bibletools 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: b39f3947e9bf8e827ce070ad544f2f03a5b28e43554588ec99e6511aaf7c7109
+  data.tar.gz: 6d88f41a49b461adc25993c65e2abbeffc6616b9d727bab0bcc93c3570bcc824
+SHA512:
+  metadata.gz: '09532d8e8b4d88ae66ffdcb7f62aec4c7887cb9b87497deb5b04206f6b3c5cbcbcffa618e2ded85a683a57f43907e8f5e30dcb0d62885481fc0a95540240cad6'
+  data.tar.gz: ec3bc05ded3b431231eaea8f2e00cde75a4da60bc8cc4fbb6fda1cd3d8312fabd1d50aa7e096742f7beb05b36e306b853b4cd92d446a9bb060333ce544614645

data/lib/bibletools.rb

@@ -0,0 +1,209 @@
+#!/usr/bin/env ruby
+
+# file: bibletools.rb
+
+require 'rexle'
+require 'yawc'
+require 'nokorexi'
+
+
+module BibleTools
+
+  class ScraperErr < Exception
+  end
+  
+  class Scraper
+
+    def initialize(book: 'Exodus', url: '')
+      
+      raise ScraperErr, 'Please specify the URL' if url.empty?
+      
+      baseurl = url
+
+      books = ["Genesis",
+       "Exodus",
+       "Leviticus",                                                                  
+       "Numbers",
+       "Deuteronomy",
+       "Joshua",
+       "Judges",
+       "Ruth", 
+       "1 Samuel",
+       "2 Samuel",
+       "1 Kings",
+       "2 Kings",
+       "1 Chronicles",
+       "2 Chronicles",
+       "Ezra",
+       "Nehemiah",
+       "Tobit",
+       "Judith",
+       "Esther",
+       "1 Maccabees",
+       "2 Maccabees",
+       "Job",
+       "Psalms",
+       "The Proverbs",
+       "Ecclesiastes",
+       "The Song of Songs",
+       "Wisdom",
+       "Ecclesiasticus / Sirach",
+       "Isaiah",
+       "Jeremiah",
+       "Lamentations",
+       "Baruch",
+       "Ezekiel",
+       "Daniel",
+       "Hosea",
+       "Joel",
+       "Amos",
+       "Obadiah",
+       "Jonah",
+       "Micah",
+       "Nahum",
+       "Habakkuk",
+       "Zephaniah",
+       "Haggai",
+       "Zechariah",
+       "Malachi",
+       "Matthew",                                                                   
+       "Mark",  
+       "Luke",
+       "John",
+       "Acts of Apostles",
+       "Romans",
+       "1 Corinthians", 
+       "2 Corinthians",
+       "Galatians", 
+       "Ephesians",
+       "Philippians",
+       "Colossians",
+       "1 Thessalonians",
+       "2 Thessalonians",
+       "1 Timothy",
+       "2 Timothy",
+       "Titus",
+       "Philemon",
+       "Hebrews",
+       "James",
+       "1 Peter",
+       "2 Peter",
+       "1 John",
+       "2 John",
+       "3 John",
+       "Jude",
+       "Revelation"]
+
+      id = if book.is_a? String then
+        (books.index(book) + 1).to_s
+      else
+        book.to_s
+      end
+
+
+
+      url2 = baseurl + '?id=' + id
+      doc = Nokorexi.new(url2).to_doc
+      e = doc.root.at_css('.pagination')
+      endchapter = e.xpath('li')[-2].text('a')
+
+
+      book = Rexle.new('<book/>')
+
+      (1..endchapter.to_i).each do |chp|
+
+        c = chp.to_s
+        puts 'reading chapter ' + c
+
+        sleep 1
+        url2 = baseurl + ("?id=%s&bible_chapter=%s" % [id, c])
+        doc = Nokorexi.new(url2).to_doc
+        a = doc.root.xpath('//div/p')
+        a2 = a.select {|e| e2 = e.element('a'); e2.attributes[:name] if e2}
+
+        chapter = Rexle::Element.new('chapter', attributes: {no: c})
+
+        a2.each.with_index do |e, i|
+
+          puts 'processing verse ' + i.to_s
+          txt = e.plaintext
+          n = txt.slice!(0,2).to_i.to_s
+          chapter.add Rexle::Element.new('verse', attributes: {no: n}).add_text(txt)
+
+        end
+
+        book.root.add chapter
+
+      end
+
+      @doc = book
+
+    end
+
+    def to_doc
+      @doc
+    end
+
+  end
+  
+  class Analyse
+    
+    def initialize(bible_obj, debug: false)
+      
+      @debug = debug
+      
+      if bible_obj then
+        @doc = bible_obj.to_doc
+        @verses = @doc.root.xpath('chapter/verse')
+      end
+      
+    end
+    
+    def wordtally()
+      
+      return unless @doc
+      Yawc.new(@doc.root.plaintext).to_h
+      
+    end
+    
+    alias words wordtally
+    
+    def read(chapter, verse)
+      @doc.root.element("chapter[@no='#{chapter}']/verse[@no='#{verse}']")
+    end
+
+
+    def search(keyword)
+      
+      a = @verses.select {|x| x.text =~ /#{keyword}/}
+      
+      a2 = a.map.with_index do |verse, i|
+        txt = verse.text
+        
+        puts 'txt: ' + txt.inspect if @debug
+        
+        n = 0
+        chapter = verse.parent.attributes[:no]
+        
+        until txt.rstrip[-1] == '.' or n > 2 do
+          n +=1
+          nverse = read(chapter, verse.attributes[:no].to_i + n)
+          txt += nverse.text
+        end 
+        
+        if @debug then
+          puts 'n: ' + n.inspect
+          puts '_txt: ' + txt.inspect
+        end
+        
+        [verse.parent.attributes[:no], verse.attributes[:no], txt]
+      end
+
+      h1 = a2.group_by(&:first)
+    end
+    
+    
+  end
+
+end
+

metadata

@@ -0,0 +1,112 @@
+--- !ruby/object:Gem::Specification
+name: bibletools
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- James Robertson
+autorequire: 
+bindir: bin
+cert_chain:
+- |
+  -----BEGIN CERTIFICATE-----
+  MIIEljCCAv6gAwIBAgIBATANBgkqhkiG9w0BAQsFADBIMRIwEAYDVQQDDAlnZW1t
+  YXN0ZXIxHjAcBgoJkiaJk/IsZAEZFg5qYW1lc3JvYmVydHNvbjESMBAGCgmSJomT
+  8ixkARkWAmV1MB4XDTIyMTEwMTE5NDkwMVoXDTIzMTEwMTE5NDkwMVowSDESMBAG
+  A1UEAwwJZ2VtbWFzdGVyMR4wHAYKCZImiZPyLGQBGRYOamFtZXNyb2JlcnRzb24x
+  EjAQBgoJkiaJk/IsZAEZFgJldTCCAaIwDQYJKoZIhvcNAQEBBQADggGPADCCAYoC
+  ggGBAO4EkWGPQjC353RghcFVaChTU9wtElySDuaMxIHRfY78xcZKjS/nDC5wGyRa
+  gi/dqoSdSkOrH+X+Gc8DUVzhGDW/VBjdRGcImta4MBWioZwN2pM/MPclix0Krzm5
+  Ai3eIah8DNa3q6GjETYITmWh4CAdOhxBAUdS9RLXrg0NkseG+5EQslVK33zKLyh8
+  trL5BobHN/H42Bs+aJXaEJbUGE6uSYmU48FiuQ7GRsHIzalTINfpkrhiaxY2rDY7
+  nF1hgXniZPeQ0LOdhWWDr1NhgLMZkcQkTQCHsNCYsGhn7ey/kiCNSHe7VL1ZP8fI
+  5VU2cMjbDqhTPmDJOHIFI7Odq1fANMODWYmu4b0DG6GucKDqyWiMSOlSOHpVVYhf
+  +TTddq5MzpiaUMZ5axUgUYjnXwMZxLdWj8tmLDTpf8OG/uVsVVlf1ZksDqQbEaiP
+  hKXSuzUL5hc4qbR5+vuG8YS/OXlhRJlgJzLAip4mADyXHcQn9gAq6kUHPT+s8ANA
+  7ND/tQIDAQABo4GKMIGHMAkGA1UdEwQCMAAwCwYDVR0PBAQDAgSwMB0GA1UdDgQW
+  BBSJNr8LDr9bFKicE6Fy0esYh7VOkDAmBgNVHREEHzAdgRtnZW1tYXN0ZXJAamFt
+  ZXNyb2JlcnRzb24uZXUwJgYDVR0SBB8wHYEbZ2VtbWFzdGVyQGphbWVzcm9iZXJ0
+  c29uLmV1MA0GCSqGSIb3DQEBCwUAA4IBgQC4rcqtsT3VmXV5P8azIQB6Ek/msm2u
+  CstleVVm/EwF7jh0gGJJiDJQN5AVgx8KuTUgMG7ZV/545tyvMehterxdOnGu/BVK
+  Vj4x122PiswtVHH0mEGaLAhPN7ZFwuFrcqOnBvvQu2KzHL/pq4G0H7nH2DarIRVk
+  Taw5ZF8P5xQvJlhZgi+5nRRiZoTwKwWqp+qqh6O4yTOWfBFRf3Jbnc5Zl+MqhOpX
+  uhkwF7pXCOW657/b0ZHpc4VOMtTZc7zexqAvrYluKT9RNMT8UWpS3b2jWjHSujww
+  T017aRDqdDpFR4Nr83t0ZE5JZlGbtMBK1vPw//PKr/r720mqWEShWNqoedmKWAj7
+  bJS0iHnCBeWKWn0HK15PbywyBS9X8SB8WSEabEcxFRUY6NKK3JtC6breJGNWFZih
+  hIlyeyH9vsaJLam1TYsSqh3KUBmRCIvc3XELg2MAlggTrHuCjBPdYXqjIOFvO6HZ
+  Z1XDnMf4RhcEPF4AU3Q+Fefsw4qKRWH3YUw=
+  -----END CERTIFICATE-----
+date: 2022-11-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokorexi
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.7.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.7.0
+- !ruby/object:Gem::Dependency
+  name: yawc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+description: 
+email: digital.robertson@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/bibletools.rb
+homepage: https://github.com/jrobertson/bibletools
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.7
+signing_key: 
+specification_version: 4
+summary: Performs a word count within a specified book. Returns the verses within
+  a specified book for a given keyword.
+test_files: []