Python PDF转DOCX全攻略：批量脚本、核心库与高效工具推荐

pip install pymupdf python-docx watchdog

import fitz # PyMuPDF
from docx import Document
from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler
import time
import os
class PDFHandler(FileSystemEventHandler):
def on_created(self, event):
if event.src_path.endswith('.pdf'):
self.convert_pdf_to_docx(event.src_path)
def convert_pdf_to_docx(self, pdf_path):
doc = fitz.open(pdf_path)
word_doc = Document()
for page in doc:
text = page.get_text()
word_doc.add_paragraph(text)
output_path = pdf_path.replace('.pdf', '.docx')
word_doc.save(output_path)
print(f"Converted: {output_path}")
if __name__ == "__main__":
path = "watch_folder" # Create this folder
if not os.path.exists(path):
os.makedirs(path)
event_handler = PDFHandler()
observer = Observer()
observer.schedule(event_handler, path, recursive=True)
observer.start()
try:
while True:
time.sleep(1)
except KeyboardInterrupt:
observer.stop()
observer.join()

python pdf_to_docx_automate.py