python 下载网页并保存 脚本

import sys, os, urllib.request, urllib.parse showlines = 6 try: servername, filename = sys.argv[1:3] # first 2 cmdline args? except: servername, filename = 'learning-python.com', '/index.html'

remoteaddr = 'http://%s%s' % (servername, filename) # any address on the Net if len(sys.argv) == 4: # get result filename localname = sys.argv[3] else: (scheme, server, path, parms, query, frag) = urllib.parse.urlparse(remoteaddr) localname = os.path.split(path)[1]

print(remoteaddr, localname) urllib.request.urlretrieve(remoteaddr, localname) # can be file or script remotedata = open(localname, 'rb').readlines() # saved to local file for line in remotedata[:showlines]: print(line) # file is bytes/binary

只浏览不保存

import sys from urllib.request import urlopen showlines = 6 try: servername, filename = sys.argv[1:] # cmdline args? except: servername, filename = 'learning-python.com', '/index.html'

remoteaddr = 'http://%s%s' % (servername, filename) # can name a CGI script too print(remoteaddr) remotefile = urlopen(remoteaddr) # returns input file object remotedata = remotefile.readlines() # read data directly here remotefile.close() for line in remotedata[:showlines]: print(line) # bytes with embedded \n