爬取腾讯招聘职位列表和详情

from urllib import request
from bs4 import BeautifulSoup
urls = []
def qq():
    url = "https://hr.tencent.com/position.php?keywords=python&lid=2196&tid=87"
    a = request.urlopen(url)
    b = a.read()
    soup = BeautifulSoup(b,'lxml')
    tr1 = soup.select("tr[class='even']")
    tr2 = soup.select("tr[class='odd']")
    tr = tr1 + tr2
    print('找到的职位列表如下：')
    for k in tr:
        name = k.select('td a')[0].get_text()
        href = k.select('td a')[0].attrs['href']
        leixing = k.select('td')[1].get_text()
        addr = k.select('td')[3].get_text()
        urls.append('https://hr.tencent.com/'+href)
        print(name)
    print('*'*20)

def zpxq():
    print('找到的职位详情如下：')
    for url in urls:
        a = request.urlopen(url)
        b = a.read()
        soup = BeautifulSoup(b,'lxml')
        tr = soup.select("tr")
        for k in tr:
            name = k.select("td")[0].get_text()
            print(name)
        print('=='*15)

if __name__ == '__main__':
    qq()
    zpxq()

转载于:https://www.cnblogs.com/billchen1991/p/10341713.html