1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
|
"""
Compare the speed of downloading URLs sequentially vs. using futures.
"""
import sys
import time
import functools
try:
from urllib.request import urlopen
except ImportError:
from urllib2 import urlopen
try:
from concurrent.futures import ThreadPoolExecutor
except ImportError:
ThreadPoolExecutor = lambda n: None
try:
from concurrent.futures import ProcessPoolExecutor
except ImportError:
ProcessPoolExecutor = lambda n: None
from mpi4py.futures import MPIPoolExecutor, as_completed
URLS = [
'http://www.google.com/',
'http://www.apple.com/',
'http://www.ibm.com',
'http://www.thisurlprobablydoesnotexist.com',
'http://www.slashdot.org/',
'http://www.python.org/',
'http://www.bing.com/',
'http://www.facebook.com/',
'http://www.yahoo.com/',
'http://www.youtube.com/',
'http://www.blogger.com/',
]
def load_url(url, timeout):
return urlopen(url, timeout=timeout).read()
def download_urls_sequential(urls, timeout=60):
url_to_content = {}
for url in urls:
try:
url_to_content[url] = load_url(url, timeout=timeout)
except:
pass
return url_to_content
def download_urls_with_executor(executor, urls, timeout=60):
if executor is None: return {}
try:
url_to_content = {}
future_to_url = {
executor.submit(load_url, url, timeout): url
for url in urls
}
for future in as_completed(future_to_url):
try:
url_to_content[future_to_url[future]] = future.result()
except:
pass
return url_to_content
finally:
executor.shutdown()
def main():
for meth, fn in [('sequential',
functools.partial(download_urls_sequential,
URLS)),
('threads',
functools.partial(download_urls_with_executor,
ThreadPoolExecutor(10), URLS)),
('processes',
functools.partial(download_urls_with_executor,
ProcessPoolExecutor(10), URLS)),
('mpi4py',
functools.partial(download_urls_with_executor,
MPIPoolExecutor(10), URLS))]:
sys.stdout.write('%s: ' % meth.ljust(11))
sys.stdout.flush()
start = time.time()
url_map = fn()
elapsed = time.time() - start
sys.stdout.write('%5.2f seconds (%2d of %d downloaded)\n' %
(elapsed, len(url_map), len(URLS)))
sys.stdout.flush()
if __name__ == '__main__':
main()
|
