ocr-stream 1.1__tar.gz → 1.2__tar.gz

ocr_stream-1.2/PKG-INFO

@@ -0,0 +1,63 @@
+Metadata-Version: 2.4
+Name: ocr_stream
+Version: 1.2
+Summary: Extrair textos de documentos digitalizados e imagens.
+Author: Bruno Chaves
+Requires: PyPDF2
+Requires: PyMuPDF
+Requires: reportlab
+Requires: openpyxl
+Requires: openpyxl
+Requires: pandas
+Requires: Pillow
+Requires: opencv_python
+Requires: requests
+Requires: pytesseract
+Requires: soup_files
+Requires: convert_stream
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: PyPDF2==3.0.1
+Requires-Dist: PyMuPDF==1.25.5
+Requires-Dist: reportlab==4.3.1
+Requires-Dist: openpyxl==3.1.5
+Requires-Dist: pandas==2.2.3
+Requires-Dist: Pillow==11.2.1
+Requires-Dist: opencv-python==4.11.0.86
+Requires-Dist: convert_stream
+Requires-Dist: soup_files
+Dynamic: requires
+
+# ocrlib
+
+# Uso simples
+
+
+from ocr_stream import File, TextRecognized, RecognizeImage, RecognizePdf
+
+# passo 1:
+#   instânciar o objeto para reconhecer texto, utilizando o caminho do tesseract
+
+tess: File = File('/usr/bin/tesseract') # Substitua pelo tesseract do seu sistema
+ocr = RecognizeImage.create(path_tesseract=tess)
+
+# passo 2:
+#   instânciar um arquivo de imagem para extrair o texto.
+image: File = File('path/to/file.png')
+
+# passo 3:
+#   extrair o texto
+text: str = ocr.image_to_string(image)
+print(text)
+
+# passo 4 opcional:
+#   você pode salvar um arquivo PDF com o texto extraido
+output_file: File = File('path/to/save.pdf')
+recognized: TextRecognized = ocr.image_recognize(image)
+recognized.to_document().to_file_pdf(output_file)
+
+# passo 5 opcional:
+#   você pode salvar uma planilha com o texto da imagem
+output_excel: File = File('path/to/file.xlsx')
+recognized: TextRecognized = ocr.image_recognize(image)
+recognized.to_document().to_excel(output_excel)

ocr_stream-1.2/README.md

@@ -0,0 +1,33 @@
+# ocrlib
+
+# Uso simples
+
+
+from ocr_stream import File, TextRecognized, RecognizeImage, RecognizePdf
+
+# passo 1:
+#   instânciar o objeto para reconhecer texto, utilizando o caminho do tesseract
+
+tess: File = File('/usr/bin/tesseract') # Substitua pelo tesseract do seu sistema
+ocr = RecognizeImage.create(path_tesseract=tess)
+
+# passo 2:
+#   instânciar um arquivo de imagem para extrair o texto.
+image: File = File('path/to/file.png')
+
+# passo 3:
+#   extrair o texto
+text: str = ocr.image_to_string(image)
+print(text)
+
+# passo 4 opcional:
+#   você pode salvar um arquivo PDF com o texto extraido
+output_file: File = File('path/to/save.pdf')
+recognized: TextRecognized = ocr.image_recognize(image)
+recognized.to_document().to_file_pdf(output_file)
+
+# passo 5 opcional:
+#   você pode salvar uma planilha com o texto da imagem
+output_excel: File = File('path/to/file.xlsx')
+recognized: TextRecognized = ocr.image_recognize(image)
+recognized.to_document().to_excel(output_excel)

{ocr_stream-1.1 → ocr_stream-1.2}/ocr_stream/__init__.py

@@ -1,10 +1,8 @@
 #!/usr/bin/env python3
 
-from .models.m_modules_ocr import (
-    LibraryOCR,
-)
-
+from .models.m_modules_ocr import LibraryOCR
 from .modules_ocr import TextRecognized
+from .utils import File, Directory, InputFiles, UserFileSystem
 from .extractors import RecognizeImage, RecognizePdf
 from ._version import __version__, __modify_data__
 

{ocr_stream-1.1 → ocr_stream-1.2}/ocr_stream/__main__.py

@@ -5,8 +5,7 @@
     Configuração instalação:
 ------------------------------------------------------------
  $ pip3 install -r requirements.txt
- $ pip3 install https://gitlab.com/bschaves/pdflib/-/archive/V1.0/pdflib-V1.0.zip
-
+ 
 ------------------------------------------------------------
     Referências:
 ------------------------------------------------------------
@@ -22,6 +21,7 @@ https://github.com/h/pytesseract
 pyocr
 https://gitlab.gnome.org/World/OpenPaperwork/pyocr
 """
+
 import sys, os
 this_file = os.path.abspath(os.path.relpath(__file__))
 dir_of_project = os.path.dirname(this_file)
@@ -30,14 +30,17 @@ sys.path.insert(0, dir_of_project)
 from convert_stream import print_title
 from ocr_stream import __version__, __modify_data__
 
+
 def test():
     # /usr/bin/tesseract
     # /usr/share/tesseract-ocr/5/tessdata
     pass
     
+    
 def main():
     print_title(f' ocrlib Versão: {__version__} | Atualização: {__modify_data__} ')
     test()
 
+
 if __name__ == '__main__':
     main()

ocr_stream-1.2/ocr_stream/_version.py

@@ -0,0 +1,5 @@
+#!/usr/bin/env python3
+#
+
+__version__ = '1.2'
+__modify_data__ = '2025-06-22'

{ocr_stream-1.1 → ocr_stream-1.2}/ocr_stream/extractors.py

@@ -1,24 +1,14 @@
 #!/usr/bin/env python3
 from __future__ import annotations
-
 from ocr_stream.utils import (
-    File, 
-    Directory, 
-    ImageObject, 
-    DataFrame, 
-    PageDocumentPdf, 
-    DocumentPdf, 
-    PdfStream, 
-    LibraryPDF,    
-)
-
-from ocr_stream.models import ( 
-    ABCRecognizeImage,
-    LibraryOCR,
+    File, Directory, ImageObject, 
+    DataFrame, PageDocumentPdf, 
+    DocumentPdf, PdfStream, LibraryPDF,    
 )
-
+from ocr_stream.models import ABCRecognizeImage, LibraryOCR
 from ocr_stream.modules_ocr import ModuleOcr, TextRecognized
 
+
 class RecognizeImage(ABCRecognizeImage):
     def __init__(self, module_ocr):
         super().__init__(module_ocr)
@@ -48,8 +38,16 @@ class RecognizeImage(ABCRecognizeImage):
             raise ValueError(f'{__class__.__name__}\nUse: ImageObject() ou File(), não {type(img)}')
     
     @classmethod
-    def create(cls, library_ocr=LibraryOCR.PYTESSERACT, *, path_tesseract, lang=None, tess_data_dir=None) -> RecognizeImage:
-        module_ocr:ModuleOcr = ModuleOcr.create(
+    def create(
+                cls, 
+                library_ocr = LibraryOCR.PYTESSERACT, 
+                *, 
+                path_tesseract, 
+                lang=None, 
+                tess_data_dir=None
+            ) -> RecognizeImage:
+        #
+        module_ocr: ModuleOcr = ModuleOcr.create(
             library_ocr,
             path_tesseract=path_tesseract,
             lang=lang,
@@ -59,8 +57,8 @@ class RecognizeImage(ABCRecognizeImage):
   
   
 class RecognizePdf(object):
-    def __init__(self, recognize_image:RecognizeImage):
-        self.recognize_image:RecognizeImage = recognize_image
+    def __init__(self, recognize_image: RecognizeImage):
+        self.recognize_image: RecognizeImage = recognize_image
 
     def recognize_page_pdf(self, page:PageDocumentPdf) -> PageDocumentPdf:
         """
@@ -69,27 +67,28 @@ class RecognizePdf(object):
         """
         pdf_stream = PdfStream(library_pdf=LibraryPDF.FITZ)
         pdf_stream.add_page(page)
-        img:ImageObject = pdf_stream.to_images()[0]
+        img: ImageObject = pdf_stream.to_images()[0]
         text_recognized:TextRecognized = self.recognize_image.image_recognize(img)
         return text_recognized.to_page_pdf()
     
     def recognize_document(self, doc:DocumentPdf) -> DocumentPdf:
-        new:DocumentPdf = DocumentPdf()
+        new: DocumentPdf = DocumentPdf()
         for page in doc.pages:
-            recognized_page:PageDocumentPdf = self.recognize_page_pdf(page)
+            recognized_page: PageDocumentPdf = self.recognize_page_pdf(page)
             new.add_page(recognized_page)
         return new
 
     @classmethod
     def create(
                 cls, 
-                library_ocr=LibraryOCR.PYTESSERACT, 
+                library_ocr = LibraryOCR.PYTESSERACT, 
                 *,
-                path_tesseract:File, 
+                path_tesseract: File, 
                 lang:str=None,
-                tess_data_dir:Directory=None,
+                tess_data_dir: Directory=None,
             ) -> RecognizePdf:
-        ##
+        #
+        #
         recognize_image = RecognizeImage.create(
                     library_ocr, 
                     path_tesseract=path_tesseract, 
@@ -97,6 +96,7 @@ class RecognizePdf(object):
                     tess_data_dir=tess_data_dir
                 )
         return cls(recognize_image)
+
    
 
             

{ocr_stream-1.1 → ocr_stream-1.2}/ocr_stream/models/m_modules_ocr.py

@@ -31,13 +31,14 @@ class ABCTextRecognized(ABC):
         pass
     
     @abstractmethod
-    def to_dataframe(self, column:str='TEXT') -> DataFrame:
+    def to_dataframe(self, separator:str='\n', column_text: str = 'TEXT') -> DataFrame:
         pass
     
     @abstractmethod
-    def to_dict(self) -> Dict[str, List[str]]:
+    def to_dict(self, separator:str='\n', column_text: str = 'TEXT') -> Dict[str, List[str]]:
         pass
   
+  
 #======================================================================#
 # Abstração para o módulo que extrai o texto das imagens (OCR)
 # pode ser implementado com pytesseract ou outros.

{ocr_stream-1.1 → ocr_stream-1.2}/ocr_stream/modules_ocr.py

@@ -5,19 +5,17 @@ from typing import List, Dict
 from pathlib import Path
 import re
 import os
-
+from pandas import DataFrame
+from pytesseract import pytesseract, Output
 from ocr_stream.models import ( 
-    ABCModuleOcr,
-    ABCTextRecognized,
-    LibraryOCR,
+    ABCModuleOcr, ABCTextRecognized, LibraryOCR,
 )
-from pandas import DataFrame
 from ocr_stream.utils import (
-    PageDocumentPdf, DocumentPdf, LibraryImage, ImageObject, ArrayString, DataString,
-    File, Directory
+    PageDocumentPdf, DocumentPdf, LibraryImage, LibraryPDF,
+    ImageObject, ArrayString, DataString, File, Directory
 )
 
-from pytesseract import pytesseract, Output
+
 
 def get_temp_dir(prefix=Path().home()) -> str:
     prefix = Path().home()
@@ -204,9 +202,12 @@ class TextRecognizedToi(object):
     def line_roteiro(self) -> DataString:
         return DataString(None) 
 
+
 #======================================================================#
 # Texto reconhecido de uma imagem.
 #======================================================================#
+
+
 class TextRecognized(ABCTextRecognized):
     """
         Recebe os bytes de uma página PDF reconhecida de imagem
@@ -215,10 +216,10 @@ class TextRecognized(ABCTextRecognized):
     -> str
     -> PageDocumentPdf()
     """
-    def __init__(self, bytes_recognized):
+    def __init__(self, bytes_recognized: bytes):
         super().__init__(bytes_recognized)
         
-        self.list_bad_char:List[str] = [
+        self.list_bad_char: List[str] = [
                             ':', ',', ';', '$', '=', 
                             '!', '}', '{', '(', ')', 
                             '|', '\\', '‘', '*'
@@ -232,33 +233,37 @@ class TextRecognized(ABCTextRecognized):
         return self.to_page_pdf().to_string()
     
     def to_page_pdf(self) -> PageDocumentPdf:
-        return PageDocumentPdf.create_from_page_bytes(self.bytes_recognized)
+        _page = PageDocumentPdf.create_from_page_bytes(
+            self.bytes_recognized, 
+            library = LibraryPDF.FITZ
+        )
+        return _page
     
     def to_document(self) -> DocumentPdf:
-        doc: DocumentPdf = DocumentPdf()
-        doc.add_page(self.to_page_pdf())
+        doc = DocumentPdf(pages=self.to_page_pdf())
         return doc
     
-    def to_dict(self, separator:str='\n') -> Dict[str, List[str]]:
+    def to_dict(self, separator = '\n', column_text = 'TEXT') -> Dict[str, List[str]]:
         image_dict:Dict[str, List[str]] = {
-            'TEXT': [],
+            column_text: [],
             'NUM_LINHA': [],
         }
         image_text:str = self.to_string()
         if (image_text is None) or (image_text == ''):
             return {
-                    'TEXT': ['nan'],
+                    column_text: ['nan'],
                     'NUM_LINHA': ['nan'],
                 }
         
-        image_lines:List[str] = image_text.split(separator)
+        image_lines: List[str] = image_text.split(separator)
         for num, line in enumerate(image_lines):
-            image_dict['TEXT'].append(line)
+            image_dict[column_text].append(line)
             image_dict['NUM_LINHA'].append(num+1)
         return image_dict    
     
-    def to_dataframe(self, column = 'TEXT', separator:str='\n') -> DataFrame:
-        return DataFrame(self.to_dict(separator))
+    def to_dataframe(self, separator = '\n', column_text = 'TEXT') -> DataFrame:
+        return DataFrame(self.to_dict(separator, column_text))
+    
     
 #======================================================================#
 # Modulo OCR pytesseract
@@ -381,7 +386,7 @@ class IModulePyOcr(ABCModuleOcr):
     
 
 class ModuleOcr(ABCModuleOcr):
-    def __init__(self, module_ocr:ABCModuleOcr):
+    def __init__(self, module_ocr: ABCModuleOcr):
         super().__init__(
                 cmd_executable=module_ocr.cmd_executable, 
                 lang=module_ocr.lang, 
@@ -389,7 +394,7 @@ class ModuleOcr(ABCModuleOcr):
             )
         self.module_ocr:ABCModuleOcr = module_ocr
         
-    def image_content_data(self, img:ImageObject) -> DataFrame:
+    def image_content_data(self, img: ImageObject) -> DataFrame:
         return self.module_ocr.image_content_data(img)
     
     def image_recognize(self, img:ImageObject) -> TextRecognized:
@@ -403,7 +408,7 @@ class ModuleOcr(ABCModuleOcr):
                 cls, 
                 library_ocr = LibraryOCR.PYTESSERACT, 
                 *, 
-                path_tesseract, 
+                path_tesseract: File, 
                 lang = None, 
                 tess_data_dir = None
             ) -> ModuleOcr:

ocr_stream-1.2/ocr_stream.egg-info/PKG-INFO

@@ -0,0 +1,63 @@
+Metadata-Version: 2.4
+Name: ocr_stream
+Version: 1.2
+Summary: Extrair textos de documentos digitalizados e imagens.
+Author: Bruno Chaves
+Requires: PyPDF2
+Requires: PyMuPDF
+Requires: reportlab
+Requires: openpyxl
+Requires: openpyxl
+Requires: pandas
+Requires: Pillow
+Requires: opencv_python
+Requires: requests
+Requires: pytesseract
+Requires: soup_files
+Requires: convert_stream
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: PyPDF2==3.0.1
+Requires-Dist: PyMuPDF==1.25.5
+Requires-Dist: reportlab==4.3.1
+Requires-Dist: openpyxl==3.1.5
+Requires-Dist: pandas==2.2.3
+Requires-Dist: Pillow==11.2.1
+Requires-Dist: opencv-python==4.11.0.86
+Requires-Dist: convert_stream
+Requires-Dist: soup_files
+Dynamic: requires
+
+# ocrlib
+
+# Uso simples
+
+
+from ocr_stream import File, TextRecognized, RecognizeImage, RecognizePdf
+
+# passo 1:
+#   instânciar o objeto para reconhecer texto, utilizando o caminho do tesseract
+
+tess: File = File('/usr/bin/tesseract') # Substitua pelo tesseract do seu sistema
+ocr = RecognizeImage.create(path_tesseract=tess)
+
+# passo 2:
+#   instânciar um arquivo de imagem para extrair o texto.
+image: File = File('path/to/file.png')
+
+# passo 3:
+#   extrair o texto
+text: str = ocr.image_to_string(image)
+print(text)
+
+# passo 4 opcional:
+#   você pode salvar um arquivo PDF com o texto extraido
+output_file: File = File('path/to/save.pdf')
+recognized: TextRecognized = ocr.image_recognize(image)
+recognized.to_document().to_file_pdf(output_file)
+
+# passo 5 opcional:
+#   você pode salvar uma planilha com o texto da imagem
+output_excel: File = File('path/to/file.xlsx')
+recognized: TextRecognized = ocr.image_recognize(image)
+recognized.to_document().to_excel(output_excel)

{ocr_stream-1.1 → ocr_stream-1.2}/ocr_stream.egg-info/requires.txt

@@ -1,4 +1,3 @@
-soup_files==1.0.1
 PyPDF2==3.0.1
 PyMuPDF==1.25.5
 reportlab==4.3.1
@@ -6,4 +5,5 @@ openpyxl==3.1.5
 pandas==2.2.3
 Pillow==11.2.1
 opencv-python==4.11.0.86
-convert_stream==1.1.1
+convert_stream
+soup_files

{ocr_stream-1.1 → ocr_stream-1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ocr_stream"
-version = "1.1" 
+version = "1.2" 
 authors = [
   { name="Bruno Chaves"},
 ]
@@ -13,7 +13,6 @@ readme = "README.md"
 requires-python = ">=3.11"
 
 dependencies = [
-    "soup_files==1.0.1",
     "PyPDF2==3.0.1",
     "PyMuPDF==1.25.5",
     "reportlab==4.3.1",
@@ -21,7 +20,9 @@ dependencies = [
     "pandas==2.2.3",
     "Pillow==11.2.1",
     "opencv-python==4.11.0.86",
-    "convert_stream==1.1.1",
+    "convert_stream",
+    "soup_files",
 ]
+
 [tool.setuptools]
 packages = ["ocr_stream", "ocr_stream.models", "ocr_stream.utils"]

{ocr_stream-1.1 → ocr_stream-1.2}/setup.py

@@ -1,14 +1,5 @@
 #!/usr/bin/env python3
 
-#!/usr/bin/env python3
-
-
-"""
-REQUERIMENTOS EXTERNOS:
-
-pip3 install 'https://gitlab.com/bschavesbr/file-utils/-/archive/main/file-utils-main.zip'
-pip3 install https://gitlab.com/bschaves/pdflib/-/archive/V1.0/pdflib-V1.0.zip
-"""
 import os
 import sys
 
@@ -20,7 +11,6 @@ except Exception as e:
 
 file_setup = os.path.abspath(os.path.realpath(__file__))
 dir_of_project = os.path.dirname(file_setup)
-
 sys.path.insert(0, dir_of_project)
 
 
@@ -29,21 +19,23 @@ LONG_DESCRIPTION = ''
 
 setup(
 	name='ocrlib',
-	version='1.0',
+	version='1.2',
 	description=DESCRIPTION,
 	long_description=LONG_DESCRIPTION,
 	license='MIT',
 	requires=[
-     			'PyPDF2',
-				'PyMuPDF',
-				'reportlab',
-				'openpyxl',
-				'openpyxl',
-				'pandas',
-				'Pillow',
-				'opencv_python',
-				'requests',
-				'pytesseract',
+			'PyPDF2',
+			'PyMuPDF',
+			'reportlab',
+			'openpyxl',
+			'openpyxl',
+			'pandas',
+			'Pillow',
+			'opencv_python',
+			'requests',
+			'pytesseract',
+			'soup_files',
+			'convert_stream',
 	],
 	packages=['ocrlib', 'ocrlib.models', 'ocrlib.utils'],
 	zip_safe=False,

ocr_stream-1.1/PKG-INFO

@@ -1,57 +0,0 @@
-Metadata-Version: 2.4
-Name: ocr_stream
-Version: 1.1
-Summary: Extrair textos de documentos digitalizados e imagens.
-Author: Bruno Chaves
-Requires: PyPDF2
-Requires: PyMuPDF
-Requires: reportlab
-Requires: openpyxl
-Requires: openpyxl
-Requires: pandas
-Requires: Pillow
-Requires: opencv_python
-Requires: requests
-Requires: pytesseract
-Requires-Python: >=3.11
-Description-Content-Type: text/markdown
-Requires-Dist: soup_files==1.0.1
-Requires-Dist: PyPDF2==3.0.1
-Requires-Dist: PyMuPDF==1.25.5
-Requires-Dist: reportlab==4.3.1
-Requires-Dist: openpyxl==3.1.5
-Requires-Dist: pandas==2.2.3
-Requires-Dist: Pillow==11.2.1
-Requires-Dist: opencv-python==4.11.0.86
-Requires-Dist: convert_stream==1.1.1
-Dynamic: requires
-
-# ocrlib
-
-# Uso simples
-
-from ocrlib.utils import File, DocumentPdf
-from ocrlib import RecognizeImage
-
-# passo 1 instânciar o objeto para reconhecer texto, ultilzaremos o caminho do tesseract
-# Substitua pelo tesseract do seu sistema
-
-tess = File('/usr/bin/tesseract')
-ocr = RecognizeImage.create(path_tesseract=tess)
-
-# passo 2 instânciar um arquivo de imagem para extrair o texto.
-image = File('path/to/file.png')
-
-# passo 3 extrair o texto
-text = ocr.image_to_string(image)
-print(text)
-
-# passo 4 opcional - você pode salvar um arquivo PDF com o texto extraido
-output_file = File('path/to/save.pdf')
-recognized = ocr.image_recognize(image)
-recognized.to_document().to_file_pdf(output_file)
-
-# passo 5 opcional - você pode salvar uma planilha com o texto da imagem
-output_excel = File('path/to/file.xlsx')
-recognized = ocr.image_recognize(image)
-recognized.to_document().to_excel(output_excel)

ocr_stream-1.1/README.md

@@ -1,29 +0,0 @@
-# ocrlib
-
-# Uso simples
-
-from ocrlib.utils import File, DocumentPdf
-from ocrlib import RecognizeImage
-
-# passo 1 instânciar o objeto para reconhecer texto, ultilzaremos o caminho do tesseract
-# Substitua pelo tesseract do seu sistema
-
-tess = File('/usr/bin/tesseract')
-ocr = RecognizeImage.create(path_tesseract=tess)
-
-# passo 2 instânciar um arquivo de imagem para extrair o texto.
-image = File('path/to/file.png')
-
-# passo 3 extrair o texto
-text = ocr.image_to_string(image)
-print(text)
-
-# passo 4 opcional - você pode salvar um arquivo PDF com o texto extraido
-output_file = File('path/to/save.pdf')
-recognized = ocr.image_recognize(image)
-recognized.to_document().to_file_pdf(output_file)
-
-# passo 5 opcional - você pode salvar uma planilha com o texto da imagem
-output_excel = File('path/to/file.xlsx')
-recognized = ocr.image_recognize(image)
-recognized.to_document().to_excel(output_excel)

ocr_stream-1.1/ocr_stream/_version.py

@@ -1,5 +0,0 @@
-#!/usr/bin/env python3
-#
-
-__version__ = '1.1'
-__modify_data__ = '2025-04-22'

ocr_stream-1.1/ocr_stream.egg-info/PKG-INFO

@@ -1,57 +0,0 @@
-Metadata-Version: 2.4
-Name: ocr_stream
-Version: 1.1
-Summary: Extrair textos de documentos digitalizados e imagens.
-Author: Bruno Chaves
-Requires: PyPDF2
-Requires: PyMuPDF
-Requires: reportlab
-Requires: openpyxl
-Requires: openpyxl
-Requires: pandas
-Requires: Pillow
-Requires: opencv_python
-Requires: requests
-Requires: pytesseract
-Requires-Python: >=3.11
-Description-Content-Type: text/markdown
-Requires-Dist: soup_files==1.0.1
-Requires-Dist: PyPDF2==3.0.1
-Requires-Dist: PyMuPDF==1.25.5
-Requires-Dist: reportlab==4.3.1
-Requires-Dist: openpyxl==3.1.5
-Requires-Dist: pandas==2.2.3
-Requires-Dist: Pillow==11.2.1
-Requires-Dist: opencv-python==4.11.0.86
-Requires-Dist: convert_stream==1.1.1
-Dynamic: requires
-
-# ocrlib
-
-# Uso simples
-
-from ocrlib.utils import File, DocumentPdf
-from ocrlib import RecognizeImage
-
-# passo 1 instânciar o objeto para reconhecer texto, ultilzaremos o caminho do tesseract
-# Substitua pelo tesseract do seu sistema
-
-tess = File('/usr/bin/tesseract')
-ocr = RecognizeImage.create(path_tesseract=tess)
-
-# passo 2 instânciar um arquivo de imagem para extrair o texto.
-image = File('path/to/file.png')
-
-# passo 3 extrair o texto
-text = ocr.image_to_string(image)
-print(text)
-
-# passo 4 opcional - você pode salvar um arquivo PDF com o texto extraido
-output_file = File('path/to/save.pdf')
-recognized = ocr.image_recognize(image)
-recognized.to_document().to_file_pdf(output_file)
-
-# passo 5 opcional - você pode salvar uma planilha com o texto da imagem
-output_excel = File('path/to/file.xlsx')
-recognized = ocr.image_recognize(image)
-recognized.to_document().to_excel(output_excel)