from six.moves import urllib
import os
import sys
import tensorflow as tf
import tarfile
FLAGS = tf.app.flags.FLAGS#提取系统参数作用的变量
tf.app.flags.DEFINE_string('dir','D:/download_html','directory of html')#将下载目录保存到变量dir中,通过FLAGS.dir提取
directory = FLAGS.dir#从FLAGS中提取dir变量
url = 'http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz'
filename = url.split('/')[-1]#-1表示分割后的最后一个元素
filepath = os.path.join(directory,filename)
if not os.path.exists(directory):
 os.makedirs(directory)
if not os.path.exists(filepath):
 def _recall_func(num,block_size,total_size):
 sys.stdout.write('\r downloading %s %.1f%%' % (filename,float(num*block_size)/float(total_size)*100.0))
 sys.stdout.flush()
 urllib.request.urlretrieve(url,filepath,_recall_func)
 print()
 file_info = os.stat(filepath)
 print('Successfully download',filename,file_info.st_size,'bytes')
tar = tarfile.open(filepath,'r:gz')#指定解压路径和解压方式为解压gzip
tar.extractall(directory)#全部解压

from six.moves import urllib
import os
import sys
import tensorflow as tf
FLAGS = tf.app.flags.FLAGS#提取系统参数作用的变量
tf.app.flags.DEFINE_string('dir','D:/download_html','directory of html')#将下载目录保存到变量dir中,通过FLAGS.dir提取
directory = FLAGS.dir#从FLAGS中提取dir变量
url = 'http://www.douyu.com/'
filename = 'douyu.html'#保存成你想要的名字，这里保存成douyu.html
filepath = os.path.join(directory,filename)
if not os.path.exists(directory):
 os.makedirs(directory)
if not os.path.exists(filepath):
 def _recall_func(num,block_size,total_size):
 sys.stdout.write('\r downloading %s %.1f%%' % (filename,float(num*block_size)/float(total_size)*100.0))
 sys.stdout.flush()
 urllib.request.urlretrieve(url,filepath,_recall_func)
 print()
 file_info = os.stat(filepath)#获取文件信息
 print('Successfully download',filename,file_info.st_size,'bytes')#.st_size文件的大小，以字节为单位