import PyPDF2
from docx import Document
def convert_pdf_to_word(pdf_path, doc_path):
pdf_file = open(pdf_path, 'rb')
pdf_reader = PyPDF2.PdfReader(pdf_file)
doc = Document()
for page_num in range(len(pdf_reader.pages)):
page = pdf_reader.pages[page_num]
text = page.extract_text()
paragraph = doc.add_paragraph()
paragraph.add_run(text)
doc.save(doc_path)
pdf_file.close()
pdf_path = 'path.pdf'
doc_path = 'output.docx'
# Call the conversion function
convert_pdf_to_word(pdf_path, doc_path)
PDF转word---python
最新推荐文章于 2024-09-12 19:48:43 发布