#用户代理池的构建
import urllib.request
import re
import random
uapools=[
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 BIDUBrowser/8.7 Safari/537.36",
] //这里可以随意加多个浏览器的。
def ua(uapools):
thisua=random.choice(uapools)
print(thisua)
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="https://www.qiushibaike.com/8hr/page/"+str(i+1)+"/"
data=urllib.request.urlopen(thisurl).read().decode("utf-8","ignore")
pat='<div class="content">.*?<span>(.*?)</span>.*?</div>'
rst=re.compile(pat,re.S).findall(data)
print(rst)
for j in range(0,len(rst)):
print(rst[j])
print("-------")
网友评论