unisat 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 67fa8182506bbe32a101682e64ba4660f0b558789d876f2dafd3628dafc257be
+  data.tar.gz: 64dbb1c6e34b9b84a8df7bebbea5b08bac283cd3aaaadf1ec91051e3884fc89b
+SHA512:
+  metadata.gz: a503beaab753968070d54cf00be80a733dcb27fcd3e7d581e93ae920eb35a4615f20b9e1757976502f2c4d41700a75be810692baf1cd7d17a6a862deeb00c35d
+  data.tar.gz: 9757e1a741d451cc155e017ec694764019e17b138171a0fc57d54876ce508bda2455f87a536cd703006166f15dc1dec0c8b1b21730aaec4bb457fe464d8ccdf6

data/CHANGELOG.md

@@ -0,0 +1,3 @@
+### 0.0.1 / 2023-08-14
+
+* Everything is new. First release

data/Manifest.txt

@@ -0,0 +1,7 @@
+CHANGELOG.md
+Manifest.txt
+README.md
+Rakefile
+lib/unisat.rb
+lib/unisat/cache.rb
+lib/unisat/version.rb

data/README.md

@@ -0,0 +1,33 @@
+# UniSat.io Lite Helpers for Full-Text Search in Bitcoin Ordinal Inscriptions
+
+unisat - lite helpers for full-text search in bitcoin ordinal inscriptions powered by unisat.io
+
+* home  :: [github.com/ordbase/unisat](https://github.com/ordbase/unisat)
+* bugs  :: [github.com/ordbase/unisat/issues](https://github.com/ordbase/unisat/issues)
+* gem   :: [rubygems.org/gems/unisat](https://rubygems.org/gems/unisat)
+* rdoc  :: [rubydoc.info/gems/unisat](http://rubydoc.info/gems/unisat)
+
+
+
+##  Usage
+
+To be done
+
+
+
+
+
+
+## License
+
+The scripts are dedicated to the public domain.
+Use it as you please with no restrictions whatsoever.
+
+
+## Questions? Comments?
+
+Join us in the [Ordgen / ORC-721 discord (chat server)](https://discord.gg/dDhvHKjm2t). Yes you can.
+Your questions and commetary welcome.
+
+
+Or post them over at the [Help & Support](https://github.com/geraldb/help) page. Thanks.

data/Rakefile

@@ -0,0 +1,31 @@
+require 'hoe'
+require './lib/unisat/version.rb'
+
+Hoe.spec 'unisat' do
+
+  self.version =  Unisat::VERSION
+
+  self.summary = "unisat - lite helpers for full-text search in bitcoin ordinal inscriptions powered by unisat.io"
+  self.description = summary
+
+  self.urls    = { home: 'https://github.com/ordbase/ordbase' }
+
+  self.author  = 'Gerald Bauer'
+  self.email   = 'gerald.bauer@gmail.com'
+
+  # switch extension to .markdown for gihub formatting
+  self.readme_file  = 'README.md'
+  self.history_file = 'CHANGELOG.md'
+
+  self.extra_deps = [
+    ['cocos'],
+    ['puppeteer-ruby'],
+    ['nokogiri'],
+  ]
+
+  self.licenses = ['Public Domain']
+
+  self.spec_extras = {
+    required_ruby_version: '>= 2.3'
+  }
+end

data/lib/unisat/cache.rb

@@ -0,0 +1,108 @@
+module Unisat
+###
+##  todo: use a config block in the future - why? why not?
+def self.cache_dir=( dir ) @cache = Cache.new( dir ); end 
+def self.cache()  @cache ||= Cache.new( './unisat' ); end
+
+
+def self.parse_page( html )
+    doc = Nokogiri::HTML( html )
+  
+    items = [] 
+  
+    sats = doc.css( '.item-container' )
+    sats.each_with_index do |el,i|
+      puts "==> sat ##{i+1}/#{sats.size}..."
+  
+      h = {}
+  #    <a href="https://ordinals.com/inscription/
+  #    9613d44f53a1245bf34f43820163bb3064a5715c19f0d6c767a14d1b49f46614i0" 
+  #    target="_blank" rel="noreferrer" class="sats-item  ">
+      a = el.at( 'a.sats-item' )
+      h['href'] = a['href']
+  
+      name = el.at( '.name' )
+      h['name'] = name.text
+  
+      num = el.at( '.num' )
+      h['num'] = num.text
+  
+      address = el.at( '.address' )
+      h['address'] = address.text
+  
+      date = el.at( '.date' )
+      h['date'] = date.text
+      ##pp h
+      
+      items << h
+    end  
+    items
+end  # method _parse_page
+  
+
+class Cache
+  def initialize( dir )
+    @dir = dir
+  end
+
+  ## todo:
+  ## - add offset: nil, limit: nil  - why? why not?
+  def read( key ) 
+      recs = []
+
+     paths = Dir.glob( "#{@dir}/#{key}/*.json" )
+     puts "   #{paths.size} page(s) in cache"
+
+     paths.each_with_index do |path,i|
+       results = read_json( path )
+       puts "==> #{i+1}/#{paths.size} - #{results.size} inscribe(s) in >#{path}<..."
+
+       results.each do |h|
+           date = h['date']  # note: might include unconfirmed!!!
+          ##  always "auto-magically" filter out unconfirmed for now 
+          if date == 'unconfirmed'
+             puts "  !! INFO - skipping unconfirmed inscribe"
+             next
+          end
+
+          ## todo/fix:
+          ##  reformat date here/parse
+          ##   and change to iso e.g. 2023-12-24 17:18 or such - why? why not!!!!
+
+
+          ## id -- split href by / and get last part (is id)
+          id  = h['href'].split( '/')[-1] 
+          ## num -- remove/ strip leadingnumber sign (#)  
+          num = h['num'].sub( '#', '' )  
+          recs << { 
+             'id'      => id,
+             'num'     => num,
+             'date'    => date,
+             'address' => h['address'],
+             'text'    => h['name'],  ## change name to text
+          }
+       end
+      end
+      puts "   #{recs.size} inscribe(s) - total"
+      recs
+  end # method read
+
+
+  def exist?( key, offset: )
+    outpath = "#{@dir}/#{key}/#{offset}.json"
+    File.exist?( outpath )
+  end
+
+  def add_page( page, key, offset: )
+     data = Unisat.parse_page( page )
+
+     ## note: only write if results > 0
+     if data.size > 0
+        outpath = "#{@dir}/#{key}/#{offset}.json"
+        write_json( outpath, data )   
+     else
+        puts "!! WARN - no results found in page #{offset} for key >#{key}<"
+     end
+  end
+end  # class Cache
+end   # module Unisat

data/lib/unisat/version.rb

@@ -0,0 +1,21 @@
+
+module Unisat
+
+  # sync version w/ sport.db n friends - why? why not?
+  MAJOR = 0 ## todo: namespace inside version or something - why? why not??
+  MINOR = 0
+  PATCH = 1
+  VERSION = [MAJOR,MINOR,PATCH].join('.')
+
+  def self.version
+    VERSION
+  end
+
+  def self.banner
+    "unisat/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}] in >#{root}<"
+  end
+
+  def self.root
+    File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )
+  end
+end

data/lib/unisat.rb

@@ -0,0 +1,116 @@
+require 'cocos'
+
+require 'puppeteer-ruby'
+require 'nokogiri'
+
+
+# our own code
+require_relative 'unisat/version'   # always goes first
+require_relative 'unisat/cache'
+
+
+  
+
+module Unisat
+module Puppeteer
+
+###
+##  todo: use a config block in the future - why? why not?
+def self.chrome_path=( path )
+  if File.exist?( path )
+    puts "** bingo! found chrome executable @ path >#{path}<"
+  else
+    puts "*** ERROR - sorry; cannot find chrome executable @ path >#{path}<"
+    exit 1
+  end
+
+  @chrome_path = path
+end
+
+def self.chrome_path() @chrome_path; end
+
+## use/rename to wait_in_secs - why? why not? 
+def self.wait_in_s=( s ) @wait_in_s = s; end 
+def self.wait_in_s() @wait_in_s ||= 10; end
+
+## shortcut helper
+def self.cache()  Unisat.cache; end  
+
+
+###
+# search
+def self.search( q, offset: 1, 
+                    limit: 1,
+                    force: false )
+
+   opts = {}
+   opts[:headless]        = false
+   opts[:executable_path] = chrome_path  if chrome_path   ## add only if set (default is nil)
+
+
+  ::Puppeteer.launch( **opts ) do |browser|
+
+    page = browser.new_page
+ 
+    limit.times do |i|
+      count = offset+i
+
+      page_url  = "https://unisat.io/search?q=#{q}&type=text&p=#{count}"
+      print page_url
+     
+      ## check if already in cache
+      if force == false && cache.exist?( q, offset: count )
+        print "...in cache\n"
+        next 
+      end
+
+      print "... goto page ...\n"
+      response = page.goto( page_url )
+      pp response.headers
+
+      puts "sleeping #{wait_in_s} sec(s)..."
+      sleep( wait_in_s )
+  
+      ## print search result summary / counts
+      page.wait_for_selector('div.result-notice')
+      el =  page.query_selector("div.result-notice")
+      puts
+      puts el.evaluate("el => el.innerText")
+      #=> Searched for "biixel" among 3252336 records, found 1105 results.
+
+ 
+      ## print pagination 
+      page.wait_for_selector('ul.ant-pagination')
+      el =  page.query_selector("ul.ant-pagination")
+      puts
+      puts el.evaluate("el => el.innerText")
+      #=> 1 ••• 32 33 34 35
+
+      
+      ## get search results (32 inscribes per page)
+      page.wait_for_selector('div.sats-list')
+      el =  page.query_selector("div.sats-list")
+  
+      html = el.evaluate("el => el.innerHTML")
+      # puts
+      # puts html
+   
+      cache.add_page( html, q, 
+                            offset: count )
+    end
+
+    puts "sleeping 2 secs before shutdown..."
+    sleep( 2 )
+  end
+end  # method search  
+end # module Puppeteer
+end # module Unisat
+
+
+
+## add alternate name alias - why? why not?
+UniSat = Unisat
+
+
+
+puts Unisat.banner

metadata

@@ -0,0 +1,132 @@
+--- !ruby/object:Gem::Specification
+name: unisat
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Gerald Bauer
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2023-08-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: cocos
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: puppeteer-ruby
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
+- !ruby/object:Gem::Dependency
+  name: hoe
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+description: unisat - lite helpers for full-text search in bitcoin ordinal inscriptions
+  powered by unisat.io
+email: gerald.bauer@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- CHANGELOG.md
+- Manifest.txt
+- README.md
+files:
+- CHANGELOG.md
+- Manifest.txt
+- README.md
+- Rakefile
+- lib/unisat.rb
+- lib/unisat/cache.rb
+- lib/unisat/version.rb
+homepage: https://github.com/ordbase/ordbase
+licenses:
+- Public Domain
+metadata: {}
+post_install_message:
+rdoc_options:
+- "--main"
+- README.md
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.3'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.4.10
+signing_key:
+specification_version: 4
+summary: unisat - lite helpers for full-text search in bitcoin ordinal inscriptions
+  powered by unisat.io
+test_files: []