如何用正则表达式爬取开始标签之间的数据

爬取去哪网的景点

# -*- codeing = utf-8 -*-
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  # 制定URL，获取网页数据
import xlwt  # 进行excel操作

findTitle = re.compile(r'<span class="cn_tit">(.*?)</span>')
findRating = re.compile(r'<span class="ranking_sum">(.*?)</span>')
findInq = re.compile(r'<div class="desbox">(.*?)</div>')


def main():
    baseurl = "https://travel.qunar.com/p-cs299914-beijing-jingdian-1-"  # 要爬取的网页链接
    datalist = getData(baseurl)
    savepath = "北京景点.xls"  # 当前目录新建XLS，存储进去
    saveData(datalist, savepath)


# 爬取网页
def getData(baseurl):
    datalist = []  # 用来存储爬取的网页信息
    for i in range(0, 20):  # 调用获取页面信息的函数，10次
        url = baseurl + str(i + 1)
        html = askURL(url)
        soup = BeautifulSoup(html, "html.parser")
        for item in soup.find_all('li', class_="item"):  # 查找符合要求的字符串
            data = []  # 保存一部电影所有信息
            item = str(item)
            titles = re.findall(findTitle, item)
            data.append(titles)
            rating = re.findall(findRating, item)
            data.append(rating)
            inq = re.findall(findInq, item)
            data.append(inq)
            datalist.append(data)
    return datalist


# 得到指定一个URL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 / 80.0.3987.122  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


# 保存数据到表格
def saveData(datalist, savepath):
    print("save.......")
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  # 创建workbook对象
    sheet = book.add_sheet('北京景点', cell_overwrite_ok=True)  # 创建工作表
    col = ("景点名称", "排名", "介绍")
    for i in range(0, 3):
        sheet.write(0, i, col[i])  # 列名
    for i in range(0, 200):
        # print("第%d条" %(i+1))       #输出语句，用来测试
        data = datalist[i]
        for j in range(0, 3):
            sheet.write(i + 1, j, data[j])  # 数据
    book.save(savepath)  # 保存


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

爬取出的数据老是会有多出的标签

还有为什么爬出的数据不是200个？