end
|
263
|
+
else
|
264
|
+
# Overloading a list of arguments as one array argument
|
265
|
+
return_value = cve(arg_cve)
|
266
|
+
end
|
267
|
+
return return_value
|
268
|
+
end
|
269
|
+
|
270
|
+
# Return a list with the name of all available CVEs in the feed.
|
271
|
+
# Can only be called after {#json_pull}.
|
272
|
+
# @return [Array<String>] List with the name of all available CVEs. May return thousands CVEs.
|
273
|
+
def available_cves
|
274
|
+
raise 'json_file is nil, it needs to be populated with json_pull' if @json_file.nil?
|
275
|
+
raise "json_file (#{@json_file}) doesn't exist" unless File.file?(@json_file)
|
276
|
+
doc = Oj::Doc.open(File.read(@json_file))
|
277
|
+
# Quicker than doc.fetch('/CVE_Items').size
|
278
|
+
cve_names = []
|
279
|
+
(1..@data_number_of_cves).each do |i|
|
280
|
+
doc.move("/CVE_Items/#{i}")
|
281
|
+
cve_names.push(doc.fetch('cve/CVE_data_meta/ID'))
|
282
|
+
end
|
283
|
+
doc.close
|
284
|
+
return cve_names
|
285
|
+
end
|
286
|
+
|
287
|
+
# @param arg_name [String] the new name of the feed.
|
288
|
+
# @return [String] the new name of the feed.
|
289
|
+
# @example
|
290
|
+
# 'CVE-2007'
|
291
|
+
def name=(arg_name)
|
292
|
+
raise "name (#{arg_name}) is not a string" unless arg_name.is_a?(String)
|
293
|
+
@name = arg_name
|
294
|
+
end
|
295
|
+
|
296
|
+
# @param arg_updated [String] the last update date of the feed information on the NVD website.
|
297
|
+
# @return [String] the new date.
|
298
|
+
# @example
|
299
|
+
# '10/19/2017 3:27:02 AM -04:00'
|
300
|
+
def updated=(arg_updated)
|
301
|
+
raise "updated date (#{arg_updated}) is not a string" unless arg_updated.is_a?(String)
|
302
|
+
@updated = arg_updated
|
303
|
+
end
|
304
|
+
|
305
|
+
# @param arg_meta_url [String] the new URL of the metadata file of the feed.
|
306
|
+
# @return [String] the new URL of the metadata file of the feed.
|
307
|
+
# @example
|
308
|
+
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.meta'
|
309
|
+
def meta_url=(arg_meta_url)
|
310
|
+
raise "meta_url (#{arg_meta_url}) is not a string" unless arg_meta_url.is_a?(String)
|
311
|
+
@meta_url = arg_meta_url
|
312
|
+
end
|
313
|
+
|
314
|
+
# @param arg_gz_url [String] the new URL of the gz archive of the feed.
|
315
|
+
# @return [String] the new URL of the gz archive of the feed.
|
316
|
+
# @example
|
317
|
+
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.json.gz'
|
318
|
+
def gz_url=(arg_gz_url)
|
319
|
+
raise "gz_url (#{arg_gz_url}) is not a string" unless arg_gz_url.is_a?(String)
|
320
|
+
@gz_url = arg_gz_url
|
321
|
+
end
|
322
|
+
|
323
|
+
# @param arg_zip_url [String] the new URL of the zip archive of the feed.
|
324
|
+
# @return [String] the new URL of the zip archive of the feed.
|
325
|
+
# @example
|
326
|
+
# 'https://static.nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-2007.json.zip'
|
327
|
+
def zip_url=(arg_zip_url)
|
328
|
+
raise "zip_url (#{arg_zip_url}) is not a string" unless arg_zip_url.is_a?(String)
|
329
|
+
@zip_url = arg_zip_url
|
330
|
+
end
|
331
|
+
|
332
|
+
# Download a file.
|
333
|
+
# @param file_url [String] the URL of the file.
|
334
|
+
# @param opts [Hash] the optional downlaod parameters.
|
335
|
+
# @option opts [String] :destination_path the destination path (may
|
336
|
+
# overwrite existing file).
|
337
|
+
# Default use {Feed#default_storage_location}.
|
338
|
+
# @option opts [String] :sha256 the SHA256 hash to check, if the file
|
339
|
+
# already exist and the hash matches then the download will be skipped.
|
340
|
+
# @return [String] the saved file path.
|
341
|
+
# @example
|
342
|
+
# download_file('https://example.org/example.zip') # => '/tmp/example.zip'
|
343
|
+
# download_file('https://example.org/example.zip', destination_path: '/srv/save/') # => '/srv/save/example.zip'
|
344
|
+
# download_file('https://example.org/example.zip', {destination_path: '/srv/save/', sha256: '70d6ea136d5036b6ce771921a949357216866c6442f44cea8497f0528c54642d'}) # => '/srv/save/example.zip'
|
345
|
+
def download_file(file_url, opts = {})
|
346
|
+
opts[:destination_path] ||= Feed.default_storage_location
|
347
|
+
opts[:sha256] ||= nil
|
348
|
+
|
349
|
+
destination_path = opts[:destination_path]
|
350
|
+
destination_path += '/' unless destination_path[-1] == '/'
|
351
|
+
skip_download = false
|
352
|
+
uri = URI(file_url)
|
353
|
+
filename = uri.path.split('/').last
|
354
|
+
destination_file = destination_path + filename
|
355
|
+
unless opts[:sha256].nil?
|
356
|
+
if File.file?(destination_file)
|
357
|
+
# Verify hash to see if it is the latest
|
358
|
+
computed_h = Digest::SHA256.file(destination_file)
|
359
|
+
skip_download = true if opts[:sha256].casecmp(computed_h.hexdigest).zero?
|
360
|
+
end
|
361
|
+
end
|
362
|
+
unless skip_download
|
363
|
+
res = Net::HTTP.get_response(uri)
|
364
|
+
raise "#{file_url} ended with #{res.code} #{res.message}" unless res.is_a?(Net::HTTPSuccess)
|
365
|
+
open(destination_file, 'wb') do |file|
|
366
|
+
file.write(res.body)
|
367
|
+
end
|
368
|
+
end
|
369
|
+
return destination_file
|
370
|
+
end
|
371
|
+
|
372
|
+
# Update the feed
|
373
|
+
# @param fresh_feed [Feed] the fresh feed from which the feed will be updated.
|
374
|
+
# @return [Boolean] +true+ if the feed was updated, +false+ if it wasn't.
|
375
|
+
# @note Is not intended to be used directly, use {NVDFeedScraper#update_feeds} instead.
|
376
|
+
def update!(fresh_feed)
|
377
|
+
return_value = false
|
378
|
+
raise "#{fresh_feed} is not a Feed" unless fresh_feed.is_a?(Feed)
|
379
|
+
# update attributes
|
380
|
+
if updated != fresh_feed.updated
|
381
|
+
self.name = fresh_feed.name
|
382
|
+
self.updated = fresh_feed.updated
|
383
|
+
self.meta_url = fresh_feed.meta_url
|
384
|
+
self.gz_url = fresh_feed.gz_url
|
385
|
+
self.zip_url = fresh_feed.zip_url
|
386
|
+
# update if @meta was set
|
387
|
+
meta_pull unless @meta.nil?
|
388
|
+
# update if @json_file was set, this will also update @data_*
|
389
|
+
json_pull unless @json_file.nil?
|
390
|
+
return_value = true
|
391
|
+
end
|
392
|
+
return return_value
|
393
|
+
end
|
394
|
+
|
395
|
+
protected :name=, :updated=, :meta_url=, :gz_url=, :zip_url=, :download_file
|
396
|
+
end
|
397
|
+
end
|
@@ -0,0 +1,115 @@
|
|
1
|
+
# Ruby internal
|
2
|
+
require 'net/https'
|
3
|
+
|
4
|
+
class NVDFeedScraper
|
5
|
+
# Manage the meta file from a feed.
|
6
|
+
#
|
7
|
+
# == Usage
|
8
|
+
#
|
9
|
+
# @example
|
10
|
+
# s = NVDFeedScraper.new
|
11
|
+
# s.scrap
|
12
|
+
# metaUrl = s.feeds("CVE-2014").meta_url
|
13
|
+
# m = NVDFeedScraper::Meta.new
|
14
|
+
# m.url = metaUrl
|
15
|
+
# m.parse
|
16
|
+
# m.sha256
|
17
|
+
#
|
18
|
+
# Several ways to set the url:
|
19
|
+
#
|
20
|
+
# m = NVDFeedScraper::Meta.new(metaUrl)
|
21
|
+
# m.parse
|
22
|
+
# # or
|
23
|
+
# m = NVDFeedScraper::Meta.new
|
24
|
+
# m.url = metaUrl
|
25
|
+
# m.parse
|
26
|
+
# # or
|
27
|
+
# m = NVDFeedScraper::Meta.new
|
28
|
+
# m.parse(metaUrl)
|
29
|
+
class Meta
|
30
|
+
# {Meta} last modified date getter
|
31
|
+
# @return [String] the last modified date and time.
|
32
|
+
# @example
|
33
|
+
# '2017-10-19T03:27:02-04:00'
|
34
|
+
attr_reader :last_modified_date
|
35
|
+
|
36
|
+
# {Meta} JSON size getter
|
37
|
+
# @return [String] the size of the JSON file uncompressed.
|
38
|
+
# @example
|
39
|
+
# '29443314'
|
40
|
+
attr_reader :size
|
41
|
+
|
42
|
+
# {Meta} zip size getter
|
43
|
+
# @return [String] the size of the zip file.
|
44
|
+
# @example
|
45
|
+
# '2008493'
|
46
|
+
attr_reader :zip_size
|
47
|
+
|
48
|
+
# {Meta} gz size getter
|
49
|
+
# @return [String] the size of the gz file.
|
50
|
+
# @example
|
51
|
+
# '2008357'
|
52
|
+
attr_reader :gz_size
|
53
|
+
|
54
|
+
# {Meta} JSON sha256 getter
|
55
|
+
# @return [String] the SHA256 value of the uncompressed JSON file.
|
56
|
+
# @example
|
57
|
+
# '33ED52D451692596D644F23742ED42B4E350258B11ACB900F969F148FCE3777B'
|
58
|
+
attr_reader :sha256
|
59
|
+
|
60
|
+
# @param url [String, nil] see {Feed#meta_url}.
|
61
|
+
def initialize(url = nil)
|
62
|
+
@url = url
|
63
|
+
end
|
64
|
+
|
65
|
+
# {Meta} URL getter.
|
66
|
+
# @return [String] The URL of the meta file of the feed.
|
67
|
+
attr_reader :url
|
68
|
+
|
69
|
+
# {Meta} URL setter.
|
70
|
+
# @param url [String] see {Feed#meta_url}.
|
71
|
+
def url=(url)
|
72
|
+
@url = url
|
73
|
+
@last_modified_date = @size = @zip_size = @gz_size = @sha256 = nil
|
74
|
+
end
|
75
|
+
|
76
|
+
# Parse the meta file from the URL and set the attributes.
|
77
|
+
# @overload parse
|
78
|
+
# Parse the meta file from the URL and set the attributes.
|
79
|
+
# @return [Integer] Returns +0+ when there is no error.
|
80
|
+
# @overload parse(url)
|
81
|
+
# Set the URL of the meta file of the feed and
|
82
|
+
# parse the meta file from the URL and set the attributes.
|
83
|
+
# @param url [String] see {Feed.meta_url}
|
84
|
+
# @return [Integer] Returns +0+ when there is no error.
|
85
|
+
def parse(*arg)
|
86
|
+
if arg.empty?
|
87
|
+
elsif arg.length == 1 # arg = url
|
88
|
+
self.url = arg[0]
|
89
|
+
else
|
90
|
+
raise 'Too much arguments'
|
91
|
+
end
|
92
|
+
|
93
|
+
raise "Can't parse if the URL is empty" if @url.nil?
|
94
|
+
uri = URI(@url)
|
95
|
+
|
96
|
+
meta = Net::HTTP.get(uri)
|
97
|
+
|
98
|
+
meta = Hash[meta.split.map { |x| x.split(':', 2) }]
|
99
|
+
|
100
|
+
raise 'no lastModifiedDate attribute found' unless meta['lastModifiedDate']
|
101
|
+
raise 'no valid size attribute found' unless /[0-9]+/.match?(meta['size'])
|
102
|
+
raise 'no valid zipSize attribute found' unless /[0-9]+/.match?(meta['zipSize'])
|
103
|
+
raise 'no valid gzSize attribute found' unless /[0-9]+/.match?(meta['gzSize'])
|
104
|
+
raise 'no valid sha256 attribute found' unless /[0-9A-F]{64}/.match?(meta['sha256'])
|
105
|
+
|
106
|
+
@last_modified_date = meta['lastModifiedDate']
|
107
|
+
@size = meta['size']
|
108
|
+
@zip_size = meta['zipSize']
|
109
|
+
@gz_size = meta['gzSize']
|
110
|
+
@sha256 = meta['sha256']
|
111
|
+
|
112
|
+
0
|
113
|
+
end
|
114
|
+
end
|
115
|
+
end
|
data/lib/nvd_feed_api/version.rb
CHANGED
data/pages/CHANGELOG.md
CHANGED
@@ -1,3 +1,17 @@
|
|
1
|
+
# [0.2.0] - 20 January 2018
|
2
|
+
|
3
|
+
[0.2.0]: https://gitlab.com/noraj/nvd_api/tags/v0.2.0
|
4
|
+
|
5
|
+
- new attributes for the Feed class:
|
6
|
+
+ `data_type`
|
7
|
+
+ `data_format`
|
8
|
+
+ `data_version`
|
9
|
+
+ `data_number_of_cves`
|
10
|
+
+ `data_timestamp`
|
11
|
+
- fix `update_feeds` method by using the new `update!` method from the Feed class
|
12
|
+
- split source code in several files, one by class
|
13
|
+
- improve tests and documentation
|
14
|
+
|
1
15
|
# [0.1.0] - 17 January 2018
|
2
16
|
|
3
17
|
[0.1.0]: https://gitlab.com/noraj/nvd_api/tags/v0.1.0
|
data/test/test_nvd_feed_api.rb
CHANGED
@@ -120,10 +120,6 @@ class NVDAPITest < Minitest::Test
|
|
120
120
|
# Test updated
|
121
121
|
assert_instance_of(String, f.updated, "updated doesn't return a string")
|
122
122
|
refute_empty(f.updated, 'updated is empty')
|
123
|
-
# Test meta
|
124
|
-
assert_nil(f.meta)
|
125
|
-
# Test json_file
|
126
|
-
assert_nil(f.json_file)
|
127
123
|
# Test gz_url
|
128
124
|
assert_instance_of(String, f.gz_url, "gz_url doesn't return a string")
|
129
125
|
refute_empty(f.gz_url, 'gz_url is empty')
|
@@ -136,6 +132,30 @@ class NVDAPITest < Minitest::Test
|
|
136
132
|
assert_instance_of(String, f.meta_url, "meta_url doesn't return a string")
|
137
133
|
refute_empty(f.meta_url, 'meta_url is empty')
|
138
134
|
assert_equal(meta_url, f.meta_url, 'The meta_url url of the feed was modified')
|
135
|
+
# Test meta (before json_pull)
|
136
|
+
assert_nil(f.meta)
|
137
|
+
# Test json_file
|
138
|
+
assert_nil(f.json_file)
|
139
|
+
f.json_pull
|
140
|
+
assert_instance_of(String, f.json_file, "json_file doesn't return a string")
|
141
|
+
refute_empty(f.json_file, 'json_file is empty')
|
142
|
+
# Test meta (after json_pull)
|
143
|
+
f.meta_pull
|
144
|
+
assert_instance_of(NVDFeedScraper::Meta, f.meta, "meta doesn't return a Meta object")
|
145
|
+
|
146
|
+
# Test data (require json_pull)
|
147
|
+
# Test data_type
|
148
|
+
assert_instance_of(String, f.data_type, "data_type doesn't return a String")
|
149
|
+
refute_empty(f.data_type, 'data_type is empty')
|
150
|
+
# Test data_format
|
151
|
+
assert_instance_of(String, f.data_format, "data_format doesn't return a String")
|
152
|
+
refute_empty(f.data_format, 'data_format is empty')
|
153
|
+
# Test data_version
|
154
|
+
assert_instance_of(Float, f.data_version, "data_version doesn't return a Float")
|
155
|
+
# Test data_number_of_cves
|
156
|
+
assert_instance_of(Integer, f.data_number_of_cves, "data_number_of_cves doesn't return an Integer")
|
157
|
+
# Test data_timestamp
|
158
|
+
assert_instance_of(Date, f.data_timestamp, "data_timestamp doesn't return a Date")
|
139
159
|
end
|
140
160
|
|
141
161
|
def test_feed_available_cves
|
@@ -202,8 +222,21 @@ class NVDAPITest < Minitest::Test
|
|
202
222
|
|
203
223
|
def test_feed_meta_pull
|
204
224
|
f = @s.feeds('CVE-2005')
|
205
|
-
|
206
|
-
|
225
|
+
assert_instance_of(NVDFeedScraper::Meta, f.meta_pull, "meta_pull doesn't return a Meta object")
|
226
|
+
end
|
227
|
+
|
228
|
+
def test_feed_update!
|
229
|
+
f = @s.feeds('CVE-2006')
|
230
|
+
@s.scrap
|
231
|
+
f_new = @s.feeds('CVE-2006')
|
232
|
+
# Right arg
|
233
|
+
# can't use assert_instance_of because there is no boolean class
|
234
|
+
assert(%w[TrueClass FalseClass].include?(f.update!(f_new).class.to_s), "update! doesn't return a boolean")
|
235
|
+
# Bad arg
|
236
|
+
err = assert_raises(RuntimeError) do
|
237
|
+
f.update!('bad_arg')
|
238
|
+
end
|
239
|
+
assert_equal('bad_arg is not a Feed', err.message)
|
207
240
|
end
|
208
241
|
|
209
242
|
def test_meta_parse_noarg
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: nvd_feed_api
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Alexandre ZANNI
|
@@ -189,6 +189,8 @@ files:
|
|
189
189
|
- bin/nvd_feed_api_console
|
190
190
|
- bin/nvd_feed_api_setup
|
191
191
|
- lib/nvd_feed_api.rb
|
192
|
+
- lib/nvd_feed_api/feed.rb
|
193
|
+
- lib/nvd_feed_api/meta.rb
|
192
194
|
- lib/nvd_feed_api/version.rb
|
193
195
|
- nvd_feed_api.gemspec
|
194
196
|
- pages/CHANGELOG.md
|