#coding=utf-8
importrequestsimportrefrom bs4 importBeautifulSoup
count=1
#爬取小米应用市场前十页
while count<11:#获取排行榜页面的网页内容
wbdata = requests.get("http://app.mi.com/topList?page=" +str(count)).textprint("开始爬取第" + str(count) + "页")
soup= BeautifulSoup(wbdata,'lxml')
applist= soup.find(class_='applist')for li in applist.find_all(name='li'):#print('输出每个li:', li)
pkg_name = li.a['href']
appname=li.h5.string
categroy=li.p.stringprint(appname+'|'+pkg_name+'|'+categroy)
count+= 1