使用Python从将文本编码为图像的PDF中抓取文本

import PyPDF2
from PIL import Image
import pytesseract

pdf_file = open('your_pdf_file.pdf', 'rb')
pdf_reader = PyPDF2.PdfFileReader(pdf_file)

text_pages = []
for page_num in range(pdf_reader.numPages):
    page = pdf_reader.getPage(page_num)
    text_pages.append(page.extract_text())

image_pages = []
for text_page in text_pages:
    image = Image.new('RGB', (800, 600), (255, 255, 255))
    image_draw = ImageDraw.Draw(image)
    image_draw.text((10, 10), text_page, fill=(0, 0, 0))
    image_pages.append(image)

extracted_text = []
for image_page in image_pages:
    text = pytesseract.image_to_string(image_page)
    extracted_text.append(text)

with open('extracted_text.txt', 'w') as file:
    for text in extracted_text:
        file.write(text + '\n')