爬取騰訊招聘資訊-Beautiful Soup 

---------------------------------------

============================================

===========================================================

================================================

===================================================

 1 '''
 2
 
 爬取騰訊招聘的網站 https://hr.tencent.com/position.php?&start=10#a
 3 
 4 '''
 5 
 6 from bs4 import  BeautifulSoup
 7 from urllib import request
 8 
 9 
10 
11 def qq():
12     # 獲取頁面
13     url = 'https://hr.tencent.com/position.php?&start=10#a'
14     rsp = request.urlopen(url)
15     html = rsp.read()
16
 
 
17 
18     # 提取資料
19     # 用bs解析,lxml驅動
20     soup = BeautifulSoup(html, 'lxml')
21 
22     # 建立css選擇器，得到相應的tags，even/odd，奇數偶數行，一行一個崗位資訊，trs = tr1 + tr2 得到所有崗位資訊
23     tr1 = soup.select("tr[class='even']")
24     tr2 = soup.select("tr[class='odd']")
25     trs = tr1 + tr2
26 
27     for tr in trs:
 
28         name = tr.select('td a')[0].get_text()
29         print(name)
30         href = tr.select('td a')[0].attrs['href']
31         print(href)
32         catalog = tr.select('td')[1].get_text()
33         print(catalog)
34         location = tr.select('td')[3].get_text()
35         print(location)
36         print("==" * 12)
37 
38 if __name__ == '__main__':
39     qq()