爬虫腾讯招聘 目前腾讯招聘网页已经做了反爬虫的升级 ajax异步请求 目前只爬取了一页...

import requests
headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36'
    }


def parse_url():
    url = 'https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1564727219057&countryId=&cityId=3&bgIds=&productId=&categoryId=&parentCategoryId=&attrId=&keyword=python&pageIndex=2&pageSize=10&language=zh-cn&area=cn'
    response = requests.get(url, headers=headers)
    json_position = response.json()
    position_list = json_position['Data']['Posts']
    page_one_position_list = []
    for single_positon in position_list:
        position_name = single_positon['RecruitPostName']
        location_name = single_positon['LocationName']
        responsibility = single_positon['Responsibility']
        #详情页的url
        Post_url = single_positon['PostURL']
        position = {
            '工作岗位':position_name,
            '工作地点':location_name,
            '工作详情':responsibility,
            '详情url':Post_url
        }
        page_one_position_list.append(position)
    print(page_one_position_list)

if __name__ == '__main__':
    parse_url()

转载于:https://www.cnblogs.com/miaosixian/p/11289394.html