urllib库使用

 

import urllib.request
import urllib.parse

# url='http://www.baidu.com/'
# r=urllib.request.urlopen(url)
# print(r.geturl())

# url='http://tieba.baidu.com/hottopic/browse/hottopic?'
# dic={'topic_id':'281490','topic_name':'打工人','red_tag':'w3489610227'}
# r=urllib.parse.urlencode(dic)
# b=url+r
# print(b)


# url='xxxx'
# handler=urllib.request.ProxyHandler({
#     'http':'127.0.0.1:4561'
#     'https':'127.0.0.1:4561'

# })
# opener=urllib.request.build_opener(handler)
# r=opener.open(url)

url='http://www.baidu.com/'
r=urllib.parse.urlparse(url)
print(r)

　　

import urllib.request
import http.cookiejar


# url='https://t8.baidu.com/it/u=1484500186,1503043093&fm=79&app=86&size=h300&n=0&g=4n&f=jpeg?sec=1603459244&t=4ea8b8bf44b0e438af3306f2320bf49a'
# filename='c:\\1.jpg'
# def call(a,b,c):

#     d=100*a*b/c
#     if d>100:
#         d=100
#     print('已经下载了: %.2f%%'%d)

# r=urllib.request.urlretrieve(url,filename,call)

# url='http://www.baidu.com/'
# data={
#     'name':'alex',
#     'age':'18'
# }
# headers={
#     'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:81.0) Gecko/20100101 Firefox/81.0',
    
#     'Accept-Language':'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
#     'Connection':'keep-alive'

    
# }
# r=urllib.request.Request(url,data=data,headers=headers)
# print(r)

url='http://www.baidu.com/'
cooike= http.cookiejar.CookieJar()
handler=urllib.request.HTTPCookieProcessor(cooike)
opener=urllib.request.build_opener(handler)
r=opener.open(url)
for item in cooike:
    print("cooike name="+item.name+"cooike value="+item.value)

　　

import urllib.request
import socket
urllib.error

url='http://www.baidu.com/'
try:
    r=urllib.request.urlopen(url=url,timeout=0.0001)
except urllib.error.URLError as e:
    if isinstance(e.reason,socket.timeout):
        print("time out")

 

 如果使用 url=url就不需要一个空格了