wayback_machine_downloader 0.4.1 → 0.4.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/bin/wayback_machine_downloader +4 -0
- data/lib/wayback_machine_downloader.rb +7 -3
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: dfe1b1274056f709121477fb93bdaa45b1580745
|
4
|
+
data.tar.gz: 1c97898ad292a2a2a89377c19e8e96f623a4ce2b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0c196f8e23887413a6f694f88548ff960b85115d3b5b0fccdb120b5b6b7efd9a2ad23ebdf24e34c8f5ab66cfdfd7c7c4b36db034f14ae864da6d392509bb6873
|
7
|
+
data.tar.gz: 0f0a42c3d5d0679c11eabacae2420ed901119af4a18246798320dc836dae4f9c64d57500dd6edf424d6c9ae8612b93162e57551fd76d3d27ec40910617bdbcbc
|
@@ -30,6 +30,10 @@ option_parser = OptionParser.new do |opts|
|
|
30
30
|
options[:exclude_filter] = t
|
31
31
|
end
|
32
32
|
|
33
|
+
opts.on("-a", "--all", "Expand downloading to error files (40x and 50x) and redirections (30x)") do |t|
|
34
|
+
options[:all] = true
|
35
|
+
end
|
36
|
+
|
33
37
|
opts.on("-v", "--version", "Display version") do |t|
|
34
38
|
options[:version] = t
|
35
39
|
end
|
@@ -8,9 +8,9 @@ require_relative 'wayback_machine_downloader/to_regex'
|
|
8
8
|
|
9
9
|
class WaybackMachineDownloader
|
10
10
|
|
11
|
-
VERSION = "0.4.
|
11
|
+
VERSION = "0.4.2"
|
12
12
|
|
13
|
-
attr_accessor :base_url, :from_timestamp, :to_timestamp, :only_filter, :exclude_filter
|
13
|
+
attr_accessor :base_url, :from_timestamp, :to_timestamp, :only_filter, :exclude_filter, :all
|
14
14
|
|
15
15
|
def initialize params
|
16
16
|
@base_url = params[:base_url]
|
@@ -18,6 +18,7 @@ class WaybackMachineDownloader
|
|
18
18
|
@to_timestamp = params[:to_timestamp].to_i
|
19
19
|
@only_filter = params[:only_filter]
|
20
20
|
@exclude_filter = params[:exclude_filter]
|
21
|
+
@all = params[:all]
|
21
22
|
end
|
22
23
|
|
23
24
|
def backup_name
|
@@ -55,7 +56,10 @@ class WaybackMachineDownloader
|
|
55
56
|
end
|
56
57
|
|
57
58
|
def get_file_list_curated
|
58
|
-
parameters_for_wayback_machine_api = "&fl=timestamp,original&
|
59
|
+
parameters_for_wayback_machine_api = "&fl=timestamp,original&collapse=original"
|
60
|
+
unless @all
|
61
|
+
parameters_for_wayback_machine_api += "&filter=statuscode:200"
|
62
|
+
end
|
59
63
|
if @from_timestamp and @from_timestamp != 0
|
60
64
|
parameters_for_wayback_machine_api += "&from=" + @from_timestamp.to_s
|
61
65
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wayback_machine_downloader
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.4.
|
4
|
+
version: 0.4.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- hartator
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-07-
|
11
|
+
date: 2016-07-31 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rake
|