beautiful爬取豆瓣信息

我简要说下，我这里的问题，有几处错误，使得自己始终获取不到数据。

beautifulsoup的文档

http://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/

1.属性后面是用键值对修饰的

moviesol = soup.find('ol',attrs = {'class':"grid_view"})
movieLi = moviesol.find_all('li')

2.attrs是关键字，不能写错

好了，不多说，直接上代码进行说明

import requests
import re
from bs4 import BeautifulSoup
import xlwt

def gethtml(url,pagerow):
    header = {"User-Agent":'Mozilla/4.0'}
    # proxy = {"https":'221.5.54.6:808'}
    param = {'start':pagerow,'filter':''}
    r = requests.get(url,params=param,headers =header)
    # print(r.text)
    return r.text

dataList = []
def getdata(html):
    soup = BeautifulSoup(html,'html.parser')
    moviesol = soup.find('ol',attrs = {'class':"grid_view"})
    movieLi = moviesol.find_all('li')
    for eachmovie in movieLi:
        data = []
        moviehd = eachmovie.find('div',attrs={"class":"hd"})
        movietitle = moviehd.find('span',attrs={"class":"title"}).getText()
        data.append(movietitle)
        moviebd = eachmovie.find('div',attrs={"class":"bd"})
        moviestar = moviebd.find('div',attrs={"class":"star"})
        star = moviestar.find('span',attrs={"class":"rating_num"}).getText()
        data.append(star)
        critical = re.findall(r'\d+',str(moviestar))[-1]
        data.append(critical)
        # moviequote = moviebd.find('p',attrs={"class":"quote"})
        quote = eachmovie.find('span',attrs = {"class":"inq"})
        # 如果这里不限制，将会出错，不信可以自己调试
        if quote:
            quote = quote.getText()
        else:
            quote = '无评论'
        data.append(quote)
        dataList.append(data)
    return

def saveToExcel(path):
    book = xlwt.Workbook()
    sheet = book.add_sheet('douban')
    col = ('title','star','critical','quote')
    for i in range(4):
        sheet.write(0,i,col[i])
    for i in range(len(dataList)):
        data = dataList[i]
        for j in range(4):
            sheet.write(i+1,j,data[j])
    book.save(path)
    return

def mainFunction():
    url = "http://movie.douban.com/top250"
    for page in range(10):
        if page==0:
            pagerow=0
        else:
            pagerow=(page-1)*25
        html = gethtml(url,pagerow)
        # print(html)
        getdata(html)
    saveToExcel('douban.xls')
    return

mainFunction()