feat(web): 新增 Web 观测台（形态 A）+ 抽出 render/targets 共用层
- tcaptcha/web/：FastAPI + SSE + 零构建单页。把同步阻塞的 solve() 包成可观测 后台任务（工作线程 + 全局串行，因 onnxruntime session 非线程安全），用 logging.Handler 零侵入把 client 日志变成事件流；按靶子实测 min_interval 强制节流。 - tcaptcha/render.py：标注图（点击顺序编号 + 质心偏差）与点位量尺，CLI 与 web 共用。 - tcaptcha/targets.py：靶子表提为单一来源（含实测频控间隔 1ms=60s / mliev=3s）。 - fastapi/uvicorn 走 optional extra `web`，核心包零 web 依赖（带回归断言）。 - 修两个真 bug：hook 求解器时 args[0] 是实例自身（真入参从 args[1] 起）； client 默认每次新建 solver，预热实例未被复用（每发重载 56MB ONNX）。 - 复验：icon/text/slider 三题型各拿到 errorCode=0；selftest 全绿；依赖隔离通过。 用法：uv run --extra web python -m tcaptcha.web.app
This commit is contained in:
yml2213
@@ -28,13 +28,11 @@ from __future__ import annotations
|
||||
import argparse
|
||||
import base64
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Sequence, Tuple
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[2]
|
||||
@@ -45,14 +43,9 @@ import tcaptcha.protocol.client as client_mod # noqa: E
|
||||
import tcaptcha.solvers.icon_click as icon_mod # noqa: E402
|
||||
from tcaptcha.protocol.client import (KIND_ICON_CLICK, KIND_SLIDER, # noqa: E402
|
||||
KIND_TEXT_CLICK, TencentCaptchaClient)
|
||||
from tcaptcha.render import annotate_points, icon_centroid_offset # noqa: E402
|
||||
from tcaptcha.targets import TARGETS, get_target # noqa: E402
|
||||
|
||||
# 内置靶子：aid / entry_url / referer / wb
|
||||
TARGETS: Dict[str, Tuple[str, str, str, str]] = {
|
||||
"1ms": ("195672344", "https://1ms.run/console/personal/benefits/check-in",
|
||||
"https://1ms.run/", "1"),
|
||||
"mliev": ("190758559", "https://mliev.login.wang/auth/#/oidc/authorize",
|
||||
"https://mliev.login.wang/", "1"),
|
||||
}
|
||||
KIND_MAP = {
|
||||
"text": (KIND_TEXT_CLICK,),
|
||||
"icon": (KIND_ICON_CLICK,),
|
||||
@@ -60,53 +53,8 @@ KIND_MAP = {
|
||||
"any": (KIND_TEXT_CLICK, KIND_ICON_CLICK, KIND_SLIDER),
|
||||
}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# 「点得准不准」的独立量尺：点击点 vs 该处图标的**暗色笔画质心**
|
||||
# --------------------------------------------------------------------------- #
|
||||
def icon_centroid_offset(bg_pil, x: int, y: int, half: int = 32) -> Optional[Tuple[float, float, float]]:
|
||||
"""返回 (质心x, 质心y, 离点击点的距离px)；估不出来返回 None。
|
||||
|
||||
原理：图标是近黑的线条画，背景是彩色的（天空/水面/木纹…）。在点击点周围截
|
||||
(2*half)² 的窗口，用 Otsu 分出暗色笔画，取笔画质心当作"图标视觉中心"。
|
||||
**这是独立于我求解器的量尺**（求解器用的是 YOLO box 中心），所以能回答
|
||||
"我们到底点偏了多少"。
|
||||
"""
|
||||
w, h = bg_pil.size
|
||||
box = (max(0, x - half), max(0, y - half), min(w, x + half), min(h, y + half))
|
||||
patch = np.array(bg_pil.crop(box).convert("L"))
|
||||
if patch.size == 0:
|
||||
return None
|
||||
thr, binimg = cv2.threshold(patch.astype(np.uint8), 0, 255,
|
||||
cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
|
||||
ys, xs = np.nonzero(binimg)
|
||||
if len(xs) < 20:
|
||||
return None
|
||||
cx, cy = float(xs.mean()), float(ys.mean())
|
||||
lx, ly = x - box[0], y - box[1] # 点击点在窗口内的坐标
|
||||
return (cx + box[0], cy + box[1], float(np.hypot(cx - lx, cy - ly)))
|
||||
|
||||
|
||||
def annotate(bg_bytes: bytes, points: Sequence[Sequence[int]], prompt_bytes: Optional[bytes],
|
||||
offsets: Sequence[Optional[float]]) -> bytes:
|
||||
"""底图上画**按点击顺序编号**的红圈；右上角贴提示图；标注每点偏离质心的 px。"""
|
||||
bgr = cv2.imdecode(np.frombuffer(bg_bytes, np.uint8), cv2.IMREAD_COLOR)
|
||||
for i, (x, y) in enumerate(points, 1):
|
||||
cv2.circle(bgr, (int(x), int(y)), 18, (0, 0, 255), 2)
|
||||
cv2.circle(bgr, (int(x), int(y)), 2, (0, 0, 255), -1)
|
||||
cv2.putText(bgr, str(i), (int(x) - 8, int(y) - 22),
|
||||
cv2.FONT_HERSHEY_SIMPLEX, 0.85, (0, 255, 0), 2)
|
||||
if prompt_bytes:
|
||||
pr = cv2.imdecode(np.frombuffer(prompt_bytes, np.uint8), cv2.IMREAD_COLOR)
|
||||
if pr is not None:
|
||||
ph = bgr.shape[0] // 4
|
||||
pw = max(1, int(pr.shape[1] * ph / pr.shape[0]))
|
||||
pr = cv2.resize(pr, (pw, ph))
|
||||
y0, x0 = 4, bgr.shape[1] - pw - 4
|
||||
if x0 >= 0:
|
||||
bgr[y0:y0 + ph, x0:x0 + pw] = pr
|
||||
cv2.rectangle(bgr, (x0, y0), (x0 + pw, y0 + ph), (255, 255, 255), 1)
|
||||
return cv2.imencode(".jpg", bgr)[1].tobytes()
|
||||
# 点位的"量尺"（点击点 vs 图标暗色笔画质心）与标注图渲染统一在 tcaptcha.render，
|
||||
# 与 Web 界面共用同一份实现 —— 别在这里再抄一遍。
|
||||
|
||||
|
||||
def main() -> int:
|
||||
@@ -118,11 +66,14 @@ def main() -> int:
|
||||
help="给答案整体平移 DX,DY 像素（容差标定用）")
|
||||
ap.add_argument("--swap", action="store_true", help="故意交换前两个点（负对照，必错）")
|
||||
ap.add_argument("--max-refreshes", type=int, default=40)
|
||||
ap.add_argument("--interval", type=float, default=1.0,
|
||||
help="两次求解之间的间隔秒数（1ms 连打会触发频控，建议 3~5）")
|
||||
ap.add_argument("--outdir", default=None)
|
||||
ap.add_argument("--max-retries", type=int, default=1)
|
||||
args = ap.parse_args()
|
||||
|
||||
aid, entry, referer, wb = TARGETS[args.target]
|
||||
tgt = get_target(args.target)
|
||||
aid, entry, referer, wb = tgt["aid"], tgt["entry_url"], tgt["referer"], tgt["wb"]
|
||||
dx, dy = (int(v) for v in args.offset.split(","))
|
||||
tag = "%s_%s_n%d_off%s%s" % (args.target, args.kind, args.n, args.offset,
|
||||
"_swap" if args.swap else "")
|
||||
@@ -245,7 +196,8 @@ def main() -> int:
|
||||
offsets.append(None if est is None else round(est[2], 1))
|
||||
centroids.append(None if est is None else [round(est[0], 1), round(est[1], 1)])
|
||||
(d / "bg.jpg").write_bytes(bg_raw)
|
||||
(d / "annotated.jpg").write_bytes(annotate(bg_raw, pts, prompt_raw, offsets))
|
||||
(d / "annotated.jpg").write_bytes(
|
||||
annotate_points(bg_raw, pts, prompt=prompt_raw, offsets=offsets))
|
||||
if prompt_raw is not None:
|
||||
(d / "prompt.jpg").write_bytes(prompt_raw)
|
||||
(d / "points.json").write_text(json.dumps({
|
||||
@@ -257,26 +209,36 @@ def main() -> int:
|
||||
"prehandles": counters["prehandle"],
|
||||
}, ensure_ascii=False, indent=1), encoding="utf-8")
|
||||
|
||||
row = {"run": n, "errorCode": ec, "points": [list(p) for p in pts],
|
||||
row = {"run": n, "errorCode": ec, "kind": res.get("kind"),
|
||||
"instruction": res.get("instruction"),
|
||||
"points": [list(p) for p in pts],
|
||||
"collect_len": last_gen.get("collect_len"),
|
||||
"off_px": offsets, "secs": round(time.time() - t0, 1),
|
||||
"prehandles": counters["prehandle"]}
|
||||
rows.append(row)
|
||||
print("run%-2d ec=%-4s 偏离质心px=%-22s prehandle=%-3d points=%s %.0fs" % (
|
||||
n, ec, str(offsets), counters["prehandle"], pts, time.time() - t0))
|
||||
time.sleep(1.0)
|
||||
print("run%-2d ec=%-4s kind=%-10s 偏离质心px=%-20s prehandle=%-3d points=%s %.0fs" % (
|
||||
n, ec, res.get("kind") or "?", str(offsets), counters["prehandle"], pts,
|
||||
time.time() - t0))
|
||||
time.sleep(max(0.0, args.interval))
|
||||
finally:
|
||||
c.close()
|
||||
icon_mod.CaptchaSolver.solve = real_icon_solve
|
||||
client_mod.generate_telemetry = real_gen
|
||||
|
||||
counts: Dict[str, int] = {}
|
||||
by_kind: Dict[str, Dict[str, int]] = {}
|
||||
for r in rows:
|
||||
counts[str(r.get("errorCode"))] = counts.get(str(r.get("errorCode")), 0) + 1
|
||||
ec_s = str(r.get("errorCode"))
|
||||
counts[ec_s] = counts.get(ec_s, 0) + 1
|
||||
k = str(r.get("kind") or "?")
|
||||
by_kind.setdefault(k, {})
|
||||
by_kind[k][ec_s] = by_kind[k].get(ec_s, 0) + 1
|
||||
all_off = [v for r in rows for v in (r.get("off_px") or []) if isinstance(v, (int, float))]
|
||||
summary = {
|
||||
"target": args.target, "kind": args.kind, "n": args.n,
|
||||
"offset_applied": [dx, dy], "swapped": args.swap,
|
||||
"errorCode_counts": counts,
|
||||
"by_kind": by_kind,
|
||||
"centroid_offset_px": {
|
||||
"count": len(all_off),
|
||||
"min": min(all_off) if all_off else None,
|
||||
@@ -291,6 +253,9 @@ def main() -> int:
|
||||
print("靶子=%s 题型=%s 次数=%d 答案平移=%s 交换=%s" % (args.target, args.kind, args.n,
|
||||
args.offset, args.swap))
|
||||
print("errorCode 计数: %s" % json.dumps(counts, ensure_ascii=False))
|
||||
if len(by_kind) > 1 or "?" not in by_kind:
|
||||
for k in sorted(by_kind):
|
||||
print(" 按题型 %-12s %s" % (k, json.dumps(by_kind[k], ensure_ascii=False)))
|
||||
if all_off:
|
||||
print("点击点偏离图标笔画质心: 均值 %.1fpx / 最小 %.1f / 最大 %.1f（%d 个点）"
|
||||
% (np.mean(all_off), min(all_off), max(all_off), len(all_off)))
|
||||
|
||||
Reference in New Issue
Block a user