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 19:00:56 +08:00
parent 88ed668b7d
commit 0d4f892ead
7 changed files with 37 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Apps/XinDianTu/Config/Setting.py
View File

@@ -4,7 +4,7 @@
# 调大步长 (从 0.25 调至 0.5)，提高采集效率
SCROLL_DISTANCE_RATIO = 0.5
# 最大滑动/翻页次数，达到此次数后停止采集
MAX_SCROLLS = 60
MAX_SCROLLS = 100
# 默认抓取半径（公里），当检测到场站距离超过此值时停止采集
MAX_CRAWL_DISTANCE = 50
# 场站去重过期时间（秒），在此时间内重复出现的场站不会再次点击进入详情页

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

Binary file not shown.

87
Apps/XinDianTu/Crawler.py
View File

@@ -164,36 +164,9 @@ async def get_station_list(d, service, uploader, max_scrolls=MAX_SCROLLS):
image_uuid = str(uuid.uuid4())
screenshot_path = take_screenshot(d, image_uuid, save_dir=TEMP_IMAGE_DIR)
# 检查是否存在广告 (VL)
logger.info("检查是否存在广告弹窗...")
ad_res = await ReadImageKit.detect_ad_popup(screenshot_path, device_info=device_info)
ad_top_y_norm = 0.78 # 恢复默认的点击边界 (0.78)，不再需要为了避开兔子而设为 0.90
if ad_res:
ad_type = ad_res.get("ad_type")
if ad_type == "rabbit":
logger.info(">>> 检测到兔子广告。尝试使用图片识别关闭...")
try:
# 使用基于图片的关闭方案
template_path = os.path.join(os.path.dirname(__file__), "Template", "X.jpg")
if d.image.click(template_path, timeout=3.0):
logger.info(">>> 成功通过图片识别关闭兔子广告。")
await asyncio.sleep(1.5)
# 重新截图，因为广告已关闭
if os.path.exists(screenshot_path): os.remove(screenshot_path)
screenshot_path = take_screenshot(d, image_uuid, save_dir=TEMP_IMAGE_DIR)
else:
logger.warning(">>> 图片识别未找到兔子广告关闭按钮。")
except Exception as ex:
logger.error(f">>> 图片识别关闭兔子广告异常: {ex}")
else:
x, y = ad_res['x'], ad_res['y']
logger.info(f"检测到非兔子广告: {ad_res} [Type: {ad_type}]，正在关闭...")
d.click(x, y)
await asyncio.sleep(1.5)
# 重新截图
if os.path.exists(screenshot_path): os.remove(screenshot_path)
screenshot_path = take_screenshot(d, image_uuid, save_dir=TEMP_IMAGE_DIR)
# 【优化】不再在每页滚动时检查兔子广告，仅在 Opener 进入时检查一次
# 如果后续发现有其它非兔子广告弹出，可在此处恢复非兔子广告的检测逻辑
ad_top_y_norm = 0.78 # 默认的点击边界 (0.78)
# 检查是否已经滚动到底部 (排除状态栏后，内容与上次一致)
current_md5 = Kit.get_image_content_md5(
@@ -275,32 +248,10 @@ async def get_station_list(d, service, uploader, max_scrolls=MAX_SCROLLS):
detail_path = take_screenshot(d, detail_uuid, save_dir=TEMP_IMAGE_DIR)
# 【新增】二级页面广告检测 (如：免费停车提示)
logger.info("检查详情页是否存在干扰弹窗...")
detail_ad_res = await ReadImageKit.detect_ad_popup(detail_path, device_info=device_info)
if detail_ad_res:
dad_type = detail_ad_res.get("ad_type")
if dad_type == "rabbit":
logger.info(">>> 详情页检测到 rabbit 广告。尝试使用图片识别关闭...")
try:
template_path = os.path.join(os.path.dirname(__file__), "Template", "X.jpg")
if d.image.click(template_path, timeout=3.0):
logger.info(">>> 详情页成功通过图片识别关闭兔子广告。")
await asyncio.sleep(1.5)
# 重新截图
if os.path.exists(detail_path): os.remove(detail_path)
detail_path = take_screenshot(d, detail_uuid, save_dir=TEMP_IMAGE_DIR)
else:
logger.warning(">>> 详情页图片识别未找到兔子广告关闭按钮，跳过。")
except Exception as ex:
logger.error(f">>> 详情页图片识别关闭兔子广告异常: {ex}")
else:
dx, dy = detail_ad_res["x"], detail_ad_res["y"]
logger.info(f"检测到详情页弹窗: {dad_type}，正在点击关闭 ({dx}, {dy})...")
d.click(dx, dy)
await asyncio.sleep(1.5)
# 重新截图，确保后续流程使用的是清理后的界面
if os.path.exists(detail_path): os.remove(detail_path)
detail_path = take_screenshot(d, detail_uuid, save_dir=TEMP_IMAGE_DIR)
# 【优化】不再在详情页检查广告，节省时间和 Token
# detail_ad_res = await ReadImageKit.detect_ad_popup(detail_path, device_info=device_info)
# if detail_ad_res:
# ... (代码已移除)
# 【优化】后台解析详情页地址，直接传本地路径，避免等待上传
logger.info(f"已启动后台分析详情页: {station_name}")
@@ -326,11 +277,25 @@ async def get_station_list(d, service, uploader, max_scrolls=MAX_SCROLLS):
# 1. 尝试模板匹配
match_res = d.image.match(template_qbsd)
if match_res:
click_pos = (match_res['x'], match_res['y'])
logger.info(f"通过 qbsd.jpg成功找到！坐标: {click_pos}")
else:
# 2. 模板匹配失败，降级为 VL 识别
logger.info("qbsd.jpg 匹配失败，降级使用 VL 识别...")
# 兼容 uiautomator2 不同版本的返回结果 (Match对象或dict)
if hasattr(match_res, 'point') and match_res.point:
click_pos = match_res.point
elif isinstance(match_res, dict):
if 'point' in match_res and match_res['point']:
click_pos = match_res['point']
elif 'x' in match_res and 'y' in match_res:
click_pos = (match_res['x'], match_res['y'])
elif isinstance(match_res, (list, tuple)) and len(match_res) >= 2:
click_pos = (match_res[0], match_res[1])
if click_pos:
logger.info(f"通过 qbsd.jpg 成功找到！坐标: {click_pos}")
else:
logger.warning(f"模板匹配成功但无法解析坐标: {match_res}")
# 如果模板匹配未成功解析坐标，或者匹配直接失败，则降级到 VL
if not click_pos:
logger.info("模板匹配未找到或解析失败，降级使用 VL 识别...")
res = await ReadImageKit.find_all_time_button_coordinate(detail_path, device_info=device_info)
if res.get("uia_center_x"):
click_pos = (res.get("uia_center_x"), res.get("uia_center_y"))

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

Binary file not shown.

20
Config/Config.py
View File

@@ -1,16 +1,16 @@
# 黄海在公司内网开发时的配置信息
DORIS_HOST = "10.10.14.204"
DORIS_PORT = 9030
DORIS_FENODES = "10.10.14.204:8030"
REDIS_HOST = '10.10.14.14'
REDIS_PASSWORD = None # 如果没有密码则设为 None
# DORIS_HOST = "10.10.14.204"
# DORIS_PORT = 9030
# DORIS_FENODES = "10.10.14.204:8030"
# REDIS_HOST = '10.10.14.14'
# REDIS_PASSWORD = None # 如果没有密码则设为 None
# 黄海在家开发时的配置信息
# DORIS_HOST = "www.hzkjai.com"
# DORIS_PORT = 27025
# DORIS_FENODES = "www.hzkjai.com:27024"
# REDIS_HOST = '127.0.0.1'
# REDIS_PASSWORD = "DsideaL147258369"
DORIS_HOST = "www.hzkjai.com"
DORIS_PORT = 27025
DORIS_FENODES = "www.hzkjai.com:27024"
REDIS_HOST = '127.0.0.1'
REDIS_PASSWORD = "DsideaL147258369"
# 视觉模型配置
VL_MODEL_NAME = "qwen3-vl-flash"

BIN
Config/__pycache__/Config.cpython-310.pyc
View File

Binary file not shown.

0
Apps/XinDianTu/Test/KillRabbitAd.py → Tools/T5_KillRabbitAd.py
View File