首页 > > 网络编程 > 其它 >

Python 爬虫招聘信息并存入数据库

2018-08-21 05:42:02来源：博客园阅读 ()

新学习了selenium,啪一下腾讯招聘

 1 from lxml import etree
 2 from selenium import webdriver
 3 import pymysql
 4 def Geturl(fullurl):#获取每个招聘网页的链接
 5     browser.get(fullurl)
 6     shouye_html_text = browser.page_source
 7     shouye_ele = etree.HTML(shouye_html_text)
 8     zp_list = shouye_ele.xpath('//*[@id="position"]/div[1]/table/tbody/tr/td/a/@href')#链接url
 9     zp_url_list  = []
10     for zp_url_lost in zp_list:
11         zp_url  = 'https://hr.tencent.com/'+zp_url_lost
12         zp_url_list.append(zp_url)
13     return zp_url_list
14 def Getinfo(zp_url_list):#获取每个招聘链接内部的内容
15     for zp_url in zp_url_list:
16         browser.get(zp_url)
17         zp_info_html = browser.page_source
18         zp_ele = etree.HTML(zp_info_html)
19         zp_info_title = str(zp_ele.xpath('//*[@id="sharetitle"]/text()')[0])
20         zp_info_location = str(zp_ele.xpath('//*[@id="position_detail"]/div/table/tbody/tr[2]/td[1]/text()')[0])
21         zp_info_type = str(zp_ele.xpath('//*[@id="position_detail"]/div/table/tbody/tr[2]/td[2]/text()')[0])
22         zp_info_num = str(zp_ele.xpath('//*[@id="position_detail"]/div/table/tbody/tr[2]/td[3]/text()')[0])
23         zp_info_need = str(zp_ele.xpath('//*[@id="position_detail"]/div/table/tbody/tr[3]/td/ul/li/text()'))
24         connection = pymysql.connect(host='localhost', user='root', password='1234', db='txzp', )
25         try:
26             with connection.cursor() as cursor:
27                 sql = "INSERT INTO `txzp_info` (`title`, `location`,`type`,`num`,`need`) VALUES (%s,%s,%s,%s, %s)"
28                 cursor.execute(sql, (zp_info_title,zp_info_location,zp_info_type,zp_info_num,zp_info_need))
29             connection.commit()
30         finally:
31             connection.close()
32         print(zp_info_title,zp_info_location,zp_info_type,zp_info_num,zp_info_need)
33 if __name__ == '__main__':
34     browser = webdriver.Chrome()
35     pags = int(input('需要几页?'))
36     for i in range(0,pags):
37         url = 'https://hr.tencent.com/position.php?keywords=&tid=0&start={}'
38         fullurl = url.format(str(i*10))
39         zp_url_list = Geturl(fullurl)
40         Getinfo(zp_url_list)
41     browser.close()