xpath拉取链家二手房信息并保存到excel中

import os.path

import requests
from lxml import etree
import xlwt
import xlrd


def create_excel():
    if not os.path.exists('./lianjia_excel.xls'):
        book = xlwt.Workbook(encoding='utf-8', style_compression=0)

        sheet = book.add_sheet(f'{city}-链家二手房', cell_overwrite_ok=True)
        col = ('房源名称', '所在小区', '所在地区', '房源信息', '发布时间', '房源标签', '房源价格', '房源单价')
        # 创建列名
        for i in range(0, 8):
            sheet.write(0, i, col[i])
        savepath = './lianjia_excel.xls'
        book.save(savepath)
        return book
    book = xlrd.open_workbook('./lianjia_excel.xls')  # 得到文件
    return book


if __name__ == '__main__':
    city = input('请输入需要查询的城市数据：')
    # 创建一个excel
    book = xlwt.Workbook(encoding='utf-8', style_compression=0)

    sheet = book.add_sheet(f'{city}-链家二手房', cell_overwrite_ok=True)
    col = ('房源名称', '所在小区', '所在地区', '房源信息', '发布时间', '房源标签', '房源价格', '房源单价')
    # 创建列名
    for i in range(0, 8):
        sheet.write(0, i, col[i])

    url = 'https://cd.lianjia.com/ershoufang/'
    headers = {
        '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'
    }

    page = requests.get(url=url, headers=headers)
    page.encoding = 'utf-8'
    tree = etree.HTML(page.text)
    li_list = tree.xpath('//div[@class="content "]/div/ul[@class="sellListContent"]/li')
    data_list = []
    for li in li_list:

        li_div = li.xpath('./div[@class="info clear"]')
        if len(li_div) <= 0:
            continue
        li_div = li.xpath('./div[@class="info clear"]')[0]
        # 房源名称
        li_title = li_div.xpath('./div[@class="title"]/a/text()')[0]

        # 房源链接
        li_url = li_div.xpath('./div[@class="title"]/a/@href')[0]
        # 所在小区
        li_xiaoqu = li_div.xpath('./div[@class="flood"]/div/a[1]/text()')[0]
        # 所在小区URL
        li_xiaoqu_url = li_div.xpath('./div[@class="flood"]/div/a[1]/@href')[0]
        # 所在地区
        li_diqu = li_div.xpath('./div[@class="flood"]/div/a[2]/text()')[0]
        # 所在地区URL
        li_diqu_url = li_div.xpath('./div[@class="flood"]/div/a[2]/@href')[0]
        # 房源信息
        li_houseinfo = li_div.xpath('./div[@class="address"]/div/text()')[0]
        # 发布时间
        li_followinfo = li_div.xpath('./div[@class="followInfo"]//text()')
        # 房源标签
        li_tag = li_div.xpath('./div[@class="tag"]//text()')
        # 房源总价
        li_price = li_div.xpath('./div[@class="priceInfo"]/div[1]/span/text()')[0]
        li_price = li_price + '万'
        # 房源单价
        li_unitPrice = li_div.xpath('./div[@class="priceInfo"]/div[2]/span/text()')[0]
        data_list.append([li_title, li_xiaoqu, li_diqu, li_houseinfo, li_followinfo, li_tag, li_price, li_unitPrice])

    for data in data_list:
        for i in range(0, len(data_list)):
            data = data_list[i]
            for j in range(0, 8):
                sheet.write(i + 1, j, data[j])
    savepath = './lianjia_excel.xls'
    book.save(savepath)

excel保存效果如图：