Python 技巧分享：NEF文件的元数据提取

import requests
from bs4 import BeautifulSoup
from PIL import Image
import piexif
from io import BytesIO

# 爬虫代理加强版配置（亿牛云爬虫代理加强版）
proxy_host = "www.proxy.cn"
proxy_port = "9020"
proxy_user = "your_proxy_user"
proxy_pass = "your_proxy_pass"

proxy_meta = f"http://{proxy_user}:{proxy_pass}@{proxy_host}:{proxy_port}"
proxies = {
    "http": proxy_meta,
    "https": proxy_meta,
}

# 爬取网页并下载 NEF 文件
def download_nef_files(url):
    response = requests.get(url, proxies=proxies)
    if response.status_code == 200:
        soup = BeautifulSoup(response.content, 'html.parser')
        nef_links = soup.find_all('a', href=lambda href: href and href.endswith('.nef'))
        nef_files = []
        for link in nef_links:
            file_url = link['href']
            nef_response = requests.get(file_url, proxies=proxies)
            if nef_response.status_code == 200:
                nef_files.append(BytesIO(nef_response.content))
        return nef_files
    else:
        print("Failed to retrieve the webpage.")
        return []

# 提取 NEF 文件的元数据并打印各项参数
def extract_and_print_metadata(nef_file):
    try:
        image = Image.open(nef_file)
        exif_data = piexif.load(image.info['exif'])
        for ifd in exif_data:
            print(f"--- {ifd} ---")
            for tag in exif_data[ifd]:
                tag_name = piexif.TAGS[ifd][tag]["name"]
                tag_value = exif_data[ifd][tag]
                print(f"{tag_name}: {tag_value}")
    except Exception as e:
        print(f"Error extracting metadata: {e}")

# 示例 URL（需要替换为实际的含有 NEF 文件链接的网页）
url = "https://example.com/nef_files"

# 下载 NEF 文件并提取元数据
nef_files = download_nef_files(url)
for nef_file in nef_files:
    extract_and_print_metadata(nef_file)