Created
July 3, 2013 15:42
-
-
Save ivanjr0/5919547 to your computer and use it in GitHub Desktop.
CurlMulti based downloader
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
# -*- coding: utf-8 -*- | |
# NOQA # Baseado em http://pycurl.cvs.sourceforge.net/viewvc/pycurl/pycurl/examples/retriever-multi.py?view=markup | |
try: | |
import signal | |
from signal import SIGPIPE, SIG_IGN | |
signal.signal(signal.SIGPIPE, signal.SIG_IGN) | |
except ImportError: | |
pass | |
import os | |
from urlparse import urlparse | |
import pycurl | |
def download(root_path, conns, urls): | |
errors = [] | |
m = pycurl.CurlMulti() | |
m.handles = [] | |
for _ in range(conns): | |
c = pycurl.Curl() | |
c.fp = None | |
c.setopt(pycurl.FOLLOWLOCATION, 0) | |
c.setopt(pycurl.FAILONERROR, 1) | |
c.setopt(pycurl.NOSIGNAL, 1) | |
c.setopt(pycurl.CONNECTTIMEOUT, 30) | |
c.setopt(pycurl.TIMEOUT, 300) | |
m.handles.append(c) | |
queue = [] | |
for url in urls: | |
url_path = urlparse(url).path | |
filename = url_path.rsplit('/', 1)[-1] | |
path = os.path.join(root_path, os.path.dirname(url_path)[1:]) | |
try: | |
os.makedirs(path) | |
except OSError, e: | |
if not 'File exists' in str(e): | |
raise e | |
queue.append((url, os.path.join(path, filename))) | |
num_processed = 0 | |
num_total = len(queue) | |
freelist = m.handles[:] | |
while num_processed < num_total: | |
while queue and freelist: | |
url, filename = queue.pop(0) | |
c = freelist.pop() | |
c.fp = open(filename, 'wb') | |
c.setopt(pycurl.URL, url) | |
c.setopt(pycurl.WRITEDATA, c.fp) | |
m.add_handle(c) | |
c.filename = filename | |
c.url = url | |
while 1: | |
ret, num_handles = m.perform() | |
if ret != pycurl.E_CALL_MULTI_PERFORM: | |
break | |
while 1: | |
num_q, ok_list, err_list = m.info_read() | |
for c in ok_list: | |
c.fp.close() | |
c.fp = None | |
m.remove_handle(c) | |
freelist.append(c) | |
for c, errno, errmsg in err_list: | |
errors.append(c.url) | |
c.fp.close() | |
c.fp = None | |
m.remove_handle(c) | |
freelist.append(c) | |
num_processed = num_processed + len(ok_list) + len(err_list) | |
if num_q == 0: | |
break | |
m.select(1.0) | |
for c in m.handles: | |
if c.fp is not None: | |
c.fp.close() | |
c.fp = None | |
c.close() | |
m.close() | |
return errors |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment