Python爬虫_豆瓣TOP250

有数据库 和 表格 没有详细分开 后续整理吧
先上代码

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

findLink = re.compile(r'<a href="(.*?)">')  # 创建正则表达对象，表示规则
findImgSrc = re.compile(r'img.*src="(.*?)"', re.S)  # re.S 让换行符包含在内
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>')
#概述
findInq = re.compile(r'<span class="inq">(.*)</span>')
#相关内容
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)


def main():
    baseurl = "https://movie.douban.com/top250?start="
    # 1.爬取网页
    dataList = getData(baseurl)
    #savepath = "豆瓣电影Top250.xls"
    dbpath = "movie.db"
    # 3.保存数据
    #saveData(dataList, savepath)
    saveDataDB(dataList, dbpath)

# 爬取网页
def getData(baseurl):
    dataList = []
    for i in range(0, 250, 25):  # 调用获取页面
        url = baseurl + str(i)
        html = askURL(url)  # 保存获取到的网页源码

        # 2.逐步解析数据
        soup = bs4.BeautifulSoup(html, "html.parser")
        for item in soup.find_all('div', class_="item"):  # 查找符合要求的字符串，形成列表
            data = []  # 保存一部电影的所有信息
            item = str(item)

            # 影片详情连接
            link = re.findall(findLink, item)[0]  # re库通过正则表达式查找指定字符
            data.append(link)


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

            titles = re.findall(findTitle, item)  # 片名可能只有一个中文名，没有英语

            if len(titles) == 2:
                ctitle = titles[0]
                data.append(ctitle)
                otitle = titles[1].replace("&nbsp;", "")
                otitle = titles[1].replace("/", "")
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')  # 留空占位

            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("。", "")  # 去掉句号
                data.append(inq)
            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)
            data.append(bd.strip())  # 去掉空格

            dataList.append(data)

    return dataList


# 得到直顶URL的网页内容
def askURL(url):
    # 伪装为windows
    head = {  # 模拟浏览器头部信息，向豆瓣发消息
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, like; Gecko) Chrome / 86.0; .4240; .198; 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


# 3.保存数据
def saveData(dataList, savepath):
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  # 创建对象
    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", "中文名", "外国名", "评分", "评价数", "概述", "相关信息")
    for i in range(8):
        sheet.write(0, i, col[i])  # 列名
    for i in range(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)

def saveDataDB(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,oname,score,rated,introduction,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,
        oname varchar,
        score numeric,
        rated numeric,
        introduction text,
        info text);
    
    
    
    ''' #创建数据表
    conn = sqlite3.connect(dbpath)
    cursor = conn.cursor()
    cursor.execute(sql)
    conn.commit()
    conn.close()


if __name__ == '__main__':
    main()
    #init_db("movietest.db")    #测试