def splitPdfOnePageEach(file, wayToSaveFiles, sequential=0):
try:
nameFile = funcoesUteis.getOnlyNameFile(os.path.basename(file))
nameDirectoryToSave = f"{nameFile}-{sequential}"
wayBaseToSaveFile = os.path.join(wayToSaveFiles, 'pdfs',
nameDirectoryToSave)
os.makedirs(wayBaseToSaveFile)
with open(file, 'rb') as filePdf:
pdfReader = PyPDF2.PdfFileReader(filePdf)
countPages = pdfReader.getNumPages()
for numberPage in range(countPages):
pageContent = pdfReader.getPage(numberPage)
pdfWriter = PyPDF2.PdfFileWriter()
pdfWriter.addPage(pageContent)
with open(f'{wayBaseToSaveFile}\\{numberPage+1}.pdf',
'wb') as newPdfPerPage:
pdfWriter.write(newPdfPerPage)
except Exception as e:
pass #print(f'\t - Não foi possível processar o arquivo {file}, provavelmente o PDF está inválido e com erro no momento de abrir!')
def ImageToText(file, wayToSaveFile):
nameFile = funcoesUteis.getOnlyNameFile(os.path.basename(file))
wayToSave = f"{wayToSaveFile}/{nameFile}.txt"
wayToSave = open(wayToSave, "w", encoding='utf-8')
content = ocr.image_to_string(Image.open(file), lang='por')
wayToSave.write(content)
wayToSave.close()
def PDFImgToText(file, wayToSaveFile):
nameFile = funcoesUteis.getOnlyNameFile(os.path.basename(file))
wayToSave = f"{wayToSaveFile}/{nameFile}.jpg"
command = f'magick -density 300 "{file}" "{wayToSave}"'
os.system(command)
ImageToText(wayToSave, wayToSaveFile)
def PDFToText(file, wayToSaveFile, mode="simple"):
nameFile = funcoesUteis.getOnlyNameFile(os.path.basename(file))
wayToSave = f"{wayToSaveFile}/{nameFile}.txt"
try:
textPdf = ""
with open(file, 'rb') as filePdf:
documents = slate.PDF(filePdf)
for document in documents:
textPdf += document
if funcoesUteis.treatTextField(textPdf) == "":
PDFImgToText(file, wayToSaveFile)
else:
command = f'{fileDir}/exe/pdftotext64.exe -{mode} "{file}" "{wayToSave}"'
os.system(command)
except Exception as ex:
print(f"Nao foi possivel transformar o arquivo \"{file}\". O erro é: {str(ex)}")