python学习——爬取数据到excel

python的学习直接使用网页爬虫，将内容爬取到excel，也是为之后的大数据学习做铺垫。

下面的代码是我爬取的豆瓣电影Top250的电影基本信息，当然，也可以爬取到数据库中

# -*- coding:utf-8 -*-  
# 上面这一行的目的是防止乱码

from bs4 import BeautifulSoup  # 数据解析，处理html
import re  # 正则表达式
import urllib.request, urllib.error
import xlwt  # 进行excel操作


def main():
    baseurl = "https://movie.douban.com/top250?start="
    # 1、爬取网页
    datalist = getData(baseurl)
    # 3、保存数据
    savepath = "C:\\Users\\Jzz\\Desktop\\python\\豆瓣电影top250.xls"
    saveData(datalist, savepath)


# 影片链接
findlink = re.compile(r'<a href="(.*?)">')  # 创建正则表达式对象，表示规则
# 影片图片链接
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)  # re.S使换行符包含在字符中
# 片名
findTitle = re.compile(r'<span class="title">(.*?)</span>')
# 影片评分
findRate = 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>')
# 概况
findIng = re.compile(r'<span class="inq">(.*)</span>')
# 找到影片内容
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
            data = []  # 保存一部电影所有信息,列表
            item = str(item)
            # 影片链接
            link = re.findall(findlink, item)[0]  # re库通过正则表达式查找指定字符串
            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
            if (len(titles) == 2):
                ctitle = titles[0]
                data.append(ctitle)
                ftitle = titles[1].replace("/", "")
                data.append(ftitle)
            else:
                data.append(titles[0])
                data.append(' ')  # 外文名留空

            rate = re.findall(findRate, item)[0]
            data.append(rate)

            judge = re.findall(findJudge, item)[0]
            data.append(judge)

            ing = re.findall(findIng, item)
            if (len(ing) != 0):
                ing = ing[0].replace("。", "")
                data.append(ing)
            else:
                data.append(' ')

            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


# 得到指定网页的内容
def askUrl(url):
    # 模拟浏览器头部
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36"}
    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.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


def saveData(datalist, savepath):
    workbook = xlwt.Workbook(encoding="utf-8", style_compression=0)
    worksheet = workbook.add_sheet("豆瓣电影Top250", cell_overwrite_ok=True)
    col = ('电影链接', "图片链接", "影片中文名", "影片别名", "评分", "评价", "概况", "相关信息")
    for i in range(0, 8):
        worksheet.write(0, i, col[i])
    for i in range(0, 250):
        print("第%d条" % i)
        data = datalist[i]
        for j in range(0, 8):
            worksheet.write(i + 1, j, data[j])
    workbook.save(savepath)


if __name__ == '__main__':  # python的main函数
    main()

爬取的效果是这样的