腾讯招聘（简单封装）

import requests,os
from lxml import etree
from def2_mysql import MysqlHelper

myhelper =MysqlHelper()
sql = 'INSERT INTO tengxun (one_title, one_didian, one_leibie, one_renshu, one_zhize, tow_yaoqiu) VALUES' \
          ' (%s, %s, %s, %s, %s, %s)'

# 构建代理
proxy = {
    'http' : 'http://alice:123456@120.78.166.84:6666',
    'https' : 'http://alice:123456@120.78.166.84:6666'
}
headers={
    "User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36",
}


def A(fenlei,yema):

    for pa in range(0,yema,10):
        print(yema)
        url = 'https://hr.tencent.com/position.php?keywords={}&lid=0&tid=0&start={}'.format(fenlei,pa)
        response=requests.get(url,headers=headers,proxies=proxy)
        # 返回bytes
        html_bytes=response.content
        # # xpath
        html_ele = etree.HTML(html_bytes)
        # 获取每一个URL列表
        li_list = html_ele.xpath('//table[@class="tablelist"]/tr/td/a/@href')
        # print(li_list)
        print('正在保存第' + str(int(pa/10 +1)) + '页.............')
        B(li_list)

# 再次发起请求获取每一个主题的
def B(li_list):
    # 循环主题列表
    for li_ele in li_list:
        print(li_ele)
        # 循环取列表每个url  循环后返回一个列表
        last_url = 'https://hr.tencent.com/' + li_ele

        response = requests.get(last_url, headers=headers, proxies=proxy)
        # 返回html
        img_html_str = response.text
        img_ele = etree.HTML(img_html_str)
        #     # 获取整体信息
        img_sum = img_ele.xpath('//table[@class="tablelist textl"]')
        # 循环访问主题的每一条信息
        for j in img_sum:
            one_title = j.xpath('./tr[1]/td/text()')[0]
            print(one_title)
            one_didian = j.xpath('./tr[2]/td[1]/text()')[0]
            one_leibie = j.xpath('./tr[2]/td[2]/text()')[0]
            one_renshu = j.xpath('./tr[2]/td[3]/text()')[0]
            one_zhize = j.xpath('./tr[3]/td/ul/li/text()')[0]
            one_yaoqiu = j.xpath('./tr[4]/td/ul/li/text()')
            tow_yaoqiu = ' '.join(one_yaoqiu)
            # print(tow_yaoqiu)
            data = (one_title, one_didian, one_leibie, one_renshu, one_zhize, tow_yaoqiu)
            myhelper.execute_modify_sql(sql, data)

if __name__=='__main__':
    fenglei = input('请输入您要搜索的分类：')
    yema=int(input('请输入您要几页：'))*10
    cc=A(fenglei,yema)