python之多线程可加快下载速度

如何同时下载多个链接？我下面的脚本有效，但一次只能下载一个，而且速度非常慢。我不知道如何在我的脚本中加入多线程。

Python 脚本:

from BeautifulSoup import BeautifulSoup 
import lxml.html as html 
import urlparse 
import os, sys 
import urllib2 
import re 
 
print ("downloading and parsing Bibles...") 
root = html.parse(open('links.html')) 
for link in root.findall('//a'): 
  url = link.get('href') 
  name = urlparse.urlparse(url).path.split('/')[-1] 
  dirname = urlparse.urlparse(url).path.split('.')[-1] 
  f = urllib2.urlopen(url) 
  s = f.read() 
  if (os.path.isdir(dirname) == 0):  
    os.mkdir(dirname) 
  soup = BeautifulSoup(s) 
  articleTag = soup.html.body.article 
  converted = str(articleTag) 
  full_path = os.path.join(dirname, name) 
  open(full_path, 'w').write(converted) 
  print(name) 

名为 links.html 的 HTML 文件:

<a href="http://www.youversion.com/bible/gen.1.nmv-fas">http://www.youversion.com/bible/gen.1.nmv-fas</a> 
 
<a href="http://www.youversion.com/bible/gen.2.nmv-fas">http://www.youversion.com/bible/gen.2.nmv-fas</a> 
 
<a href="http://www.youversion.com/bible/gen.3.nmv-fas">http://www.youversion.com/bible/gen.3.nmv-fas</a> 
 
<a href="http://www.youversion.com/bible/gen.4.nmv-fas">http://www.youversion.com/bible/gen.4.nmv-fas</a> 

请您参考如下方法:

我使用 multiprocessing 进行并行处理——出于某种原因，我更喜欢它而不是 threading

from BeautifulSoup import BeautifulSoup 
import lxml.html as html 
import urlparse 
import os, sys 
import urllib2 
import re 
import multiprocessing 
 
 
print ("downloading and parsing Bibles...") 
def download_stuff(link): 
  url = link.get('href') 
  name = urlparse.urlparse(url).path.split('/')[-1] 
  dirname = urlparse.urlparse(url).path.split('.')[-1] 
  f = urllib2.urlopen(url) 
  s = f.read() 
  if (os.path.isdir(dirname) == 0):  
    os.mkdir(dirname) 
  soup = BeautifulSoup(s) 
  articleTag = soup.html.body.article 
  converted = str(articleTag) 
  full_path = os.path.join(dirname, name) 
  open(full_path, 'w').write(converted) 
  print(name) 
 
root = html.parse(open('links.html')) 
links = root.findall('//a') 
pool = multiprocessing.Pool(processes=5) #use 5 processes to download the data 
output = pool.map(download_stuff,links)  #output is a list of [None,None,...] since download_stuff doesn't return anything