python从pdf中提取图片时出现错误

Question

报错:AttributeError: 'Pixmap' object has no attribute 'writePNG'. Did you mean: '_writeIMG'?

import fitz
import re

import os

file_path = r'img.pdf'  
dir_path = r'pdf' 


def pdf2image1(path, pic_path):
    checkIM = r"/Subtype(?= */Image)"
    pdf = fitz.open(path)
    lenXREF = pdf.xref_length()
    count = 1
    for i in range(1, lenXREF):
        text = pdf.xref_object(i)
        isImage = re.search(checkIM, text)
        if not isImage:
            continue
        pix = fitz.Pixmap(pdf, i)
        new_name = f"img_{count}.png"
        pix.writePNG(os.path.join(pic_path, new_name))
        count += 1
        pix = None


pdf2image1(file_path, dir_path)

Answer 1

望采纳

由于pdf文件的结构比较复杂，我们需要使用一些第三方库来帮助我们提取图片。下面是一个示例代码，使用了PyMuPDF库来读取pdf文件并提取图片：

import fitz

# 打开pdf文件
pdf_file = fitz.open('example.pdf')

# 遍历pdf中的所有页面
for page in pdf_file:
  # 查找页面中的图片
  for image in page.get_image_list():
    # 提取图片并保存
    img_bytes = image[0]
    img_ext = image[1]
    with open(f"image.{img_ext}", "wb") as f:
      f.write(img_bytes)