爬虫--urllib基础

import urllib.request

# urlretrieve(网址，本地文件存储地址)   直接下载网页到本地
urllib.request.urlretrieve('https://baidu.com','C:/Users/Nicht_sehen/Desktop/1.html')

# urlcleanup() 清除缓存
urllib.request.urlcleanup()

# info() 得到当前页面信息
inf =urllib.request.urlopen("https://read.douban.com/provider/all")
print(inf.info())

# getcode() 输出当前状态码 200为正常状态码
print(inf.getcode())

# geturl() 获取当前访问网页url
print(inf.geturl())

# 超时设置
ff = urllib.request.urlopen("https://read.douban.com/provider/all",timeout=1)
try:
    print(ff.read())
except Exception as err:
    print("异常")