核心代碼:urllib + BytesIO + PIL
import io
import urllib.request
from PIL import Image
def get_remote_image_info(url, timeout=10):
try:
req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'})
with urllib.request.urlopen(req, timeout=timeout) as resp:
data = resp.read()
# 內存流包裝
stream = io.BytesIO(data)
with Image.open(stream) as im:
# 強制加載以獲取尺寸(某些格式需 load())
im.load()
return {
'format': im.format, # JPEG, PNG, GIF...
'size': im.size, # (width, height)
'mode': im.mode, # RGB, RGBA, P...
'content_length': len(data),
'content_type': resp.headers.get('Content-Type')
}
except Exception as e:
return {'error': str(e)}
# 使用
info = get_remote_image_info('https://jb51.net/images/logo.gif')
print(info)
# {'format': 'GIF', 'size': (200, 60), 'mode': 'P', 'content_length': 4523, ...}
關鍵點
Image.open(BytesIO) 不讀取像素數據,極快
im.load() 觸發解碼,獲取真實尺寸(對於某些格式如 PNG 可能需要)
- 不寫入磁盤,適合爬蟲、驗證、預覽生成
- 大文件注意內存佔用,可改用
urllib.request.urlopen 流式讀取 + ImageFile.Parser 增量解碼
增量解析大圖(不載入完整文件)
from PIL import ImageFile
import urllib.request
def get_size_streaming(url):
parser = ImageFile.Parser()
with urllib.request.urlopen(url) as resp:
while True:
chunk = resp.read(8192)
if not chunk: break
parser.feed(chunk)
if parser.image:
return parser.image.size # 解析到尺寸即停止
return None