xml_row_finder 0.2.0 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- checksums.yaml.gz.sig +3 -6
- data/lib/xml_row_finder.rb +65 -10
- data.tar.gz.sig +0 -0
- metadata +6 -6
- metadata.gz.sig +0 -0
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 29c7aa56863bd3e1d4d7cc5bcc35c05a3c447fa6e3529b7cef763dbe2ca14091
|
4
|
+
data.tar.gz: 4113bc3c0d63433df71e5e04720c084a457a698eb432544c0043bc5ee4aa09f1
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b1424142187bb87172c1c772f54a4693c36b8f903fc20781275ea5c70003cff388472c33eb68815ea2ce1d2f70e0b0b9ba84db1caa04032615b8fc7a1a74a259
|
7
|
+
data.tar.gz: d34b7cf995f00cadf57c4ecec858d56540cf43ca7234b1db4937b4ac83cea440f32d6ed38479983476e37ad11e00a9d6242bae33159586981d77174992d42698
|
checksums.yaml.gz.sig
CHANGED
@@ -1,6 +1,3 @@
|
|
1
|
-
|
2
|
-
�
|
3
|
-
|
4
|
-
+I�����6`��h>�����y6l+��@�Iq=�/"���v�����HN�>���s4G3�/�H
|
5
|
-
�2���?նͰ;��8O�W�߯�M�����E��
|
6
|
-
�~���7��
|
1
|
+
n��v,s�oF6D:�K��A���ƈiK3S���`5��h�Iᇔ����Po��
|
2
|
+
\f���@���s�*���j"��w7�}
|
3
|
+
���!�1uj��j^�
|
data/lib/xml_row_finder.rb
CHANGED
@@ -2,29 +2,44 @@
|
|
2
2
|
|
3
3
|
# file: xml_row_finder.rb
|
4
4
|
|
5
|
-
require '
|
6
|
-
require 'rexml'
|
7
|
-
include REXML
|
5
|
+
require 'nokorexi'
|
8
6
|
|
9
7
|
|
10
8
|
class XMLRowFinder
|
11
9
|
|
12
10
|
attr_reader :to_a
|
13
11
|
|
14
|
-
def initialize(
|
12
|
+
def initialize(raws, debug: false)
|
15
13
|
|
16
14
|
@debug = debug
|
17
|
-
|
18
|
-
@
|
15
|
+
|
16
|
+
@doc = if raws =~ /^http/ then
|
17
|
+
|
18
|
+
nki = Nokorexi.new(url=raws) do |doc1|
|
19
|
+
doc1.xpath('//*[@onclick]').each do |e|
|
20
|
+
e.attributes['onclick'].value = ''
|
21
|
+
end
|
22
|
+
|
23
|
+
doc1.xpath('//*[@onmousedown]').each do |e|
|
24
|
+
e.attributes['onmousedown'].value = ''
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
28
|
+
|
29
|
+
nki.to_doc
|
30
|
+
|
31
|
+
else
|
32
|
+
Rexle.new(raws)
|
33
|
+
end
|
19
34
|
|
20
35
|
a = []
|
21
36
|
|
22
|
-
doc.root.each_recursive do |e|
|
37
|
+
@doc.root.each_recursive do |e|
|
23
38
|
e.attributes.delete
|
24
39
|
a << e.backtrack.to_xpath
|
25
40
|
end
|
26
41
|
|
27
|
-
@to_a = a2 = a.map {|e| [a.count(e), e] }
|
42
|
+
@to_a = a2 = a.map {|e| [a.count(e), e] }.uniq
|
28
43
|
xpath = a2.max_by(&:first).last
|
29
44
|
|
30
45
|
a3 = xpath.split('/')
|
@@ -35,20 +50,60 @@ class XMLRowFinder
|
|
35
50
|
p1 << a3.pop; a4 << a3.join('/') + "[%s]" % p1.reverse.join('/')
|
36
51
|
end
|
37
52
|
|
53
|
+
# using Nokogiri since Rexle has a bug with xpath predicates
|
54
|
+
#
|
55
|
+
@doc2 = Nokogiri::XML(@doc.root.xml)
|
56
|
+
|
38
57
|
a5 = a4[0..-2].map do |xpath2|
|
39
|
-
[
|
58
|
+
[@doc2.xpath(xpath2).length, xpath2]
|
40
59
|
end
|
41
60
|
|
42
61
|
@xpath = a5.reverse.detect {|num, xpath2| num > 1}.last
|
43
62
|
|
63
|
+
last_row = @doc2.xpath(@xpath).last
|
64
|
+
|
65
|
+
# find the container element
|
66
|
+
xpath = @xpath[/^[^\[]+/]
|
67
|
+
axpath = xpath.split('/')
|
68
|
+
e = @doc.element xpath
|
69
|
+
|
70
|
+
until (e.xml.include? last_row) do
|
71
|
+
axpath.pop
|
72
|
+
e = @doc.element axpath.join('/')
|
73
|
+
end
|
74
|
+
|
75
|
+
@cont_xpath = axpath.join('/')
|
76
|
+
|
77
|
+
end
|
78
|
+
|
79
|
+
# returns the container element for all rows
|
80
|
+
# object returned: Rexle::Element
|
81
|
+
#
|
82
|
+
def body()
|
83
|
+
@doc.element @cont_xpath
|
44
84
|
end
|
45
85
|
|
86
|
+
# returns the xpath pointing to the container element for all rows
|
87
|
+
#
|
88
|
+
def body_xpath()
|
89
|
+
@cont_xpath
|
90
|
+
end
|
91
|
+
|
92
|
+
|
93
|
+
# returns rows
|
94
|
+
# object returned: An array of Nokogiri XML Element object
|
95
|
+
#
|
46
96
|
def rows()
|
47
|
-
|
97
|
+
@doc2.xpath @xpath
|
48
98
|
end
|
49
99
|
|
100
|
+
# returns the xpath pointing to the rows
|
101
|
+
#
|
50
102
|
def to_xpath()
|
51
103
|
@xpath
|
52
104
|
end
|
53
105
|
|
106
|
+
alias rows_xpath to_xpath
|
107
|
+
|
108
|
+
|
54
109
|
end
|
data.tar.gz.sig
CHANGED
Binary file
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: xml_row_finder
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- James Robertson
|
@@ -38,25 +38,25 @@ cert_chain:
|
|
38
38
|
date: 2022-01-24 00:00:00.000000000 Z
|
39
39
|
dependencies:
|
40
40
|
- !ruby/object:Gem::Dependency
|
41
|
-
name:
|
41
|
+
name: nokorexi
|
42
42
|
requirement: !ruby/object:Gem::Requirement
|
43
43
|
requirements:
|
44
44
|
- - "~>"
|
45
45
|
- !ruby/object:Gem::Version
|
46
|
-
version: '
|
46
|
+
version: '0.5'
|
47
47
|
- - ">="
|
48
48
|
- !ruby/object:Gem::Version
|
49
|
-
version:
|
49
|
+
version: 0.5.4
|
50
50
|
type: :runtime
|
51
51
|
prerelease: false
|
52
52
|
version_requirements: !ruby/object:Gem::Requirement
|
53
53
|
requirements:
|
54
54
|
- - "~>"
|
55
55
|
- !ruby/object:Gem::Version
|
56
|
-
version: '
|
56
|
+
version: '0.5'
|
57
57
|
- - ">="
|
58
58
|
- !ruby/object:Gem::Version
|
59
|
-
version:
|
59
|
+
version: 0.5.4
|
60
60
|
description:
|
61
61
|
email: digital.robertson@gmail.com
|
62
62
|
executables: []
|
metadata.gz.sig
CHANGED
Binary file
|