如何使用python将给定的PDF文件提取为文本和表格，并将数据存储在.csv文件中？

import tabula
import PyPDF2
import csv

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

text_data = ''
for page_num in range(pdf_reader.numPages):
    page = pdf_reader.getPage(page_num)
    text_data += page.extractText()

text_data = text_data.replace('\n', ' ')  # 清除换行符

tables = tabula.read_pdf('your_pdf_file.pdf', pages='all', multiple_tables=True)
table_data = []
for table in tables:
    table_data.append(table.values.tolist())

csv_file = open('output.csv', 'w', newline='', encoding='utf-8')
csv_writer = csv.writer(csv_file)
csv_writer.writerow(['Text', 'Table'])  # 写入表头

# 写入文本数据
csv_writer.writerow([text_data])

# 写入表格数据
for table in table_data:
    csv_writer.writerow([''])
    for row in table:
        csv_writer.writerow(row)

csv_file.close()