Python读取pdf并将pdf转换为图片

您可以使用Python的PyPDF2库来读取PDF文件，并使用Pillow库将PDF页面转换为图像。以下是示例代码：

import PyPDF2
from PIL import Image

# 打开PDF文件
pdf_file = open('example.pdf', 'rb')
pdf_reader = PyPDF2.PdfFileReader(pdf_file)

# 将每个页面转换为图像并保存
for page_num in range(pdf_reader.getNumPages()):
    page = pdf_reader.getPage(page_num)
    # 获取页面大小
    width, height = int(page.mediaBox.getWidth()), int(page.mediaBox.getHeight())
    # 将页面转换为RGB图像
    img = Image.new('RGB', (width, height), 'white')
    img_draw = ImageDraw.Draw(img)
    # 逐个绘制页面对象中的每个对象
    for obj in page:
        if isinstance(obj, PyPDF2.generic.TextStringObject):
            # 绘制文本对象
            font = ImageFont.truetype('arial.ttf', obj['size'])
            text_color = (0, 0, 0) if obj['color'] == [0, 0, 0] else (255, 255, 255)
            img_draw.text((obj['x0'], height - obj['y0']), obj.decode('utf-8'), text_color, font=font)
        elif isinstance(obj, PyPDF2.generic.RectangleObject):
            # 绘制矩形对象
            img_draw.rectangle((obj['x0'], height - obj['y1'], obj['x1'], height - obj['y0']), fill=(255, 0, 0))
    # 保存图像
    img.save(f'page{page_num+1}.png')

# 关闭文件
pdf_file.close()