python 爬虫 抓取2020最新房价信息 买不起看看总可以吧

运行结果：

代码实现：

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2020/11/21 12:00
# @Author  : huni
# @File    : 2020房价信息爬取.py
# @Software: PyCharm

import requests
from lxml import etree
import sqlite3

def getData(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36'
    }

    page_text = requests.get(url=url,headers=headers).text

    tree = etree.HTML(page_text)

    li_list = tree.xpath('/html/body/div[6]/ul/li')

    all_info_list = []
    for li in li_list:
        i = []
        city = li.xpath('./a/span[1]/text()')[0]
        price = li.xpath('./a/span[2]/text()')[0]
        u_d = li.xpath('./a/@class')[0]
        rate = li.xpath('./a/span[3]/text()')[0]
        i.append(city)
        i.append(price)
        i.append(u_d)
        i.append(rate)
        all_info_list.append(i)
    return all_info_list

#初始化数据库
def init_db(dbpath):
    sql = '''
        create table if not exists 房价信息2020
        (
        城市 varchar unique ,
        价格 varchar ,
        涨跌 varchar ,
        幅度 varchar 
        )

    '''  # 创建数据表
    conn = sqlite3.connect(dbpath)
    cursor = conn.cursor()
    cursor.execute(sql)
    conn.commit()
    conn.close()

#数据保存到数据库
def saveDatadb(dbpath,all_info_list):
    init_db(dbpath)
    conn = sqlite3.connect(dbpath)
    cur = conn.cursor()

    for data in all_info_list:
        for index in range(len(data)):
            data[index] = '"'+str(data[index])+'"'
        sql = '''
                replace into 房价信息2020 (
                城市,价格 ,涨跌,幅度) 
                values(%s)'''%",".join(data)
        # print(sql)
        cur.execute(sql)
        conn.commit()
    cur.close()
    conn.close()

def main():

    url = 'https://mobile.anjuke.com/fangjia/quanguo2020/'
    all_info_list = getData(url)
    dbpath = '2020房价.db'
    saveDatadb(dbpath,all_info_list)

if __name__ == '__main__':
    main()
    print('保存成功！')