python爬取豆瓣top250的电影数据并存入excle

import requests
from lxml import etree
import xlwtall_list=[]#传入save函数的结果集
def get_page(url):
res=requests.get(url)
if res.status_code==200:
html=etree.HTML(res.content)
all=html.xpath('//div[@class="article"]/ol/li')#所有的数据都在li标签下,我们一这个为总节点
for detail in all:
title=detail.xpath('.//div[@class="hd"]/a/span[1]/text()')[0]#电影名字
score=detail.xpath('.//span[@class="rating_num"]/text()')[0]#评分
comment_sum=detail.xpath('.//div[@class="star"]/span[4]/text()')[0]#评论人数
quote=detail.xpath('.//p[@class="quote"]/span/text()')#引言 由于有的电影没有引言,不判断会报错
if len(quote)==0:
quote='暂无引言'
else:
quote=quote[0]
list=[]
list.append(title)
list.append(score)
list.append(comment_sum)
list.append(quote)
print(list) #输出结果在下面
all_list.append(list)#将所有的list都添加进一个list
else:
print(res.status_code1)def save(lists):
book=xlwt.Workbook()
sheet=book.add_sheet('douban')
head = ['名字', '评分', '评价人数', '引言']
for h in range(len(head)):
sheet.write(0, h, head[h])#写一个表头
row=1#控制行
for list in lists:
print(list)
col=0#控制列
for s in list:#循环我们的list的值
sheet.write(row,col,s)
col+=1
row+=1
book.save("doubantop250.xls")
if __name__ == '__main__':
#0 25 50 75
for x in range(0,11):
if x==0:
url='https://movie.douban.com/top250?start=0'
get_page(url)
else:
x=x*25
url='https://movie.douban.com/top250?start='+str(x)
get_page(url)
save(all_list)#讲结果集传入save函数