pdf转图片(png,jpg)的python脚本
PDF转图片工具
1.安装库 pip install pymupdf
2.如果需要pdf转jpg的更改DEFAULT_FORMAT即可
3.一定注意要将脚本与待转化的.pdf文件放在同一个目录
4.运行脚本,将脚本所在目录所有.pdf文件转换成图片,并存放在对应名称的文件夹中
import os
import sys
import fitz
import time
from typing import List
# 配置项
DEFAULT_ZOOM = 2.0
SUPPORTED_FORMATS = ['png', 'jpg']
DEFAULT_FORMAT = 'png'
JPEG_QUALITY = 95
def get_script_dir() -> str:
"""获取脚本所在的绝对目录路径"""
return os.path.dirname(os.path.abspath(__file__))
def get_pdf_files() -> List[str]:
"""获取脚本目录下的PDF文件(返回完整路径)"""
script_dir = get_script_dir()
pdf_files = []
try:
for filename in os.listdir(script_dir):
if filename.lower().endswith('.pdf'):
full_path = os.path.join(script_dir, filename)
if os.path.isfile(full_path):
pdf_files.append(full_path)
return pdf_files
except Exception as e:
print(f"[ERROR] 扫描PDF失败: {str(e)}")
return []
def convert_pdf_to_images(
pdf_path: str,
output_format: str = DEFAULT_FORMAT,
zoom: float = DEFAULT_ZOOM
) -> bool:
"""转换PDF为图片(输出到脚本所在目录)"""
try:
script_dir = get_script_dir()
pdf_name = os.path.splitext(os.path.basename(pdf_path))[0]
# 在脚本目录下创建输出文件夹
output_folder = os.path.join(script_dir, f"{pdf_name}_images")
os.makedirs(output_folder, exist_ok=True)
doc = fitz.open(pdf_path)
total_pages = len(doc)
print(f"\n转换中: {os.path.basename(pdf_path)} (共{total_pages}页)")
print(f"输出到: {output_folder}")
for pg in range(total_pages):
page = doc[pg]
pix = page.get_pixmap(matrix=fitz.Matrix(zoom, zoom))
output_path = os.path.join(
output_folder,
f"{pdf_name}_page{pg+1:03d}.{output_format}"
)
pix.save(output_path, jpg_quality=JPEG_QUALITY if output_format == 'jpg' else None)
print(f" ✓ 第 {pg+1}/{total_pages} 页")
doc.close()
print(f"✔ 转换完成!")
return True
except Exception as e:
print(f"✕ 转换失败: {str(e)}")
return False
if __name__ == '__main__':
print("="*50)
print("PDF转图片工具(输出到脚本目录版)")
print("="*50)
pdf_files = get_pdf_files()
if not pdf_files:
print("\n! 未找到PDF文件!请确保:")
print(" 1. PDF文件与脚本在同一目录")
print(" 2. 文件扩展名是.pdf")
input("\n按Enter键退出...")
sys.exit()
print("\n找到以下PDF文件:")
for i, pdf in enumerate(pdf_files, 1):
print(f" {i}. {os.path.basename(pdf)}")
input("\n按Enter键开始转换...")
for pdf in pdf_files:
convert_pdf_to_images(pdf)
input("\n全部完成!按Enter键退出...")