使用线程池
import concurrent.futures
import urllib.request
URLS = [
'http://www.baidu.com/',
'http://www.qq.com/',
'http://durongjie.com/'
]
def load_url(url, timeout):
with urllib.request.urlopen(url, timeout=timeout) as conn:
return conn.read()
with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
future_to_url = {executor.submit(load_url, url, 60): url for url in URLS}
# executor.shutdown(wait=True) # 等待所有任务完成
# 每个任务执行后调用函数,阻塞的是子任务,不是阻塞等待所有完成。
for future in concurrent.futures.as_completed(future_to_url):
url = future_to_url[future]
try:
data = future.result()
except Exception as exc:
print('%s 产生异常 %s' % (url, exc))
else:
print('%s 页面大小为 %d bytes' % (url, len(data)))