豆瓣电影top250

import re
from bs4 import BeautifulSoup
import urllib.request
import xlwt

def main():
    baseurl = "https://movie.douban.com/top250?start="
    datalist = GetData(baseurl)
    datalist = GetData(baseurl)
    # #获取数据
    # #解析数据
    # #存储数据
    savepath = './豆瓣爬取demo.xls'
    saveData(savepath,datalist)
def GetData(baseurl):
    datalist = []
    for i in range(0,10):
        url = baseurl+str(i*25)
        html = askURL(url)
        soup = BeautifulSoup(html,'html.parser')
        for item in soup.find_all('div',class_="item"):
            item = str(item)
            data = []
            findlink = re.compile(r'<a href="(.*?)">')
            link = re.findall(findlink,item)[0]
            data.append(link)

            findimgSrc = re.compile('<img.*src="(.*?)"')
            imgSrc = re.findall(findimgSrc,item)[0]
            data.append(imgSrc)

            findtitle = re.compile('<span class="title">(.*?)</span>')
            title = re.findall(findtitle,item)
            if (len(title)==2):
                ctitle = title[0]
                data.append(ctitle)
                otitle = title[1]
                data.append(otitle)
            else:
                ctitle =title[0]
                data.append(ctitle)
                data.append('')

            findrating = re.compile('<span class="rating_num" property="v:average">(.*?)</span>')
            rating = re.findall(findrating,item)[0]
            data.append(rating)

            findJadge =re.compile('<span>(.*?)人评价</span>')
            Jadge = re.findall(findJadge,item)[0]
            data.append(Jadge)

            findIng = re.compile('<span class="inq">(.*?)</span>')
            Ing = re.findall(findIng,item)
            if (len(Ing)!=0):
                Ing = Ing[0].replace('。','')
                data.append(Ing)
            else:
                data.append('')

            findBd = re.compile('<p class="">(.*?)</p>',re.S) ##########################
            Bd = re.findall(findBd,item)[0]
            Bd = re.sub('<br(\s+)?/>(\s+)?','',Bd)
            Bd = re.sub('/','',Bd)
            data.append(Bd.strip())
            datalist.append(data)
            # print(datalist)
    return datalist
def askURL(url):
    head= {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"
    }
    req = urllib.request.Request(url,headers =head)
    reponse = urllib.request.urlopen(req) #urlopen
    html = reponse.read().decode('utf-8')
    return html

def saveData(savepath,datalist):
    book = xlwt.Workbook(encoding='utf-8')
    sheet = book.add_sheet('shee1')
    col = ('链接','图片','中文名','英文名','相关信息','评价人数','评分','内容')
    for i in range(0,8):
        sheet.write(0,i,col[i])

    for i in range(0,250):
        data = datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])
    book.save(savepath)
if __name__ =="__main__":
    main()