爬取豆瓣Top250成品(附带详细注释)

爬取豆瓣Top250代码(附带详细注释)

from bs4 import BeautifulSoup#网页解析-获取数据
import re #正则表达式-用于文字匹配
import urllib.request,urllib.error#制定URl-获取网页数据
import xlwt#进行excel操作
import sqlite3#进行SQLite数据库操作


def main():
    baseurl = "https://movie.douban.com/top250?start="
    savepath = "豆瓣电影top250.xls"
    dbpath = "movie250.db"
    #1.爬取网页
    datalist = getData(baseurl)
    #2.解析数据
    #3.保存数据
    saveData(datalist,savepath)
    #saveData2DB(datalist,dbpath)

#影片详情的规则
findLink = re.compile(r'<a href="(.*?)">')    #创建正则表达式对象,表示规则(字符串的模式)
#影片图片
findImgSrc = re.compile(r'<img.*src="(.*?)">',re.S)  #让换行符包含在字符中
#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>')
#评价人数
findJudge = re.compile(r'<span>(\d*)人评价</span>')
#找到概况
findIng = 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)


#爬取网页
def getData(baseurl):
    #逐一解析数据
    datalist = []
    for i in range(10):#调用获取页面信息10次
        url = baseurl + str(i*25)
        html = askURL(url)
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.findall('div',class_="item"):     #查找符合要求的字符串,形成列表
            #print(item)    #测试:查看电影item全部信息
            data=[] #保存一部电影的所有信息
            item = str(item)
            link = re.findall(findLink,item)[0]   #re库用来通过正则表达式查找指定的字符串
            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)   #片名可能只有一个中文名-没有外国名
            if len(titles) == 2:
                ctitle = titles[0]
                data.append(ctitle)               #添加中文名
                etitle = titles[1].replace("/","")#去掉无关字符
                etitle = etitle.replace("\xa0", "")  # 去掉无关字符
                data.append(etitle)               #添加外国名
            else:
                data.append(titles[0])
                data.append(" ")                  #外国名留空
            rating = re.findall(findRating,item)[0]
            if len(rating) != 0:
                data.append(rating)                   #添加评分
            else:
                data.append(" ")                        #留空

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

            ing = re.findall(findIng,item)
            if len(ing) != 0:
                ing = ing[0].replace("。","")        #去掉句号
                ing = ing.replace("\xa0", "")
                data.append(ing)                  #添加概况
            else:
                data.append(" ")                  #流空

            bd = re.findall(findBd,item)[0]
            bd = re.sub('<br(\s+)?/>(\s+)?',"",bd)  #去掉<br/>
            bd = re.sub('/',"",bd)         #替换/
            bd = re.sub('\xa0', "", bd)
            data.append(bd.strip())         #去掉前后的空格

            datalist.append(data)
    return datalist

def saveData(datalist,savepath):
    book = xlwt.Workbook(encoding='utf-8',style_compression=0)      #创建Worlbook对象
    sheet = book.add_sheet("豆瓣电影Top250",cell_overwrite_ok=True)    #创建工作表
    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")
    print(datalist)
    for i in range(len(col)):
        sheet.write(0,i,col[i])  #列名
    for i in range(len(datalist)):
        print("第%d部"%(i+1))
        data = datalist[i]
        for j in range(len(data)):
            sheet.write(i+1,j,data[j])  #数据
    book.save(savepath)

def saveData2DB(datalist,dbpath):
    init_db(dbpath)
    conn = sqlite3.connect(dbpath)
    cur = conn.cursor()

    for data in datalist:
        for index in range(len(data)):
            if index == 4 or index == 5:
                continue
            data[index] = '"'+data[index]+'"'
        sql = '''
            insert into movie250(
            info_link,pic_link,cname,ename,score,rated,instroduction,info)
            values(%s)'''%",".join(data)
        cur.execute(sql)
        conn.commit()


    cur.close()
    conn.close()

def init_db(dbpath):
    sql = '''
        create table movie250
        (
        id integer primary key  autoincrement,
        info_link text,
        pic_link text,
        cname varchar,
        ename varchar,
        score numeric,
        rated numeric,
        instroduction text,
        info text
        )
    '''
    #创建数据表
    conn = sqlite3.connect(dbpath)
    cursor = conn.cursor()
    cursor.execute(sql)
    conn.commit()
    conn.close()


def askURL(url):
    head = {#模拟浏览器头部信息-向豆瓣服务器发送消息
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.182 Safari/537.36"
    }#用户代理-表示告诉豆瓣服务器-我们是什么类型的机器\浏览器(本质上是告诉浏览器-我们可以接收什么水平的文件)
    req = urllib.request.Request(url,headers=head)
    html = ""
    try:
        res = urllib.request.urlopen(req)
        html = res.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__':#当函数执行时
    #程序入口
    main()
    print("爬取完毕!")

部分运行结果截图: