python 爬虫 5i5j房屋信息 获取并存储到数据库

 1 from lxml import etree
 2 from selenium import webdriver
 3 import pymysql
 4 
 5 def geturl(fullurl):#获取每个招聘网页的链接
 6     browser.get(fullurl)
 7     shouye_html_text = browser.page_source
 8     shouye_ele = etree.html(shouye_html_text)
 9     zf_list = shouye_ele.xpath('/html/body/div[4]/div[1]/div[2]/ul/li/div/h3/a/@href')#链接url
10     zf_url_list  = []
11     for zf_url_lost in zf_list:
12         zf_url  = 'https://bj.5i5j.com'+zf_url_lost
13         zf_url_list.append(zf_url)
14     return zf_url_list
15 def getinfo(zp_url_list):
16     for zp_url in zp_url_list:
17         browser.get(zp_url)
18         zp_info_html = browser.page_source
19         zp_ele = etree.html(zp_info_html)
20         zp_info_title = str(zp_ele.xpath('//html/body/div[3]/div[1]/div[1]/h1/text()')[0])
21         zp_info_num = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[1]/div[1]/div/p[1]/text()')[0])+'元/月'#价格
22         zp_info_type = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[1]/div[2]/div/p[1]/text()')[0])#户型
23         zp_info_zone = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[1]/div[3]/div/p[1]/text()')[0])+'平米'#房屋大小
24         zp_info_need_1 = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[2]/ul/li[1]/span/text()')[0])#房屋信息
25         zp_info_need_2 = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[2]/ul/li[1]/a/text()')[0])#房屋信息
26         zp_info_need = zp_info_need_1+zp_info_need_2
27         connection = pymysql.connect(host='localhost', user='root', password='1234', db='5i5j', )
28         try:
29             with connection.cursor() as cursor:
30                 sql = "insert into `5i5j_info` (`title`,`num`,`type`, `zone`,`need`) values (%s,%s,%s,%s, %s)"
31                 cursor.execute(sql, (zp_info_title,zp_info_num,zp_info_type,zp_info_zone,zp_info_need))
32             connection.commit()
33         finally:
34             connection.close()
35         print(zp_info_title,zp_info_num,zp_info_type,zp_info_zone,zp_info_need)
36 if __name__ == '__main__':
37     browser = webdriver.chrome()
38     pags = int(input('需要几页?'))
39     for i in range(1,pags+1):
40         url = 'https://bj.5i5j.com/zufang/huilongguan/n{}/'
41         fullurl = url.format(str(i))
42         zf_url_list = geturl(fullurl)
43         print(fullurl)
44         # print(zf_url_list)
45         getinfo(zf_url_list)
46     browser.close()