First Commit

Author: lakshay1296

.idea/Python-OCR-Django.iml

@@ -0,0 +1,124 @@
+"""
+Django settings for OCR_Django_App project.
+
+Generated by 'django-admin startproject' using Django 1.11.20.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/1.11/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/1.11/ref/settings/
+"""
+
+import os
+
+# Build paths inside the project like this: os.path.join(BASE_DIR, ...)
+BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/1.11/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = '=!3*5*bo4t)6=7el(1w1n^x6$9fd-03&k&q1w_14y$fsx(nsb)'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = []
+
+STATICFILES_DIRS = (
+    os.path.join(os.path.dirname(__file__), 'static').replace('\\','/'),
+)
+
+# Application definition
+
+INSTALLED_APPS = [
+    'index.apps.IndexConfig',
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'OCR_Django_App.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'OCR_Django_App.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/1.11/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.sqlite3',
+        'NAME': os.path.join(BASE_DIR, 'db.sqlite3'),
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/1.11/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/1.11/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_L10N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/1.11/howto/static-files/
+
+STATIC_URL = '/static/'

.idea/misc.xml

@@ -0,0 +1,8 @@
+from django.contrib import admin
+#from django.urls import path
+from django.conf.urls import url, include
+
+urlpatterns = [
+    url(r'admin/', admin.site.urls),
+    url(r'index/', include('index.urls')),
+]

.idea/modules.xml

@@ -0,0 +1,16 @@
+"""
+WSGI config for OCR_Django_App project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/1.11/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "OCR_Django_App.settings")
+
+application = get_wsgi_application()

.idea/vcs.xml

@@ -0,0 +1,6 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+from django.contrib import admin
+
+# Register your models here.

OCR_Django_App/__init__.py

@@ -0,0 +1,8 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+from django.apps import AppConfig
+
+
+class IndexConfig(AppConfig):
+    name = 'index'

OCR_Django_App/settings.py

@@ -0,0 +1,8 @@
+# -*- coding: utf-8 -*-
+from django.db import models
+
+# Create your models here.
+
+class FileName(models.Model):
+    file_name = models.CharField(max_length=500)
+    file_extension = models.CharField(max_length=100)

OCR_Django_App/urls.py

@@ -0,0 +1,127 @@
+import os
+
+from pdf2image import convert_from_path
+import re
+import  numpy as np
+
+# For importing PyTesseract
+try:
+    from PIL import Image
+except ImportError:
+    import Image
+import pytesseract
+
+# If you don't have tesseract executable in your PATH, include the following:
+pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files (x86)\Tesseract-OCR\tesseract.exe'
+
+'''
+    Function for merging PNG's
+'''
+def merge_pdf (folder_path):
+    list_im = []
+    for root, dir, files in os.walk(folder_path):
+        for singFile in files:
+            if str(singFile).endswith(".png"):
+                new_path = folder_path + "\\" + singFile
+                list_im.append(new_path)
+
+    # Getting current folder name
+    folder_name = str(os.path.basename(folder_path))
+    # Creating PNG Name through folder name
+    file_name = folder_name[:-4]
+
+    imgs = [Image.open(i) for i in list_im]
+    min_shape = sorted([(np.sum(i.size), i.size) for i in imgs])[0][1]
+
+    # for a vertical stacking it is simple: use vstack
+    imgs_comb = np.vstack((np.asarray(i.resize(min_shape)) for i in imgs))
+    imgs_comb = Image.fromarray(imgs_comb)
+    imgs_comb.save(folder_path + "\\" + file_name + '.png', 'PNG')
+
+    # For removing PDF's Page PNG's
+    for image in list_im:
+        os.remove(image)
+        print "File: " + str(image) + " removed."
+
+'''
+    Function for processing OCR of Single Image File
+'''
+# def multi_file_tesseract(path, folder_path, single_image):
+def multi_file_tesseract(path, folder_path):
+
+    for root, dir, files in os.walk(path):
+        for Singfile in files:
+            print Singfile
+            if str(Singfile).endswith(".png"):
+
+                file_path = (root + "\\" + Singfile)
+                print "this: " + file_path
+
+                file_name = Singfile.split(".pdf")
+                final_name = file_name[0]
+                # Simple image to string
+                ocr_text = (pytesseract.image_to_string(Image.open(file_path)))
+
+                # Creating TXT Files
+                text_file = open(folder_path + "\\" + str(final_name) + ".txt", "a")
+                text_file.write(str(ocr_text))
+                text_file.close()
+
+        #return ocr_text
+
+
+'''
+    For OCR'ing a single file and saving it in same directory
+'''
+def single_file_tesseract(path):
+    print(path)
+
+    image_formats = ['.png', '.jpg', '.jpeg']
+
+    for format in image_formats:
+        if format in path:
+            # Simple image to string
+            ocr_text = (pytesseract.image_to_string(Image.open(path)))
+        else:
+            ocr_text = "File not supported."
+
+        # Creating TXT Files
+        text_file = open(path + ".txt", "a")
+        text_file.write(str(ocr_text))
+        #print ocr_text
+
+        return ocr_text
+
+'''
+    Function for converting PDF to image
+'''
+def pdf_to_image(file_path):
+    pages = convert_from_path(file_path, 300)
+    pdf_file = file_path[:-4]
+
+    # For getting file name of the PDF
+    newFile = str(file_path).split("\\")
+    file_name = str(newFile[len(newFile)-1])
+    file_name_proper = file_name[:-4]
+
+    # Replacing file name in path to create PNG folder.
+    new_pdf_path = str(pdf_file).replace(file_name_proper, "")
+
+    # New path for placing PNG's.
+    create_folder = new_pdf_path + "\\PNG\\" + file_name
+    print "This is the path that I need to pick up: " + create_folder
+    if not os.path.exists(create_folder):
+        os.makedirs(create_folder)
+    else:
+        print "Folder Already Exists."
+
+    # To save PNG's in same folder as name.
+    new_png_path = create_folder + "\\" + file_name
+    for page in pages:
+        page.save("%s-page%d.png" % (new_png_path, pages.index(page)), "PNG")
+
+    alert = "JPEG has been created."
+
+    #merge_pdf(create_folder)
+
+    return create_folder