aranha-parsers 0.19.1 → 0.21.0
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/aranha/parsers/html/base.rb +7 -0
- data/lib/aranha/parsers/html/node/default/miscellaneous_support.rb +23 -0
- data/lib/aranha/parsers/html/node/default/nodes_support.rb +30 -0
- data/lib/aranha/parsers/html/node/default.rb +3 -23
- data/lib/aranha/parsers/version.rb +1 -1
- metadata +6 -10
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6020b51d20ef2c677664058978015a69c4ed80c15c7c169f300acaa5b5335a22
|
4
|
+
data.tar.gz: 44bfaaa2b28b7cacd935074b9f48bfaf9cf62e9d952f2744e8bb76fe4045a72f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f1a926d3f7b051f17ee9df3c4642fcf9cf7707c9c9c70600d9a58be63bce9f80fdc35e589c41899365a854e0c506ddcf038cb96776761c2fb0916f7acd8e84da
|
7
|
+
data.tar.gz: c27820771a1fd288597218fc7af862c43a4eed9eb3d9c87454cc4da84814b8e270782507d16a697bd42ffc85c859b1a672978fbe02401ec4978fb81eb22cbb78
|
@@ -25,6 +25,13 @@ module Aranha
|
|
25
25
|
from_string(node.to_html)
|
26
26
|
end
|
27
27
|
|
28
|
+
# @param node [String]
|
29
|
+
# @param klass [String]
|
30
|
+
# @return [String]
|
31
|
+
def xpath_contains_class(klass, node = '@class')
|
32
|
+
"contains(concat(' ', normalize-space(#{node}), ' '), ' #{klass} ')"
|
33
|
+
end
|
34
|
+
|
28
35
|
# @param haystack [String]
|
29
36
|
# @param needle [String]
|
30
37
|
# @return [String]
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'aranha/parsers/html/node/base'
|
4
|
+
require 'eac_ruby_utils/core_ext'
|
5
|
+
|
6
|
+
module Aranha
|
7
|
+
module Parsers
|
8
|
+
module Html
|
9
|
+
module Node
|
10
|
+
class Default < ::Aranha::Parsers::Html::Node::Base
|
11
|
+
module MiscellaneousSupport
|
12
|
+
# @param node [Nokogiri::XML::Node]
|
13
|
+
# @param xpath [String]
|
14
|
+
# @return [Boolean]
|
15
|
+
def boolean_value(node, xpath)
|
16
|
+
node_value(node, xpath).to_bool
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'aranha/parsers/html/node/base'
|
4
|
+
require 'eac_ruby_utils/core_ext'
|
5
|
+
|
6
|
+
module Aranha
|
7
|
+
module Parsers
|
8
|
+
module Html
|
9
|
+
module Node
|
10
|
+
class Default < ::Aranha::Parsers::Html::Node::Base
|
11
|
+
module NodesSupport
|
12
|
+
# @param node [Nokogiri::XML::Node]
|
13
|
+
# @param xpath [String]
|
14
|
+
# @return [Nokogiri::XML::NodeSet]
|
15
|
+
def node_set_value(node, xpath)
|
16
|
+
node.xpath(xpath)
|
17
|
+
end
|
18
|
+
|
19
|
+
# @param node [Nokogiri::XML::Node]
|
20
|
+
# @param xpath [String]
|
21
|
+
# @return [Nokogiri::XML::Node]
|
22
|
+
def node_value(node, xpath)
|
23
|
+
node.at_xpath(xpath)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
@@ -10,31 +10,11 @@ module Aranha
|
|
10
10
|
class Default < ::Aranha::Parsers::Html::Node::Base
|
11
11
|
require_sub __FILE__, include_modules: true
|
12
12
|
|
13
|
-
def join_value(node, xpath)
|
14
|
-
m = ''
|
15
|
-
node_set_value(node, xpath).each do |n|
|
16
|
-
m << n.text.strip
|
17
|
-
end
|
18
|
-
m
|
19
|
-
end
|
20
|
-
|
21
|
-
def duration_value(node, xpath)
|
22
|
-
m = /(\d+) m/.match(join_value(node, xpath))
|
23
|
-
m ? m[1].to_i : nil
|
24
|
-
end
|
25
|
-
|
26
|
-
# @param node [Nokogiri::XML::Node]
|
27
|
-
# @param xpath [String]
|
28
|
-
# @return [Nokogiri::XML::NodeSet]
|
29
|
-
def node_set_value(node, xpath)
|
30
|
-
node.xpath(xpath)
|
31
|
-
end
|
32
|
-
|
33
13
|
# @param node [Nokogiri::XML::Node]
|
34
14
|
# @param xpath [String]
|
35
|
-
# @return [
|
36
|
-
def
|
37
|
-
node
|
15
|
+
# @return [Boolean]
|
16
|
+
def boolean_value(node, xpath)
|
17
|
+
node_value(node, xpath).to_bool
|
38
18
|
end
|
39
19
|
end
|
40
20
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: aranha-parsers
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.21.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Esquilo Azul Company
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-
|
11
|
+
date: 2023-06-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activesupport
|
@@ -50,20 +50,14 @@ dependencies:
|
|
50
50
|
requirements:
|
51
51
|
- - "~>"
|
52
52
|
- !ruby/object:Gem::Version
|
53
|
-
version: '0.
|
54
|
-
- - ">="
|
55
|
-
- !ruby/object:Gem::Version
|
56
|
-
version: 0.3.2
|
53
|
+
version: '0.4'
|
57
54
|
type: :runtime
|
58
55
|
prerelease: false
|
59
56
|
version_requirements: !ruby/object:Gem::Requirement
|
60
57
|
requirements:
|
61
58
|
- - "~>"
|
62
59
|
- !ruby/object:Gem::Version
|
63
|
-
version: '0.
|
64
|
-
- - ">="
|
65
|
-
- !ruby/object:Gem::Version
|
66
|
-
version: 0.3.2
|
60
|
+
version: '0.4'
|
67
61
|
- !ruby/object:Gem::Dependency
|
68
62
|
name: eac_ruby_utils
|
69
63
|
requirement: !ruby/object:Gem::Requirement
|
@@ -147,6 +141,8 @@ files:
|
|
147
141
|
- lib/aranha/parsers/html/node.rb
|
148
142
|
- lib/aranha/parsers/html/node/base.rb
|
149
143
|
- lib/aranha/parsers/html/node/default.rb
|
144
|
+
- lib/aranha/parsers/html/node/default/miscellaneous_support.rb
|
145
|
+
- lib/aranha/parsers/html/node/default/nodes_support.rb
|
150
146
|
- lib/aranha/parsers/html/node/default/numeric_support.rb
|
151
147
|
- lib/aranha/parsers/html/node/default/string_support.rb
|
152
148
|
- lib/aranha/parsers/invalid_state_exception.rb
|