Dianping-query

v1.0.0

查询大众点评餐厅信息。使用场景:(1) 用户要查询某家餐厅的评分、人均消费、地址 (2) 用户要搜索特定菜系或区域的餐厅推荐 (3) 用户要获取附近美食推荐。登录账号:一定S。重要:搜索时URL需包含城市ID(如hangzhou页面),账号定位北京时需使用URL参数方式绕过。

1· 2.2k·7 current·8 all-time
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
The name/description (query Dianping restaurant info) matches the SKILL.md steps: open city URL, run searches, and extract listing fields. No unrelated services, binaries, or credentials are requested.
Instruction Scope
Instructions are narrowly focused on opening Dianping pages, using browser.tabs, and extracting restaurant data. Two points to note: (1) the doc both says '无需登录即可访问杭州地区内容' and also instructs to '确认登录状态' and provides a named account ('一定S'), which is inconsistent and could confuse operators; (2) it tells the agent to prompt the user for a phone number and verification code to log in—this is sensitive user data and outside simple read-only scraping.
Install Mechanism
Instruction-only skill with no install steps and no code files — nothing is written to disk or downloaded by the skill itself.
Credentials
The skill declares no environment variables or secrets, which is proportionate. However, it explicitly expects interactive login flow and requests the user's phone number and verification code if not logged in; this is sensitive and the skill doesn't state how such data is handled or stored.
Persistence & Privilege
No 'always' flag, no requested system persistence, and no explicit credentials are stored by the skill. Model invocation is not disabled (default), so the model could invoke the skill autonomously unless platform-level controls prevent that.
Assessment
This skill appears to do what it says: open Dianping city pages and extract restaurant info. Before installing, confirm you trust the skill's source (no homepage or maintainer info is provided). Be cautious about providing phone numbers or verification codes—prefer logging in yourself in a trusted browser session rather than handing codes to an automated skill. If you don't want the skill invoked autonomously, ask the platform to disable model-initiated calls or set the skill to require explicit user invocation. Finally, if the named account ('一定S') is supposed to be used, ask the publisher why it’s included and whether any credentials will be stored or transmitted.

Like a lobster shell, security has layers — review code before you run it.

latestvk9734cp7y9r18zf0h3k4v1wsf580f4cb
2.2kdownloads
1stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Dianping Query

Quick Start

  1. 用 browser 工具打开大众点评杭州首页https://www.dianping.com/hangzhou
    • 无需登录即可访问杭州地区内容
    • URL中的 /hangzhoucityId=3 表示杭州
  2. 确认登录状态(显示"一定S"即已登录)
  3. 在搜索框输入餐厅名称或关键词
  4. 重要:搜索结果在新标签页打开,URL格式为 https://www.dianping.com/ai-search?keyword=...
  5. 使用 browser.tabs 查看所有打开的页面
  6. 从AI搜索结果页面提取餐厅信息卡片

登录账号

  • 用户名:一定S
  • 如果未登录,需要用户配合输入手机号和验证码

城市定位问题处理

问题现象

  • 账号显示定位在北京,无法切换到杭州
  • 搜索结果会跳转到北京地区

解决方案(按优先级)

方案1:使用杭州URL(推荐)

  • 直接访问 https://www.dianping.com/hangzhou 而非首页
  • 搜索结果会自动关联杭州地区
  • 无需账号切换,cookie定位不影响URL访问

方案2:搜索时指定城市

  • 搜索词加上城市名,如:"杭州滨江区好吃的餐厅"
  • URL参数会包含城市信息:keyword/3/0_杭州滨江区...

方案3:浏览器地址栏修改

  • 在地址栏手动修改城市ID
  • 北京是 cityId=2,杭州是 cityId=3

城市ID参考

城市cityIdURL示例
杭州3dianping.com/hangzhou
北京2dianping.com/
上海1dianping.com/shanghai

搜索结果提取

从AI搜索结果页面提取以下信息:

  • 餐厅名称(link元素)
  • 评分(⭐数字星)
  • 人均消费(¥数字)
  • 地址/位置
  • 特色描述和推荐菜品
  • 用户评价摘要

常见搜索场景

按名称查询:

搜索词:靠北泰式打抛饭
结果:店铺名称、评分4.2星、¥37、地址在拱墅区银树湾

按区域查询(使用杭州URL):

URL: https://www.dianping.com/hangzhou
搜索词:滨江区好吃的餐厅
结果:7,799个相关商户,包含TOP推荐列表

按菜系查询:

搜索词:杭州泰式料理
结果:多家泰式餐厅列表,包含评分、人均、地址

注意事项

  • 搜索结果页面可能需要滚动加载完整内容
  • 店休、营业时间等特殊信息也会显示在结果中
  • 点击餐厅名称可查看详情页
  • 使用杭州URL可以绕过账号定位问题

Comments

Loading comments...