wayback_machine_downloader 0.4.0 → 0.4.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/bin/wayback_machine_downloader +10 -5
- data/lib/wayback_machine_downloader.rb +3 -1
- metadata +6 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 98ea352b6eae2e49f915634245d65f109a864ed0
|
4
|
+
data.tar.gz: 5eee04e5f319e23709ef94f6677c194deaa81640
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6788c3f2e764e1ebe02ee967e4653814b1fe8de316ffc8eb307dbd85eabc5c6b867b4abda5b2dd36300cd5e96f353429740b206d6ad871cd1b78b760f99ca029
|
7
|
+
data.tar.gz: 7795541cd32a39a7b78875a8a841ec8124df01aa38b9504e8f29109d2d431b1299d76170624739786d3ebf28fa8eeacd1081ed496498e69ef6fa40f31dfc29c0
|
@@ -9,20 +9,24 @@ option_parser = OptionParser.new do |opts|
|
|
9
9
|
opts.banner = "Usage: wayback_machine_downloader http://example.com"
|
10
10
|
|
11
11
|
opts.separator ""
|
12
|
-
opts.separator "Download
|
12
|
+
opts.separator "Download an entire website from the Wayback Machine."
|
13
13
|
|
14
14
|
opts.separator ""
|
15
15
|
opts.separator "Optional options:"
|
16
16
|
|
17
|
-
opts.on("-
|
18
|
-
options[:
|
17
|
+
opts.on("-f", "--from TIMESTAMP", Integer, "Only files on or after timestamp supplied (ie. 20060716231334)") do |t|
|
18
|
+
options[:from_timestamp] = t
|
19
|
+
end
|
20
|
+
|
21
|
+
opts.on("-t", "--to TIMESTAMP", Integer, "Only files on or before timestamp supplied (ie. 20100916231334)") do |t|
|
22
|
+
options[:to_timestamp] = t
|
19
23
|
end
|
20
24
|
|
21
25
|
opts.on("-o", "--only ONLY_FILTER", String, "Restrict downloading to urls that match this filter (use // notation for the filter to be treated as a regex)") do |t|
|
22
26
|
options[:only_filter] = t
|
23
27
|
end
|
24
28
|
|
25
|
-
opts.on("-x", "--exclude EXCLUDE_FILTER", String, "Skip urls that match this filter (use // notation for the filter to be treated as a regex)") do |t|
|
29
|
+
opts.on("-x", "--exclude EXCLUDE_FILTER", String, "Skip downloading of urls that match this filter (use // notation for the filter to be treated as a regex)") do |t|
|
26
30
|
options[:exclude_filter] = t
|
27
31
|
end
|
28
32
|
|
@@ -32,7 +36,8 @@ option_parser = OptionParser.new do |opts|
|
|
32
36
|
end.parse!
|
33
37
|
|
34
38
|
if (base_url = ARGV[-1])
|
35
|
-
|
39
|
+
options[:base_url] = base_url
|
40
|
+
wayback_machine_downloader = WaybackMachineDownloader.new options
|
36
41
|
wayback_machine_downloader.download_files
|
37
42
|
elsif options[:version]
|
38
43
|
puts WaybackMachineDownloader::VERSION
|
@@ -8,7 +8,7 @@ require_relative 'wayback_machine_downloader/to_regex'
|
|
8
8
|
|
9
9
|
class WaybackMachineDownloader
|
10
10
|
|
11
|
-
VERSION = "0.4.
|
11
|
+
VERSION = "0.4.1"
|
12
12
|
|
13
13
|
attr_accessor :base_url, :from_timestamp, :to_timestamp, :only_filter, :exclude_filter
|
14
14
|
|
@@ -110,6 +110,8 @@ class WaybackMachineDownloader
|
|
110
110
|
puts "No files to download."
|
111
111
|
puts "Possible reaosons:"
|
112
112
|
puts "\t* Site is not in Wayback Machine Archive."
|
113
|
+
puts "\t* From timestamp too much in the future." if @from_timestamp and @from_timestamp != 0
|
114
|
+
puts "\t* To timestamp too much in the past." if @to_timestamp and @to_timestamp != 0
|
113
115
|
puts "\t* Only filter too restrictive (#{only_filter.to_s})" if @only_filter
|
114
116
|
puts "\t* Exclude filter too wide (#{exclude_filter.to_s})" if @exclude_filter
|
115
117
|
return
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
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: 0.4.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- hartator
|
@@ -38,9 +38,10 @@ dependencies:
|
|
38
38
|
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '5.2'
|
41
|
-
description: Download
|
42
|
-
Archive (archive.org) is an awesome tool to view any website at any
|
43
|
-
but lacks an export feature. Wayback Machine Downloader brings exactly
|
41
|
+
description: Download an entire website from the Wayback Machine. Wayback Machine
|
42
|
+
by Internet Archive (archive.org) is an awesome tool to view any website at any
|
43
|
+
point of time but lacks an export feature. Wayback Machine Downloader brings exactly
|
44
|
+
this.
|
44
45
|
email: hartator@gmail.com
|
45
46
|
executables:
|
46
47
|
- wayback_machine_downloader
|
@@ -74,5 +75,5 @@ rubyforge_project:
|
|
74
75
|
rubygems_version: 2.4.5.1
|
75
76
|
signing_key:
|
76
77
|
specification_version: 4
|
77
|
-
summary: Download
|
78
|
+
summary: Download an entire website from the Wayback Machine.
|
78
79
|
test_files: []
|