Python-爬虫-例子：豆瓣电影Top250

这个是我这几天学习爬取豆瓣电影Top250的代码（不是很完善，在慢慢凝练中！）：

from bs4 import BeautifulSoup
import re
import urllib.request,urllib.error
import xlwt
import sqlite3

def main():
    baseurl="https://movie.douban.com/top250?start="
    datalist=getData(baseurl)
    #askUrl("https://movie.douban.com/top250?start=")
    savepath="C:\\python\\1"
    saveData(datalist,savepath)
    
findLink=re.compile(r'<a href="(.*?)">')
findimgsrc=re.compile(r'img.*src="(.*?)"',re.S)
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)

def askUrl(url):
    head={
"User-Agent": "（这里需要你电脑上的用户信息，随便找一个网页，按f12后，点击网络就会看到User-Agent，把这个User-Agent的信息复制到这里就可以了。）"
    }
    request=urllib.request.Request(url,headers=head)
    html=""
    try:
        response=urllib.request.urlopen(request)
        html=response.read().decode("utf-8")  #我的电脑是“utf-8”的
        #print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html
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)

            title=re.findall(findtitle,item)
            if (len(title)==2):
                ctitle=title[0]
                data.append(ctitle)
                otitle=title[1].replace("/","")
                data.append(otitle)
            else:
                data.append(title[0])
                data.append(" ")

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

            judge=re.findall(findjudge,item)[0]
            data.append(judge)

            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)
            ba=re.sub('/'," ",bd)
            data.append(bd.strip())
            datalist.append(data)
    #print(datalist) #（这个是看看打印出来是什么样子的）
    return datalist

def saveData(datalist,savepath):
    book=xlwt.Workbook(encoding="utf-8",style_compression=0)
    sheet=book.add_sheet("豆瓣电影Top250",cell_overwrite_ok=True)
    col=("电影详情链接","图片链接","影片中文名","影片外文名","评分","评价人数","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))  #时刻关注运行到第几条了。其实运行很快的，没啥用。
        data=datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])
    book.save("豆瓣电影Top250.xls")

if __name__=="__main__":
    main()
    print("爬取完毕！")