豆瓣数据爬取

#导入模块
from bs4 import BeautifulSoup#数据获取网页解析
import re #正则表达式文字匹配
import urllib.request,urllib.error#制定url获取指定数据
import xlwt#进行excel操作
import sqlite3#数据库包

def main():
    baseurl = "https://movie.douban.com/top250?start=0"
    datalist = getData(baseurl)#爬取网页
    savepath = "豆瓣电影TOP250.xls"
    #保存数据
    saveData(datalist,savepath)
    # askURL("https://movie.douban.com/top250?start=0")

#影片详情链接的规则
findLink = re.compile(r'<a href="(.*?)>')#创建正则对象表示规则
#影片图片链接
findImgs = re.compile(r'<img.*src="(.*?)" ',re.S)
#影片片名链接
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>')#\d数字等价于0-9
#找到概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
#找到影片相关内容
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)

#爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0,10):
        url = baseurl + str(i * 25)
        html = askURL(url)
        
        #逐一解析
        soup = BeautifulSoup(html,"html.parser")
        #查找符合要求字符串，形成列表
        for item in soup.find_all('div',class_="item"):
            #print(item)#测试查看电影item
            data = []
            item = str(item)

            #影片详情链接
            Link = re.findall(findLink,item)[0]
            data.append(Link)
            imgsrc = re.findall(findImgs,item)[0]
            data.append(imgsrc)#添加图片
            titles = re.findall(findTitle,item)#片名只添加中文名
            if(len(titles) == 2):
                ctitle = titles[0]       #添加中文名
                data.append(ctitle)
                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(' ')#外国名字留空

            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("。"," ")#去掉句号
               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)#/替换成空值
            data.append(bd.strip())#去掉前后空格

            datalist.append(data)  #处理好的电影放入datalist
    print(datalist)
    return datalist


#得到一个指定的URL网页内容
def askURL(url):
    #伪装其实也可以理解告诉服务器我们可以接收什么水平的文件内容
    head = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36"}
    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)#创建workbook对象，压缩风格
    sheet = book.add_sheet('豆瓣电影TOP250',cell_overwrite_ok=True)#创建工作表，单元覆盖以前内容
    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])#数据
    book.save(savepath)#保存数据

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