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 20:36:20 +08:00
parent 9c03442035
commit b3a2bd4816
9 changed files with 893 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
Apps/AiTeJiYiChong/Crawler.py
View File

@@ -232,50 +232,50 @@ async def get_station_list(d, service, max_stations_count=MAX_STATIONS_COUNT):
if before_click_md5 != after_click_md5:
entered_price_page = True
# 抓取三级页面图片
price_screenshots = []
price_screenshots.append(after_click_path)
# 滑动处理
last_price_md5 = after_click_md5
for scroll_idx in range(2):
d.swipe(w // 2, int(h * 0.7), w // 2, int(h * 0.3), duration=0.4)
await asyncio.sleep(1)
scroll_path = take_screenshot(d, f"price_scroll_{scroll_idx}_{station_name}", save_dir=TEMP_IMAGE_DIR)
curr_price_md5 = Kit.get_image_content_md5(
scroll_path,
top_ratio=SAFE_EXCLUDE_RATIO,
price_screenshots = []
price_screenshots.append(after_click_path)
# 滑动处理
last_price_md5 = after_click_md5
for scroll_idx in range(2):
d.swipe(w // 2, int(h * 0.7), w // 2, int(h * 0.3), duration=0.4)
await asyncio.sleep(1)
scroll_path = take_screenshot(d, f"price_scroll_{scroll_idx}_{station_name}", save_dir=TEMP_IMAGE_DIR)
curr_price_md5 = Kit.get_image_content_md5(
scroll_path,
top_ratio=SAFE_EXCLUDE_RATIO,
bottom_ratio=BOTTOM_SAFE_EXCLUDE_RATIO
)
if curr_price_md5 == last_price_md5: break
price_screenshots.append(scroll_path)
last_price_md5 = curr_price_md5
# 后台处理价格图片
logger.info(f"已启动后台分析价格页: {station_name}，共 {len(price_screenshots)} 张图")
task_price = asyncio.create_task(analyze_prices_background(service, station_name, price_screenshots))
background_tasks.append(task_price)
# 立即返回
d.press("back")
await asyncio.sleep(0.5)
# 检查返回后的页面状态
check_back_path = take_screenshot(d, f"check_back_{detail_uuid}", save_dir=TEMP_IMAGE_DIR)
check_list_md5 = Kit.get_image_content_md5(
check_back_path,
top_ratio=SAFE_EXCLUDE_RATIO,
bottom_ratio=BOTTOM_SAFE_EXCLUDE_RATIO
)
if curr_price_md5 == last_price_md5: break
price_screenshots.append(scroll_path)
last_price_md5 = curr_price_md5
check_detail_md5 = Kit.get_image_content_md5(check_back_path)
if os.path.exists(check_back_path): os.remove(check_back_path)
# 后台处理价格图片
logger.info(f"已启动后台分析价格页: {station_name}，共 {len(price_screenshots)} 张图")
task_price = asyncio.create_task(analyze_prices_background(service, station_name, price_screenshots))
background_tasks.append(task_price)
# 立即返回
d.press("back")
await asyncio.sleep(0.5)
# 检查返回后的页面状态
check_back_path = take_screenshot(d, f"check_back_{detail_uuid}", save_dir=TEMP_IMAGE_DIR)
check_list_md5 = Kit.get_image_content_md5(
check_back_path,
top_ratio=SAFE_EXCLUDE_RATIO,
bottom_ratio=BOTTOM_SAFE_EXCLUDE_RATIO
)
check_detail_md5 = Kit.get_image_content_md5(check_back_path)
if os.path.exists(check_back_path): os.remove(check_back_path)
if check_list_md5 == current_md5:
logger.info("检测到已直接返回列表页，跳过后续返回操作。")
should_back_to_list = False
elif check_detail_md5 == before_click_md5:
logger.info("检测到返回详情页，需执行第二次返回。")
if check_list_md5 == current_md5:
logger.info("检测到已直接返回列表页，跳过后续返回操作。")
should_back_to_list = False
elif check_detail_md5 == before_click_md5:
logger.info("检测到返回详情页，需执行第二次返回。")
except Exception as e:
logger.error(f"处理三级页面详情异常 ({station_name}): {e}")