urllib基础练习1

#

第四章练习

import urllib.request

file = urllib.request.urlopen(“http://www.baidu.com“)
data = file.read()
dataline = file.readlines()

fhandle = open(“C:/Users/yehuo/PycharmProjects/pachong1/1.html”,”wb”)
fhandle.write(data)
fhandle.close()
filename = urllib.request.urlretrieve(“http://www.baidu.com“,filename=”C:/Users/yehuo/PycharmProjects/pachong1/2.html”)
urllib.request.urlcleanup()
print(file.getcode())
print(file.geturl())

编码操作

print (urllib.request.quote(“http://www.sina.com.cn“))#汉字变代码用quote 反向unquote

加报头操作

url = ‘eee.eee’
headers = (“xxx”,”ppp”)
openner = urllib.request.build_opener()
openner.addheaders = [headers]
data = openner.open(url).read()

req = urllib.request.Request(url)
req.add_header(headers)

传递Post

url=’xxxx’
import urllib.parse
postdata = urllib.parse.urlencode({
“xxx”:”xxx”,
“sss”:”xx”
}).encode(“utf-8”)
req = urllib.request.Request(url,postdata)
req.add_header(“xxxx”)
data = urllib.request.urlopen(req).read()
写文件保存操作

urllib.request.urlopen(timeout=)设置超时