easy_captcha_solver 0.0.4 → 0.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: dcb594800ad2a3d11471aa0b1b96bf5a3cf9bf97
-  data.tar.gz: 342afccdf933e33ff81699d93029c93458ac0fdb
+  metadata.gz: 0e812e7f2b327ace5217bdb9f41d62b36d20dafc
+  data.tar.gz: 25e4e3575a6a4e7cb8e0d0c9fa592780b18e8c41
 SHA512:
-  metadata.gz: 49dcf36addcbd3e6b4985ec06afb85bedea30cf03eeb22f748c129ef5b539f5b64622bf78f5748b80b6cf89bb8e315c5ee979f75182f9a701ff33b3a01d6da9a
-  data.tar.gz: 0ec408b14ec8bea14155a08b4758df777b9fe4bfaa3676ae0a02225a53a299fe2f8d902d5ee3f5ee4a8ab5ceff8077f03159692b9b09ac962aa270f98430f2d8
+  metadata.gz: b1a34ef70f02a8324523be85414bcce4c0a6f68caa5442d32dc6b98597fb37f7059820f970d64b08829d4d32c8d15d6c0d61711e00c9bfef570728c3fe773f05
+  data.tar.gz: 2bb91e8f255736e6b4703dc82b71761b632f11336356d409c54ae692b57558d64b02cfea9bcdd8ff94fb220c5add6b140f954299c8778b55eeafe99f87e93020

data/lib/easy_captcha_solver.rb

@@ -5,59 +5,58 @@ class EasyCaptchaSolver
   attr_reader :captcha
 
   def initialize ( options = {} )
-    # Mechanize initializacion, pretends to be Mac Safari
-    agent = Mechanize.new { |agent|
-      agent.user_agent_alias = 'Mac Safari'
-    }
+    image = options[:image_path] if options[:image_path]
+    image = get_captcha_image(options[:image_url]) if options[:image_url]
 
-    @image = options[:image_path] if options[:image_path]
+    throw Exception.new "Image path or image URL must be provided.
+    Example:  easy_c = EasyCaptcha.new( image_url: 'http://www.example.com/captcha' )
+      or easy_c = EasyCaptcha.new( image_path: './captcha.jpg' )" unless image
 
-    # If URL, save a file instead of trying to solve the captcha from memory because of tesseract limitations with .png images
-    if options[:image_url]
-      image = agent.get(options[:image_url]).save!  "./tmp_image"
-
-      # Guess image extension and rename tmp file
-      @image  = "./tmp_image.#{get_image_extension(image)}"
-      File.rename( image,  @image)
-    end
+    # Try to solve the captcha and delete temp img if necessary
+    solve_captcha(image) ensure File.delete(image) if options[:image_url] && File.exist?(image)
+  end
 
-    unless @image
-      throw Exception.new "A local image path or a image URL must be provided. Example:  easy_c = EasyCaptcha.new( image_url: 'http://www.example.com/captcha_img.jpg')"
-    end
+  private
+  def get_captcha_image( image_url )
+    agent = Mechanize.new { |agent|
+      agent.user_agent_alias = 'Mac Safari'
+    }
 
-    solve_captcha ensure File.delete(@image) if options[:image_url]
+    # Save a file instead of trying to solve the captcha from memory
+    # because of tesseract limitations with .png images
+    image = agent.get(image_url).save!  "./tmp_image"
+    image_extension  = "./tmp_image.#{get_image_extension(image)}"
+    File.rename( image,  image_extension)
 
+    image_extension
   end
 
-  private
-
-  def solve_captcha()
-    # Solve captcha using Tesseract-ocr
+  def solve_captcha(image)
     e = Tesseract::Engine.new {|e|
       e.language  = :eng
       e.blacklist = '|'
     }
-
-    @captcha = e.text_for(@image).strip # => 'ABC'
+    @captcha = e.text_for(image).strip # => 'ABC'
   end
-end
 
-def get_image_extension(local_file_path)
-  png = Regexp.new("\x89PNG".force_encoding("binary"))
-  jpg = Regexp.new("\xff\xd8\xff\xe0\x00\x10JFIF".force_encoding("binary"))
-  jpg2 = Regexp.new("\xff\xd8\xff\xe1(.*){2}Exif".force_encoding("binary"))
-  case IO.read(local_file_path, 10)
-  when /^GIF8/
-    'gif'
-  when /^#{png}/
-    'png'
-  when /^#{jpg}/
-    'jpg'
-  when /^#{jpg2}/
-    'jpg'
-  else
-    mime_type = `file #{local_file_path} --mime-type`.gsub("\n", '') # Works on linux and mac
-    raise UnprocessableEntity, "unknown file type" if !mime_type
-    mime_type.split(':')[1].split('/')[1].gsub('x-', '').gsub(/jpeg/, 'jpg').gsub(/text/, 'txt').gsub(/x-/, '')
+  def get_image_extension(local_file_path)
+    png = Regexp.new("\x89PNG".force_encoding("binary"))
+    jpg = Regexp.new("\xff\xd8\xff\xe0\x00\x10JFIF".force_encoding("binary"))
+    jpg2 = Regexp.new("\xff\xd8\xff\xe1(.*){2}Exif".force_encoding("binary"))
+    case IO.read(local_file_path, 10)
+    when /^GIF8/
+      'gif'
+    when /^#{png}/
+      'png'
+    when /^#{jpg}/
+      'jpg'
+    when /^#{jpg2}/
+      'jpg'
+    else
+      mime_type = `file #{local_file_path} --mime-type`.gsub("\n", '') # Works on linux and mac
+      raise UnprocessableEntity, "unknown file type" if !mime_type
+      mime_type.split(':')[1].split('/')[1].gsub('x-', '').gsub(/jpeg/, 'jpg').gsub(/text/, 'txt').gsub(/x-/, '')
+    end
   end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: easy_captcha_solver
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors:
 - Alex Rodriguez