利用python爬虫爬百度百聘招聘数据----利用Ajax的方式抓取

---

前言

爬取步骤

1.引入库

代码如下（示例）：

import requests
from urllib.parse import urlencode
from pyquery import PyQuery as pq
import time

2.代码如下

base_url = 'https://zhaopin.baidu.com/api/qzasync?'

headers = {
    'Host':'zhaopin.baidu.com',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    }
def get_page(page):
    params = {
        'query':'销售代表',
        'city':'重庆',
        'is_adq':'1',
        'pcmod':'1',
        'token': '==gxgG7pa6K1Ut1ZlZGmypZlWu5ZVZobVapldKJZm5ma',
        'pn':str(page),
        'rn':'20'
        }
    url = base_url + urlencode(params)
    try:
        response = requests.get(url, headers=headers)
        time.sleep(2)
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError as e:
        print('Error',e.args)


def parse_page(json):
    if json:
        items = json.get('data').get('disp_data')
        for item in items:
            job = {}
            job['companydescription'] = item.get('companydescription')
            job['city'] = item.get('city')
            job['requirements'] = item.get('requirements')
            job['company'] = item.get('company')
            job['ori_salary'] = item.get('ori_salary')
            yield job
            

if __name__ == '__main__':
    k = 0
    for i in range(0,100, 20):
        json = get_page(i)
        for j in parse_page(json):
            print('success')




   

---

总结