Python爬取豆瓣点评前250名（来自b站教学视频）

简单爬虫操作

#-*- coding = utf-8 -*-
#@Time : 2020/7/16 0:18
#@Author : LZR
#@File : 爬虫训练.py
#@Software : PyCharm



import sys
from bs4 import BeautifulSoup #网页解析
import re
import urllib.request#获取网页
import urllib.error
import xlwt     #excel
import sqlite3


def main():
    baseurl='https://movie.douban.com/top250?start='
    datalist=getData(baseurl)
    savepath='doubantop250.xsl'
    saveData(datalist,savepath)




findlink=re.compile(r'<a href="(.*?)">')   #创建正则对象
findImagSrc = re.compile(r'<img.*src="(.*?)"',re.S)   #图片的链接
findTitle = re.compile(r'<span class="title">(.*)</span>')  #片名
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
#找到评价人数
findJudge = re.compile(r'<span>(\d*)人评价</span>')
#找到概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
#找到影片的相关内容
findBd = re.compile(r'<p class="">(.*?)</p>,re.S')



def getData(baseurl):    #爬取网页
    datalist=[]
    for i in range(0,10):
        url=baseurl+str(i*25)
        html=aksURl(url)  #保存获取到的网页源码
        #逐一解析
        soup=BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):
            data=[]   #保存一部电影的所有信息
            item=str(item)

            #获取影片详情的连接
            link=re.findall(findlink,item) #re库来通过正则表达式
            data.append(link)

            imgSrc = re.findall(findImagSrc,item)
            data.append((imgSrc))

            titles = re.findall(findTitle,item)
            if(len(titles)==2):
                ctitles = titles
                data.append(ctitles)
                otitle = titles[1].replace("/","")
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')   #外文名留空

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

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

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

            #bd = re.findall(findBd,item)
            #bd = re.sub('<br(\S+)?/>(\S+)?'," ",bd)  #去掉<br/>
            #bd = re.sub('/'," ",bd)
            #data.append(bd.strip())

            datalist.append(data)    #一部影片
    print(datalist)
    return datalist



#保存数据
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','评价数','相关信息')
    for i in  range(0,7):
        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(0,7):
            sheet.write(i+1,j,data[j])
    book.save('250.xls')


def aksURl(url):
    head={
        "User-Agent":"Mozilla / 5.0(Windows NT 10.0; Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 83.04103.116Safari / 537.36Edg / 83.0.478.61"
    }    #用户代理，告诉豆瓣服务器，我们是什么类型的机器
    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

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