初始提交：抖音视频批量采集流水线

App 端免签名接口（设备注册 + detail + CDN 直链），一体化流水线下载→抽音→传COS→记录→删本地，AI 作品四档判定，四份文档： README（使用指南）、PROGRESS（批次进度）、RE（逆向全过程）、AI（判定规则）。 Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-09-29 16:31:10 +08:00
commit 2bb83f3685
39 changed files with 298874 additions and 0 deletions
--- a/douyin/crypto.py
+++ b/douyin/crypto.py
@@ -0,0 +1,179 @@
+"""a_bogus 依赖的底层密码学原语：SM3、RC4、自定义 Base64。
+
+这三样都是公开算法，与抖音无关，可以独立验证正确性：
+  - SM3  见 GB/T 32905-2016，本文件底部带官方测试向量自检
+  - RC4  标准流密码
+  - 自定义 Base64 只是把标准码表换成抖音自己那套字符顺序
+"""
+
+from __future__ import annotations
+
+from typing import Iterable, List, Sequence
+
+# --------------------------------------------------------------------------- #
+# SM3
+# --------------------------------------------------------------------------- #
+
+_IV = [
+    0x7380166F, 0x4914B2B9, 0x172442D7, 0xDA8A0600,
+    0xA96F30BC, 0x163138AA, 0xE38DEE4D, 0xB0FB0E4E,
+]
+_MASK = 0xFFFFFFFF
+
+
+def _rotl(x: int, n: int) -> int:
+    n &= 31
+    return ((x << n) | (x >> (32 - n))) & _MASK
+
+
+def _ff(j: int, x: int, y: int, z: int) -> int:
+    return (x ^ y ^ z) if j < 16 else ((x & y) | (x & z) | (y & z))
+
+
+def _gg(j: int, x: int, y: int, z: int) -> int:
+    return (x ^ y ^ z) if j < 16 else ((x & y) | ((~x & _MASK) & z))
+
+
+def _p0(x: int) -> int:
+    return x ^ _rotl(x, 9) ^ _rotl(x, 17)
+
+
+def _p1(x: int) -> int:
+    return x ^ _rotl(x, 15) ^ _rotl(x, 23)
+
+
+def _cf(v: Sequence[int], block: bytes) -> List[int]:
+    """压缩函数 CF(V, B)。"""
+    w = [int.from_bytes(block[i * 4:i * 4 + 4], "big") for i in range(16)]
+    for j in range(16, 68):
+        w.append(
+            _p1(w[j - 16] ^ w[j - 9] ^ _rotl(w[j - 3], 15))
+            ^ _rotl(w[j - 13], 7)
+            ^ w[j - 6]
+        )
+    w1 = [w[j] ^ w[j + 4] for j in range(64)]
+
+    a, b, c, d, e, f, g, h = v
+    for j in range(64):
+        t = 0x79CC4519 if j < 16 else 0x7A879D8A
+        ss1 = _rotl((_rotl(a, 12) + e + _rotl(t, j)) & _MASK, 7)
+        ss2 = ss1 ^ _rotl(a, 12)
+        tt1 = (_ff(j, a, b, c) + d + ss2 + w1[j]) & _MASK
+        tt2 = (_gg(j, e, f, g) + h + ss1 + w[j]) & _MASK
+        d = c
+        c = _rotl(b, 9)
+        b = a
+        a = tt1
+        h = g
+        g = _rotl(f, 19)
+        f = e
+        e = _p0(tt2)
+
+    return [x ^ y for x, y in zip(v, (a, b, c, d, e, f, g, h))]
+
+
+def sm3(data: bytes) -> bytes:
+    """SM3 摘要，返回 32 字节。"""
+    bit_len = len(data) * 8
+    padded = data + b"\x80"
+    padded += b"\x00" * ((56 - len(padded) % 64) % 64)
+    padded += bit_len.to_bytes(8, "big")
+
+    v = list(_IV)
+    for i in range(0, len(padded), 64):
+        v = _cf(v, padded[i:i + 64])
+    return b"".join(x.to_bytes(4, "big") for x in v)
+
+
+def sm3_to_list(data: bytes | Iterable[int]) -> List[int]:
+    """SM3 摘要，返回 32 个 int（a_bogus 内部按字节数组传递）。"""
+    if not isinstance(data, (bytes, bytearray)):
+        data = bytes(bytearray(data))
+    return list(sm3(bytes(data)))
+
+
+# --------------------------------------------------------------------------- #
+# RC4
+# --------------------------------------------------------------------------- #
+
+def rc4(key: bytes, data: bytes) -> bytes:
+    """标准 RC4。加解密同一函数。"""
+    s = list(range(256))
+    j = 0
+    klen = len(key)
+    for i in range(256):
+        j = (j + s[i] + key[i % klen]) & 0xFF
+        s[i], s[j] = s[j], s[i]
+
+    out = bytearray(len(data))
+    i = j = 0
+    for n, ch in enumerate(data):
+        i = (i + 1) & 0xFF
+        j = (j + s[i]) & 0xFF
+        s[i], s[j] = s[j], s[i]
+        out[n] = ch ^ s[(s[i] + s[j]) & 0xFF]
+    return bytes(out)
+
+
+# --------------------------------------------------------------------------- #
+# 自定义码表 Base64
+# --------------------------------------------------------------------------- #
+
+STD_ALPHABET = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/="
+
+
+def b64_encode(data: bytes, alphabet: str, pad: bool = True) -> str:
+    """按给定 64(+1) 字符码表做 Base64 编码。
+
+    alphabet 长度为 64 时不补位；为 65 时最后一位作为填充字符。
+    """
+    if len(alphabet) not in (64, 65):
+        raise ValueError(f"码表长度必须是 64 或 65，收到 {len(alphabet)}")
+    fill = alphabet[64] if len(alphabet) == 65 else ""
+
+    out: List[str] = []
+    for i in range(0, len(data), 3):
+        chunk = data[i:i + 3]
+        n = int.from_bytes(chunk + b"\x00" * (3 - len(chunk)), "big")
+        quad = [alphabet[(n >> shift) & 0x3F] for shift in (18, 12, 6, 0)]
+        keep = len(chunk) + 1  # 1字节->2字符, 2字节->3字符, 3字节->4字符
+        out.extend(quad[:keep])
+        if pad and fill:
+            out.extend(fill * (4 - keep))
+    return "".join(out)
+
+
+# --------------------------------------------------------------------------- #
+# 自检
+# --------------------------------------------------------------------------- #
+
+# GB/T 32905-2016 附录 A 给出的两组标准测试向量
+_SM3_VECTORS = [
+    (b"abc",
+     "66c7f0f462eeedd9d1f2d46bdc10e4e24167c4875cf2f7a2297da02b8f4ba8e0"),
+    (b"abcd" * 16,
+     "debe9ff92275b8a138604889c18e5a4d6fdb70e5387e5765293dcba39c0c5732"),
+]
+
+
+def self_test() -> None:
+    """跑通即说明 SM3/RC4/Base64 实现无误。"""
+    for msg, want in _SM3_VECTORS:
+        got = sm3(msg).hex()
+        assert got == want, f"SM3({msg[:8]!r}...) = {got}, 期望 {want}"
+
+    # RC4 官方测试向量：key="Key", plaintext="Plaintext" -> BBF316E8D940AF0AD3
+    assert rc4(b"Key", b"Plaintext").hex().upper() == "BBF316E8D940AF0AD3"
+
+    # 用标准码表时，自定义 Base64 应与 base64 模块完全一致
+    import base64
+    import os
+    for n in range(1, 40):
+        raw = os.urandom(n)
+        assert b64_encode(raw, STD_ALPHABET) == base64.b64encode(raw).decode()
+
+    print("crypto self-test OK: SM3 / RC4 / custom-base64 均通过")
+
+
+if __name__ == "__main__":
+    self_test()