wayback_machine_downloader 0.1.9 → 0.1.10
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/lib/wayback_machine_downloader.rb +8 -4
- 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: 496908f840d930edf5e8b5f3b5c59e3d58e73be9
|
4
|
+
data.tar.gz: 063fd94ab7d33a93144d2681cf95441cd569aa4d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b2297fb81c3f58ceab2ce9ce4deabfc4a9a2b1d3005f935ec1f19ab296120860a04704944b34e7fd85d75269f402b05fe113911aaae60c7b49f9093ed4b9feaf
|
7
|
+
data.tar.gz: 35ee0a0087c9bff653e874baa4c4a5dfeed9e62d08dfcef0d8b4aea39c933589aa7976382625f40e32c7fc0f45f8b11e3628db55338bce1a163be3847b345b27
|
@@ -1,9 +1,10 @@
|
|
1
1
|
require 'open-uri'
|
2
2
|
require 'fileutils'
|
3
|
+
require_relative 'tidy_bytes'
|
3
4
|
|
4
5
|
class WaybackMachineDownloader
|
5
6
|
|
6
|
-
VERSION = "0.1.
|
7
|
+
VERSION = "0.1.10"
|
7
8
|
|
8
9
|
attr_accessor :base_url, :timestamp
|
9
10
|
|
@@ -31,7 +32,10 @@ class WaybackMachineDownloader
|
|
31
32
|
file_url = line[2]
|
32
33
|
file_id = file_url.split('/')[3..-1].join('/')
|
33
34
|
file_id = URI.unescape file_id
|
34
|
-
|
35
|
+
file_id = file_id.tidy_bytes unless file_id == ""
|
36
|
+
if file_id.nil?
|
37
|
+
puts "Malformed file url, ignoring: #{file_url}"
|
38
|
+
elsif @timestamp == 0 or file_timestamp <= @timestamp
|
35
39
|
if file_list_curated[file_id]
|
36
40
|
unless file_list_curated[file_id][:timestamp] > file_timestamp
|
37
41
|
file_list_curated[file_id] = {file_url: file_url, timestamp: file_timestamp}
|
@@ -55,7 +59,7 @@ class WaybackMachineDownloader
|
|
55
59
|
end
|
56
60
|
|
57
61
|
def download_files
|
58
|
-
puts "Downlading #{@base_url} from Wayback Machine..."
|
62
|
+
puts "Downlading #{@base_url} to #{backup_path} from Wayback Machine..."
|
59
63
|
puts
|
60
64
|
file_list_curated = get_file_list_curated
|
61
65
|
count = 0
|
@@ -84,7 +88,7 @@ class WaybackMachineDownloader
|
|
84
88
|
rescue OpenURI::HTTPError => e
|
85
89
|
puts "#{file_url} # #{e}"
|
86
90
|
file.write(e.io.read)
|
87
|
-
rescue
|
91
|
+
rescue StandardError => e
|
88
92
|
puts "#{file_url} # #{e}"
|
89
93
|
end
|
90
94
|
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: 0.1.
|
4
|
+
version: 0.1.10
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- hartator
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-08-
|
11
|
+
date: 2015-08-18 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: pry-rescue
|