mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-06-01 15:37:26 +08:00
feat: B站爬虫签名实现
This commit is contained in:
71
media_platform/bilibili/help.py
Normal file
71
media_platform/bilibili/help.py
Normal file
@@ -0,0 +1,71 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2023/12/2 23:26
|
||||
# @Desc : bilibili 请求参数签名
|
||||
# 逆向实现参考:https://socialsisteryi.github.io/bilibili-API-collect/docs/misc/sign/wbi.html#wbi%E7%AD%BE%E5%90%8D%E7%AE%97%E6%B3%95
|
||||
import urllib.parse
|
||||
from hashlib import md5
|
||||
from typing import Dict
|
||||
|
||||
from tools import utils
|
||||
|
||||
|
||||
class BilibiliSign:
|
||||
def __init__(self, img_key: str, sub_key: str):
|
||||
self.img_key = img_key
|
||||
self.sub_key = sub_key
|
||||
self.map_table = [
|
||||
46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35, 27, 43, 5, 49,
|
||||
33, 9, 42, 19, 29, 28, 14, 39, 12, 38, 41, 13, 37, 48, 7, 16, 24, 55, 40,
|
||||
61, 26, 17, 0, 1, 60, 51, 30, 4, 22, 25, 54, 21, 56, 59, 6, 63, 57, 62, 11,
|
||||
36, 20, 34, 44, 52
|
||||
]
|
||||
|
||||
def get_salt(self) -> str:
|
||||
"""
|
||||
获取加盐的 key
|
||||
:return:
|
||||
"""
|
||||
salt = ""
|
||||
mixin_key = self.img_key + self.sub_key
|
||||
for mt in self.map_table:
|
||||
salt += mixin_key[mt]
|
||||
return salt[:32]
|
||||
|
||||
def sign(self, req_data: Dict) -> Dict:
|
||||
"""
|
||||
请求参数中加上当前时间戳对请求参数中的key进行字典序排序
|
||||
再将请求参数进行 url 编码集合 salt 进行 md5 就可以生成w_rid参数了
|
||||
:param req_data:
|
||||
:return:
|
||||
"""
|
||||
current_ts = utils.get_unix_timestamp()
|
||||
req_data.update({"wts": current_ts})
|
||||
req_data = dict(sorted(req_data.items()))
|
||||
req_data = {
|
||||
# 过滤 value 中的 "!'()*" 字符
|
||||
k: ''.join(filter(lambda ch: ch not in "!'()*", str(v)))
|
||||
for k, v
|
||||
in req_data.items()
|
||||
}
|
||||
query = urllib.parse.urlencode(req_data)
|
||||
salt = self.get_salt()
|
||||
wbi_sign = md5((query + salt).encode()).hexdigest() # 计算 w_rid
|
||||
req_data['w_rid'] = wbi_sign
|
||||
# print(urllib.parse.urlencode(req_data))
|
||||
return req_data
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
_img_key = "7cd084941338484aae1ad9425b84077c"
|
||||
_sub_key = "4932caff0ff746eab6f01bf08b70ac45"
|
||||
_search_url = "category_id=&search_type=video&ad_resource=5654&__refresh__=true&_extra=&context=&page=1&page_size=42&order=click&from_source=&from_spmid=333.337&platform=pc&highlight=1&single_column=0&keyword=python&qv_id=OQ8f2qtgYdBV1UoEnqXUNUl8LEDAdzsD&source_tag=3&gaia_vtoken=&dynamic_offset=0&web_location=1430654"
|
||||
_req_data = dict()
|
||||
for params in _search_url.split("&"):
|
||||
kvalues = params.split("=")
|
||||
key = kvalues[0]
|
||||
value = kvalues[1]
|
||||
_req_data[key] = value
|
||||
print("pre req_data", _req_data)
|
||||
_req_data = BilibiliSign(img_key=_img_key, sub_key=_sub_key).sign(req_data=_req_data)
|
||||
print(_req_data)
|
||||
Reference in New Issue
Block a user