python 爬虫 豆瓣Top250电影信息

# -*- codeing = utf-8 -*-
# @Time : time


from bs4 import BeautifulSoup  # 网页解析，获取数据
import re  # 正则表达式，进行文字匹配
import urllib.request, urllib.error  # 指定url，获取网页数据
import xlwt  # 进行excel操作
import sqlite3  # 进行SqlLite数据库操作

P = 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)
    saveData2Db(datalist,dbpath)
    # print("hello",a)

    # askURL("https://movie.douban.com/top250?start=")

#影片详情链接的规则
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)     #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>')
# 找到评价人数
findjudge = re.compile(r'<span>(\d*)人评价</span>')
# 找的概况
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)


# 爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0, 10):          # 调用获取页面信息的函数、10次
        url = baseurl + str(i*25)
        html = askURL(url)      # 保存获取到的网页源码

        # 2.逐一解析数据
        soup = 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)
            # print(item)
            # break

            # 影片详情的链接
            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
            # print(link)
            data.append(link)
            # 影片图片
            ImgSrc = re.findall(findImgSrc, item)[0]
            data.append(ImgSrc)
            # 影片片名
            titles = re.findall(findTitle, item)
            if len(titles) == 2:
                ctitle = titles[0]         #添加中文名
                data.append(ctitle)
                otitle = titles[1].replace("/","")    #添加外国名   去掉无关的 /
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')      #外国名字留空
            # 影片评分
            rating = re.findall(findRating, item)[0]
            data.append(rating)
            # 找到评价人数
            judgenum = re.findall(findjudge, item)[0]
            data.append(judgenum)
            # 找的概况
            inq = re.findall(findBd, item)
            if len(inq) != 0:
                inq = inq[0].replace("。", "")
                data.append(inq)
            else:
                data.append(" ")
            # 找到影片的相关内容
            bd = re.findall(findBd, item)[0]
            bd = re.sub('<br(\s+)?/>(\s+)?', " ",bd)    #去掉<br/>
            data.append(bd.strip())    #去掉前后的空格

            datalist.append(data)    # 把处理存的一部电影信放入datalist


    #print(datalist)
    return datalist


# 得到指定一个UPL的网页内容
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/87.0.4280.88 Safari/537.36 Edg/87.0.664.66"
    }
    # 用户代理·表示告诉豆播服务器﹐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T以接收什么水平的文件内容)
    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


# main(2)


# 保存数据
def saveData(datalist,savepath):
    # print(1)
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  # 创建workbook对象
    sheet = book.add_sheet('豆瓣电影Top250',cell_overwrite_ok=True)  # 创建工作表
    col = ("电影详情链梓","图片链接”","影片中立名","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])

    book.save(savepath)  # 保存数据表


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
            else:
                data[index] = '"'+data[index]+'"'
        sql = '''
            insert into movie250 (
            info_link,pic_link,cname,ename,score,rated,instroduction,info)
            values(%s)'''%",".join(data)
        # print(sql)
        cur.execute(sql)
        conn.commit()
    cur.close()
    conn.close()

    print("...")


def init_db(dbpath):
    # 创建数据表
    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
        )
    """

    conn = sqlite3.connect(dbpath)
    cursor = conn.cursor()
    cursor.execute(sql)
    conn.commit()
    conn.close()


if __name__ == "__main__":  # 当程序执行时
    # 调用函数
    main()
    print("爬取完毕")