huanghai/aiData
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

'commit'

Browse Source
This commit is contained in:
HuangHai
2026-01-13 08:20:28 +08:00
parent b07dca28b5
commit ed4a240325
10 changed files with 266 additions and 182 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
Apps/AiTeJiYiChong/Crawler.py
View File

@@ -80,15 +80,20 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
if ad_type == "rabbit":
logger.info(">>> 检测到顽固的兔子广告，执行强力双击策略...")
# 使用 u2 的 double_click，它比两次 click + sleep 更快
d.double_click(x, y, duration=0.05)
# 处理“误触背景卡片”的逻辑
logger.info(">>> 考虑到可能误触背景卡片，等待 2s 后执行返回操作...")
await asyncio.sleep(2.0)
logger.info(">>> 等待 3s 以确认是否进入了二级页面...")
await asyncio.sleep(3.0)
# 爱特极特征元素检测 (列表页特征)
is_list_page = d(text="筛选").exists or d(text="排序").exists or d(text="搜索").exists
if not is_list_page:
logger.info(">>> 检测到当前不在列表页，尝试执行返回操作...")
d.press("back")
await asyncio.sleep(1.0)
logger.info(">>> 已尝试从误触页面返回。")
await asyncio.sleep(1.5)
else:
logger.info(">>> 当前仍在列表页，无需返回。")
else:
d.click(x, y)
await asyncio.sleep(1.5)

3
Apps/AiTeJiYiChong/Opener.py
View File

@@ -4,7 +4,8 @@ import logging
import os
import time
import uiautomator2 as u2
from Apps.AiTeJiYiChong.Kit import click_image_template
from Apps.AiTeJiYiChong.Kit import click_image_template, take_screenshot
from Config.Config import TEMP_IMAGE_DIR
logging.basicConfig(
level=logging.INFO,

91
Apps/AiTeJiYiChong/ReadImageKit.py
View File

@@ -11,13 +11,16 @@ import cv2
import uuid
from openai import AsyncOpenAI, BadRequestError
from Config.Config import (
ALY_LLM_API_KEY, VL_MODEL_NAME, VL_MODEL_NAME_AD
ALY_LLM_API_KEY, VL_MODEL_NAME, VL_MODEL_NAME_AD, TEMP_IMAGE_DIR
)
from Apps.AiTeJiYiChong.Config.Setting import (
SAFE_EXCLUDE_RATIO, FALLBACK_WIDTH, FALLBACK_HEIGHT,
BOTTOM_SAFE_EXCLUDE_RATIO
)
from Apps.AiTeJiYiChong import Kit
from Apps.AiTeJiYiChong.Kit import (
read_image, save_image
)
logger = logging.getLogger(__name__)
@@ -78,92 +81,6 @@ class ReadImageKit:
"严格返回纯JSON格式。"
)
@classmethod
async def detect_ad_popup(cls, image_path: str, device_info=None):
"""
使用 VL 模型检测是否存在弹窗广告，并返回关闭按钮坐标
"""
if not os.path.exists(image_path):
return None
with open(image_path, "rb") as image_file:
encoded_image = base64.b64encode(image_file.read()).decode("utf-8")
img_input = {"url": f"data:image/jpeg;base64,{encoded_image}"}
# 构建提示词
prompt = (
"请仔细检查这张图片中是否存在**弹窗广告**或**悬浮广告**。\n"
"广告可能有以下几种形式：\n"
"1. **屏幕中央的大型弹窗广告**：通常遮挡了页面内容，内容多为优惠券、活动推广等。\n"
"2. **'新电兔AI'专属悬浮广告**（高频）：\n"
" - **位置范围**：严格锁定在**屏幕左侧边缘**（水平坐标约 0-250），**垂直高度处于中下部**（垂直坐标约 600-900）。\n"
" - **视觉特征**：一个卡通兔子头，或带有'新电兔AI'字样的气泡图标。\n"
" - **关闭按钮**：务必寻找位于该图标**正下方**的一个**黑色圆形小按钮（内含白色X）**。注意：关闭按钮通常与图标本体分离，悬浮在图标下方约 20-50 像素处。请精确返回这个黑色圆形按钮的中心坐标。\n"
"3. **底部的横幅广告**：带有明显的关闭按钮。\n\n"
"如果发现了上述任何一种广告，请务必找到该广告的**关闭按钮**（通常是一个'X'符号，或者'关闭'字样，或者位于广告下方/右上角的圆圈叉号）。\n"
"请返回该关闭按钮的**中心坐标**。\n\n"
"请以纯 JSON 格式输出：\n"
"{\n"
" \"has_ad\": true/false,\n"
" \"ad_type\": \"rabbit\", // \"rabbit\" (新电兔AI/兔子) | \"center\" (中央弹窗) | \"bottom\" (底部横幅) | \"other\"\n"
" \"close_point\": [x, y] // 0-1000 归一化坐标\n"
"}\n"
"如果没有广告，请返回 `{\"has_ad\": false}`。\n"
"只输出 JSON，不要包含任何其他文字。"
)
try:
resp = await cls._client.chat.completions.create(
model=VL_MODEL_NAME, # 使用默认 VL 模型即可，或者使用 AD 专用
timeout=30,
messages=[
{
"role": "user",
"content": [
{"type": "image_url", "image_url": img_input},
{"type": "text", "text": prompt},
],
}
],
)
content = resp.choices[0].message.content.strip()
raw_json = cls._extract_json(content)
result = json.loads(raw_json)
if result.get("has_ad") and result.get("close_point"):
if result.get("ad_type") == "rabbit":
logger.info("大模型找到了兔子广告！")
# 强制使用固定坐标 (94, 830) - 归一化 0-1000
# 根据多次 CV 测试结果 (94, 828) 和 (93, 830) 的综合评估
logger.info(">>> 采用强制固定坐标策略 (94, 830) 以确保点击准确性")
norm_point = [94, 830]
else:
norm_point = result["close_point"]
# 转换坐标
if len(norm_point) == 2:
if not device_info:
device_info = cls._FALLBACK_DEVICE_INFO
w = device_info.get("displayWidth", FALLBACK_WIDTH)
h = device_info.get("displayHeight", FALLBACK_HEIGHT)
# 假设模型返回的是 0-1000 的坐标
x = int(norm_point[0] / 1000 * w)
y = int(norm_point[1] / 1000 * h)
return {
"x": x,
"y": y,
"ad_type": result.get("ad_type", "unknown")
}
return None
except Exception as e:
logger.error(f"Failed to detect ad popup: {e}")
return None
@staticmethod
def _extract_json(text: str) -> str:
if not text:

18
Apps/XinDianTu/Crawler.py
View File

@@ -175,15 +175,21 @@ async def get_station_list(d, service, uploader, max_scrolls=MAX_SCROLLS):
if ad_type == "rabbit":
logger.info(">>> 检测到顽固的兔子广告，执行强力双击策略...")
# 使用 u2 的 double_click，它比两次 click + sleep 更快
d.double_click(x, y, duration=0.05)
# 处理“误触背景卡片”的逻辑：既然可能进去了，就等一会儿再退出来
logger.info(">>> 考虑到可能误触背景卡片，等待 2s 后执行返回操作...")
await asyncio.sleep(2.0)
# 处理“误触背景卡片”的逻辑
logger.info(">>> 等待 3s 以确认是否进入了二级页面...")
await asyncio.sleep(3.0)
# 检查是否还在列表页 (新电途列表页通常有“全城”或“综合排序”按钮)
# 如果这些按钮不存在，说明可能进到了详情页
is_list_page = d(text="全城").exists or d(text="综合排序").exists or d(text="搜索场站").exists
if not is_list_page:
logger.info(">>> 检测到当前不在列表页，尝试执行返回操作...")
d.press("back")
await asyncio.sleep(1.0)
logger.info(">>> 已尝试从误触页面返回。")
await asyncio.sleep(1.5)
else:
logger.info(">>> 当前仍在列表页，无需返回。")
else:
d.click(x, y)
await asyncio.sleep(1.5)

104
Apps/XinDianTu/Kit.py
View File

@@ -137,6 +137,110 @@ def is_background_dimmed(image_path, threshold=80):
return avg_brightness < threshold
def detect_rabbit_ad_close(image_path, debug_dir=None):
"""
通过图形学算法检测“新电兔AI”广告的关闭按钮
特征：黑色圆，中间有白色X
:param image_path: 截图路径
:param debug_dir: 调试图保存目录
:return: (x, y) 归一化坐标，如果未找到返回 None
"""
if not os.path.exists(image_path):
return None
img = read_image(image_path)
if img is None:
return None
h, w = img.shape[:2]
# ROI: 左侧，中下部 (x: 0-25%, y: 60-90%)
roi_x1, roi_x2 = 0, int(w * 0.25)
roi_y1, roi_y2 = int(h * 0.6), int(h * 0.9)
roi = img[roi_y1:roi_y2, roi_x1:roi_x2]
gray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
candidates = []
# 尝试多个阈值以应对不同的亮度环境
for threshold_val in [40, 60, 80, 100]:
_, thresh = cv2.threshold(gray, threshold_val, 255, cv2.THRESH_BINARY_INV)
# Find contours
contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
for cnt in contours:
area = cv2.contourArea(cnt)
# 圆形度检查
perimeter = cv2.arcLength(cnt, True)
if perimeter == 0: continue
circularity = 4 * np.pi * (area / (perimeter * perimeter))
# 兔子广告关闭按钮通常很小 (面积在 100-4000 之间)
if 100 < area < 4000 and circularity > 0.4:
# 获取该候选区域的 bounding box
x, y, w_cnt, h_cnt = cv2.boundingRect(cnt)
# 在这个黑色圆内部，检查是否有亮色的 'X'
padding = 2
inner_roi = gray[max(0, y-padding):min(roi.shape[0], y+h_cnt+padding),
max(0, x-padding):min(roi.shape[1], x+w_cnt+padding)]
# 找亮色物体 (X)
_, inner_thresh = cv2.threshold(inner_roi, 180, 255, cv2.THRESH_BINARY)
inner_contours, _ = cv2.findContours(inner_thresh, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
has_x = False
for i_cnt in inner_contours:
i_area = cv2.contourArea(i_cnt)
# X 应该比圆小很多
if 10 < i_area < area * 0.5:
has_x = True
break
if has_x or circularity > 0.7:
M = cv2.moments(cnt)
if M["m00"] != 0:
cX = int(M["m10"] / M["m00"]) + roi_x1
cY = int(M["m01"] / M["m00"]) + roi_y1
norm_x = int(cX / w * 1000)
norm_y = int(cY / h * 1000)
# 避免重复
if not any(abs(cX - c[0]) < 15 and abs(cY - c[1]) < 15 for c in candidates):
candidates.append((cX, cY, area, norm_x, norm_y, has_x))
if not candidates:
return None
# 评分逻辑
def score_candidate(c):
# c = (cx, cy, area, nx, ny, has_x)
has_x = c[5]
# 基础分：如果有 X，大幅加分
score = 1000 if has_x else 0
# 距离分：越靠近预期的 (93, 830) 分越高
dist = np.sqrt((c[3] - 93)**2 + (c[4] - 830)**2)
score -= dist * 2
# 面积分：理想面积在 500-1500 之间
if 500 < c[2] < 1500: score += 200
return score
candidates.sort(key=score_candidate, reverse=True)
best = candidates[0]
logger.info(f"CV detected rabbit ad close button at Norm({best[3]}, {best[4]}) with score {score_candidate(best):.2f}")
if debug_dir:
os.makedirs(debug_dir, exist_ok=True)
debug_img = img.copy()
cv2.circle(debug_img, (best[0], best[1]), 10, (0, 0, 255), -1) # 使用红点表示识别结果
save_image(os.path.join(debug_dir, "debug_rabbit_ad_cv.jpg"), debug_img)
return [best[3], best[4]]
def detect_black_agree_button(image_path, debug_dir=None):
"""
通过计算机图形学检测黑色的"同意"按钮 (Image 1 场景)

15
Apps/XinDianTu/Opener.py
View File

@@ -68,15 +68,20 @@ async def check_and_close_ad(d):
# 针对“新电兔AI”兔子广告的强力关闭策略
if ad_type == "rabbit":
logger.info(">>> 检测到顽固的兔子广告，执行强力双击策略...")
# 使用 u2 的 double_click，它比两次 click + sleep 更快
d.double_click(x, y, duration=0.05)
# 处理“误触背景卡片”的逻辑
logger.info(">>> 考虑到可能误触背景卡片，等待 2s 后执行返回操作...")
await asyncio.sleep(2.0)
logger.info(">>> 等待 3s 以确认是否进入了二级页面...")
await asyncio.sleep(3.0)
# 检查是否还在列表页
is_list_page = d(text="全城").exists or d(text="综合排序").exists or d(text="搜索场站").exists
if not is_list_page:
logger.info(">>> 检测到当前不在列表页，尝试执行返回操作...")
d.press("back")
await asyncio.sleep(1.0)
logger.info(">>> 已尝试从误触页面返回。")
await asyncio.sleep(1.5)
else:
logger.info(">>> 当前仍在列表页，无需返回。")
else:
d.click(x, y)

47
Apps/XinDianTu/ReadImageKit.py
View File

@@ -8,8 +8,11 @@ import aiohttp
import logging
import base64
from openai import AsyncOpenAI, BadRequestError
from Apps.XinDianTu.Kit import (
read_image, save_image, detect_rabbit_ad_close
)
from Config.Config import (
ALY_LLM_API_KEY, VL_MODEL_NAME, VL_MODEL_NAME_AD
ALY_LLM_API_KEY, VL_MODEL_NAME, VL_MODEL_NAME_AD, TEMP_IMAGE_DIR
)
from Apps.XinDianTu.Config.Setting import (
SAFE_EXCLUDE_RATIO, FALLBACK_WIDTH, FALLBACK_HEIGHT,
@@ -77,11 +80,28 @@ class ReadImageKit:
@classmethod
async def detect_ad_popup(cls, image_path: str, device_info=None):
"""
使用 VL 模型检测是否存在弹窗广告，并返回关闭按钮坐标
使用 VL 模型 + 图形学算法检测是否存在弹窗广告，并返回关闭按钮坐标
"""
if not os.path.exists(image_path):
return None
# 1. 优先使用图形学算法检测“新电兔AI”广告，因为它的特征非常明显
cv_rabbit_point = detect_rabbit_ad_close(image_path, debug_dir=TEMP_IMAGE_DIR)
if cv_rabbit_point:
logger.info(f">>> 图形学算法精准捕捉到兔子广告关闭按钮: {cv_rabbit_point}")
norm_point = cv_rabbit_point
ad_type = "rabbit"
# 转换坐标并返回
if not device_info:
device_info = cls._FALLBACK_DEVICE_INFO
w = device_info.get("displayWidth", FALLBACK_WIDTH)
h = device_info.get("displayHeight", FALLBACK_HEIGHT)
x = int(norm_point[0] / 1000 * w)
y = int(norm_point[1] / 1000 * h)
return {"x": x, "y": y, "ad_type": ad_type}
# 2. 如果图形学没找到，再请求大模型进行全量检测
with open(image_path, "rb") as image_file:
encoded_image = base64.b64encode(image_file.read()).decode("utf-8")
img_input = {"url": f"data:image/jpeg;base64,{encoded_image}"}
@@ -91,26 +111,21 @@ class ReadImageKit:
"请仔细检查这张图片中是否存在**弹窗广告**或**悬浮广告**。\n"
"广告可能有以下几种形式：\n"
"1. **屏幕中央的大型弹窗广告**：通常遮挡了页面内容，内容多为优惠券、活动推广等。\n"
"2. **'新电兔AI'专属悬浮广告**（高频）：\n"
" - **位置范围**：严格锁定在**屏幕左侧边缘**（水平坐标约 0-250），**垂直高度处于中下部**（垂直坐标约 600-900）。\n"
" - **视觉特征**：一个卡通兔子头，或带有'新电兔AI'字样的气泡图标。\n"
" - **关闭按钮**：务必寻找位于该图标**正下方**的一个**黑色圆形小按钮（内含白色X）**。注意：关闭按钮通常与图标本体分离，悬浮在图标下方约 20-50 像素处。请精确返回这个黑色圆形按钮的中心坐标。\n"
"2. **'新电兔AI'专属悬浮广告**（高频）：一个卡通兔子头，带有'新电兔AI'字样，关闭按钮是一个黑色圆圈内含白色X。\n"
"3. **底部的横幅广告**：带有明显的关闭按钮。\n\n"
"如果发现了上述任何一种广告，请务必找到该广告的**关闭按钮**（通常是一个'X'符号，或者'关闭'字样，或者位于广告下方/右上角的圆圈叉号）。\n"
"请返回该关闭按钮的**中心坐标**。\n\n"
"请返回关闭按钮的中心坐标。\n\n"
"请以纯 JSON 格式输出：\n"
"{\n"
" \"has_ad\": true/false,\n"
" \"ad_type\": \"rabbit\", // \"rabbit\" (新电兔AI/兔子) | \"center\" (中央弹窗) | \"bottom\" (底部横幅) | \"other\"\n"
" \"ad_type\": \"rabbit\" | \"center\" | \"bottom\" | \"other\",\n"
" \"close_point\": [x, y] // 0-1000 归一化坐标\n"
"}\n"
"如果没有广告，请返回 `{\"has_ad\": false}`。\n"
"只输出 JSON，不要包含任何其他文字。"
"如果没有广告，请返回 `{\"has_ad\": false}`。"
)
try:
resp = await cls._client.chat.completions.create(
model=VL_MODEL_NAME, # 使用默认 VL 模型即可，或者使用 AD 专用
model=VL_MODEL_NAME,
timeout=30,
messages=[
{
@@ -128,10 +143,9 @@ class ReadImageKit:
if result.get("has_ad") and result.get("close_point"):
if result.get("ad_type") == "rabbit":
logger.info("大模型找到了兔子广告！")
# 强制使用固定坐标 (94, 830) - 归一化 0-1000
# 根据多次 CV 测试结果 (94, 828) 和 (93, 830) 的综合评估
logger.info(">>> 采用强制固定坐标策略 (94, 830) 以确保点击准确性")
logger.info("大模型找到了兔子广告，但 CV 没找到。")
# 如果大模型找到了但 CV 没找到，说明可能 CV 阈值没对上，此时采用固定坐标作为兜底
logger.info(">>> 采用兜底固定坐标策略 (94, 830)")
norm_point = [94, 830]
else:
norm_point = result["close_point"]
@@ -144,7 +158,6 @@ class ReadImageKit:
w = device_info.get("displayWidth", FALLBACK_WIDTH)
h = device_info.get("displayHeight", FALLBACK_HEIGHT)
# 假设模型返回的是 0-1000 的坐标
x = int(norm_point[0] / 1000 * w)
y = int(norm_point[1] / 1000 * h)

BIN
Apps/XinDianTu/__pycache__/Crawler.cpython-310.pyc
View File

Binary file not shown.

BIN
Apps/XinDianTu/__pycache__/Opener.cpython-310.pyc
View File

Binary file not shown.

123
Tools/TestAdClick.py
View File

@@ -44,10 +44,11 @@ def test_click():
# Convert to grayscale
gray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
# The close button is a black circle. So it should be very dark.
# Try multiple thresholds to find the best candidates
# The close button is a black circle with a white X.
# We look for a dark circle, and then check if it contains something bright.
candidates = []
for threshold_val in [50, 70, 90, 110]:
# 尝试多个阈值以应对不同的亮度环境
for threshold_val in [40, 60, 80, 100]:
_, thresh = cv2.threshold(gray, threshold_val, 255, cv2.THRESH_BINARY_INV)
# Find contours
@@ -55,82 +56,114 @@ def test_click():
for cnt in contours:
area = cv2.contourArea(cnt)
# Approximate circle check
# 圆形度检查
perimeter = cv2.arcLength(cnt, True)
if perimeter == 0: continue
circularity = 4 * np.pi * (area / (perimeter * perimeter))
# Filter by size and circularity
# Size: it's a small button
if 50 < area < 6000 and circularity > 0.35:
# 兔子广告关闭按钮通常很小 (40x40 左右在 1080p 下是 1600 面积)
if 100 < area < 4000 and circularity > 0.4:
# 获取该候选区域的 bounding box
x, y, w_cnt, h_cnt = cv2.boundingRect(cnt)
# 在这个黑色圆内部，检查是否有亮色的 'X'
# 我们可以对这个区域做反向阈值，找亮色物体
padding = 2
inner_roi = gray[max(0, y-padding):min(roi.shape[0], y+h_cnt+padding),
max(0, x-padding):min(roi.shape[1], x+w_cnt+padding)]
# 找亮色物体 (X)
_, inner_thresh = cv2.threshold(inner_roi, 180, 255, cv2.THRESH_BINARY)
inner_contours, _ = cv2.findContours(inner_thresh, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
has_x = False
for i_cnt in inner_contours:
i_area = cv2.contourArea(i_cnt)
# X 应该比圆小很多
if 10 < i_area < area * 0.5:
has_x = True
break
if has_x:
M = cv2.moments(cnt)
if M["m00"] != 0:
cX = int(M["m10"] / M["m00"]) + roi_x1
cY = int(M["m01"] / M["m00"]) + roi_y1
# Calculate normalized coordinates
norm_x = int(cX / w * 1000)
norm_y = int(cY / h * 1000)
# Avoid duplicates
if not any(abs(cX - c[0]) < 10 and abs(cY - c[1]) < 10 for c in candidates):
candidates.append((cX, cY, area, norm_x, norm_y))
# 避免重复
if not any(abs(cX - c[0]) < 15 and abs(cY - c[1]) < 15 for c in candidates):
candidates.append((cX, cY, area, norm_x, norm_y, True)) # True means found X
# 保存候选区域图片以便调试
cv2.imwrite(rf"d:\dsWork\aiData\Output\cand_{len(candidates)-1}_roi.jpg", inner_roi)
else:
# 如果没找到 X，但圆形度很高，也可以作为一个低优先级候选
if circularity > 0.7:
M = cv2.moments(cnt)
if M["m00"] != 0:
cX = int(M["m10"] / M["m00"]) + roi_x1
cY = int(M["m01"] / M["m00"]) + roi_y1
norm_x = int(cX / w * 1000)
norm_y = int(cY / h * 1000)
if not any(abs(cX - c[0]) < 15 and abs(cY - c[1]) < 15 for c in candidates):
candidates.append((cX, cY, area, norm_x, norm_y, False))
cv2.imwrite(rf"d:\dsWork\aiData\Output\cand_{len(candidates)-1}_roi.jpg", inner_roi)
# Save thresh image for debugging
_, debug_thresh = cv2.threshold(gray, 70, 255, cv2.THRESH_BINARY_INV)
cv2.imwrite(r"d:\dsWork\aiData\Output\debug_thresh.jpg", debug_thresh)
cv2.imwrite(r"d:\dsWork\aiData\Output\debug_thresh.jpg", thresh)
# Sort by proximity to expected location (Left side, Middle-Bottom)
# Expected norm: (93, 830)
# 评分逻辑
def score_candidate(c):
# Weighting: X proximity is important, Y proximity is also important, Area around 400-500 is ideal
dist_x = abs(c[3] - 93)
dist_y = abs(c[4] - 830)
area_diff = abs(c[2] - 450) / 450.0
return dist_x * 2 + dist_y + area_diff * 100
# c = (cx, cy, area, nx, ny, has_x)
has_x = c[5]
# 基础分：如果有 X，大幅加分
score = 1000 if has_x else 0
# 距离分：越靠近预期的 (93, 830) 分越高
dist = np.sqrt((c[3] - 93)**2 + (c[4] - 830)**2)
score -= dist * 2
# 面积分：理想面积在 500-1500 之间
if 500 < c[2] < 1500:
score += 200
return score
candidates.sort(key=score_candidate)
candidates.sort(key=score_candidate, reverse=True)
target_x, target_y = int(w * 0.08), int(h * 0.835) # Default fallback
norm_target_x, norm_target_y = 80, 835
if candidates:
print(f"Found {len(candidates)} candidate close buttons via CV:")
for i, (cx, cy, area, nx, ny) in enumerate(candidates):
score = score_candidate((cx, cy, area, nx, ny))
print(f" Candidate {i}: ({cx}, {cy}), Area: {area}, Norm: ({nx}, {ny}), Score: {score:.2f}")
for i, (cx, cy, area, nx, ny, has_x) in enumerate(candidates):
score = score_candidate((cx, cy, area, nx, ny, has_x))
print(f" Candidate {i}: ({cx}, {cy}), Area: {area}, Norm: ({nx}, {ny}), HasX: {has_x}, Score: {score:.2f}")
# Pick the best one
best_c = candidates[0]
target_x, target_y = best_c[0], best_c[1]
norm_target_x, norm_target_y = best_c[3], best_c[4]
print(f"Selected CV target: ({target_x}, {target_y}), Norm: ({norm_target_x}, {norm_target_y})")
else:
print("No CV candidates found. Using fixed coordinates.")
print(f"Selected CV target: ({target_x}, {target_y}), Norm: ({norm_target_x}, {norm_target_y}), HasX: {best_c[5]}")
# Visualize
cv2.circle(img, (target_x, target_y), 20, (0, 255, 0), -1)
cv2.putText(img, f"Click ({target_x}, {target_y})", (target_x + 30, target_y), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
# Also draw the fixed point for comparison (Blue)
fixed_x = int(w * 0.08)
fixed_y = int(h * 0.835)
cv2.circle(img, (fixed_x, fixed_y), 15, (255, 0, 0), -1)
viz_img = cv2.imread(screenshot_path)
cv2.circle(viz_img, (target_x, target_y), 3, (0, 0, 255), -1)
debug_path = r"d:\dsWork\aiData\Output\debug_ad_point.jpg"
cv2.imwrite(debug_path, img)
print(f"Debug image saved to {debug_path}")
red_point_path = r"d:\dsWork\aiData\Output\_redpoint.jpg"
cv2.imwrite(debug_path, viz_img)
cv2.imwrite(red_point_path, viz_img)
print(f"Debug images saved to {debug_path} and {red_point_path}")
# 4. Perform click
print(f"Clicking ({target_x}, {target_y}) using double_click...")
# Use d.double_click for a faster interaction
d.double_click(target_x, target_y, duration=0.05)
print(f"Clicking ({target_x}, {target_y}) using single click...")
d.click(target_x, target_y)
# NEW: Handle potential background click as per user's latest request
print("Waiting 2s for potential background card to load...")
time.sleep(2)
print("Pressing BACK to return to main page...")
d.press("back")
print("Waiting 3s for user to observe if the ad is closed...")
time.sleep(3)
# print("Pressing BACK to return to main page...")
# d.press("back")
else:
print("No CV candidates found. Skipping click to avoid accidental background interaction.")
time.sleep(2)