wayback_archiver 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/bin/wayback_archiver +2 -0
- data/lib/wayback_archiver/archive.rb +31 -15
- data/lib/wayback_archiver/null_logger.rb +9 -0
- data/lib/wayback_archiver/url_collector.rb +1 -1
- data/lib/wayback_archiver/version.rb +1 -1
- data/lib/wayback_archiver.rb +24 -2
- metadata +22 -7
- data/lib/wayback_archiver/process_queue.rb +0 -28
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: ccebbb815d374658a9b2e1b2998a40041115d295
|
4
|
+
data.tar.gz: 153afa895756670988fa3663f44fd1fd5a2e5e3e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: db7d655b1ea642618797d7fa3ece8357fa608dcb60322da76be7d793de11cd61df61f796025000ed0099edd96711aa78db607ce0614e9256e5921c252a7d931b
|
7
|
+
data.tar.gz: 919d8473c7f97bbd36c9065b95a99304ace7e0556a8dcd0f92eedf00d65961400dd92c63d86e405aa97babd5d254b522384f665ff39ababdc71afed9c13333ad
|
data/bin/wayback_archiver
CHANGED
@@ -4,29 +4,45 @@ module WaybackArchiver
|
|
4
4
|
# Wayback Machine base URL.
|
5
5
|
WAYBACK_BASE_URL = 'https://web.archive.org/save/'.freeze
|
6
6
|
# Default concurrency for archiving URLs
|
7
|
-
DEFAULT_CONCURRENCY =
|
7
|
+
DEFAULT_CONCURRENCY = 5
|
8
8
|
# Send URLs to Wayback Machine.
|
9
9
|
# @return [Array] with sent URLs.
|
10
10
|
# @param [Array] urls URLs to send.
|
11
11
|
# @param [Hash] options
|
12
|
-
# @example Archive
|
12
|
+
# @example Archive urls, asynchronously
|
13
13
|
# Archive.post(['http://example.com'])
|
14
|
-
# @example Archive
|
14
|
+
# @example Archive urls, using only 1 thread
|
15
15
|
# Archive.post(['http://example.com'], concurrency: 1)
|
16
|
-
def self.post(urls,
|
17
|
-
|
18
|
-
concurrency
|
19
|
-
|
20
|
-
puts "=== WAYBACK ARCHIVER ==="
|
21
|
-
puts "Request are sent with up to #{concurrency} parallel threads"
|
22
|
-
puts "Total urls to be sent: #{urls.length}"
|
16
|
+
def self.post(urls, concurrency: DEFAULT_CONCURRENCY)
|
17
|
+
WaybackArchiver.logger.info "=== WAYBACK ARCHIVER ==="
|
18
|
+
WaybackArchiver.logger.info "Request are sent with up to #{concurrency} parallel threads"
|
19
|
+
WaybackArchiver.logger.info "Total urls to be sent: #{urls.length}"
|
23
20
|
|
24
|
-
|
21
|
+
pool = Concurrent::FixedThreadPool.new(concurrency)
|
22
|
+
urls.each do |url|
|
23
|
+
pool.post { Archive.post_url(url) }
|
24
|
+
end
|
25
25
|
|
26
|
-
|
26
|
+
WaybackArchiver.logger.info "#{urls.length} URLs sent to Internet archive"
|
27
27
|
urls
|
28
28
|
end
|
29
29
|
|
30
|
+
# Send URLs to Wayback Machine by crawling the site.
|
31
|
+
# @return [Array] with URLs sent to the Wayback Machine.
|
32
|
+
# @param [String] source for URL to crawl.
|
33
|
+
# @param [Integer] concurrency (default is 5).
|
34
|
+
# @example Crawl example.com and send all URLs of the same domain
|
35
|
+
# WaybackArchiver.crawl('example.com')
|
36
|
+
# @example Crawl example.com and send all URLs of the same domain with low concurrency
|
37
|
+
# WaybackArchiver.crawl('example.com', concurrency: 1)
|
38
|
+
def self.crawl(source, concurrency: DEFAULT_CONCURRENCY)
|
39
|
+
pool = Concurrent::FixedThreadPool.new(concurrency) # X threads
|
40
|
+
|
41
|
+
UrlCollector.crawl(source) do |url|
|
42
|
+
pool.post { Archive.post_url(url) }
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
30
46
|
# Send URL to Wayback Machine.
|
31
47
|
# @return [String] the sent URL.
|
32
48
|
# @param [String] url to send.
|
@@ -35,11 +51,11 @@ module WaybackArchiver
|
|
35
51
|
def self.post_url(url)
|
36
52
|
request_url = "#{WAYBACK_BASE_URL}#{url}"
|
37
53
|
response = Request.response(request_url)
|
38
|
-
|
54
|
+
WaybackArchiver.logger.info "[#{response.code}, #{response.message}] #{url}"
|
39
55
|
url
|
40
56
|
rescue Exception => e
|
41
|
-
|
42
|
-
|
57
|
+
WaybackArchiver.logger.error "Error message: #{e.message}"
|
58
|
+
WaybackArchiver.logger.error "Failed to archive: #{url}"
|
43
59
|
end
|
44
60
|
end
|
45
61
|
end
|
data/lib/wayback_archiver.rb
CHANGED
@@ -1,11 +1,13 @@
|
|
1
1
|
require 'uri'
|
2
2
|
require 'net/http'
|
3
3
|
|
4
|
+
require 'concurrent'
|
5
|
+
|
6
|
+
require 'wayback_archiver/null_logger'
|
4
7
|
require 'wayback_archiver/version'
|
5
8
|
require 'wayback_archiver/url_collector'
|
6
9
|
require 'wayback_archiver/archive'
|
7
10
|
require 'wayback_archiver/request'
|
8
|
-
require 'wayback_archiver/process_queue'
|
9
11
|
|
10
12
|
# WaybackArchiver, send URLs to Wayback Machine. By crawling, sitemap, file or single URL.
|
11
13
|
module WaybackArchiver
|
@@ -28,11 +30,31 @@ module WaybackArchiver
|
|
28
30
|
def self.archive(source, type = :crawl)
|
29
31
|
case type.to_s
|
30
32
|
when 'file' then Archive.post(UrlCollector.file(source))
|
31
|
-
when 'crawl' then
|
33
|
+
when 'crawl' then crawl(source)
|
32
34
|
when 'sitemap' then Archive.post(UrlCollector.sitemap(source))
|
33
35
|
when 'url' then Archive.post_url(Request.resolve_url(source))
|
34
36
|
else
|
35
37
|
raise ArgumentError, "Unknown type: '#{type}'. Allowed types: sitemap, url, file, crawl"
|
36
38
|
end
|
37
39
|
end
|
40
|
+
|
41
|
+
# Crawl site for URLs to send to the Wayback Machine.
|
42
|
+
# @return [Array] with URLs sent to the Wayback Machine.
|
43
|
+
# @param [String] source for URL(s).
|
44
|
+
# @param [Integer] concurrency.
|
45
|
+
# @example Crawl example.com and send all URLs of the same domain
|
46
|
+
# WaybackArchiver.crawl('example.com') # Default concurrency is 5
|
47
|
+
# @example Crawl example.com and send all URLs of the same domain with low concurrency
|
48
|
+
# WaybackArchiver.crawl('example.com', concurrency: 1)
|
49
|
+
def self.crawl(source, concurrency: Archive::DEFAULT_CONCURRENCY)
|
50
|
+
Archive.crawl(source, concurrency: concurrency)
|
51
|
+
end
|
52
|
+
|
53
|
+
def self.logger=(logger)
|
54
|
+
@logger = logger
|
55
|
+
end
|
56
|
+
|
57
|
+
def self.logger
|
58
|
+
@logger ||= NullLogger.new
|
59
|
+
end
|
38
60
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wayback_archiver
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jacob Burenstam
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-
|
11
|
+
date: 2017-07-01 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: spidr
|
@@ -52,6 +52,20 @@ dependencies:
|
|
52
52
|
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '0.1'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: concurrent-ruby
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.0'
|
55
69
|
- !ruby/object:Gem::Dependency
|
56
70
|
name: bundler
|
57
71
|
requirement: !ruby/object:Gem::Requirement
|
@@ -150,7 +164,8 @@ dependencies:
|
|
150
164
|
- - ">"
|
151
165
|
- !ruby/object:Gem::Version
|
152
166
|
version: '0'
|
153
|
-
description: Send URLs to Wayback Machine. By crawling, sitemap,
|
167
|
+
description: Send URLs to Wayback Machine (Internet Archive). By crawling, sitemap,
|
168
|
+
file or single URL.
|
154
169
|
email:
|
155
170
|
- burenstam@gmail.com
|
156
171
|
executables:
|
@@ -161,7 +176,7 @@ files:
|
|
161
176
|
- bin/wayback_archiver
|
162
177
|
- lib/wayback_archiver.rb
|
163
178
|
- lib/wayback_archiver/archive.rb
|
164
|
-
- lib/wayback_archiver/
|
179
|
+
- lib/wayback_archiver/null_logger.rb
|
165
180
|
- lib/wayback_archiver/request.rb
|
166
181
|
- lib/wayback_archiver/url_collector.rb
|
167
182
|
- lib/wayback_archiver/version.rb
|
@@ -177,7 +192,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
177
192
|
requirements:
|
178
193
|
- - ">="
|
179
194
|
- !ruby/object:Gem::Version
|
180
|
-
version:
|
195
|
+
version: 2.0.0
|
181
196
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
182
197
|
requirements:
|
183
198
|
- - ">="
|
@@ -185,8 +200,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
185
200
|
version: '0'
|
186
201
|
requirements: []
|
187
202
|
rubyforge_project:
|
188
|
-
rubygems_version: 2.6.
|
203
|
+
rubygems_version: 2.6.11
|
189
204
|
signing_key:
|
190
205
|
specification_version: 4
|
191
|
-
summary: Send URLs to Wayback Machine
|
206
|
+
summary: Send URLs to Wayback Machine (Internet Archive)
|
192
207
|
test_files: []
|
@@ -1,28 +0,0 @@
|
|
1
|
-
require 'thread'
|
2
|
-
|
3
|
-
module WaybackArchiver
|
4
|
-
class ProcessQueue
|
5
|
-
# Process enumerable data in parallel.
|
6
|
-
# @return [Array] of URLs defined found during crawl.
|
7
|
-
# @param [Object] Enumberable object
|
8
|
-
# @example Print list of names in parallel
|
9
|
-
# ProcessQueue.process(%w(jacob peter eva)) { |v| puts n }
|
10
|
-
# @example Print list of names using 2 threads
|
11
|
-
# ProcessQueue.process(%w(jacob peter eva), threads_count: 2) { |v| puts n }
|
12
|
-
def self.process(data_array, threads_count: 5)
|
13
|
-
queue = Queue.new
|
14
|
-
data_array.each { |data| queue.push(data) }
|
15
|
-
workers = threads_count.times.map do
|
16
|
-
Thread.new do
|
17
|
-
begin
|
18
|
-
while data = queue.pop(true)
|
19
|
-
yield(data)
|
20
|
-
end
|
21
|
-
rescue ThreadError
|
22
|
-
end
|
23
|
-
end
|
24
|
-
end
|
25
|
-
workers.map(&:join)
|
26
|
-
end
|
27
|
-
end
|
28
|
-
end
|