爬取链家租房信息

import requests
from lxml import etree
import mysqlhelper

base_url = 'https://bj.lianjia.com/zufang/changping/pg%s/'
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
    # print(url)
    response=requests.get(url)
    html_ele = etree.HTML(response.text)

    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.fangfa(sql, data)