用python爬取网站数据期末作业_Python作业2:使用LXML方法爬取数据

import requests

from lxml import etree

import xlwt

all_info_list=[]

def get_info(url):

res = requests.get(url)

html = etree.HTML(res.text)

infos = html.xpath('//ul[@class="rank_list"]/li')

for infoin infos:

rank1 = info.xpath('em ')[0]

rank = rank1.xpath('string(.)').strip()

name = info.xpath('a/text()')[0]

size = info.xpath('i/text()')[0]

popularity = info.xpath('span/text()')[0]

# print(game,size,popularity)

info_list = [rank,name,size,popularity]

all_info_list.append(info_list)

if __name__ =='__main__':

book = xlwt.Workbook(encoding='utf-8')

sheet = book.add_sheet('Sheet1')

header = ['rank','name','size','popularity']

for t  in range(len(header)):

sheet.write(0, t, header[t])

urls = ['http://www.doyo.cn/rank/shouji/100/page/{}'.format(str(i))for i  in range(1,4)]

for url in urls:

get_info(url)

i =1

for list in all_info_list:

j =0

for datain list:

sheet.write(i, j, data)

j +=1

i +=1

book.save('C:/Users/Xumeiling/Desktop/手机游戏排行榜.xls')