|
小红书web端的cookie包含4个参数：xhsTrackerId， extra_exp_ids， timestamp2， timestamp2.sig。 前面两个参数直接携带请求小红书主页即可获取，后两个需要携带data两个参数做post请求获取。  如上图，id是经由sign字符加密而来，sign是由UA、版本号、还有一些不知何物的字符拼接组成。下面是抠出来的js代码，用以填入sign生成id
function get_id() {
for (y = function(t) {
for (var e, n = t.length, r = n + 8, o = 16 * ((r - r % 64) / 64 + 1), i = Array(o - 1), a = 0, c = 0; c
var r = t.charCodeAt(n);
r > 12 | 224),
e += String.fromCharCode(r >> 6 & 63 | 128)),
e += String.fromCharCode(63 & r | 128))
}
return e
}("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36~~~false~~~zh-CN~~~24~~~8~~~4~~~-480~~~Asia/Taipei~~~1~~~1~~~1~~~1~~~unknown~~~Win32~~~PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Chrome PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Chromium PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Microsoft Edge PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,WebKit built-in PDF::Portable Document Format::application/pdf~pdf,text/pdf~pdf~~~canvas winding:yes~canvas fp:10cfbbb02b2606dbc2ccb15a3cd2b558~~~false~~~false~~~false~~~false~~~false~~~0;false;false~~~4;7;8~~~124.04347527516074hasaki")),
d = 1732584193,
v = 4023233417,
h = 2562383102,
g = 271733878,
a = 0;
a
var e, n = "",
r = "";
for (e = 0; e >> 8 * e & 255).toString(16)).substr(r.length - 2, 2);
return n
}
function o(t, e, n, r, o, i, a) {
return u(c(t = u(t, u(u(n ^ (e | ~r), o), a)), i), e)
}
function e(t, e, n, r, o, i, a) {
return u(c(t = u(t, u(u(e & n | ~e & r, o), a)), i), e)
}
function n(t, e, n, r, o, i, a) {
return u(c(t = u(t, u(u(e & r | n & ~r, o), a)), i), e)
}
function r(t, e, n, r, o, i, a) {
return u(c(t = u(t, u(u(e ^ n ^ r, o), a)), i), e)
}
function c(t, e) {
return t > 32 - e
}
执行get_id函数即可得到加密结果  其实id跟sign写死也可以，哈哈哈。贴个python代码
def get_xhs_cookie(proxies):
url = 'https://www.xiaohongshu.com'
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36',
}
xhs_cookie = ''
res = requests.get(url, headers=headers, verify=False, proxies=proxies, timeout=10)
cookies = res.headers['Set-Cookie'].split(';')
for cookie in cookies:
re_str1 = re.search('xhsTrackerId', cookie)
re_str2 = re.search('extra_exp_ids', cookie)
if re_str1 or re_str2:
xhs_cookie += cookie
xhs_cookie += ';'
url = 'https://www.xiaohongshu.com/fe_api/burdock/v2/shield/registerCanvas?p=cc'
headers = {
'Cookie': xhs_cookie,
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36',
}
print(xhs_cookie)
data = {
'id': "79c4bb50cddbc552b754f642f33a220b",
'sign': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36~~~false~~~zh-CN~~~24~~~8~~~4~~~-480~~~Asia/Taipei~~~1~~~1~~~1~~~1~~~unknown~~~Win32~~~PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Chrome PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Chromium PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Microsoft Edge PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,WebKit built-in PDF::Portable Document Format::application/pdf~pdf,text/pdf~pdf~~~canvas winding:yes~canvas fp:10cfbbb02b2606dbc2ccb15a3cd2b558~~~false~~~false~~~false~~~false~~~false~~~0;false;false~~~4;7;8~~~124.04347527516074" # 'sign':"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0~~~false~~~zh-CN~~~24~~~8~~~4~~~-480~~~Asia/Taipei~~~1~~~1~~~1~~~1~~~unknown~~~Win32~~~PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Chrome PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Chromium PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,Microsoft Edge PDF Viewer::Portable Document Format::application/pdf~pdf,text/pdf~pdf,WebKit built-in PDF::Portable Document Format::application/pdf~pdf,text/pdf~pdf~~~canvas winding:yes~canvas fp:10cfbbb02b2606dbc2ccb15a3cd2b558~~~false~~~false~~~false~~~false~~~false~~~0;false;false~~~4;7;8~~~124.04347527516074hasaki"
}
res = requests.post(url, headers=headers, data=data, verify=False, proxies=proxies, timeout=10)
cookies = res.headers['Set-Cookie'].split(';')
for cookie in cookies:
re_str1 = re.search('timestamp2', cookie)
if re_str1:
xhs_cookie += cookie
xhs_cookie += ';'
print(xhs_cookie)
return xhs_cookie
代码加了代理，工作需要。不想要可以直接去掉代理，但小红书web端爬多了也会弹滑块，最简单的方法就是挂代理去执行生成过程。
|