convert-stream 1.1__py3-none-any.whl

convert_stream/pdf_page.py

@@ -0,0 +1,251 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+from __future__ import annotations
+from typing import List, Dict
+from io import BytesIO
+from PyPDF2 import PdfReader, PdfWriter, PageObject
+
+try:
+    from fitz import Page, Pixmap, Document
+except:
+    from pymupdf import Page, Pixmap, Document
+
+from soup_files import File, Directory
+from convertlib.models.m_text import TableText
+from convertlib.models.m_imgelib import LibraryImage
+from convertlib.models.m_pdf_page import LibraryPDF, ABCPagePdf
+from convertlib.imagelib import ImageObject, ImageInverColor
+
+#======================================================================#
+# Página PDF
+#======================================================================#
+
+class PyPdf2PagePdf(ABCPagePdf):
+    """Implementação para manipular páginas PDF com PyPDF2"""
+    def __init__(self, page:PageObject, page_number: int):
+        if not isinstance(page, PageObject):
+            raise ValueError(f'{__class__.__name__} Use: PageObject(), não {type(page)}')
+        self.page:PageObject = page
+        self.page_number:int = page_number
+        self.current_library = LibraryPDF.PYPDF
+
+    def to_string(self) -> str:
+        s = self.page.extract_text()
+        if (s is None) or (s == ''):
+            return None
+        return s
+    
+    def to_list(self, separator:str='\n') -> List[str]:
+        return self.to_string().split(separator) if self.to_string() is not None else []
+    
+    def to_table(self, separator:str='\n') -> TableText:
+        s = self.to_string()
+        if s is None:
+            return TableText('', separator=separator)
+        return TableText(s, separator=separator)
+
+    def rotate(self, degrees: int):
+        self.page.rotate(degrees)
+
+    def to_bytes(self) -> bytes:
+        pdf_writer = PdfWriter()
+        pdf_writer.add_page(self.page)
+        output_bytes = BytesIO()
+        pdf_writer.write(output_bytes)
+        pdf_bytes = output_bytes.getvalue()
+        output_bytes.close()
+        return pdf_bytes
+    
+    def set_paisagem(self):
+        if not self.is_paisagem():
+            self.rotate(-90)
+    
+    def is_paisagem(self):
+        return False if self.page.mediabox.width < self.page.mediabox.height else True
+    
+    def set_page_fitz(self):
+        pass
+    
+    def set_page_pypdf2(self):
+        pass
+    
+    @classmethod
+    def create_from_page_bytes(cls, page_bytes) -> PyPdf2PagePdf:
+        try:
+            pdf_writer = PdfWriter()
+            pdf_reader = PdfReader(BytesIO(page_bytes))  # Carrega o PDF a partir dos bytes
+            pdf_writer.add_page(pdf_reader.pages[0])  # Adiciona cada página ao escritor
+        except Exception as e:
+            print(e)
+            return None
+        else:
+            return cls(pdf_writer.pages[0], 1)
+        
+    @classmethod
+    def create_from_page_pypdf2(cls, page:PageObject):
+        if not isinstance(page, PageObject):
+            raise ValueError(f'{__class__.__name__}Use: PageObject(), não {type(page)}')
+        return cls(page, 1)
+    
+    @classmethod
+    def create_from_page_fitz(cls, page) -> None:
+        pass
+           
+            
+class FitzPagePdf(ABCPagePdf):
+    """Implementação para manipular páginas PDF com fitz"""
+    def __init__(self, page: Page, page_number:int):
+        self.page:Page = page
+        self.page_number:int = page_number
+        self.current_library = LibraryPDF.FITZ
+
+    def to_string(self) -> str:
+        s = self.page.get_text()
+        if (s is None) or (s == ''):
+            return None
+        return s
+    
+    def to_list(self, separator:str='\n') -> List[str]:
+        return self.to_string().split(separator) if self.to_string() is not None else []
+    
+    def to_table(self, separator:str='\n') -> TableText:
+        s = self.to_string()
+        if s is None:
+            return TableText('', separator=separator)
+        return TableText(s, separator=separator)
+
+    def rotate(self, degrees: int):
+        # Ajuste para rotação anti-horária
+        current_rotation = self.page.rotation  # Obter rotação atual da página
+        new_rotation = (current_rotation + degrees) % 360  # Atualizar a rotação acumulativa
+        self.page.set_rotation(new_rotation)  # Aplicar a nova rotação
+        
+    def to_bytes(self) -> bytes:
+        temp_doc = Document()
+        temp_doc.insert_pdf(self.page.parent, from_page=self.page.number, to_page=self.page.number)
+        return temp_doc.write()
+    
+    def set_paisagem(self):
+        if not self.is_paisagem():
+            self.page.set_rotation(-90)  # Rotaciona 90 graus para paisagem
+    
+    def is_paisagem(self):
+        return False if self.page.rect.height > self.page.rect.width else True 
+    
+    def set_page_fitz(self):
+        pass
+    
+    def set_page_pypdf2(self):
+        pass
+    
+    @classmethod
+    def create_from_page_bytes(cls, page_bytes) -> FitzPagePdf:
+        try:
+            merged_document = Document()
+            temp_doc:Document = Document(stream=page_bytes, filetype="pdf")  
+            merged_document.insert_pdf(temp_doc)  
+            current_page:Page = merged_document[0]
+        except Exception as e:
+            print(e)
+            return None
+        else:
+            return cls(current_page, current_page.number)
+        
+    @classmethod
+    def create_from_page_pypdf2(cls, page:object) -> None:
+        pass
+    
+    @classmethod
+    def create_from_page_fitz(cls, page) -> FitzPagePdf:
+        if not isinstance(page, Page):
+            raise ValueError(f'{__class__.__name__}Use: Page(), não {type(page)}')
+        return cls(page, 1)        
+
+#======================================================================#
+# FACADE para trabalhar com uma página PDF.
+#======================================================================#
+class PageDocumentPdf(ABCPagePdf):
+    def __init__(self, page:ABCPagePdf):
+        self.__page:ABCPagePdf = page
+        self.page_number:int = page.page_number
+        self.current_library:LibraryPDF = page.current_library
+        
+    @property
+    def page(self) -> ABCPagePdf:
+        return self.__page
+    
+    @page.setter
+    def page(self, new:ABCPagePdf):    
+        if isinstance(new, PyPdf2PagePdf):
+            self.__page = new
+        elif isinstance(new, FitzPagePdf):
+            self.__page = new
+        elif isinstance(new, PageDocumentPdf):
+            self.__page = new.page
+        else:
+            raise ValueError(f'{__class__.__name__} Use: ABCPagePdf(), não {type(new)}')
+        self.page_number = self.__page.page_number
+        self.current_library = self.__page.current_library
+
+    def __eq__(self, value: ABCPagePdf):
+        return (self.to_string() == value.to_string()) and (self.page_number == value.page_number)
+    
+    def __hash__(self) -> int:
+        h1 = hash(self.page_number)
+        h2 = hash(self.to_string())
+        return hash(f'{h1}_{h2}')
+
+    def to_string(self) -> str | None:
+        return self.page.to_string()
+    
+    def to_list(self, separator:str='\n') -> List[str]:
+        return self.page.to_list(separator)
+    
+    def to_table(self, separator:str='\n') -> TableText:
+        return self.page.to_table(separator)
+        
+    def to_bytes(self) -> bytes:
+        return self.page.to_bytes()
+
+    def is_paisagem(self) -> bool:
+        return self.page.is_paisagem()
+
+    def set_paisagem(self):
+        self.page.set_paisagem()
+        
+    def set_page_fitz(self):
+        if self.page.current_library == LibraryPDF.FITZ:
+            return
+        pg = FitzPagePdf.create_from_page_bytes(self.to_bytes())
+        self.page = pg
+    
+    def set_page_pypdf2(self):
+        if self.page.current_library == LibraryPDF.PYPDF:
+            return
+        pg = PyPdf2PagePdf.create_from_page_bytes(self.to_bytes())
+        self.page = pg
+
+    def rotate(self, degrees: int):
+        self.page.rotate(degrees)
+    
+    @classmethod
+    def create_from_page_bytes(cls, page_bytes:bytes, *, library:LibraryPDF=LibraryPDF.PYPDF) -> PageDocumentPdf:
+        if library == LibraryPDF.PYPDF:
+            pg = PyPdf2PagePdf.create_from_page_bytes(page_bytes)
+        elif library == LibraryPDF.FITZ:
+            pg = FitzPagePdf.create_from_page_bytes(page_bytes)
+        else:
+            raise ValueError("Biblioteca inválida: escolha 'fitz' ou 'pypdf2'.")
+        #
+        return cls(pg)
+        
+    @classmethod
+    def create_from_page_pypdf2(cls, page:PageObject) -> None:
+        pg = PyPdf2PagePdf.create_from_page_pypdf2(page)
+        return cls(pg)
+    
+    @classmethod
+    def create_from_page_fitz(cls, page) -> FitzPagePdf:
+        pg = FitzPagePdf.create_from_page_fitz(page)
+        return cls(pg)    

convert_stream/text.py

@@ -0,0 +1,8 @@
+#!/usr/bin/env python3
+#
+
+from convertlib.models import (
+    print_line, print_title, save_data,
+    ConvertDate, DataString, ArrayString,
+    LibraryDates, TableText
+)

convert_stream-1.1.dist-info/METADATA

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: convert_stream
+Version: 1.1
+Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
+Author: Bruno Chaves
+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: requests==2.32.3
+
+# Configuração instalação:
+pip3 install -r requirements.txt
+
+
+# Uso dividir páginas de um arquivo PDF:
+    >>> from file import File, Directory
+    >>> from pdflib import PdfStream
+    # instâncie o caminho do arquivo PDF e o diretório para exportar os dados.
+    f = File('path/to/file.pdf')
+    d = Directory('path/to/save')
+
+    pdf_stream = PdfStream()
+    pdf_stream.add_file_pdf(f)
+    pdf_stream.to_files_pdf(d) # isso irá converter cada página em um arquivo PDF
+
+# Uso para unir vários arquivos PDF.
+    >>> from file import File, Directory
+    >>> from pdflib import PdfStream
+    # instâncie o caminho dos arquivos PDF que deseja unir.
+    f = File('path/to/file.pdf')
+    f2 = File('path/to/file2.pdf)
+    ...
+    ... # Adicione quantos arquivos desejar.
+    
+    pdf_stream = PdfStream()
+    pdf_stream.add_file_pdf(f)
+    pdf_stream.add_file_pdf(f2)
+    pdf_stream.to_file_pdf(File('path/to/new_file.pdf'))

convert_stream-1.1.dist-info/RECORD

@@ -0,0 +1,20 @@
+convert_stream/__init__.py,sha256=18yF0aKg1TurBEuN52X-m_-Kucvj4rCRUe4mBIc2dSY,605
+convert_stream/__main__.py,sha256=P8AoCKLEwJDZz7RViIbUs2waHXVtblvvDSJgl9nh6u8,762
+convert_stream/_version.py,sha256=_bhIn9J0WZrzFZygDF5NNOJC59lTtcupK9R0-atfshI,172
+convert_stream/convert.py,sha256=fLpmdWf4j3jHMiYWWgO1nMXtTz4_id_m_8ZHpTvk6Ts,11258
+convert_stream/imagelib.py,sha256=HtMndduCW92toRr2mEJWuj-fgdwfuwYk8D1O5UWvpc8,19644
+convert_stream/library.py,sha256=x2Wnj6yGdXd0AOD_rALHW_lAk1XZ9-IACip3OuWiRNs,148
+convert_stream/pdf_convert.py,sha256=3PGDJMlRneyd4MQFJWbInzqR83dIKHGWegQW8UmuyXE,11804
+convert_stream/pdf_document.py,sha256=1_Pn8pFU9vHtdJ9cZaOU72BInm1JUzb4N48pF1xj4-M,18935
+convert_stream/pdf_page.py,sha256=H9xjbhlz8EbeVT6XiRTkUC2RRc0foUvSsPt07Pmr6Ew,8666
+convert_stream/text.py,sha256=apRYAV8POoJfQqosXO_6QxqCwJGG_UGKU0u1o-71o8s,169
+convert_stream/models/__init__.py,sha256=gXVkNtXXUokv_u5h52mx2Io9DCDZCZRDwBocUlCJli8,392
+convert_stream/models/m_imgelib.py,sha256=qMrcSkUBf3NYlkaJQR5-vb1ZDVGiLbLJap-14UpGUBU,2022
+convert_stream/models/m_pdf_convert.py,sha256=W3eBW8sWXhABKsSwUtXHj3vOYXxpkE_yXy4TYVgXK0k,4533
+convert_stream/models/m_pdf_document.py,sha256=r1W6MIpUmUgutLTIaaKkqiux6sBYogqXRfGeHbVPbjs,3027
+convert_stream/models/m_pdf_page.py,sha256=Ghr1wTdrzxax-tlCawsxORUGy0M6WiGApIYsu_YosRk,1687
+convert_stream/models/m_text.py,sha256=27pNjdmcj7XrE80Ha4zcuBrnE4F5Ue27uXESMYNw5Ms,15723
+convert_stream-1.1.dist-info/METADATA,sha256=ReupXsW67Yhyvt9H7qVHwimHvoecUGAsPaM7lHjirT0,1453
+convert_stream-1.1.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
+convert_stream-1.1.dist-info/top_level.txt,sha256=km2_p00LQvaGe1uG4rF7lFnoLiU4pBfSrsa-2JomPDk,15
+convert_stream-1.1.dist-info/RECORD,,

convert_stream-1.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (79.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

convert_stream-1.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+convert_stream