spider（豆瓣电影TOP250）

#-*- coding=utf-8 -*-
import urllib.parse
import urllib.request
import re
from bs4 import BeautifulSoup
import xlwt


def main():
    baseurl='https://movie.douban.com/top250?start='
    datalist=getData(baseurl)
    savepath='豆瓣电影TOP250.xls'
    saveData(datalist,savepath)

    # askURL(baseurl)

#影片链接
findLink=re.compile(r'<a href="(.*?)">')
#影片图片
findImgSrc=re.compile(r'<img.*src="(.*?)"',re.S)
#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>')
#影片评价人数
findJudge=re.compile(r'<span>(.*)人评价</span>')
#找到概况
findInq=re.compile(r'<span class="inq">(.*)</span>')
#影片的相关内容
findBd=re.compile(r'<p class="">(.*?)</p>',re.S)
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"):
            data=[]
            item=str(item)

            link=re.findall(findLink,item)[0]
            data.append(link)

            imgSrc=re.findall(findImgSrc,item)[0]
            data.append(imgSrc)

            titles=re.findall(findTitle,item)
            if(len(titles)==2):
                ctitle=titles[0]
                data.append(ctitle)
                otitle=titles[1].replace('/','')
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')

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

            judgeNum=re.findall(findJudge,item)[0]
            data.append(judgeNum)

            inq=re.findall(findInq,item)
            if len(inq)!=0:
                inq=inq[0].replace("。","")
                data.append(inq)
            else:
                data.append(" ")

            bd=re.findall(findBd,item)[0]
            bd=re.sub('<br(\s+)?/>(\s+)?'," ",bd)
            bd=re.sub('/'," ",bd)
            bd=re.sub('\xa0',' ',bd)
            data.append(bd.strip())

            datalist.append(data)
    print(datalist)
    return datalist

def saveData(datalist,savepath):
    book=xlwt.Workbook(encoding='utf-8',style_compression=0)
    sheet=book.add_sheet('豆瓣电影250',cell_overwrite_ok=True)
    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])
    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)


def askURL(url):
    head={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36"
    }
    request=urllib.request.Request(url,headers=head)
    html=""
    try:
        response=urllib.request.urlopen(request)
        html=response.read().decode('utf-8')

    except urllib.error.URLError as e:
        if hasattr(e,'code'):
            print(e.code)
        if hasattr(e,'reason'):
            print(e.reason)
    return html
if __name__=='__main__':
    main()
    print('爬取完成，下次光临')

www.dan