抓包 代码

# ！user/bin/env python3
# -*-coding: utf-8 -*-
__author__ = 'xxx'

import requests
import re
import json


def handle(page):
    r = requests.get(
        'https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1571759757407&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=&attrId=&keyword=&pageIndex={}&pageSize=10&language=zh-cn&area=cn'.format(
            page)).content.decode('utf-8')
    # print(r)
    urls = re.findall(r'"PostId":"(\d+)","RecruitPostId"', r, re.S)
    # print(urls)
    for url in urls:
        new_url = 'https://careers.tencent.com/tencentcareer/api/post/ByPostId?timestamp=1571760048441&postId={}&language=zh-cn'.format(
            url)
        new_r = requests.get(new_url).content.decode()
        # print(new_r)
        position = re.findall(r'"RecruitPostName":"(.*?)","LocationId"', new_r, re.S)
        contents = re.findall(r'"Responsibility":"(.*?)","Requirement":"(.*?)","LastUpdateTime"', new_r, re.S)
        # print(position, content[0], content[-1])
        # print(len(content))
        # print(content)
        content = contents.__str__().split(',')
        responsibility = content[0].__str__().replace('\\n', '').replace('\\r', '').replace(', ', '').replace('\\', '')
        requirement = content[-1].__str__().replace('\\n', '').replace('\\r', '').replace(', ', '').replace('\\', '')
        print(position, responsibility, requirement)
        data = {
            '职责': position,
            '义务': responsibility,
            '需求': requirement,
        }
        with open('feizhai3.json', 'a+', encoding='utf-8') as f:
            json.dump(data, f, ensure_ascii=False, indent=4)


if __name__ == '__main__':
    for page in range(1, 412):
        handle(page)