Python实现批量下载文件

Python实现批量下载文件

#!/usr/bin/env python
# -*- coding:utf-8 -*-

from gevent import monkey
monkey.patch_all()
from gevent.pool import Pool
import requests
import sys
import os

def download(url):
 chrome = 'Mozilla/5.0 (X11; Linux i86_64) AppleWebKit/537.36 ' + 
 '(KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36'
 headers = {'User-Agent': chrome}
 filename = url.split('/')[-1].strip()
 r = requests.get(url.strip(), headers=headers, stream=True)
 with open(filename, 'wb') as f:
 for chunk in r.iter_content(chunk_size=1024):
 if chunk:
f.write(chunk)
f.flush()
 print filename,"is ok"

def removeLine(key, filename):
 os.system('sed -i /%s/d %s' % (key, filename))

if __name__ =="__main__":
 if len(sys.argv) == 2:
 filename = sys.argv[1]
 f = open(filename,"r")
 p = Pool(4)
 for line in f.readlines():
 if line:
 p.spawn(download, line.strip())
 key = line.split('/')[-1].strip()
 removeLine(key, filename)
f.close()
p.join()
else:
 print 'Usage: python %s urls.txt' % sys.argv[0]

其他网友的方法：

from os.path import basename
from urlparse import urlsplit
def url2name(url):
  return basename(urlsplit(url)[2])

def download(url, localFileName = None):
  localName = url2name(url)
  req = urllib2.Request(url)
  r = urllib2.urlopen(req)
  if r.info().has_key('Content-Disposition'):
    # If the response has Content-Disposition, we take file name from it
    localName = r.info()['Content-Disposition'].split('filename=')[1]
    if localName[0] == '"' or localName[0] == "'":
      localName = localName[1:-1]
  elif r.url != url:
    # if we were redirected, the real file name we take from the final URL
    localName = url2name(r.url)
  if localFileName:
    # we can force to save the file as specified name
    localName = localFileName
  f = open(localName, 'wb')
  f.write(r.read())
  f.close()

download(r'你要下载的python文件的url地址')

以上便是本文给大家分享的全部内容了，小伙伴们可以测试下哪种方法效率更高呢。