Created
May 1, 2011 22:05
-
-
Save mpapi/950918 to your computer and use it in GitHub Desktop.
cached: Python contextmanager for cached URL fetches
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from contextlib import closing, contextmanager | |
from urllib2 import urlopen | |
import hashlib | |
import os | |
import time | |
@contextmanager | |
def cached(url, expires=0, root='/tmp'): | |
''' | |
Returns the contents of the URL through a file-based cache. If "expires" is | |
greater than zero, the contents will be re-fetched from the URL after that | |
many seconds. | |
''' | |
checksum = hashlib.md5(url).hexdigest() | |
cache_file = os.path.join(root, checksum) | |
if os.path.exists(cache_file) and time.time() - os.path.getctime(cache_file) < expires: | |
with open(cache_file, 'r') as cache_fh: | |
yield cache_fh.read() | |
else: | |
with closing(urlopen(url)) as url_fh: | |
data = url_fh.read() | |
with open(cache_file, 'w') as cache_fh: | |
cache_fh.write(data) | |
yield data |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment