672 字
3 分钟
百度百科X-Bk-Token逆向
地址: 百度百科_全球领先的中文百科全书
JS: https://bkssl.bdimg.com/resource/pages/pc-lemma-search_5755c937.js
API: https://baike.baidu.com/lemma/api/search?enc=utf8&word=双休
具有明确名称的参数(非一个单一字母, 如v, x), 可以先试试全局搜索

没找到就查看发起程序的调用堆栈, 一点点定位; 然后这个函数名就比较”明显”的意图. 很容易就找到了

断点调试逻辑, createApiTokenHeaders函数大概逻辑如下
i = { "pageToken": "RiVzODzhWR_mcU5VnDcW5g", "pageTokenExpireTime": 1750647249, "pageParams": "0"}p = new URL("https://baike.baidu.com/search?enc=utf8&word=%E5%8F%8C%E4%BC%91")x = JSON.stringify({ pageUrl: Number(i.pageParams) ? p.pathname : p.pathname + p.search, // "/search?enc=utf8&word=%E5%8F%8C%E4%BC%91" expireTime: i.pageTokenExpireTime})k = o.HmacSHA256("/lemma/api/searchenc=utf8&word=%E5%8F%8C%E4%BC%91", i.pageToken).toString(o.enc.Base64url)S = o.enc.Base64url.stringify(o.enc.Utf8.parse(x))X-Bk-Token = "".concat(S, ".").concat(k)i是通过函数y返回的, 继续的还原i的生成逻辑, y函数中获取了html中的两个值

调试分析逻辑, 大致逻辑如下
<meta name="visit-id" content="05451938112522025242564761020552325305301355" data-use-parmas="0"><meta name="visit-time" content="1750649085">
pageTokenExpireTime = Number(<visit-time>)pageParams = <data-use-parmas>
p = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_-'l = pageTokenExpireTime % p.lengthc = p.slice(l) + p.slice(0,l)// 原逻辑使用对象做映射, 比较麻烦// s = {}// c.split("").map((x,i) => {// key = i.toString().padStart(2, '0')// s[key] = x// })// // 每两位分割// f = visit_id.match(/.{1,2}/g)// pageToken = f.map(x => s[x]).join("")// 更简洁的写法, 以数组索引作为映射s = c.split("")f = visit_id.match(/.{1,2}/g)pageToken = f.map(x => s[Number(x)]).join("")转为Python后, 一步一步与网页断点生成的值校验对比是否一致;
经过对比一致, 表明算法无问题, 但是生成的X-Bk-Token无法使用;
实际整体请求经过两次请求,
第一次: https://baike.baidu.com/search 返回 visit-id 相关信息
第二次: https://baike.baidu.com/lemma/api/search 返回最终数据
关键点在于 两个请求需要携带一个共同的cookie BAIDUID_BFESS串联, 否则生成的请求无法使用
完整代码如下
import refrom bs4 import BeautifulSoupimport requestsimport jsonimport urllib.parseimport hmacimport hashlibimport base64cookies = { 'BAIDUID_BFESS': 'D6142F2E6FF25FF7CF112FED00000B0F:FG=1',}headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36 Edg/137.0.0.0',}
params = { 'enc': 'utf8', 'word': '双休',}
lemma_url = 'https://baike.baidu.com/lemma/api/search'
response = requests.get('https://baike.baidu.com/search', params=params, cookies=cookies, headers=headers)
print(response.status_code, response.url)
soup = BeautifulSoup(response.text, 'html.parser')visit_id = soup.find('meta', attrs={'name': 'visit-id'}).get('content')pageTokenExpireTime = int(soup.find('meta', attrs={'name': 'visit-time'}).get('content'))pageParams = soup.find('meta', attrs={'name': 'visit-id'}).get('data-use-parmas')# visit_id = '47023738254900123118194151080063185628602011'# pageTokenExpireTime = 1750672217# pageParams = "0"
character_set = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_-'l = pageTokenExpireTime % len(character_set)s = character_set[l:] + character_set[:l]print("s: ", s)s = list(s)# 每两位分割f = re.findall(r'.{1,2}', visit_id)# 映射并生成 pageTokenpageToken = ''.join(map(lambda x : s[int(x)], f))
print(visit_id, pageTokenExpireTime, pageParams)print("pageToken: ", pageToken)
p = urllib.parse.urlparse(response.url)page_url = p.path if int(pageParams) else p.path + "?" + p.query
# 生成 JSON 字符串 xx = json.dumps({ "pageUrl": page_url, "expireTime": pageTokenExpireTime}, separators=(",",":"))print(x)# '{"pageUrl":"/search?enc=utf8&word=%E5%8F%8C%E4%BC%91","expireTime":1750668767}'# 生成 HMAC-SHA256 签名 kkey = pageToken.encode('utf-8')
lemma_path = urllib.parse.urlparse(lemma_url).pathlemma_params = urllib.parse.urlencode(params)message = (lemma_path+lemma_params).encode('utf-8')print(message)hmac_hash = hmac.new(key, message, hashlib.sha256).digest()k = base64.urlsafe_b64encode(hmac_hash).decode('utf-8').rstrip('=')print("k: ", k)# 2gKbcIfD7n8XRsnYL9GY_skWswAaUk0-dy51U8LQmEc
# 生成 Base64 URL 编码的字符串 SS = base64.urlsafe_b64encode(x.encode('utf-8')).decode('utf-8').rstrip('=')print("S: ", S)# eyJwYWdlVXJsIjoiL3NlYXJjaD9lbmM9dXRmOCZ3b3JkPSVFNSU4RiU4QyVFNCVCQyU5MSIsImV4cGlyZVRpbWUiOjE3NTA2Njg3Njd9
# 生成 X-Bk-TokenX_Bk_Token = f"{S}.{k}"
print(f"X-Bk-Token: {X_Bk_Token}")
headers.update({ 'X-Bk-Token': X_Bk_Token})response = requests.get(lemma_url, params=params, cookies=cookies, headers=headers)print(response.status_code, response.url)
print(response.text)
百度百科X-Bk-Token逆向
https://blog.tiamix.cn/posts/百度百科x-bk-token逆向/