Das deutsche Python-Forum

Code: Alles auswählen

C:\ProgramData\Anaconda3\python.exe C:/Users/Amy_6/Desktop/Uni/Python/Probeprojekt/Datei/Pdftotxt.py
Traceback (most recent call last):
  File "C:/Users/Amy_6/Desktop/Uni/Python/Probeprojekt/Datei/Pdftotxt.py", line 50, in <module>
    convertMultiple(pdfDir, txtDir)
  File "C:/Users/Amy_6/Desktop/Uni/Python/Probeprojekt/Datei/Pdftotxt.py", line 41, in convertMultiple
    text = convert(pdfFilename)  # get string of text content of pdf
  File "C:/Users/Amy_6/Desktop/Uni/Python/Probeprojekt/Datei/Pdftotxt.py", line 25, in convert
    infile = open(fname, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\Amy_6\\Desktop\\Uni\\Python\\Probeprojekt\\Dateifw9.pdf'

Process finished with exit code 1

Code: Alles auswählen

import os
import io

from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage


# converts pdf, returns its text content as a string
def convert(fname, pages=None):
    if not pages:
        pagenums = set()
    else:
        pagenums = set(pages)

    output = io.StringIO()
    manager = PDFResourceManager()
    codec = 'utf-8'
    converter = TextConverter(manager, output, codec=codec, laparams=LAParams())
    interpreter = PDFPageInterpreter(manager, converter)

    #infile = file(fname, 'rb')
    #for page in PDFPage.get_pages(infile, pagenums):
    infile = open(fname, 'rb')
    for page in PDFPage.get_pages(infile, pagenums, caching=caching, check_extractable=True):
        interpreter.process_page(page)
    infile.close()
    converter.close()
    text = output.getvalue()
    output.close
    return text


def convertMultiple(pdfDir, txtDir):
    if pdfDir == "": pdfDir = os.getcwd() + "\\"  # if no pdfDir passed in
    for pdf in os.listdir(pdfDir):  # iterate through pdfs in pdf directory
        fileExtension = pdf.split(".")[-1]
        if fileExtension == "pdf":
            pdfFilename = pdfDir + pdf
            text = convert(pdfFilename)  # get string of text content of pdf
            textFilename = txtDir + pdf + ".txt"
            textFile = open(textFilename, "w")  # make text file
            textFile.write(text)  # write text to text file
        # textFile.close


pdfDir = r"C:\Users\Amy_6\Desktop\Uni\Python\Probeprojekt\Datei\"
txtDir = r"C:\Users\Amy_6\Desktop\Uni\Python\Probeprojekt\Datei\"
convertMultiple(pdfDir, txtDir)

Code: Alles auswählen

C:\ProgramData\Anaconda3\python.exe C:/Users/Amy_6/Desktop/Uni/Python/Probeprojekt/Datei/Pdftotxt.py
  File "C:/Users/Amy_6/Desktop/Uni/Python/Probeprojekt/Datei/Pdftotxt.py", line 48
    pdfDir = r"C:\Users\Amy_6\Desktop\Uni\Python\Probeprojekt\Datei\"
                                                                    ^
SyntaxError: EOL while scanning string literal

Process finished with exit code 1

Code: Alles auswählen

with open(file, 'w') as pdf_file:
    pdf_file.write('Bla')

Code: Alles auswählen

from pathlib import Path
def convert_multiple(input_path, output_path):
    for pdf_filename in Path(input_path).glob("*.pdf"):
        text = convert(pdf_filename)  # get string of text content of pdf
        text_filename = (Path(output_path) / pdf_filename.name).with_suffix(".txt")
        with text_filename.open("w") as output:
            output.write(text)  # write text to text file