archaeo 0.2.0 → 0.2.1
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/archaeo/availability_api.rb +1 -0
- data/lib/archaeo/bulk_downloader.rb +1 -0
- data/lib/archaeo/cdx_api.rb +9 -0
- data/lib/archaeo/fetcher.rb +8 -0
- data/lib/archaeo/page_bundle.rb +16 -0
- data/lib/archaeo/save_api.rb +1 -0
- data/lib/archaeo/version.rb +1 -1
- data/lib/archaeo.rb +1 -0
- metadata +2 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 8b82c7c8f2e568697056587556ac01bee92f51376af390aa26ed9c76221200d8
|
|
4
|
+
data.tar.gz: 411cf04b07219a02e5b049120bb74528dc17cf5fcb8424acd3c7c5ee69659bea
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ec87c66817c1ce3f318e45d5b26221ca44c1958dfa9009fbe1541a1b3bbdb8e4585f6baf66e73c6a839a10d938e189b61dbea43afccf74a6f55476ad8719e18e
|
|
7
|
+
data.tar.gz: 0c33454fa368f009a7383ebc8a6a79f3638615740bd312eaab568c21d90cb20a0c4c6615324b20634f00614021016cf6d464910679fcf61fdf8d663097935cd7
|
data/lib/archaeo/cdx_api.rb
CHANGED
|
@@ -47,6 +47,7 @@ module Archaeo
|
|
|
47
47
|
# Returns an Enumerator of Snapshot objects, auto-paginating
|
|
48
48
|
# via resume key unless an explicit page is requested.
|
|
49
49
|
def snapshots(url, **options)
|
|
50
|
+
url = UrlNormalizer.normalize(url)
|
|
50
51
|
validate_options!(options)
|
|
51
52
|
|
|
52
53
|
Enumerator.new do |yielder|
|
|
@@ -59,9 +60,15 @@ module Archaeo
|
|
|
59
60
|
end
|
|
60
61
|
|
|
61
62
|
def near(url, timestamp:)
|
|
63
|
+
url = UrlNormalizer.normalize(url)
|
|
62
64
|
ts = Timestamp.coerce(timestamp)
|
|
63
65
|
result = snapshots(url, sort: "closest",
|
|
64
66
|
closest: ts.to_s, limit: 1).first
|
|
67
|
+
if result&.blocked?
|
|
68
|
+
raise BlockedSiteError,
|
|
69
|
+
"Site is blocked: #{url}"
|
|
70
|
+
end
|
|
71
|
+
|
|
65
72
|
result || raise(NoSnapshotFound,
|
|
66
73
|
"No snapshot found near #{ts} for #{url}")
|
|
67
74
|
end
|
|
@@ -94,6 +101,7 @@ module Archaeo
|
|
|
94
101
|
|
|
95
102
|
# Returns the number of pages for a paginated query.
|
|
96
103
|
def num_pages(url, **options)
|
|
104
|
+
url = UrlNormalizer.normalize(url)
|
|
97
105
|
params = { "url" => url, "showNumPages" => "true" }
|
|
98
106
|
merge_scalar_params!(params, options)
|
|
99
107
|
response = @client.get(
|
|
@@ -109,6 +117,7 @@ module Archaeo
|
|
|
109
117
|
|
|
110
118
|
# Returns all unique original URLs under a domain.
|
|
111
119
|
def known_urls(domain, match_type: "domain")
|
|
120
|
+
domain = UrlNormalizer.normalize(domain)
|
|
112
121
|
snapshots(domain, match_type: match_type,
|
|
113
122
|
collapse: ["urlkey"]).map(&:original_url).uniq
|
|
114
123
|
end
|
data/lib/archaeo/fetcher.rb
CHANGED
|
@@ -14,6 +14,7 @@ module Archaeo
|
|
|
14
14
|
end
|
|
15
15
|
|
|
16
16
|
def fetch(url, timestamp:, identity: false)
|
|
17
|
+
url = UrlNormalizer.normalize(url)
|
|
17
18
|
ts = Timestamp.coerce(timestamp)
|
|
18
19
|
archive_url = ArchiveUrl.new(url, timestamp: ts,
|
|
19
20
|
identity: identity)
|
|
@@ -21,6 +22,13 @@ module Archaeo
|
|
|
21
22
|
build_page(response, archive_url.to_s, url, ts)
|
|
22
23
|
end
|
|
23
24
|
|
|
25
|
+
def fetch_page_with_assets(url, timestamp:)
|
|
26
|
+
page = fetch(url, timestamp: timestamp)
|
|
27
|
+
assets = AssetExtractor.new(page.content,
|
|
28
|
+
base_url: page.archive_url).extract
|
|
29
|
+
PageBundle.new(page: page, assets: assets)
|
|
30
|
+
end
|
|
31
|
+
|
|
24
32
|
private
|
|
25
33
|
|
|
26
34
|
def build_page(response, archive_url, url, timestamp)
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Archaeo
|
|
4
|
+
# A fetched page together with all its extracted asset URLs.
|
|
5
|
+
#
|
|
6
|
+
# Bundles a Page with the AssetList discovered from its HTML,
|
|
7
|
+
# providing a single object for complete page archival.
|
|
8
|
+
class PageBundle
|
|
9
|
+
attr_reader :page, :assets
|
|
10
|
+
|
|
11
|
+
def initialize(page:, assets:)
|
|
12
|
+
@page = page
|
|
13
|
+
@assets = assets
|
|
14
|
+
end
|
|
15
|
+
end
|
|
16
|
+
end
|
data/lib/archaeo/save_api.rb
CHANGED
data/lib/archaeo/version.rb
CHANGED
data/lib/archaeo.rb
CHANGED
|
@@ -19,6 +19,7 @@ module Archaeo
|
|
|
19
19
|
autoload :ArchiveUrl, "archaeo/archive_url"
|
|
20
20
|
autoload :Snapshot, "archaeo/snapshot"
|
|
21
21
|
autoload :Page, "archaeo/page"
|
|
22
|
+
autoload :PageBundle, "archaeo/page_bundle"
|
|
22
23
|
autoload :SaveResult, "archaeo/save_result"
|
|
23
24
|
autoload :AvailabilityResult, "archaeo/availability_result"
|
|
24
25
|
autoload :UrlNormalizer, "archaeo/url_normalizer"
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: archaeo
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.2.
|
|
4
|
+
version: 0.2.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Ribose Inc.
|
|
@@ -84,6 +84,7 @@ files:
|
|
|
84
84
|
- lib/archaeo/fetcher.rb
|
|
85
85
|
- lib/archaeo/http_client.rb
|
|
86
86
|
- lib/archaeo/page.rb
|
|
87
|
+
- lib/archaeo/page_bundle.rb
|
|
87
88
|
- lib/archaeo/save_api.rb
|
|
88
89
|
- lib/archaeo/save_result.rb
|
|
89
90
|
- lib/archaeo/snapshot.rb
|