A10.用户代理池.txt
UP 返回
用户代理池即将多个用户代理组建成一个池子,随后随机调用
#使用代理池爬取糗事百科
import urllib.request,re
#随机
import random
uapools=[
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/18.17763",
"Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50",
]
def ua(uapools):
thisua=random.choice(uapools)
headers=("User-Agent",thisua)
opener=urllib.request.build_opener()
opener.addheaders=[headers]
#安装为全局
urllib.request.install_opener(opener)
for i in range(0,35):
ua(uapools)
thisurl="http://www.qiushibaike.com/8hr/page/"+str(i+1)+"/?s=4948859"
urllib.request.urlopen(thisurl).read().decode("utf-8","ignore")
pat='<div class="content">.*?<span>(.*?)</span>.*?</div>'
rst=re.compile(pat,re.S).findall(data)
for j in range(0,len(rst)):
print(rst[j])
print("------")
DOWN 返回