python PyPDF2 인식 안됨

게시물 수정 , 삭제는 로그인 필요

pdf 파일의 정보들을 추출하려 다음과 같은 코드를 짰습니다

# Import necessary libraries

import os

import PyPDF2

from nltk.tokenize import word_tokenize

from nltk.corpus import stopwords

# Define function to extract text from PDF files

def extract_text_from_pdf(pdf_file_path):

    # Open PDF file

    pdf_file = open(pdf_file_path, 'rb')

    # Create PDF reader object

    pdf_reader = PyPDF2.PdfFileReader(pdf_file)

    # Initialize empty string to store text

    text = ''

    # Loop through each page in the PDF file

    for page_num in range(pdf_reader.numPages):

        # Get page object

        page = pdf_reader.getPage(page_num)

        # Extract text from page

        page_text = page.extractText()

        # Add page text to text string

        text += page_text

    # Close PDF file

    pdf_file.close()

    # Return text

    return text

# Define function to preprocess text

def preprocess_text(text):

    # Tokenize text

    tokens = word_tokenize(text)

    # Remove stop words

    stop_words = set(stopwords.words('english'))

    filtered_tokens = [token for token in tokens if token.lower() not in stop_words]

    # Join filtered tokens

    filtered_text = ' '.join(filtered_tokens)

    # Return filtered text

    return filtered_text

# Define main function

def main():

    # Define directory containing PDF files

    directory = 'example'

    # Loop through PDF files in directory

    for filename in os.listdir(directory):

        # Check if file is a PDF file

        if filename.endswith('.pdf'):

            # Get PDF file path

            pdf_file_path = os.path.join(directory, filename)

            # Extract text from PDF file

            text = extract_text_from_pdf(pdf_file_path)

            # Preprocess text

            preprocessed_text = preprocess_text(text)

            # Print preprocessed text

            print(preprocessed_text)

# Call main function

if __name__ == '__main__':

    main()

그런데 다음과 같이 나오며 실행이 되지 않습니다

Traceback (most recent call last): File "/workspace/pdf_extraction.py", line 3, in <module> import PyPDF2 ModuleNotFoundError: No module named 'PyPDF2'

pip install PyPDF2

pip install nltk

pip3 install PyPDF2

pip3 install nltk

모두 해봐도 똑같습니다

windows11입니다 도와주세요 ㅠㅠㅠ