爬取豆瓣电影信息存入Excel表

爬取豆瓣前250的电影信息存入Excel表

来源参考：添加链接描述

1. 爬取的效果图
   

2. 代码

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
import xlwt


def main():
    baseurl = "https://movie.douban.com/top250?start="
    # 爬取数据
    datalist = getData(baseurl)
    savepath = ".\\豆瓣电影Top250.xls"
    # 保存数据
    saveData(datalist,savepath)

    # 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，表示规则(字符串模式)
# 影片图片
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)
# 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>')
# 影片评价人数
findJudge = re.compile(r'<span>(\d*)人评价</span>')
# 影片概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
# 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)   # 保存获取到的网页源码

        # 逐一解析数据
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div', class_="item"):  # 查找符合条件的字符串，形成列表
            # print(item)   # 测试电影item全部信息
            data = []
            item = str(item)

            # 影片详情链接
            link = re.findall(findLink, item)[0]   # 用正则表达式查找指定字符串
            data.append(link)

            imgSrc = re.findall(findImgSrc, item)[0]
            data.append(imgSrc)     # 添加图片

            titles = re.findall(findTitle, item)  # 添加名字
            if (len(titles) == 2):
                ctitle = titles[0]
                data.append(ctitle)
                otitle = titles[1].replace("/","")
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')

            rating = re.findall(findRating, item)[0]   # 添加评分
            data.append(rating)

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

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

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

            datalist.append(data)  # 将一部电影信息存入列表中
    # print(datalist)
    return datalist


# 指定一个url的网页内容
def askURL(url):
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36"
    }            # 用户代理，告诉服务器，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


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", "电影中文名", "电影外国名", "评分", "评价数", "概况", "相关信息",)
    for i in range(0, 8):
        sheet.write(0, i, col[i])
    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)


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

注：这只供学习参考，侵权必删。