Python urllib2 Progress Hook
Why not just read data in chunks and do whatever you want to do in between, e.g. run in a thread, hook into a UI, etc etc
import urllib2
urlfile = urllib2.urlopen("http://www.google.com")
data_list = []
chunk = 4096
while 1:
data = urlfile.read(chunk)
if not data:
print "done."
break
data_list.append(data)
print "Read %s bytes"%len(data)
output:
Read 4096 bytes
Read 3113 bytes
done.
Here's a fully working example that builds on Anurag's approach of chunking in a response. My version allows you to set the the chunk size, and attach an arbitrary reporting function:
import urllib2, sys
def chunk_report(bytes_so_far, chunk_size, total_size):
percent = float(bytes_so_far) / total_size
percent = round(percent*100, 2)
sys.stdout.write("Downloaded %d of %d bytes (%0.2f%%)\r" %
(bytes_so_far, total_size, percent))
if bytes_so_far >= total_size:
sys.stdout.write('\n')
def chunk_read(response, chunk_size=8192, report_hook=None):
total_size = response.info().getheader('Content-Length').strip()
total_size = int(total_size)
bytes_so_far = 0
while 1:
chunk = response.read(chunk_size)
bytes_so_far += len(chunk)
if not chunk:
break
if report_hook:
report_hook(bytes_so_far, chunk_size, total_size)
return bytes_so_far
if __name__ == '__main__':
response = urllib2.urlopen('http://www.ebay.com');
chunk_read(response, report_hook=chunk_report)