Question

我仍然是网络抓取的初学者，我正在尝试从 API 中提取数据，但问题是它有一个不记名令牌，并且此令牌在 5 到 6 小时后更改，因此我必须再次访问网页并再次复制令牌那么有什么方法可以提取数据而无需再打开网页并再次复制令牌

import json
import pandas as pd
from time import sleep


def make_request():
    headers = {
        'Connection': 'keep-alive',
        'Pragma': 'no-cache',
        'Cache-Control': 'no-cache',
        'sec-ch-ua': '^\\^',
        'Accept': 'application/json',
        'Authorization': 'Bearer eyJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJMdXRiZlZRUVZhWlpmNTNJbGxhaXFDY3BCVTNyaGtqZiIsInN1YiI6MzEzMTcwLCJleHAiOjE2MjQzMjU2NDcsInJvbCI6ImRpc3BhdGNoZXIiLCJyb2xlcyI6WyJodXJyaWVyLmRpc3BhdGNoZXIiLCJjb2QuY29kX21hbmFnZXIiXSwibmFtIjoiRXNsYW0gWmVmdGF3eSIsImVtYSI6ImV6ZWZ0YXd5QHRhbGFiYXQuY29tIiwidXNlcm5hbWUiOiJlemVmdGF3eUB0YWxhYmF0LmNvbSIsImNvdW50cmllcyI6WyJrdyIsImJoIiwicWEiLCJhZSIsImVnIiwib20iLCJqbyIsInEyIiwiazMiXX0.XYykBij-jaiIS_2tdqKFIfYGfw0uS0rKmcOTSHor8Nk',
        'sec-ch-ua-mobile': '?0',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36',
        'Content-Type': 'application/json;charset=UTF-8',
        'Origin': 'url',
        'Sec-Fetch-Site': 'same-origin',
        'Sec-Fetch-Mode': 'cors',
        'Sec-Fetch-Dest': 'empty',
        'Referer': 'url',
        'Accept-Language': 'en-US,en;q=0.9,ar-EG;q=0.8,ar;q=0.7',
        'dnt': '1',
    }

    
    data = {
        'status': 'picked'
    }
    response = requests.post('url/api', headers=headers, json=data)
    print(response.text)

    return json.loads(response.text)


def extract_data(row):
    data_row = {
        'order_id': row['order']['code'],
        'deedline': row['order']['deadline'].split('.')[0],
        'picked_at': row['picked_at'].split('.')[0],
        'picked_by': row['picked_by'],
        'processed_at': row['processed_at'],
        'type': row['type']
    }
    return data_row



def periodique_extract(delay):
    extract_count = 0
    while True:
        extract_count += 1
        data = make_request()
        if extract_count == 1 :
            df = pd.DataFrame([extract_data(row) for row in data['data']])
            df.to_csv(r"C:\Users\di\Desktop\New folder\a.csv", mode='a')
        else:
            df = pd.DataFrame([extract_data(row) for row in data['data']])
            df.to_csv(r"C:\Users\di\Desktop\New folder\a.csv", mode='a',header=False)
        print('exracting data {} times'.format(extract_count))
        sleep(delay)


periodique_extract(60)

#note: as the website is track live operation so I extract data every 1 min

Answer 1

您能否详细说明令牌，它是每 5-6 小时更改一次还是过期？您的问题不清楚，您能否详细说明如何首先生成令牌？您的服务可能有 refresh_token，使用它来获取新令牌而无需返回您的网站。

使用 Bearer 令牌从 API 请求数据

1 个答案: