Python通过PyMuPDF高效处理PDF文档的操作方法

pip install PyMuPDF

import fitz  # PyMuPDF 的导入名称

# 打开 PDF
doc = fitz.open("document.pdf")

# 提取第一页文本
page = doc.load_page(0)
text = page.get_text()
print(text)

# 按区块提取（保留位置信息）
blocks = page.get_text("blocks")
for block in blocks:
    print(block[4])  # 文本内容（block格式: (x0, y0, x1, y1, text)）

# 渲染为 PNG
pix = page.get_pixmap(matrix=fitz.Matrix(2, 2))  # 缩放2倍
pix.save("page0.png")

# 指定 DPI (300 dpi)
dpi = 300
mat = fitz.Matrix(dpi / 72, dpi / 72)  # 72是默认DPI
pix = page.get_pixmap(matrix=mat)

# 添加文本到新页面
new_page = doc.new_page(width=400, height=200)
new_page.insert_text((100, 50), "Hello PyMuPDF!", fontsize=24)

# 绘制红色矩形
rect = fitz.Rect(50, 70, 150, 120)
new_page.draw_rect(rect, color=(1, 0, 0), width=2)

# 保存修改
doc.save("modified.pdf")

doc1 = fitz.open("doc1.pdf")
doc2 = fitz.open("doc2.pdf")

# 将 doc2 插入到 doc1 末尾
doc1.insert_pdf(doc2)
doc1.save("merged.pdf")

for img_index, img in enumerate(page.get_images(full=True)):
    xref = img[0]  # 图像引用 ID
    base_image = doc.extract_image(xref)
    image_bytes = base_image["image"]
    with open(f"image_{img_index}.png", "wb") as f:
        f.write(image_bytes)

# 搜索所有 "important" 出现的位置
areas = page.search_for("important")
for rect in areas:
    page.add_highlight_annot(rect)  # 添加高亮注释