Python中PDF转Word的多种实现方法

pip install pdf2docx

from pdf2docx import Converter

def convert_pdf_to_word(pdf_file_path, word_file_path):
    cv = Converter(pdf_file_path)
    cv.convert(word_file_path, start=0, end=None)
    cv.close()

# 使用示例
pdf_file_path = 'sample.pdf'
word_file_path = 'output.docx'
convert_pdf_to_word(pdf_file_path, word_file_path)

from PyPDF2 import PdfFileReader
from docx import Document

def convert_pdf_to_word_pypdf2_python_docx(pdf_file_path, word_file_path):
    pdf_reader = PdfFileReader(open(pdf_file_path, 'rb'))
    doc = Document()
    for page_num in range(pdf_reader.numPages):
        page = pdf_reader.getPage(page_num)
        text = page.extractText()
        doc.add_paragraph(text)
    doc.save(word_file_path)

# 使用示例
pdf_file_path = 'sample.pdf'
word_file_path = 'output.docx'
convert_pdf_to_word_pypdf2_python_docx(pdf_file_path, word_file_path)

from pdfminer.high_level import extract_text
from docx import Document

def pdf_to_word_with_pdfminer(pdf_file_path, word_file_path):
    text = extract_text(pdf_file_path)
    doc = Document()
    doc.add_paragraph(text)
    doc.save(word_file_path)

# 使用示例
pdf_file_path = 'sample.pdf'
word_file_path = 'output.docx'
pdf_to_word_with_pdfminer(pdf_file_path, word_file_path)

import fitz  # PyMuPDF

def pdf_to_word_pymupdf(pdf_file_path, word_file_path):
    doc = fitz.open(pdf_file_path)
    text = ''
    for page_num in range(doc.page_count):
        page = doc[page_num]
        text += page.get_text()
    with open(word_file_path, 'w', encoding='utf-8') as f:
        f.write(text)

# 使用示例
pdf_file_path = 'sample.pdf'
word_file_path = 'output.docx'
pdf_to_word_pymupdf(pdf_file_path, word_file_path)