python3拉勾網爬蟲之（您操作太頻繁，請稍后訪問）

你是否經歷過這個：

那就對了~
因為需要post和相關的cookie來請求~
所以，一個簡單的代碼爬拉鈎~~~

import requests
import time
import json


def main():
    url_start = "https://www.lagou.com/jobs/list_運維?city=%E6%88%90%E9%83%BD&cl=false&fromSearch=true&labelWords=&suginput="
    url_parse = "https://www.lagou.com/jobs/positionAjax.json?city=成都&needAddtionalResult=false"
    headers = {
        'Accept': 'application/json, text/javascript, */*; q=0.01',
        'Referer': 'https://www.lagou.com/jobs/list_%E8%BF%90%E7%BB%B4?city=%E6%88%90%E9%83%BD&cl=false&fromSearch=true&labelWords=&suginput=',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
    }
    for x in range(1, 5):
        data = {
            'first': 'true',
            'pn': str(x),
            'kd': '運維'
                }
        s = requests.Session() # 創建一個session對象
        s.get(url_start, headers=headers, timeout=3)  # 用session對象發出get請求，請求首頁獲取cookies
        cookie = s.cookies  # 為此次獲取的cookies
        response = s.post(url_parse, data=data, headers=headers, cookies=cookie, timeout=3)  # 獲取此次文本
        time.sleep(5)
        response.encoding = response.apparent_encoding
        text = json.loads(response.text)
        info = text["content"]["positionResult"]["result"]
        for i in info:
            print(i["companyFullName"])
            companyFullName = i["companyFullName"]
            print(i["positionName"])
            positionName = i["positionName"]
            print(i["salary"])
            salary = i["salary"]
            print(i["companySize"])
            companySize = i["companySize"]
            print(i["skillLables"])
            skillLables = i["skillLables"]
            print(i["createTime"])
            createTime = i["createTime"]
            print(i["district"])
            district = i["district"]
            print(i["stationname"])
            stationname = i["stationname"]

if __name__ == '__main__':
    main()