学习进度05

 #返回当前正在爬取的URL地址
print(response.geturl())

#解码
url=r"https://www.baidu.com/s?ie=utf-8&f=3&rsv_bp=1&rsv_idx=1&tn=baidu&wd=ie%E6%80%8E%E4%B9%88%E6%B7%BB%E5%8A%A0%E8%AF%81%E4%B9%A6&rsv_pq=8707adb000078053&rsv_t=abc1PZW1FMJbfZnDjKVl3V7e3PQA9ULJJVfxsjJqh%2FUYqu1v9%2BmbkDSmazc&rqlang=cn&rsv_enter=1&rsv_dl=ih_5&rsv_sug3=1&rsv_sug1=1&rsv_sug7=001&rsv_sug2=1&rsp=5&rsv_sug9=es_1_1&rsv_sug4=2350&rsv_sug=9"
newUrl =urllib.request.unquote(url)
print(newUrl)
#编码
newUrl2=urllib.request.quote(newUrl)
print(newUrl2)

import urllib.request

#在执行过程中会产生一些缓存
response = urllib.request.urlretrieve("http://www.baidu.com",filename=r"E:/3.txt")
#清除缓存
urllib.request.urlcleanup()

import urllib.request
import random
import re
#取消证书验证
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
url="https://book.douban.com/"
#模拟请求头
agentList=[
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0"
    "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)"
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)"
]
agentStr= random.choice(agentList)
req = urllib.request.Request(url)
req.add_header(‘User-Agent‘,agentStr)
#发起请求
response = urllib.request.urlopen(req)

#如果网页长时间未响应，系统判断超时，无法爬取
for i in range(1,100):
    try:
        response = urllib.request.urlopen(req,timeout=0.5)
        print(len(response.read().decode("utf-8")))
    except:
        print("请求超时，继续下一个爬取")