当PDF包含图像和表格时，在python中从pdf中提取文本

import PyPDF2
import tabula

def extract_text_from_pdf(pdf_path):
    text = ""
    with open(pdf_path, "rb") as file:
        pdf_reader = PyPDF2.PdfReader(file)
        for page in pdf_reader.pages:
            text += page.extract_text()
    return text

def extract_tables_from_pdf(pdf_path):
    tables = tabula.read_pdf(pdf_path, pages="all")
    return tables

pdf_path = "path/to/your/pdf/file.pdf"

text = extract_text_from_pdf(pdf_path)
print("Extracted Text:")
print(text)

tables = extract_tables_from_pdf(pdf_path)
print("Extracted Tables:")
print(tables)

pip install PyPDF2
pip install tabula-py