feat(collect): 纯离线生成打通 1ms 签到文字点选 —— errorCode=0 收口

做了什么:
- 新增 tcaptcha/tdc_values.py: 37 个语义名的取值生成器(静态画像 / 会话量 /
  每次采集量三层)+ build_plain 四段组装 + generate_collect 纯离线出包
- crypto: 新增 generate_telemetry(mode="python_values");轨迹生成统一到
  trajectory_points()(首点绝对坐标 + 增量 + 固定收尾 [1,1,12])
- crypto.split_collect_segments 重写: pad 只有 1 个空格时旧 ` {2,}` 判据会漏段,
  且 UA 串里的普通空格会假阳性 —— 改为「模 24 算术 + 不落在 JSON 字符串内部 + 结构校验」
- tools/tdc_modules: trajectory 指纹原先指向只做 JSON.stringify 的模块,改为
  mouseMoveEvent/touchStartEvent(真轨迹模块),37/37 不变
- client 默认 telemetry_mode 改为 python_values
- 新增 scripts/verify/{align_session,audit_names,verify_values,verify_offline,send_test}.py
  与 tools/{cdp_collect,cdp_dump_scripts,tdc_profile}.py

为什么:
- 账本 #40「谁在发 HTTP 是 12 的剩余自变量」被推翻。同 aid/同客户端/同求解器、
  答案都对,只换 collect 构造方式: 本次会话构建生成 -> 0 (4/4),
  旧模板回填 -> 12 (2/2)。真因是 collect 必须与本次会话构建同源。

怎么验证:
- .venv/bin/python -m tcaptcha.selftest  全绿(含新增四段切分与纯离线闭环回归)
- scripts/verify/verify_values.py        4 份真机明文 152/152 逐槽全等
- scripts/verify/verify_offline.py       逐槽全等 + 分段几何一致
- scripts/verify/send_test.py --mode python_values  1ms 签到页文字点选 errorCode=0 x4
This commit is contained in:
yml2213
2026-10-12 03:38:18 +08:00
parent 80a122245a
commit 51dff870cf
18 changed files with 2102 additions and 91 deletions
+103
View File
@@ -0,0 +1,103 @@
#!/usr/bin/env node
/**
* cdp_dump_scripts.js —— 把某个 target 里**所有已解析脚本**逐个导出并标注特征。
*
* 为什么需要(2026-10-12 踩坑):
* cdp_script_source.js 取的是 `hits[hits.length-1]`(最后一个匹配),
* 在验证码 iframe(同 target 里有 dy-jy.js / dy-ele.js / tdc.js 多个脚本)里
* **可能取错**。有一次取到的 205KB 文件既没有 __TENCENT_CHAOS_VM 也没有 delta,
* 根本不是 tdc.js。
*
* 本工具: 一律全量导出 + 对每个脚本标注是否含 VM 锚点 / delta / 长度,绝不猜。
*
* 用法:
* node tools/cdp_dump_scripts.js --match drag_ele --outdir /tmp/1ms_bridge/scripts
*/
const fs = require('fs');
const path = require('path');
function arg(name, def) {
const i = process.argv.indexOf('--' + name);
if (i < 0) return def;
const v = process.argv[i + 1];
return (v === undefined || v.startsWith('--')) ? true : v;
}
const sleep = ms => new Promise(r => setTimeout(r, ms));
class Cdp {
constructor(ws) { this.ws = ws; this.id = 0; this.waits = new Map(); this.handlers = []; }
static async connect(url) {
const ws = new WebSocket(url);
await new Promise((res, rej) => { ws.onopen = res; ws.onerror = rej; });
const c = new Cdp(ws);
ws.onmessage = ev => {
const m = JSON.parse(ev.data);
if (m.id && c.waits.has(m.id)) {
const { res, rej } = c.waits.get(m.id);
c.waits.delete(m.id);
m.error ? rej(new Error(JSON.stringify(m.error))) : res(m.result);
} else if (m.method) { for (const h of c.handlers) h(m); }
};
return c;
}
send(method, params = {}) {
const id = ++this.id;
this.ws.send(JSON.stringify({ id, method, params }));
return new Promise((res, rej) => this.waits.set(id, { res, rej }));
}
on(fn) { this.handlers.push(fn); }
close() { try { this.ws.close(); } catch (e) {} }
}
(async () => {
const port = parseInt(arg('port', '9222'), 10);
const match = arg('match', null);
const outdir = arg('outdir', '/tmp/cdp_scripts');
const wait = parseInt(arg('wait', '2000'), 10);
const targets = (await (await fetch(`http://127.0.0.1:${port}/json/list`)).json())
.filter(t => t.type === 'page' || t.type === 'iframe');
const target = match ? targets.find(t => (t.url || '').includes(match)) : targets[0];
if (!target) throw new Error('没有匹配的 target: ' + match);
console.error(`[target] ${target.type} ${target.url.slice(0, 90)}`);
const cdp = await Cdp.connect(target.webSocketDebuggerUrl);
const scripts = [];
cdp.on(m => { if (m.method === 'Debugger.scriptParsed') scripts.push(m.params); });
await cdp.send('Debugger.enable');
await sleep(wait);
await cdp.send('Runtime.enable');
await cdp.send('Runtime.evaluate', { expression: '1' });
await sleep(500);
fs.mkdirSync(outdir, { recursive: true });
const index = [];
const seen = new Set();
for (const s of scripts) {
if (seen.has(s.scriptId)) continue;
seen.add(s.scriptId);
let src = '';
try {
const r = await cdp.send('Debugger.getScriptSource', { scriptId: s.scriptId });
src = r.scriptSource || '';
} catch (e) { continue; }
if (!src) continue;
const hasVM = src.includes('__TENCENT_CHAOS_VM');
const hasDelta = src.includes('2654435769');
const hasTDCNAME = src.includes('TDC_NAME');
const base = (s.url || 'inline').split('?')[0].split('/').pop() || 'inline';
const fn = `${String(s.scriptId).replace(/[^\w.-]/g, '_')}_${base}`.slice(0, 80);
fs.writeFileSync(path.join(outdir, fn), src, 'utf8');
index.push({
scriptId: s.scriptId, url: String(s.url || '(inline)').slice(0, 130),
bytes: src.length, hasVM, hasDelta, hasTDCNAME, file: fn,
});
}
fs.writeFileSync(path.join(outdir, 'index.json'), JSON.stringify(index, null, 1), 'utf8');
for (const r of index) {
console.log(`${r.hasVM ? 'VM ' : ' '}${r.hasDelta ? 'DELTA' : ' '}`
+ ` ${String(r.bytes).padStart(7)}B ${r.url}`);
}
console.error(`\n-> ${outdir} (共 ${index.length} 个脚本, 含 VM 的 ${index.filter(x => x.hasVM).length} 个)`);
cdp.close();
})().catch(e => { console.error('ERR', e.message); process.exit(1); });