convert-stream 2.3.5__tar.gz → 2.3.6__tar.gz

{convert_stream-2.3.5 → convert_stream-2.3.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.3.5
+Version: 2.3.6
 Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
 Author: Bruno Chaves
 Requires-Python: >=3.11

{convert_stream-2.3.5 → convert_stream-2.3.6}/convert_stream/__init__.py

@@ -13,7 +13,7 @@ from .mod_types import (
     LibImageToPdf, create_dict_map_from_file, create_void_dict_map, RotationAngle
 )
 from .image import ImageObject, CollectionImages
-from .pdf import DocumentPdf, PageDocumentPdf, CollectionPagePdf
+from .pdf import DocumentPdf, PageDocumentPdf, CollectionPagePdf, ConvertPdfToImages, ConvertImageToPdf
 from .pdf.pdf_document import SearchableTextPdf
 from .doc_stream import PdfStream, SplitPdf
 from .table_files import PdfFinder
@@ -76,9 +76,10 @@ __all__ = [
     '__modify_date__', '__author__', '__license__', '__module_name__', '__version__',
     'PdfStream', 'DocumentPdf', 'PageDocumentPdf', 'CollectionPagePdf', 'CollectionImages',
     'ImageObject', 'File', 'Directory', 'LibraryDocs', 'InputFiles', 'SearchableTextPdf',
-    'PdfFinder', 'SplitPdf', 'read_pdf', 'read_files_pdf', 'read_image',
-    'MetaDataFile', 'MetaDataItem', 'create_metadata', 'ColumnsTable', 'ListString', 'ArrayString',
+    'PdfFinder', 'SplitPdf', 'LibImageToPdf',  'RotationAngle', 'ConvertImageToPdf', 'ConvertPdfToImages',
+    'MetaDataFile', 'MetaDataItem', 'ColumnsTable', 'ListString', 'ArrayString',
     'HeadCell', 'HeadValues', 'ColumnBody', 'TextTable', 'LibDate', 'LibPDF', 'LibImage', 'LibPdfToImage',
-    'LibImageToPdf', 'create_dict_map_from_file', 'create_void_dict_map', 'RotationAngle'
+    'read_pdf', 'read_files_pdf', 'read_image', 'create_dict_map_from_file', 'create_void_dict_map',
+    'create_metadata',
 ]
 

{convert_stream-2.3.5 → convert_stream-2.3.6}/convert_stream/pdf/pdf_document.py

@@ -9,17 +9,19 @@ from io import BytesIO
 from typing import Union
 import pandas as pd
 from soup_files import File, Directory, LibraryDocs, InputFiles, ProgressBarAdapter, JsonConvert
-from convert_stream.mod_types import get_hash_from_bytes, create_metadata, MetaDataFile, MetaDataItem
+from convert_stream.mod_types import (
+    get_hash_from_bytes, create_metadata, MetaDataFile, MetaDataItem
+)
 from convert_stream.mod_types.table_types import (
-    ListItems, ListString, create_dict_map_values, concat_maps, create_void_dict_map, ColumnBody,
+    ListItems, create_dict_map_values, concat_maps, create_void_dict_map, ColumnBody,
     HeadCell, HeadValues, ColumnsTable
 )
 from convert_stream.mod_types.enums import LibPDF
 from convert_stream.mod_types.modules import (
-    DEFAULT_LIB_PDF, ModDocPdf, PdfWriter, PdfReader, PageObject, fitz,
+    DEFAULT_LIB_PDF, ModDocPdf, PdfWriter, PdfReader, fitz, MOD_FITZ, MOD_PYPDF
 )
 from convert_stream.pdf.pdf_page import PageDocumentPdf
-from convert_stream.text import print_line, show_warning, FindText
+from convert_stream.text import show_warning, FindText
 
 
 class SearchableTextPdf(object):
@@ -212,6 +214,8 @@ class ImplementDocumentFitz(ABCDocument):
             pg: fitz.Page = self.mod_doc_pdf.load_page(idx)  # retorna fitz.Page
             if pg is not None:
                 _page_pdf = PageDocumentPdf.create_from_page_fitz(pg, pg.number + 1)
+        _page_pdf.metadata = self.metadata
+        _page_pdf.metadata.md5 = MetaDataItem('nan')
         return _page_pdf
 
     def add_page(self, page: PageDocumentPdf):
@@ -242,13 +246,17 @@ class ImplementDocumentFitz(ABCDocument):
         pages = []
         for num, pg in enumerate(self.mod_doc_pdf):
             page_pdf = PageDocumentPdf.create_from_page_fitz(pg, num + 1)
+            page_pdf.metadata = self.metadata
+            page_pdf.metadata.md5 = MetaDataItem('nan')
             pages.append(page_pdf)
         return pages
 
     @classmethod
     def create_from_bytes(cls, bt: BytesIO) -> ImplementDocumentFitz:
         # Cria documento a partir de BytesIO
-        doc: ModDocPdf = fitz.open(stream=bt.getvalue(), filetype="pdf")
+        if not MOD_FITZ:
+            raise ImportError("Módulo fitz|pymupdf não instalado!\nUse pip install fitz.")
+        doc: ModDocPdf = fitz.Document(stream=bt.getvalue(), filetype="pdf")
         name = get_hash_from_bytes(bt)
         _obj_doc = cls(doc)
         _obj_doc.metadata.name = MetaDataItem(name)
@@ -258,6 +266,8 @@ class ImplementDocumentFitz(ABCDocument):
     @classmethod
     def create_from_file(cls, file: File) -> ImplementDocumentFitz:
         # Cria documento a partir de caminho no disco
+        if not MOD_FITZ:
+            raise ImportError("Módulo fitz|pymupdf não instalado!\nUse pip install fitz.")
         doc = fitz.open(file.path)
         _obj_doc = cls(doc)
         _obj_doc.metadata = create_metadata(file)
@@ -318,7 +328,10 @@ class ImplementDocumentPyPdf(ABCDocument):
             # Acessa a página pela lista self.mod_doc_pdf.pages
             pg = self.mod_doc_pdf.pages[idx]
             # O número da página é idx + 1
-            return PageDocumentPdf.create_from_page_pypdf(pg, idx + 1)
+            page_pdf_doc = PageDocumentPdf.create_from_page_pypdf(pg, idx + 1)
+            page_pdf_doc.metadata = self.metadata
+            page_pdf_doc.metadata.md5 = MetaDataItem('nan')
+            return page_pdf_doc
         return None
 
     def add_page(self, page: PageDocumentPdf):
@@ -342,12 +355,16 @@ class ImplementDocumentPyPdf(ABCDocument):
         pages_pdf: list[PageDocumentPdf] = []
         for num, page in enumerate(self.mod_doc_pdf.pages):
             pg = PageDocumentPdf.create_from_page_pypdf(page, num + 1)
+            pg.metadata = self.metadata
+            pg.metadata.md5 = MetaDataItem('nan')
             pages_pdf.append(pg)
         return pages_pdf
 
     @classmethod
     def create_from_bytes(cls, bt: BytesIO) -> ImplementDocumentPyPdf:
         # Usa PdfReader diretamente de BytesIO
+        if not MOD_PYPDF:
+            raise ImportError("Módulo pypdf não instalado!\nUse pip install pypdf.")
         bt.seek(0)
         reader = PdfReader(bt)
         bt.seek(0)
@@ -366,6 +383,8 @@ class ImplementDocumentPyPdf(ABCDocument):
     @classmethod
     def create_from_file(cls, file: File) -> ImplementDocumentPyPdf:
         # Usa PdfReader diretamente de arquivo
+        if not MOD_PYPDF:
+            raise ImportError("Módulo pypdf não instalado!\nUse pip install pypdf.")
         reader = PdfReader(file.absolute())
         pdf_writer = PdfWriter()
         for p in reader.pages:
@@ -420,8 +439,8 @@ class DocumentPdf(object):
             if lib_pdf == LibPDF.PYPDF:
                 name = get_hash_from_bytes(_tmp_bytes)
                 self.doc_pdf = ImplementDocumentPyPdf(document)
-                self.doc_pdf.metadata['name'] = name
-                self.doc_pdf.metadata['md5'] = name
+                self.doc_pdf.metadata.name = MetaDataItem(name)
+                self.doc_pdf.metadata.md5 = MetaDataItem(name)
                 del _tmp_bytes
             elif lib_pdf == LibPDF.FITZ:
                 self.doc_pdf = ImplementDocumentFitz.create_from_bytes(_tmp_bytes)
@@ -433,8 +452,8 @@ class DocumentPdf(object):
             elif lib_pdf == LibPDF.FITZ:
                 name = get_hash_from_bytes(_tmp_bytes)
                 self.doc_pdf = ImplementDocumentFitz(document)
-                self.doc_pdf.metadata['name'] = name
-                self.doc_pdf.metadata['md5'] = name
+                self.doc_pdf.metadata.name = MetaDataItem(name)
+                self.doc_pdf.metadata.md5 = MetaDataItem(name)
                 del _tmp_bytes
         elif isinstance(document, BytesIO):
             if lib_pdf == LibPDF.PYPDF:
@@ -524,7 +543,7 @@ class DocumentPdf(object):
         else:
             _values = txt_page.split(separator)
 
-        if self.metadata['file_path'] is None:
+        if not self.metadata.file_path.is_empty:
             return create_dict_map_values(
                 _values, page_num=f'{page.number_page}', file_type='.pdf',
             )
@@ -533,8 +552,8 @@ class DocumentPdf(object):
                 _values,
                 page_num=f'{page.number_page}',
                 file_type='.pdf',
-                file_path=self.metadata['file_path'],
-                dir_path=self.metadata['dir_path'],
+                file_path=self.metadata.file_path,
+                dir_path=self.metadata.dir_path,
             )
 
     def to_dict(self, separator: str = '\n') -> dict[str, ColumnBody]:
@@ -577,19 +596,15 @@ class DocumentPdf(object):
             except Exception as e:
                 print(f'{__class__.__name__} {e}')
             else:
-                file_path = self.metadata['file_path']
-                file_name = self.metadata['name']
-                dir_path = self.metadata['dir_path']
-                file_extension = self.metadata['extension']
                 new_line = {
                             ColumnsTable.KEY.value: f'{idx}',
                             ColumnsTable.NUM_PAGE.value: f'{_page.number_page}',
                             ColumnsTable.NUM_LINE.value: f'{idx+1}',
                             ColumnsTable.TEXT.value: math_text,
-                            ColumnsTable.FILE_NAME.value: file_name if file_name is not None else 'nan',
-                            ColumnsTable.FILETYPE.value: file_extension if file_extension is not None else 'nan',
-                            ColumnsTable.FILE_PATH.value: file_path if file_path is not None else 'nan',
-                            ColumnsTable.DIR.value: dir_path if dir_path is not None else 'nan',
+                            ColumnsTable.FILE_NAME.value: self.metadata.name,
+                            ColumnsTable.FILETYPE.value: self.metadata.extension,
+                            ColumnsTable.FILE_PATH.value: self.metadata.file_path,
+                            ColumnsTable.DIR.value: self.metadata.dir_path,
                         }
                 _searchable.add_line(new_line)
                 return _searchable
@@ -623,19 +638,15 @@ class DocumentPdf(object):
             except Exception as e:
                 print(f'{__class__.__name__} {e}')
             else:
-                file_path = self.metadata['file_path']
-                file_name = self.metadata['name']
-                dir_path = self.metadata['dir_path']
-                file_extension = self.metadata['extension']
                 new_line = {
                     ColumnsTable.KEY.value: f'{idx}',
                     ColumnsTable.NUM_PAGE.value: f'{_page.number_page}',
                     ColumnsTable.NUM_LINE.value: f'{idx + 1}',
                     ColumnsTable.TEXT.value: math_text,
-                    ColumnsTable.FILE_NAME.value: file_name if file_name is not None else 'nan',
-                    ColumnsTable.FILETYPE.value: file_extension if file_extension is not None else 'nan',
-                    ColumnsTable.FILE_PATH.value: file_path if file_path is not None else 'nan',
-                    ColumnsTable.DIR.value: dir_path if dir_path is not None else 'nan',
+                    ColumnsTable.FILE_NAME.value: self.metadata.name,
+                    ColumnsTable.FILETYPE.value: self.metadata.extension,
+                    ColumnsTable.FILE_PATH.value: self.metadata.file_path,
+                    ColumnsTable.DIR.value: self.metadata.dir_path,
                 }
                 _searchable.add_line(new_line)
         return _searchable

{convert_stream-2.3.5 → convert_stream-2.3.6}/convert_stream/pdf/pdf_page.py

@@ -14,6 +14,7 @@ from convert_stream.mod_types.table_types import (
 from convert_stream.mod_types.modules import (
     ModPagePdf, PageObject, fitz
 )
+from convert_stream.mod_types import MetaDataItem, MetaDataFile
 from convert_stream.text.find_text import FindText, ArrayString
 
 
@@ -25,6 +26,7 @@ class ABCPagePdf(ABC):
         self.mod_page: ModPagePdf = mod_page
         self.lib_pdf: LibPDF = LibPDF.NOT_IMPLEMENTED
         self.number_page: int = page_number
+        self.metadata: MetaDataFile = MetaDataFile()
 
     @abstractmethod
     def get_width(self) -> float:
@@ -191,6 +193,14 @@ class PageDocumentPdf(object):
         self.implement_page_pdf: ABCPagePdf = page_pdf
         self.lib_pdf: LibPDF = page_pdf.lib_pdf
 
+    @property
+    def metadata(self) -> MetaDataFile:
+        return self.implement_page_pdf.metadata
+
+    @metadata.setter
+    def metadata(self, metadata: MetaDataFile):
+        self.implement_page_pdf.metadata = metadata
+
     def __repr__(self) -> str:
         return self.to_string()
 

{convert_stream-2.3.5 → convert_stream-2.3.6}/convert_stream/pdf/pdf_to_image.py

@@ -5,11 +5,14 @@
 """
 from __future__ import annotations
 from abc import ABC, abstractmethod
+
+from convert_stream import CollectionImages
 from soup_files import Directory, ProgressBarAdapter, CreatePbar
 from convert_stream.mod_types.enums import LibPdfToImage
-from convert_stream.mod_types.modules import DEFAULT_LIB_PDF_TO_IMG, DEFAULT_LIB_IMAGE
+from convert_stream.mod_types.modules import DEFAULT_LIB_PDF_TO_IMG, DEFAULT_LIB_IMAGE, LibPDF
 from convert_stream.image.img_object import ImageObject, LibImage
 from convert_stream.pdf.pdf_document import DocumentPdf
+from convert_stream.pdf.pdf_page import PageDocumentPdf
 
 try:
     import fitz
@@ -134,24 +137,33 @@ class ImplementConvertPdfFitz(ABCConvertPdf):
 
 class ConvertPdfToImages(object):
 
-    def __init__(self, mod_convert_to_image: ABCConvertPdf):
-        self.mod_convert_to_image: ABCConvertPdf = mod_convert_to_image
+    def __init__(self, mod_conv_to_img: ABCConvertPdf | DocumentPdf):
+        if isinstance(mod_conv_to_img, ABCConvertPdf):
+            self.mod_convert_to_image: ABCConvertPdf = mod_conv_to_img
+        elif isinstance(mod_conv_to_img, ImplementConvertPdfFitz):
+            self.mod_convert_to_image: ABCConvertPdf = mod_conv_to_img
+        elif isinstance(mod_conv_to_img, DocumentPdf):
+            self.mod_conv_to_img = ImplementConvertPdfFitz(mod_conv_to_img)
+        else:
+            raise NotImplementedError()
 
     def set_pbar(self, pbar: ProgressBarAdapter):
         self.mod_convert_to_image.set_pbar(pbar)
 
     def to_images(
-                self, *, dpi: int = 300, lib_image: LibImage = DEFAULT_LIB_IMAGE
+                self, *,
+                dpi: int = 300,
+                lib_image: LibImage = DEFAULT_LIB_IMAGE,
             ) -> list[ImageObject]:
         return self.mod_convert_to_image.to_images(dpi=dpi, lib_image=lib_image)
 
     def to_files_image(
-            self,
-            output_dir: Directory, *,
-            replace: bool = False,
-            gaussian_filter: bool = False,
-            dpi: int = 300,
-            lib_image: LibImage = DEFAULT_LIB_IMAGE,
+                self,
+                output_dir: Directory, *,
+                replace: bool = False,
+                gaussian_filter: bool = False,
+                dpi: int = 300,
+                lib_image: LibImage = DEFAULT_LIB_IMAGE,
             ) -> None:
         self.mod_convert_to_image.to_files_image(
             dpi=dpi,
@@ -161,6 +173,44 @@ class ConvertPdfToImages(object):
             gaussian_filter=gaussian_filter
         )
 
+    def inner_images(self) -> CollectionImages:
+        """
+            Extrair imagens embutidas nas páginas PDF.
+        """
+        # doc = Document(stream=page_bytes, filetype="pdf")
+        collection_imgs: CollectionImages = CollectionImages([])
+        tmp_doc: fitz.Document
+        if self.mod_conv_to_img.document.lib_pdf == LibPDF.FITZ:
+            tmp_doc: fitz.Document = self.mod_conv_to_img.document.get_real_document()
+        elif self.mod_conv_to_img.document.lib_pdf == LibPDF.PYPDF:
+            tmp_doc = fitz.Document(
+                stream=self.mod_conv_to_img.document.to_bytes().getvalue(), filetype="pdf"
+            )
+        else:
+            raise NotImplementedError()
+
+        total = len(tmp_doc)
+        page: fitz.Page
+        for num, page in enumerate(tmp_doc):
+            # Extrair imagens embutidas na página
+            images_list: list = page.get_images(full=True)
+            for img in images_list:
+                try:
+                    # Referência do objeto da imagem
+                    xref = img[0]
+                    # Extrair imagem
+                    base_image = tmp_doc.extract_image(xref)
+                    # Bytes da imagem
+                    image_bytes = base_image["image"]
+                    # Extensão (jpg, png, etc.)
+                    image_ext = base_image["ext"]
+                except Exception as e:
+                    print(e)
+                else:
+                    img = ImageObject(image_bytes)
+                    collection_imgs.append(img)
+        return collection_imgs
+
     @classmethod
     def create(cls, doc: DocumentPdf) -> ConvertPdfToImages:
         _mod = ImplementConvertPdfFitz(doc)

{convert_stream-2.3.5 → convert_stream-2.3.6}/convert_stream.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.3.5
+Version: 2.3.6
 Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
 Author: Bruno Chaves
 Requires-Python: >=3.11

{convert_stream-2.3.5 → convert_stream-2.3.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "convert_stream"
-version = "2.3.5"
+version = "2.3.6"
 authors = [
   { name="Bruno Chaves"},
 ]