豆瓣TOP250电影相关信息获取

        刚开始学爬虫，根据Python爬虫编程基础5天速成（2021全新合集）Python入门+数据分析_哔哩哔哩_bilibili学习，自己简单敲了一遍：

import urllib.request
import urllib.error
import re
from bs4 import BeautifulSoup
import xlwt
baseurl = 'https://movie.douban.com/top250?start='
findLink = re.compile(r'<a href="(.*?)">')     #创建正则表达式对象
findImgSrc = re.compile(r'<img .*src="(.*?)"',re.S)     #忽略换行符
findTitle = re.compile(r'<span class="title">(.*?)</span>')
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*?)</span>')
findJudge = re.compile(r'<span>(\d*)人评价</span>')
findInq = re.compile(r'<span class="inq">(.*?)</span>')
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)
# 1.爬取网页
def askHtml(url):
    head = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'}
    request = urllib.request.Request(url=url, headers=head)
    response = urllib.request.urlopen(request)
    html = response.read().decode('utf-8')
    return html
# 2.解析数据
def get_Datalist():
    dataList = []
    for i in range(0,10):    #左闭右开
        url = baseurl + str(i * 25)
        html = askHtml(url)
        soup = BeautifulSoup(html,'html.parser')
        for item in soup.find_all('div',class_='item'):
            data = []
            item = str(item)
            # 影片详情链接
            link = re.findall(findLink,item)[0]
            data.append(link)
            # 图片链接
            img =re.findall(findImgSrc,item)[0]
            data.append(img)
            # 名字
            titles = re.findall(findTitle,item)
            if len(titles) == 2:
                ctitle = titles[0]      #添加中文名
                data.append(ctitle)
                otitle = titles[1].replace('/','')      #添加外文名
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')        #外文名留空
            # 评分
            rating = re.findall(findRating,item)[0]
            data.append(rating)
            # 评分人数
            judge = re.findall(findJudge,item)[0]
            data.append(judge)
            # 概述
            inq = re.findall(findInq,item)
            if len(inq) != 0:
                inq = inq[0].replace('。','')
                data.append(inq)
            else:
                data.append(' ')        #留空
            bd = re.findall(findBd,item)[0]
            bd =re.sub('<br(\s+)?/>(\s+)?',' ',bd)
            bd = re.sub('/',' ',bd)
            data.append(bd.strip())     #去掉前后空格
            dataList.append(data)
    return dataList
def saveData(dataList):
    workbook = xlwt.Workbook(encoding='utf-8',style_compression=0)
    worksheet = workbook.add_sheet('sheet1',cell_overwrite_ok=True)
    col = ('电影详情链接','图片链接','影片中文名','外文名','评分','评价数','概况','相关信息')
    for i in range(0,8):
        worksheet.write(0,i,col[i])     #列名
    for i in range(0,250):
        for j in range(0,8):
            worksheet.write(i + 1 ,j,dataList[i][j])
    workbook.save('豆瓣电影.xls')
dataList = get_Datalist()
saveData(dataList)