relaton-w3c 1.3.2 → 1.3.3
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/relaton_w3c/hit_collection.rb +4 -1
- data/lib/relaton_w3c/scrapper.rb +4 -3
- data/lib/relaton_w3c/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 42a40987b4156671fee680b2ef9eb9a6b42f5a356f62c09d7f56eaf9ae466578
|
|
4
|
+
data.tar.gz: dcd2de5ae0c8582a2dc3fb29473faee5367c81cf48a394f6cf09b45134c66e0d
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: b94a6b93e792f44145b7b70139c673e534addc6989272c623ccfd3a1828b3376755f7193ca9dbcf35049f169a9c0084c3e8111977653ccb62fb5e8d7a2a18c9b
|
|
7
|
+
data.tar.gz: 272f89a76aeceacd9db2366cd80a0316023c3594a9fc058bed048b883ecea0dd07e63769e14988da0ea6506581ebd0d76539ee4097750bab5ee9ea5b415f6b24
|
|
@@ -46,9 +46,12 @@ module RelatonW3c
|
|
|
46
46
|
title ||= title_date
|
|
47
47
|
result = data.select do |hit|
|
|
48
48
|
(hit["title"].casecmp?(title) ||
|
|
49
|
-
hit["link"].split("/").last.match?(
|
|
49
|
+
hit["link"].split("/").last.match?(/-#{title}-/)) &&
|
|
50
50
|
type_date_filter(hit, type, date)
|
|
51
51
|
end
|
|
52
|
+
if result.empty?
|
|
53
|
+
result = data.select { |h| h["link"].split("/").last.match? /#{title}/ }
|
|
54
|
+
end
|
|
52
55
|
result.map { |h| Hit.new(h, self) }
|
|
53
56
|
end
|
|
54
57
|
|
data/lib/relaton_w3c/scrapper.rb
CHANGED
|
@@ -48,13 +48,14 @@ module RelatonW3c
|
|
|
48
48
|
def fetch_title(hit, doc) # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/MethodLength, Metrics/PerceivedComplexity
|
|
49
49
|
titles = []
|
|
50
50
|
if doc
|
|
51
|
-
title = doc.at("
|
|
52
|
-
titles << { content: title, type: "main" } if title
|
|
51
|
+
title = doc.at("//*[contains(@id, 'title')]")&.text
|
|
52
|
+
titles << { content: title, type: "main" } if title && !title.empty?
|
|
53
53
|
subtitle = doc.at(
|
|
54
54
|
"//h2[@id='subtitle']|//p[contains(@class, 'subline')]"
|
|
55
55
|
)&.text
|
|
56
56
|
titles << { content: subtitle, tipe: "subtitle" } if subtitle
|
|
57
|
-
|
|
57
|
+
end
|
|
58
|
+
if titles.empty? && hit["title"]
|
|
58
59
|
titles << { content: hit["title"], type: "main" }
|
|
59
60
|
end
|
|
60
61
|
titles.map do |t|
|
data/lib/relaton_w3c/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: relaton-w3c
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.3.
|
|
4
|
+
version: 1.3.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Ribose Inc.
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2020-09-
|
|
11
|
+
date: 2020-09-02 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: debase
|