xml_col_finder 0.2.1 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fb9968f62dfa167170d225305499a06a3fb07949d22b44cfc5fc7aaff2250e70
-  data.tar.gz: 590549966bf32070036e68f45ff1c61cc5b81b7c11a5237466928e573758eeb5
+  metadata.gz: 82516bf9b6e8ca979788ac9be6024ec6cc698e959a89b13006a75bba13e473ba
+  data.tar.gz: deddd9d4197bab3913761d93e8f02a44f66f49968ae1985ab16e8d411ad8f755
 SHA512:
-  metadata.gz: a022f1836170e5628062360a2bef7d4fc26ac1748dd7970fd56eb76ca5fa194f2f61b75bf7f8dfe667191ef194aeb2306a8c5e94e55552aafa105e0d34a7828b
-  data.tar.gz: 2f932bcffe0ace2bfc4fdefb3df0fde1cff61e3095110fb765de6732c096c44066e13046591c8423bb75465e9b981774751c225b9791a72601bac97bb24237a5
+  metadata.gz: de927549a8e8451f66891bc558523ff2332786d79a6966f827ed5480ba06fa14b57c8116abb528176184de6b4b0357245ca1940316c2ac0d696c672ce3bc49c6
+  data.tar.gz: fdb5610f7b3f0775b0e156ec9f1c19be35a6374187fa40259481e7dd4b949c0df0202250dcc678ecb2eef906d2323c76400456081c52bbb1277cacca000fd9f3

checksums.yaml.gz.sig

@@ -1,2 +1,3 @@
-T�V�c.nf���}�"Ny�
S�dVA$�t/�n����F��*�2ay�.�7��"�L�B�ϊ#[����|��R�iQ��L�2���~�T�u��N�6r]�u[��$�4�"����ے��i���jxe8W*%rT�!mf��\�QӪ�+i5�3G�*t�*�ԡ9�;�u��:�u����Aj�IG�8���U*����i�9*��rΥ����
d�JG��,
-�d����D�n��F�*
+[�GT3M���sV����h���%f7��%GA��#N�V��Tӳ
+��L���O�9�-5*ƴtB!)O]e
w�]9�{)���2���9����[ʃ�/2�Q+\5�!�{Y:iQ����cq���J�
+����б{އ�����	�UU�jgl�h9_V���z��@���bԧ�����D

data/lib/xml_col_finder.rb

@@ -3,35 +3,49 @@
 # 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|
+    @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)
 
   end
 
-  def to_code()
+  def to_code(nametip: true)
 
+    @nametip = nametip
     @tags = {}
 
     xpath, remaining = @to_a
@@ -40,17 +54,51 @@ class XMLColFinder
     linex = formatline('doc', eid, xpath)
     a = scan(remaining, eid)
 
-    a.flatten.compact.prepend linex
+    lines = a.flatten.compact.prepend linex
+    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
 
+  def to_doc()
+    @doc
+  end
+
   private
 
   def formatline(pid, eid=nil, key=nil, tail=nil, index: nil)
 
     if eid then
-      line = "%s = %s.element(\"%s\")" % [eid, pid, key]
-      line += '.text' if tail.is_a? String
+
+      nametip = @nametip && tail.is_a?(String)
+      klass = nametip ? key.scan(/@class=['"]([^'"]+)/).last : nil
+
+      line = if klass then
+        desc = klass[0][/^[^\-]+/].gsub(/(?=[A-Z])/,' ').downcase
+        desc += " (e.g. %s)" % [tail.length < 50 ? tail : tail[0..46] + '...']
+        "\n# " + desc + "\n"
+      elsif nametip
+        "\n# e.g. %s\n" % [tail.length < 50 ? tail : tail[0..46] + '...']
+      else
+        ''
+      end
+
+      key.gsub!("[@class='']",'') # Rexle XPath bug solution!
+      line += "%s = %s.element(\"%s\")" % [eid, pid, key]
+      if tail.is_a? String
+        line += '.text'
+        #line += "\n" if nametip
+      end
+
     else
       line = index ? ("%s[%d].text" % [pid, index]) : ("%s.text" % pid)
     end
@@ -66,6 +114,8 @@ class XMLColFinder
     tag = case rawtagx.to_sym
     when :a
       'link'
+    when :p
+      'para'
     else
       rawtagx
     end
@@ -191,7 +241,7 @@ class XMLColFinder
           puts '_tail: ' + tail.inspect if @debug
           tline = tail.map.with_index do |x,i|
             formatline(pid=eid, index: i)
-          end.join("\n")
+          end
 
         end
       end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: xml_col_finder
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.3.0
 platform: ruby
 authors:
 - James Robertson
@@ -35,7 +35,7 @@ cert_chain:
   GSlZ9ilAfm8srTjbZ2cWQyNGGxH+zHQ3Z02c4ZEtgPv/wHjptd1VeBm0P1aemsRA
   ShsxXxzmzIrRENmpBp3tyR3k
   -----END CERTIFICATE-----
-date: 2022-01-23 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.