xml_col_finder 0.2.3 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4229c7009179e903163ef10f64f0917a7f67e29d588172d184bed94f716123cf
-  data.tar.gz: f543fcbacf5ca517995d28fc6050671b48f18c8ae9df539aad6133486d7b74f5
+  metadata.gz: 82516bf9b6e8ca979788ac9be6024ec6cc698e959a89b13006a75bba13e473ba
+  data.tar.gz: deddd9d4197bab3913761d93e8f02a44f66f49968ae1985ab16e8d411ad8f755
 SHA512:
-  metadata.gz: 22cd4abb94f055f100d0f56993de883fa87d1bcb2e59ef9edaf0f3f46846f49aa2c73f7e0a38f4779d40314ad5a93bfe91b22738d347bf5866afc1b2ed58c105
-  data.tar.gz: 10c48be3a91d355aa826ebaf1e5b6329e2f3ec7acabc795e8800eb4758fe0abed45cfaee761a91190f72b4407e7b0a0a9accc19b563ca770057a98aa7dfb148b
+  metadata.gz: de927549a8e8451f66891bc558523ff2332786d79a6966f827ed5480ba06fa14b57c8116abb528176184de6b4b0357245ca1940316c2ac0d696c672ce3bc49c6
+  data.tar.gz: fdb5610f7b3f0775b0e156ec9f1c19be35a6374187fa40259481e7dd4b949c0df0202250dcc678ecb2eef906d2323c76400456081c52bbb1277cacca000fd9f3

data/lib/xml_col_finder.rb

@@ -3,28 +3,41 @@
 # file: xml_col_finder.rb
 
 require 'rexle'
+require 'clipboard'
 
+# how to use this gem?
+#
+# 1. Find a web page to fetch values from
+# 2. Press F12 to invoke developer tools
+# 3. right-click on the element containing the
+#    child elements containing the values
+# 4. select copy > copy outerHTML
+# 5. paste the test into a file
+# 6. File.read the txt file and pass it to XMLColFinder.new
+
+# note: There's a to_code method which makes it convenient to fetch the
+#       values from the generated code.
 
 class XMLColFinder
 
   attr_reader :to_a
 
-  def initialize(s, debug: false)
+  def initialize(obj, debug: false)
 
     @debug = debug
-    @doc = Rexle.new(s)
+    @doc = obj.is_a?(Rexle) ? obj : Rexle.new(obj)
 
     a = []
     @doc.root.each_recursive do |node|
 
-      if node.text then
+      if node.text and node.text.strip.length >= 1 then
         a << [BacktrackXPath.new(node, ignore_id: true).to_xpath.split('/'),
               node.text]
       end
 
     end
 
-    #@to_a = a
+    @to_a = a
     h = group_by_xpath(a)
     @to_a = truncate_xpath(h).flatten(1)
 
@@ -42,8 +55,17 @@ class XMLColFinder
     a = scan(remaining, eid)
 
     lines = a.flatten.compact.prepend linex
-    lines.join("\n").lines\
-        .map {|line|  line =~ /.text$/ ? 'puts ' + line : line }.join
+    lines2 = lines.join("\n").lines\
+        .map {|line|  line =~ /.text$/ ? 'puts ' + line : line }
+    lines2[0].sub!(/(?<=\")div/,'//div')
+    s = "require 'nokorexi'
+
+url = 'https://insert-your-url'
+doc = Nokorexi.new(url).to_doc
+" + lines2.join
+
+    Clipboard.copy s
+    return s
 
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: xml_col_finder
 version: !ruby/object:Gem::Version
-  version: 0.2.3
+  version: 0.3.0
 platform: ruby
 authors:
 - James Robertson
@@ -35,7 +35,7 @@ cert_chain:
   GSlZ9ilAfm8srTjbZ2cWQyNGGxH+zHQ3Z02c4ZEtgPv/wHjptd1VeBm0P1aemsRA
   ShsxXxzmzIrRENmpBp3tyR3k
   -----END CERTIFICATE-----
-date: 2022-01-24 00:00:00.000000000 Z
+date: 2022-03-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rexle
@@ -57,6 +57,26 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 1.5.14
+- !ruby/object:Gem::Dependency
+  name: clipboard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.3.6
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.3.6
 description: 
 email: digital.robertson@gmail.com
 executables: []
@@ -83,8 +103,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.10
+rubygems_version: 3.2.22
 signing_key: 
 specification_version: 4
 summary: Attempts to return the relative xpath for each element containing text.