python爬取bilibili校园招聘网站

Question

我的任务是爬取招聘网站，于是我选择了哔哩哔哩的校园招聘网站

这是我的程序代码

import requests
import pandas as pd


url="https://jobs.bilibili.com/api/campus/position/positionList"
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36 Edg/122.0.0.0',
    'Cookie': 'i-wanna-go-back=-1; FEED_LIVE_VERSION=V8; buvid4=550D880A-1CB9-1664-25A1-F1117788A69011197-023050922-AxNIFF5DjNAxs7K6kvypyQ%3D%3D; buvid_fp=ea251a3c8679523cc28f41599b8bde57; CURRENT_BLACKGAP=0; rpdid=|(JYl~)Ylkuk0J\'uY)JYRJ|JR; b_ut=5; header_theme_version=CLOSE; enable_web_push=DISABLE; PVID=3; CURRENT_FNVAL=4048; CURRENT_QUALITY=112; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MTU0MTYxOTIsImlhdCI6MTcxNTE1NjkzMiwicGx0IjotMX0.uHjB2gDiqkcBLjQnO3G3B6WUE3wDKt2rdvualSijqYs; bili_ticket_expires=1715416132; SESSDATA=a5775916%2C1730725427%2Cd6873%2A51CjCE7jgCfZ-fD_4CNQOGkUhuIDGqa6O4RfW9xxRC5WETQ6Mcm0kRNKyIGmrMNRXhCjkSVjRUMGx1eGJIakJBQTlGU3Bfa0lqejFQOFU2TkxBc2cyMTAtcFN1al8wQUdIZ0dyX0t5X0cwVmNWTGotMldtOEFFVEpTTDM3UjV1YnpPTTFWdjE4NjJRIIEC; bili_jct=31ba1f87e551b419ae4449481795e379; DedeUserID=40761336; DedeUserID__ckMd5=b2b5f4025124b58b; sid=672rwk29; home_feed_column=5; browser_resolution=1488-742; _uuid=64DD6463-9495-D6101-2941-F385E93D7BA502613infoc; buvid3=788EC87C-9934-1078-057E-6516A00C7AC638273infoc; b_nut=1715180903; bsource=search_bing'
}
p={    'pageSize': 10,
    'pageNum': 1,
    'positionName': '',
    'postCode': [],
    'postCodeList': [],
    'workLocationList': [],
    'deptCodeList': [],
    'positionTypeList': ['3'],
    'practiceTypes': [],
    'recruitType': "null",
    'workTypeList': ['3'],
            }
rs = requests.post(url, data=p, headers=headers, verify=False)

print(rs)
print(rs.text)
#{"code":-101,"data":null,"message":"ajSessionId不能为空"}

这是我的输出结果

请问我应该怎么解决哇，谢谢各位

我想要有用的回答，机器人能不能不要来哇

Answer 1

把请求头写全

import requests
import pandas as pd

cookies = {
    'buvid3': 'D85133D4-A6B8-0710-BF23-F86C0B0523FF32408infoc',
    'b_nut': '1699100432',
    '_uuid': 'D5BB523B-26DC-10A510-B419-E3C6F46C5C4233754infoc',
    'buvid4': 'A8F9DED3-D440-C8D8-28F0-A04B97B327A992567-023102911-ocwwVqjadHK7Sbj6XtFVfV3VFLVUR1DMMN7RySqpWuB4tMzdcYqDbw%3D%3D',
    'rpdid': '0zbfVFQ4gw|2W4N8tSG|3q3|3w1R1OZQ',
    'buvid_fp_plain': 'undefined',
    'DedeUserID': '397021855',
    'DedeUserID__ckMd5': '0d9635cf054040a1',
    'hit-dyn-v2': '1',
    'fingerprint': '152b8d5afe96137987381d0b7edd5ad5',
    'buvid_fp': '152b8d5afe96137987381d0b7edd5ad5',
    'CURRENT_FNVAL': '4048',
    'PVID': '2',
    'CURRENT_QUALITY': '80',
    'bp_video_offset_397021855': '911546318273380352',
    'OUTFOX_SEARCH_USER_ID_NCOO': '1785815010.8805866',
    'SESSDATA': '4b09897b%2C1730729182%2C97669%2A52CjDFLUgjd774gedHo_nk4ec5blFLmUq7hmuHlmzv37D_iHOC-or1FPnGZR4IQaYOgHoSVjd4RzhhTEhQRXhQWDFuUl9hMkp6VkdqdlQzOXFCYko1elZQT2dobzdUeHY5cHF3WjRfdlpRc1dMSW5jZlVhc25DZ1o3QWlPWldRYnhqdmtVTjRYUFpnIIEC',
    'bili_jct': '2088f85c8efbb048892970470cc613a6',
    'sid': '6n2a9yco',
    'b_lsid': 'D8E7E86E_18F5C929A06',
    'share_source_origin': 'QQ',
    'bsource': 'share_source_qqchat',
    'bili_ticket': 'eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MTU1MDQyNjMsImlhdCI6MTcxNTI0NTAwMywicGx0IjotMX0.l5iaD7teJLyu659XmWKs0Z3UkpGaKrok0sZ5pMs4OI4',
    'bili_ticket_expires': '1715504203',
    'bp_t_offset_397021855': '911546318273380352',
}

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36',
    'x-csrf': '61a269c1-588e-4880-b3cf-c4fdae079470',
    'x-usertype': '4',
}

json_data = {
    'pageSize': 10,
    'pageNum': 1,
    'positionName': '',
    'postCode': [],
    'postCodeList': [],
    'workLocationList': [],
    'workTypeList': [
        '3',
    ],
    'positionTypeList': [
        '3',
    ],
    'deptCodeList': [],
    'recruitType': None,
    'practiceTypes': [],
}

response = requests.post('https://jobs.bilibili.com/api/campus/position/positionList', cookies=cookies, headers=headers, json=json_data)
dd=pd.DataFrame(response.json()['data']['list'])
print(dd['positionName'])