[Python知识库]Python爬虫豆瓣T250电影

# -*- codeing = utf-8 -*-
from bs4 import BeautifulSoup
import re
import urllib.request,urllib.error
import xlwt


def main():
    baseurl = "https://movie.douban.com/top250?start=0"
    #爬取网页
    datalist = getData(baseurl)
    savepath = ".\\豆瓣电影Top250.xls"
    # 保存数据
    saveData(datalist,savepath)
    #askURL("https://movie.douban.com/top250?start=0")

findLink = re.compile(r'<a href="(.*?)">')     #生成正则表达式对象
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)      #影片图片
findTitle = re.compile(r'<span class="title">(.*)</span>') #片名
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')   #评分
findJudge = re.compile(r'<span>(\d*)人评价</span>')        #评价人数
findInq = re.compile(r'<span class="inq">(.*)</span>')  #概况
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)


#爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0,10):           #调用获取页面信息函数
        url = baseurl + str(i*25)
        html = askURL(url)      #保存获取网页源码
        # 解析数据
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):         #查找符合要求的字符串 形成列表
            data = []   #保存一部电影信息
            item = str(item)

            link=re.findall(findLink,item)[0]       #re库通过正则表达式查找指定信息
            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)
            if(len(titles)==2):
                ctitle = titles[0]
                data.append(ctitle)
                otitle = titles[1].replace("/","")  #替换/
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append('')        #外国名留空

            rating = re.findall(findRating,item)[0]
            data.append(rating)     #评分

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

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

            datalist.append(data)
    return datalist

#得到一个指定URL网页
def askURL(url):
    # 模拟浏览器头部信息
    head = {
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 94.0.4606.81Safari / 537.36Edg / 94.0.992.50"
    } #伪装浏览器
    request = urllib.request.Request(url,headers=head)
    html=""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        #print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html

#保存数据
def saveData(datalist,savepath):
    print("save...")
    book = xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet = book.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)
    col = ("电影链接","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])
    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])
    book.save(savepath)
if __name__=="__main__": #当程序执行时
#调用函数
    main()
    print("爬取完毕！")