Created
October 16, 2012 13:44
-
-
Save abhinavgupta/3899375 to your computer and use it in GitHub Desktop.
Simple script for faster fetching with urllib2 with exception handling
This file contains 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
import threading, urllib2 | |
import Queue | |
def read_url(url, queue): | |
try: | |
data = urllib2.urlopen(url).read() | |
except urllib2.HTTPError, e: | |
checksLogger.error('HTTPError = ' + str(e.code)) | |
except urllib2.URLError, e: | |
checksLogger.error('URLError = ' + str(e.reason)) | |
except httplib.HTTPException, e: | |
checksLogger.error('HTTPException') | |
except Exception: | |
import traceback | |
checksLogger.error('generic exception: ' + traceback.format_exc()) | |
print('Fetched %s from %s' % (len(data), url)) | |
queue.put(data) | |
def fetch_parallel(list_of_urls): | |
result = Queue.Queue() | |
threads = [threading.Thread(target=read_url, args = (url,result)) for url in list_of_urls] | |
for t in threads: | |
t.start() | |
for t in threads: | |
t.join() | |
return result |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment