python爬虫实战（一）爬取豆瓣电影排行top250

代码如下：

from bs4 import BeautifulSoup  #网页解析 获取数据
import re   #正则
import urllib.request,urllib.error    #制定URL 获取网页数据
import sys
import xlwt


def main():
    baseurl="https://movie.douban.com/top250?start="
    datalist = getData(baseurl)
    savepath = ".\\豆瓣top250.xls"
    saveData(datalist,savepath)
#    askURL("https://movie.douban.com/top250?start=")
#影片链接
findlink = re.compile(r'<a href="(.*?)">')     #创建正则表达式
#影片图片
findImgSrc = re.compile(r'<img .*src="(.*?)"',re.S) #让换行符加入匹配
#影片片名
findTitle = re.compile(r'<span class="title">(.*)</span>')
#影片评分
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
#评价人数
findJudge = re.compile(r'<span>(\d*)人评价</span>')
#概况
findInq = re.compile(r'<span class="inq">(.*?)</span>')
#影片的相关内容
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)

#爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0,10):       #10页  10次   一页25条
        url = baseurl + str(i*25)
        html = askURL(url)
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):
            #print(item)
            data = []  #保存一部电影的信息
            item = str(item)
            #影片链接
            link = re.findall(findlink,item)[0]     #re库 正则表达式获取影片详情链接
            data.append(link)       #添加链接
            ImgSrc = re.findall(findImgSrc,item)[0]
            data.append(ImgSrc)     #添加图片
            titles = re.findall(findTitle,item)     #片名可能只有一个中文名，没有外国名
            if (len(titles) == 2):
                ctitle = titles [0]
                data.append(ctitle)                 #添加中文名
                otitle = titles [1].replace("/","")   #去掉无关符号
                data.append(otitle)     #添加外国名
            else:
                data.append(titles[0])
                data.append(' ')    #外国名留空
            rating = re.findall(findRating,item)[0]
            data.append(rating)     #添加评分

            judgeNum = re.findall(findJudge,item)[0]
            data.append(judgeNum)       #添加评价人数

            inq = re.findall(findInq,item)
            if len(inq) != 0:
                inq = inq[0].replace("。","")
                data.append(inq)            #添加概述
            else:
                data.append(" ")        # 留空
            bd = re.findall(findBd,item)[0]
            bd = re.sub('<br(\s+)?/>(\s+)?'," ",bd)  #去掉<br/>
            bd = re.sub('/'," ",bd)         #替换/
            # print(bd.strip())
            data.append(bd.strip())         #去掉前后的空格


            datalist.append(data)   #把处理好的一部电影信息放入datalist

    print(datalist)
    return datalist
#得到一个网页的页面信息
def askURL(url):
    head = {"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1"

        }
    request= urllib.request.Request(url,headers=head)
    html=""
    try:
        response=urllib.request.urlopen(request)
        html=response.read().decode("utf-8")
        # print(html)
        return html
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)


def saveData(datalist,savepath):
    print("save.....")
    book = xlwt.Workbook(encoding="utf-8")  # 创建workbook对象
    sheet = book.add_sheet('豆瓣电影top250',cell_overwrite_ok=True)  # 创建工作表
    col = ("电影详情链接","图片链接","影片中文名","影片外国名","评分","评价数","概况","相关信息")
    for i in range(0,8):
        sheet.write(0,i,col[i])#列名
    for i in range(0,250):
        print("第%d条" %(i+1))
        data = datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])      #  写入数据
    book.save(savepath)  # 保存数据表

if __name__ == "__main__": #程序的入口
    main()
    print("爬取完毕")