解析账号

This commit is contained in:
mzl
2026-01-10 22:09:31 +08:00
parent a7f36e2ef1
commit 420c9b872a
2 changed files with 25 additions and 28 deletions
+9 -24
View File
@@ -544,30 +544,15 @@ def resolve_profile(payload: Dict[str, Any], token: Optional[str] = None):
slow_mo = int(payload.get("slow_mo", 0)) slow_mo = int(payload.get("slow_mo", 0))
try: try:
# 判断是否为小红书号(纯字母数字,不含空格和特殊字符) # 统一使用搜索方式解析(按您的需求:搜索框输入 → 用户标签 → 获取URL)
import re loghub.emit(f"[解析] 开始搜索解析:{keyword}")
is_xhs_id = bool(re.match(r'^[A-Za-z0-9]+$', keyword)) profile = resolve_profile_by_search(
keyword=keyword,
if is_xhs_id: storage_state_path=storage_path,
# 对于小红书号,使用直接访问方式避免搜索跳转问题 headless=headless,
loghub.emit(f"[解析] 检测到小红书号格式,使用直接访问方式:{keyword}") slow_mo=slow_mo,
profile = resolve_profile_by_direct_url( log=loghub.emit,
xhs_id=keyword, )
storage_state_path=storage_path,
headless=headless,
slow_mo=slow_mo,
log=loghub.emit,
)
else:
# 对于昵称或其他关键词,使用搜索方式
loghub.emit(f"[解析] 使用搜索方式解析:{keyword}")
profile = resolve_profile_by_search(
keyword=keyword,
storage_state_path=storage_path,
headless=headless,
slow_mo=slow_mo,
log=loghub.emit,
)
except Exception as e: except Exception as e:
loghub.emit(f"[解析][错误] {e}") loghub.emit(f"[解析][错误] {e}")
raise HTTPException(status_code=400, detail=str(e)) raise HTTPException(status_code=400, detail=str(e))
+16 -4
View File
@@ -618,23 +618,35 @@ def resolve_profile_by_search(
continue continue
score = 0 score = 0
score_reasons = []
# 精确匹配小红书号:最高优先级 # 精确匹配小红书号:最高优先级
if xhs_no and xhs_no.lower() == kw.lower(): if xhs_no and xhs_no.lower() == kw.lower():
score += 1000 score += 1000
score_reasons.append("小红书号精确匹配")
# 精确匹配昵称:高优先级 # 精确匹配昵称:高优先级
elif nickname and nickname.lower() == kw.lower(): if nickname and nickname.lower() == kw.lower():
score += 500 score += 500
# 昵称包含关键词:中优先级 score_reasons.append("昵称精确匹配")
elif nickname and kw.lower() in nickname.lower():
# 昵称包含关键词:中优先级(不使用 elif,允许累加)
if nickname and kw.lower() in nickname.lower() and nickname.lower() != kw.lower():
score += 50 score += 50
score_reasons.append("昵称包含关键词")
# URL 中包含关键词:低优先级 # URL 中包含关键词:低优先级
if kw.lower() in href.lower(): if kw.lower() in href.lower():
score += 20 score += 20
score_reasons.append("URL包含关键词")
# 有有效的 profile ID:基础分 # 有有效的 profile ID:基础分
if _extract_profile_id_from_href(href): if _extract_profile_id_from_href(href):
score += 5 score += 5
score_reasons.append("有效Profile ID")
_log(log, f"[账号] - 昵称: {nickname[:30] if len(nickname) > 30 else nickname}, 账号: {xhs_no}, 得分: {score}") reasons_str = ", ".join(score_reasons) if score_reasons else "无匹配"
_log(log, f"[账号] - 昵称: {nickname[:30] if len(nickname) > 30 else nickname}, 账号: {xhs_no}, 得分: {score} ({reasons_str})")
if score > best_score: if score > best_score:
best_score = score best_score = score