56 lines
1.8 KiB
Python
56 lines
1.8 KiB
Python
# -*- encoding:utf-8 -*-
|
||
|
||
'''
|
||
@Author : dingjiawen
|
||
@Date : 2024/03/26 20:32
|
||
@Usage : 使用Python实现列表页的爬取
|
||
@Desc : 使用逆向分析之后，已经基本确定了token的生成逻辑：
|
||
- 将`/api/movie `放到一个列表里
|
||
- 在列表中加人当前时间戳;
|
||
- 将列表内容用逗号拼接;
|
||
- 将拼接的结果进行 SHA1 编码;
|
||
- 将编码的结果和时间戳再次拼接;
|
||
- 将拼接后的结果进行 Base64 编码。
|
||
'''
|
||
|
||
import hashlib
|
||
import time
|
||
import base64
|
||
from typing import Any, List
|
||
|
||
import requests
|
||
|
||
BASE_URL = 'https://spa6.scrape.center'
|
||
INDEX_URL = BASE_URL + "/api/movie?limit={limit}&offset={offset}&token={token}"
|
||
DETAIL_URL = BASE_URL + "/api/movie/{id}?token={token}"
|
||
SECRET = 'ef34#teuq0btua#(-57w1q5o5--j@98xygimlyfxs*-!i-0-mb'
|
||
MAX_PAGE = 10
|
||
LIMIT = 10
|
||
|
||
|
||
def generate_token(args: List[Any]):
|
||
cur_time = str(int(time.time()))
|
||
args.append(cur_time)
|
||
sign = hashlib.sha1(','.join(args).encode('utf-8')).hexdigest()
|
||
return base64.b64encode(','.join([sign, cur_time]).encode('utf-8')).decode('utf-8')
|
||
|
||
|
||
# 爬取列表页(这里暂时只爬取)
|
||
for i in range(MAX_PAGE):
|
||
args = ['/api/movie']
|
||
token = generate_token(args)
|
||
OFFSET = i * LIMIT
|
||
url = INDEX_URL.format(limit=LIMIT, offset=OFFSET, token=token)
|
||
response = requests.get(url)
|
||
print('response:', response.json())
|
||
result = response.json()
|
||
|
||
# 爬取详情页
|
||
for movie in result['results']:
|
||
id = movie['id']
|
||
encrypt_id = base64.b64encode((SECRET + str(id)).encode('utf-8')).decode('utf-8')
|
||
args = [f'/api/movie/{encrypt_id}']
|
||
detail_url = DETAIL_URL.format(id=encrypt_id, token=generate_token(args))
|
||
response = requests.get(detail_url)
|
||
print(response.json())
|