链家信息爬取

一、数据库封装

import pymysql

class MysqlHelper(object):
    def __init__(self):
        self.db = pymysql.connect(host=‘127.0.0.1‘, port=3306, user=‘root‘, password=‘abc123‘, database=‘py1011‘, charset=‘utf8‘)
        self.cursor = self.db.cursor()

def execute_modify_sql(self,sql, data):
        self.cursor.execute(sql, data)
        self.db.commit()

def __del__(self):
        self.cursor.close()
        self.db.close()

if __name__ == ‘__main__‘:
    conn = MysqlHelper()
    conn.execute_modify_sql(‘insert into lianjiaxinxi(title) VALUE (%s)‘, data=(‘huzeqi hehehe‘))

二、链家信息爬取

import requests
from lxml import etree
import mysqlhelper

# 这是我们分页的url, 所以叫base_url
base_url = ‘https://bj.lianjia.com/zufang/pg%srp1/‘
myhelper = mysqlhelper.MysqlHelper()
sql = ‘INSERT INTO lianjiaxinxi (title, region, zone, meters, location, price) VALUES‘ \
      ‘ (%s, %s, %s, %s, %s, %s)‘

for i in range(1, 4):
    url = base_url % i
    response = requests.get(url)
    html_ele = etree.HTML(response.text)

# ./div[2]/h2/a
    # ul 所有信息
    li_list = html_ele.xpath(‘//ul[@id="house-lst"]/li‘)
    for li_ele in li_list:
        title = li_ele.xpath(‘./div[2]/h2/a‘)[0].text
        print(title)
        region = li_ele.xpath(‘./div[2]/div[1]/div[1]/a/span‘)[0].text
        print(region)
        # div[2]/div[1]/div[1]/span[1]/
        zone = li_ele.xpath(‘./div[2]/div[1]/div[1]/span[1]/span‘)[0].text
        print(zone)
        meters = li_ele.xpath(‘./div[2]/div[1]/div[1]/span[2]‘)[0].text
        print(meters)
        location = li_ele.xpath(‘./div[2]/div[1]/div[1]/span[3]‘)[0].text
        print(location)
        price = li_ele.xpath(‘.//div[@class="price"]/span‘)[0].text
        print(price)
        import re
        res_match = re.match(‘\d+‘, meters)
        meters = res_match.group(0)
        data = (title, region, zone, meters, location, price)
        myhelper.execute_modify_sql(sql, data)

原文地址：https://www.cnblogs.com/luwanhe/p/9500547.html