python爬取房产信息（仅供学习使用）

import requests
from bs4 import BeautifulSoup
import time
import openpyxl


def write_mysql(lst):
    wk = openpyxl.Workbook()
    sheet = wk.active
    for i in lst:
        sheet.append(i)
    wk.save("1-房产交易信息.xlsx")
    # print('保存完成')


def parser_content(resp):
    html = resp.text
    bs = BeautifulSoup(html, 'html.parser')
    ul = bs.find('ul', class_='sellListContent')
    li = ul.find_all('li')
    # print(li, type(li))
    lst = []
    for item in li:
        title = item.find('div', class_='title').text
        positionInfo = item.find('div', class_='positionInfo').text
        houseInfo = item.find('div', class_='houseInfo').text
        followInfo = item.find('div', class_='followInfo').text
        totalPrice = item.find('div', class_='totalPrice totalPrice2').text
        unitPrice = item.find('div', class_='unitPrice').text
        lst.append([title, positionInfo, houseInfo, followInfo, totalPrice, unitPrice])
        # break
    # print(lst)
    return lst


class LianJiaSpider():

    def __init__(self):
        self.url = "https://bj.lianjia.com/ershoufang/pg{0}/"
        self.headers = {
            "User - Agent": "Mozilla / 5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KABUL, like Gecko) Chrome "
                            "/ 84.0.4147.125 Safari / 537.36 "
        }

    def send_request(self, url):
        resp = requests.get(url=url, headers=self.headers)
        if resp:
            return resp

    def start(self):
        for i in range(1, 11):
            full_url = self.url.format(i)
            # print(full_url)
            resp = self.send_request(full_url)
            # print(resp.text)
            data_list = parser_content(resp)
            write_mysql(data_list)
            time.sleep(5)


if __name__ == '__main__':
    lian_jia = LianJiaSpider()
    lian_jia.start()