feat(tcaptcha): 完成腾讯天御点选纯协议全自动化客户端与雨云业务适配器

tcaptcha/solver.py

@@ -7,11 +7,12 @@
 4. 全局匹配: 全局最大后验概率分配 -> 输出毫秒级精准有序点击坐标 [(x1, y1), (x2, y2), (x3, y3)]
 """
 
+import io
 import itertools
 import logging
 import sys
 from pathlib import Path
-from typing import List, Tuple
+from typing import List, Tuple, Union
 
 PROJECT_ROOT = Path(__file__).resolve().parent.parent
 if str(PROJECT_ROOT) not in sys.path:
@@ -75,11 +76,11 @@ class CaptchaSolver:
                 bin_t = cv2.resize(((arr < bg - 20).astype(np.uint8) * 255), (48, 48), interpolation=cv2.INTER_AREA)
                 self.templates.append((cid, bin_t))
 
-    def parse_prompt_targets(self, prompt_img_path: Path) -> List[int]:
+    def parse_prompt_targets(self, prompt_img: str | Path | bytes | Image.Image) -> List[int]:
         """
         自动识别并解析提示图中 3 个目标图标的真实类别 ID (0~11)
         """
-        crops = slice_prompt_image(prompt_img_path)
+        crops = slice_prompt_image(prompt_img)
         target_classes = []
         for crop_img, _ in crops[:3]:
             arr = np.array(crop_img.convert("L"))
@@ -92,12 +93,19 @@ class CaptchaSolver:
 
         return target_classes
 
-    def _extract_candidates(self, bg_img_path: Path) -> List[Tuple[int, int, Image.Image]]:
+    def _extract_candidates(self, bg_img: str | Path | bytes | Image.Image) -> List[Tuple[int, int, Image.Image]]:
         """从背景图中提取所有去重后的候选图标 (cx, cy, patch)"""
-        results = self.detector(str(bg_img_path), conf=0.03, verbose=False)
+        if isinstance(bg_img, Image.Image):
+            bg_pil = bg_img.convert("RGB")
+        elif isinstance(bg_img, bytes):
+            bg_pil = Image.open(io.BytesIO(bg_img)).convert("RGB")
+        else:
+            bg_pil = Image.open(bg_img).convert("RGB")
+
+        # Ultralytics detector natively accepts PIL.Image
+        results = self.detector(bg_pil, conf=0.03, verbose=False)
         boxes = results[0].boxes.xyxy.cpu().numpy()
 
-        bg_pil = Image.open(bg_img_path).convert("RGB")
         w_img, h_img = bg_pil.size
         raw_cands = []
 
@@ -120,22 +128,19 @@ class CaptchaSolver:
 
         return candidates
 
-    def solve(self, bg_img_path: str | Path, prompt_img_path: str | Path) -> List[Tuple[int, int]]:
+    def solve(self, bg_img: str | Path | bytes | Image.Image, prompt_img: str | Path | bytes | Image.Image) -> List[Tuple[int, int]]:
         """
         端到端求解验证码点选坐标
         返回 3 个目标的像素坐标: [(x1, y1), (x2, y2), (x3, y3)]
         """
-        bg_path = Path(bg_img_path)
-        prompt_path = Path(prompt_img_path)
-
         # 1. 确定提示图的目标序列 [T1, T2, T3]
-        target_classes = self.parse_prompt_targets(prompt_path)
+        target_classes = self.parse_prompt_targets(prompt_img)
         if len(target_classes) < 3:
             logger.warning("提示图未成功切出 3 个目标")
             return []
 
         # 2. 定位背景图所有候选图标
-        candidates = self._extract_candidates(bg_path)
+        candidates = self._extract_candidates(bg_img)
         if len(candidates) < 3:
             logger.warning(f"背景图检出候选图标数量不足: {len(candidates)}")
             return []