python爬虫 - 爬取智联招聘

import urllib.request
import urllib.parse
from Bs4 import BeautifulSoup
import lxml

def main():

    url = 'https://sou.zhaopin.com/jobs/searchresult.ashx?'

    jl = input('请输入工作地点：')
    kw = input('请输入工作关键字：')
    start_page = int(input('请输入起始页码：'))
    end_page = int(input('请输入结束页码：'))
    for page in range(start_page, end_page+1):
        data = {
            'jl':jl,
            'kw':kw,
            'p':page,
        }
        url_now = url + urllib.parse.urlencode(data)
        print(url_now)
        header = {'User-Agent': ' Mozilla/5.0 (Windows NT 6.1; Win64;'
                                ' x64) AppleWebKit/537.36 (KHTML, like'
                                ' Gecko) Chrome/71.0.3578.98 Safari/537.36', }
        request = urllib.request.Request(url=url_now, headers=header)
        response = urllib.request.urlopen(request)
        #print(response)
        soup = BeautifulSoup(response.read().decode('utf8'), 'lxml')
        print(soup.find('a',href='http://company.zhaopin.com/CZ000100000.htm'))
        #print(type(info))
        #for div in div_list:
        #    zwmc = div.span['title']
        #    print(zwmc)
        #    exit()

if __name__ == '__main__':
    main()