Added compatibility with linux, solved a bug and rewriten a bunch of stuff

Imagenamer.py

@@ -1,6 +1,7 @@
-"""This Program is used to rename image files with its content"""
+#!/usr/bin/python
+###This Program is used to rename image files with its content
 
-"""SETUP"""
+##SETUP
 try:
 	from PIL import Image
 except ImportError:
@@ -8,25 +9,45 @@ except ImportError:
 import pytesseract
 import os
 import string
-import uuid
+import hashlib
 
 namearray = []
 indexnow = 0
 
-pytesseract.tesseract_cmd = r'C:\Program Files (x86)\Tesseract-OCR\tesseract' #absolute path to out tesseract instalation
+print("OS name:", os.name)
+if os.name == "nt": #U are using windows?
+	pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files (x86)\Tesseract-OCR\tesseract" #absolute path to out tesseract instalation
+	PATHSEPARATOR = "\\"
+else: #No? NICE
+	pytesseract.pytesseract.tesseract_cmd = r"/usr/bin/tesseract" #absolute path to teseract instalation
+	PATHSEPARATOR = "/"
 
-"""FUNCTIONS"""
+# Define the input and output directories
+BASEPATHINPUT = "."+PATHSEPARATOR+"ImagesToConvert"
+print("BASEPATHINPUT = "+BASEPATHINPUT)
+BASEPATHOUTPUT = "."+PATHSEPARATOR+"ImagesOutput"
+print("BASEPATHOUTPUT = "+BASEPATHOUTPUT)
+
+# Getting the absolute path to the before named directories
+ABSOLUTEPATHINPUT = os.path.abspath(BASEPATHINPUT)
+print("ABSOLUTEPATHINPUT = "+ABSOLUTEPATHINPUT)
+ABSOLUTEPATHOUTPUT = os.path.abspath(BASEPATHOUTPUT)
+print("ABSOLUTEPATHOUTPUT = "+ABSOLUTEPATHOUTPUT)
+
+##FUNCTIONS
 def ocr(filename):
-    newname = pytesseract.image_to_string(Image.open(absolutebasepathin+"\\"+filename))  # Use pillow to open an image for pytesseract image2string to use
+	newname = pytesseract.image_to_string(Image.open(ABSOLUTEPATHINPUT+PATHSEPARATOR+filename))  # Use pillow to open an image for pytesseract image2string to use
 	return newname
 
+def getHashedOut(filename):
+	return hashlib.md5(Image.open(ABSOLUTEPATHINPUT+PATHSEPARATOR+filename).tobytes())
+
 def namecleaner(filename):
 	print("filenameis "+filename)
-    filename = "_".join(filename.split()) # Get rig of line braks and spaces
+	filename = "-".join(filename.split()) # Get rid of line braks and spaces
-    filename = filename.replace("__","_") # Cleaning duplicated '_'s
+	filename = filename.replace(" ","") # Get rid of spaces(For recursion)
-    filename = filename.replace(" ","") # Get rig of spaces(For recursion)
+	filename = filename.replace("\n","") # Get rid of line braks(For recursion)
-    filename = filename.replace("\n","") # Get rig of line braks(For recursion)
+	#Get rid of forbiden characters(NTFS)
-    #Get rid of forbiden characters
 	filename = filename.replace("<","")
 	filename = filename.replace(">","")
 	filename = filename.replace(":","")
@@ -37,25 +58,15 @@ def namecleaner(filename):
 	filename = filename.replace("?","")
 	filename = filename.replace("*","")
 	##################################
-    outputname = filename.replace(".","") # Get rid of extra dots
+	filename = filename.replace(".","") # Get rid of extra dots
-    print("outputnameis "+outputname)
+	while filename.count("--") != 0:
-    return outputname
+		filename = filename.replace("--","-") # Cleaning duplicated '-'s
-
+	print("outputnameis "+filename)
-"""CORECODE"""
+	return filename
-# Define the input and output directories
-basepathin = '.\ImagesToConvert'
-print("basepathin = "+basepathin)
-basepathout = '.\ImageOutput'
-print("basepathout = "+basepathout)
-
-# Getting the absolute path to the before named directories
-absolutebasepathin = os.path.abspath('.\ImagesToConvert')
-print("absolutebasepathin = "+absolutebasepathin)
-absolutebasepathout = os.path.abspath('.\ImagesOutput')
-print("absolutebasepathout = "+absolutebasepathout)
 
+##CORECODE
 # List all files in a directory using scandir()
-with os.scandir(absolutebasepathin) as entries:
+with os.scandir(ABSOLUTEPATHINPUT) as entries:
 	for entry in entries:
 		if entry.is_file():
 			# Fill an array with the list
@@ -76,16 +87,15 @@ while indexnow < arraylength:
 	cleanname = namecleaner(newname)
 	print("cleanname = "+cleanname)
 	if cleanname != "":
-        if len(cleanname) > 250:
+		if len(cleanname) > 200:
-            cleanname = cleanname[0:250]
+			cleanname = cleanname[0:200]
-        cleanname = cleanname + basename[len(basename)-4:len(basename)]
+		cleanname = cleanname + "." + basename.split(".")[-1]
-        os.rename(absolutebasepathin+"\\"+basename, absolutebasepathout+"\\"+cleanname)
+		os.rename(ABSOLUTEPATHINPUT+PATHSEPARATOR+basename, ABSOLUTEPATHOUTPUT+PATHSEPARATOR+cleanname)
 		print(basename+" is now renamed as "+cleanname)
 	else:
-        UUIDnow = str(uuid.uuid4())
+		imgHash = getHashedOut(basename).hexdigest()
-        cleanname = namecleaner(UUIDnow)
+		cleanname = imgHash + "." + basename.split(".")[-1]
-        cleanname = cleanname + basename[len(basename)-4:len(basename)]
+		os.rename(ABSOLUTEPATHINPUT+PATHSEPARATOR+basename, ABSOLUTEPATHOUTPUT+PATHSEPARATOR+cleanname)
-        os.rename(absolutebasepathin+"\\"+basename, absolutebasepathout+"\\"+cleanname)
 		print(basename+" is now "+cleanname)
 
 	indexnow += 1

Setup.bat

@@ -6,6 +6,7 @@ echo install python: https://www.python.org/downloads/
 start https://www.python.org/downloads/
 
 echo also install tesseract https://tesseract-ocr.github.io/tessdoc/Downloads.html
+echo recomended the UB Mannheim https://github.com/UB-Mannheim/tesseract/wiki
 start https://tesseract-ocr.github.io/tessdoc/Downloads.html
 
 echo wait untill instalation
@@ -15,3 +16,6 @@ md ImagesToConvert
 md ImagesOutput
 pip install Pillow
 pip install pytesseract
+pip install hashlib
+
+echo Instalation finished

setup.sh

@@ -14,5 +14,8 @@ mkdir ImagesToConvert
 mkdir ImagesOutput
 pip install Pillow
 pip install pytesseract
+pip install hashlib
+
+sudo cp eng.traineddata /usr/share/tessdata/
 
 echo "Installation finished!"