Files
dt_audio/data_request/parse-course-list.py
alsesa b10fd0e112 merge
2024-10-14 17:39:25 +08:00

60 lines
1.9 KiB
Python
Executable File

# 爬取学升中的课程目录
import json
import os
import random
import time
import requests
# 使用BearerToken认证
BearerToken = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhdWQiOiIxMDAwMDgzNDciLCJleHAiOjE2OTMwNjMxNTEsImp0aSI6ImUxMGYxMDEyLTY3MDYtNGJiYS1iMTg2LWVmNGViZmVhZDVkMCIsImlhdCI6MTY5MDM4NDc1MSwiaXNzIjoiYXBwdXNlciIsInVpZCI6ImJlMmViOGIyLTFhOTItNGVmMC05ZDAwLTA1YTlkN2E2OWRiMiIsInNjaGVtZSI6Imp3dGhzIiwic2lkIjoiMWI4ZjE1ZTItYjQ5ZC00MmRmLWEwNDUtZmQxYTUwNzI5ZjkxIn0.9TAgxEBSg_Ckbyif8IsC18MMqb9I2qhSwcPbNFk7JhE'
# 请求头
headers = {
'authority': 'bandu-api.songy.info',
'accept': '*/*',
'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
'authorization': 'Bearer ' + BearerToken,
'dnt': '1',
'origin': 'https://webapp.songy.info',
'referer': 'https://webapp.songy.info/',
'sec-ch-ua': '"Not/A)Brand";v="99", "Microsoft Edge";v="115", "Chromium";v="115"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
'sec-fetch-dest': 'empty',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-site',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36 Edg/115.0.1901.188',
}
# 请求参数
params = {
'q': '',
'offset': '0',
'limit': '20',
# 'sort': 'oldest-first',
}
has_more = True
offset = 0
# data_item = []
while(has_more):
time.sleep(1 + random.uniform(0.1, 1.2))
response = requests.get('https://bandu-api.songy.info/v1/communities/80000002/courses', params=params, headers=headers)
data = json.loads(response.text);
# data_item += data['data']['items']
has_more = data['data']['has_more']
offset += 20
print(offset)
params['offset'] = str(offset)
with open(os.path.join('courses.json'), 'a') as file:
file.write(response.text)
# if offset == 40:
# break