myocr-lib 0.1.1__tar.gz

myocr_lib-0.1.1/PKG-INFO

@@ -0,0 +1,18 @@
+Metadata-Version: 2.1
+Name: myocr_lib
+Version: 0.1.1
+Summary: To be available soon
+Keywords: utility,library,functions,ocr,image-processing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: pytesseract>=0.3.13
+Requires-Dist: ocrmypdf>=16.12.0
+Requires-Dist: Pillow>=9.0.0
+Requires-Dist: opencv-python>=4.12.0
+Requires-Dist: PyMuPDF>=1.26.7

myocr_lib-0.1.1/pyproject.toml

@@ -0,0 +1,42 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "myocr_lib"  # Replace with your actual library name
+version = "0.1.1"
+# authors = [
+    # {name = "Muhammad Asif Ali", email = "creativedeveloper151214@gmail.com"}
+# ]
+description = "To be available soon"
+readme = "README.md"
+requires-python = ">=3.10"
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+keywords = ["utility", "library","functions","ocr","image-processing"]  # Add relevant keywords
+dependencies = [
+    # Add your dependencies here, e.g.:
+    # "requests>=2.28.0",
+    # "numpy>=1.20.0",
+
+    "pytesseract>=0.3.13",
+    "ocrmypdf>=16.12.0",
+    "Pillow>=9.0.0",
+    "opencv-python>=4.12.0",
+    "PyMuPDF>=1.26.7",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-dir]
+"" = "src"

myocr_lib-0.1.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

myocr_lib-0.1.1/src/myocr_lib.egg-info/PKG-INFO

@@ -0,0 +1,18 @@
+Metadata-Version: 2.1
+Name: myocr_lib
+Version: 0.1.1
+Summary: To be available soon
+Keywords: utility,library,functions,ocr,image-processing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: pytesseract>=0.3.13
+Requires-Dist: ocrmypdf>=16.12.0
+Requires-Dist: Pillow>=9.0.0
+Requires-Dist: opencv-python>=4.12.0
+Requires-Dist: PyMuPDF>=1.26.7

myocr_lib-0.1.1/src/myocr_lib.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+README.md
+pyproject.toml
+src/myocr_lib.egg-info/PKG-INFO
+src/myocr_lib.egg-info/SOURCES.txt
+src/myocr_lib.egg-info/dependency_links.txt
+src/myocr_lib.egg-info/requires.txt
+src/myocr_lib.egg-info/top_level.txt
+src/ocr_img/__init__.py
+src/ocr_img/main_code.py
+src/ocr_pdf/__init__.py
+src/ocr_pdf/main_code.py

myocr_lib-0.1.1/src/myocr_lib.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

myocr_lib-0.1.1/src/myocr_lib.egg-info/requires.txt

@@ -0,0 +1,5 @@
+pytesseract>=0.3.13
+ocrmypdf>=16.12.0
+Pillow>=9.0.0
+opencv-python>=4.12.0
+PyMuPDF>=1.26.7

myocr_lib-0.1.1/src/myocr_lib.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+ocr_img
+ocr_pdf

myocr_lib-0.1.1/src/ocr_img/__init__.py

@@ -0,0 +1,3 @@
+from .main_code import ImageOCR
+__all__ = ['ImageOCR']
+__version__ = "0.1.1"

myocr_lib-0.1.1/src/ocr_img/main_code.py

@@ -0,0 +1,56 @@
+import cv2
+from PIL import Image
+import pytesseract
+
+
+class ImageOCR:
+    def __init__(self, image_path):
+
+        # variables section
+        self.image_path = image_path
+
+    def _preprocess_image(self, img_path):
+
+        img = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE)
+
+        # check if it supported webp
+        if img is None:
+            # Process for the webp image
+            img = Image.open(img_path).convert("RGB")
+
+
+        else:
+
+            # Light preprocessing (fast)
+            img = cv2.threshold(img, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
+
+        return img
+    
+    def _apply_ocr(self, img):
+        text = pytesseract.image_to_string(
+            img,
+            lang="eng",
+            config="--oem 3 --psm 6"
+        )
+        return text
+    
+
+    def run(self):
+        # preprocess the image for better results
+        img = self._preprocess_image(self.image_path)
+
+        # apply the ocr 
+        text = self._apply_ocr(img)
+
+        print(text)
+
+        # temporary save to file for demo
+        # get the extension
+        # ext = self.image_path.split('.')[-1]
+        # with open(f'{self.image_path.replace(ext,"txt")}', 'w') as file:
+        #     file.write(text)
+
+        return text
+
+
+

myocr_lib-0.1.1/src/ocr_pdf/__init__.py

@@ -0,0 +1,3 @@
+from .main_code import OCRDataExtractor
+__all__ = ['OCRDataExtractor']
+__version__ = "0.1.1"

myocr_lib-0.1.1/src/ocr_pdf/main_code.py

@@ -0,0 +1,176 @@
+
+import ocrmypdf
+import fitz  # PyMuPDF
+import subprocess
+import os
+
+class OCRDataExtractor:
+    def __init__(self, input_pdf_path):
+
+        # variables section
+        self.input_pdf_path = input_pdf_path
+        self.output_file_path = input_pdf_path.replace('.pdf','_output.pdf')
+        self.pages_to_ocr = [] # holds the pages needing ocr 
+
+
+
+    def _apply_whole_pdf_ocr(self):
+        # Define the Commands
+        command = [
+            "ocrmypdf",
+            f"{self.input_pdf_path}",
+            f"{self.output_file_path}",
+            # "--force-ocr",
+            "--tesseract-timeout", "1000" # increased timeout
+        ]
+
+        # run the command
+        result = subprocess.run(command, capture_output=True, text=True)
+        
+        if result.returncode == 0:
+            print("PDF Was converted to Selectable Successfully.")
+        
+            return True
+        
+        return False
+    
+
+    def _is_whole_pdf_ocr(self):
+        # read and extract the whole text from the pdf
+        THRESHOLD_VALUE = 100 # minimum text
+        is_whole_pdf_ocr_applicable = True
+
+        with fitz.open(self.input_pdf_path) as doc:
+            for page_num in range(len(doc)):
+                page = doc.load_page(page_num)
+                text = page.get_text()
+                if len(text.strip()) > THRESHOLD_VALUE:
+                    is_whole_pdf_ocr_applicable = False
+                else:
+                    # append to the page list
+                    self.pages_to_ocr.append(page_num)
+            
+        return is_whole_pdf_ocr_applicable
+    
+    def _is_page_by_page_ocr(self):
+        return len(self.pages_to_ocr) > 0
+    
+
+    def _apply_page_by_page_ocr(self):
+        # apply the ocr on all the pages needed ocr separately
+        pages_str_format = ','.join(str(page+1) for page in self.pages_to_ocr)  # Convert to 1-based indexing
+
+        print("Pages to extract text from...", pages_str_format)
+
+        # Define the Commands
+        command = [
+            "ocrmypdf",
+            f"{self.input_pdf_path}",
+            f"{self.output_file_path}",
+            # "--force-ocr",
+            '--pages',pages_str_format,
+            "--tesseract-timeout", "1000" # increased timeout
+        ]
+
+        # run the command
+        result = subprocess.run(command, capture_output=True, text=True)
+        
+        if result.returncode == 0:
+            print("Ocr was applied on the pages.")
+        
+            return True
+        
+        return False
+    
+
+    def _extract_text_whole_pdf(self):
+        text = {}
+        text = ""
+        with fitz.open(self.output_file_path) as doc:
+            # Iterate through each page
+            for page_num in range(len(doc)):
+                page = doc.load_page(page_num)
+                # text[page_num] = page.get_text()
+                text += f'Page {page_num + 1} Text\n' + '*' * 20 + page.get_text() + '\n\n'
+
+        return text
+
+    def _extract_text_page_by_page(self):
+        text = {}
+
+        with fitz.open(self.output_file_path) as doc:
+            for page_num in self.pages_to_ocr:
+                page = doc.load_page(page_num)
+                text[page_num] = page.get_text()
+
+        return text
+    
+
+    def get_ocr_results(self):
+        # apply the whole pdf ocr if all the pages are extractable
+        if self._is_whole_pdf_ocr():
+            print("Applying whole Pdf ocr...")
+
+            results = self._apply_whole_pdf_ocr()
+
+            # apply the extraction for the whole pdf through fitz
+            text = self._extract_text_whole_pdf() if results else None
+
+            print(text)
+
+            # temporary store the text
+            # ext = self.input_pdf_path.split('.')[-1]
+            # with open(self.input_pdf_path.replace(ext,'txt'),'w') as file:
+            #     file.write(text)
+
+            # delete the output file
+            self.delete_file(self.output_file_path)
+            print("Done Successfully...")
+
+            return text
+
+        
+        elif self._is_page_by_page_ocr():
+            print("Applying page by page ocr...")
+
+            # do page by page
+            results = self._apply_page_by_page_ocr()
+
+            # do the extraction for specific pages only throug fitz
+            text = self._extract_text_page_by_page() if results else None
+
+            print(text)
+
+            # delete the output file
+            self.delete_file(self.output_file_path)
+            print("Done...")
+
+            return text
+
+        else:
+            # do normal extraction
+            return None 
+
+            print("No Ocr needed...")
+            
+
+        
+    def delete_file(self, file):
+        if os.path.exists(file):
+            os.remove(file)
+            
+
+    def get_ocred_pages(self):
+        return self.pages_to_ocr
+    
+    def run(self):
+
+        text = self.get_ocr_results()
+        pages_to_ignore = self.get_ocred_pages()
+
+        return text, pages_to_ignore
+    
+    
+    
+
+