#浏览器GET请求,发送的参数有中文时,需要编码再拼接参数发送
from urllib import request
import urllib
url = r"http://www.baidu.com/s?"
#百度搜索 浏览器useragent时 地址栏为:
#https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&rsv_idx=2&tn=02049043_62_pg&wd=%E6%B5%8F%E8%A7%88%E5%99%A8useragent&rsv_spt=1&oq=%25E6%2588%2591%25E8%25A6%2581%25E8%2587%25AA%25E5%25AD%25A6%25E7%25BD%2591&rsv_pq=807c712a00023178&rsv_t=2f3fUS%2Ba5xoKtOS%2FzBZBB8Rz1nKEJLx3Fa1MR%2B1DEw%2Fl0Z1uH95MMgBBId6Us6mLfF6J1pQ&rqlang=cn&rsv_enter=1&rsv_sug3=12&rsv_sug1=12&rsv_sug7=100&bs=%E6%88%91%E8%A6%81%E8%87%AA%E5%AD%A6%E7%BD%91
#浏览器地址转码为%E6%B5%8F%E8%A7%88%E5%99%A8useragen
wd = {"wd":"浏览器useragent"}
#构造url编码
wdd = urllib.parse.urlencode(wd)
print(wdd)
url = url + wdd
req = request.Request(url)
res = request.urlopen(req).read().decode()
print(res)
#通过代理去爬取数据
from urllib import request
import random
#百度 西祠代理
#爬虫在爬数据时,可能回因为同一个ip大量访问被屏蔽,所以需要用代理模拟多台机器
proxyList = [
{"http":"171.41.86.127:9999"},
{"http":"171.41.86.90:9999"},
{"http":"112.87.70.232:9999"}
]
proxyOne = random.choice(proxyList)
print(proxyOne)
#构建代理处理器对象
proxyHandler = request.ProxyHandler(proxyOne)
#创建自定义operer
opener = request.build_opener(proxyHandler)
url = "http://www.baidu.com"
#创建请求对象
req = request.Request(url)
res = opener.open(req)
#opener.open(url) 不创建请求对象,直接请求url也是可以的
print(res.read().decode())