python 批量下载文件
之前给大家分享的python 多线程抓取网页,我觉的大家看了以后,应该会对python 抓取网页有个很好的认识,不过这个只能用python 来抓取到网页的源代码,如果你想用做python 下载文件的话,上面的可能就不适合你了,最近我在用python 做文件下载的时候就遇到这个问题了,不过最终得以解决,为了让大家以后碰过这个问题有更好的解决办法,我把代码发出来:
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')
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')
赶快去试试把,可以在本地运行python去下载一些自己想要的pdf文件吧。
文章链接:http://www.cnpythoner.com/post/pythonurldown.html 转载请保留,谢谢!