← 返回 Skills 市场
icestorms

HTML-to-Selenium

作者 张 庆 ( Zhang Qing ) · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ 安全检测通过
143
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install html-to-selenium
功能描述
General webpage element analysis and Selenium automation control script generation. Use cases: (1) Analyze HTML element structure of any webpage (2) Automati...
使用说明 (SKILL.md)

General Webpage Element Analysis & Selenium Control

Overview

This skill analyzes HTML structure of any webpage, identifies interactive elements, and generates Selenium automation control code.

⚠️ Security Warnings

  1. Dependencies Required: Install selenium package and matching WebDriver before running

    pip install selenium

    WebDriver (Edge/Chrome/Firefox) must match your browser version

  2. Sensitive Data Risk:

    • Do not access internal network pages with sensitive information
    • Page HTML may contain tokens, CSRF credentials, etc.
    • Delete temporary files after analysis

  3. Authorized Pages Only:

    • Only analyze pages you have permission to access
    • Do not automate control of devices you don't own

Workflow

Step 1: Download Page Source

python scripts/fetch_page.py \x3CURL> -o \x3Coutput_file> -w \x3Cwait_seconds>

Step 2: LLM Analysis

Send the downloaded HTML to LLM for element identification and analysis.

Step 3: Generate Control Script

Write Selenium automation script based on analysis results.

Output Format

LLM analysis should include:

  • Page overview (title, framework)
  • Element inventory table (recommended locating method)
  • Complete Python code
  • Notes & considerations

通用网页元素分析与Selenium控制

概述

这个Skill用于分析任意网页的HTML结构，识别可交互元素，并生成Selenium自动化控制代码。

⚠️ 安全警告

  1. 依赖要求：运行前需安装 selenium 包和对应浏览器的 WebDriver

    pip install selenium

    WebDriver（Edge/Chrome/Firefox）需与浏览器版本匹配

  2. 敏感数据风险：

    • 不要访问包含敏感信息的内部网络页面
    • 页面HTML可能包含token、CSRF凭证等敏感数据
    • 分析完成后建议删除临时文件

  3. 仅用于授权页面：

    • 仅分析你有权限访问的页面
    • 不要自动化控制你不拥有的设备

工作流程

步骤1: 下载网页源码

python scripts/fetch_page.py \x3CURL> -o \x3C输出文件> -w \x3C等待秒数>

步骤2: 大模型分析

将下载的HTML源码发送给大模型进行元素识别和分析。

步骤3: 生成控制脚本

根据分析结果编写Selenium自动化脚本。

输出格式要求

大模型分析后应输出：

  • 页面概述（标题、框架）
  • 元素清单表格（推荐定位方式）
  • 完整Python代码
  • 注意事项
安全使用建议
This skill appears coherent with its purpose, but take these precautions before using it: - Only run it on pages you are authorized to access. The script will load arbitrary URLs from your environment and can access internal/network-only resources if run locally. - Install and use the correct browser WebDriver (the script uses Edge by default) and the selenium Python package. The skill does not install those for you. - Be cautious about sending downloaded HTML to external LLMs: page source can include tokens, CSRF values, or personally identifiable data. Remove or redact sensitive fields before transmission. - The script saves HTML to the current directory and by default deletes it; verify the cleanup behavior (use --keep if you want to retain files). Inspect any saved files before sharing them. - If you need broader browser support, consider updating the script to detect/choose the available WebDriver or use a webdriver-manager rather than assuming Edge. If you follow the above precautions, the skill's behavior is consistent with its stated function.
能力评估
✓ Purpose & Capability
Name/description ('HTML-to-Selenium') align with the included script and SKILL.md: the bundle downloads page HTML, enumerates interactive elements, and instructs generating Selenium control code. There are no unrelated environment variables or surprising binaries requested.
ℹ Instruction Scope
SKILL.md explicitly directs downloading pages and then sending the HTML to an LLM for analysis — this matches the skill's goal but is also the main privacy/safety concern because page HTML can contain tokens/CSRF data. The SKILL.md contains warnings about only using authorized pages and deleting temporary files, which is appropriate; however sending raw HTML to an external LLM could leak sensitive data and is left as a user responsibility.
✓ Install Mechanism
No install spec and only a small Python script are included (instruction-only style). No remote downloads or archives are executed, so there is low install-time risk.
✓ Credentials
The skill requires no environment variables or credentials. It does require the user to have the selenium package and a matching WebDriver available locally (the script uses Edge WebDriver). Those requirements are proportional to the stated functionality.
✓ Persistence & Privilege
always is false and the skill does not request permanent presence or modify other skills/config. It writes temporary files to the working directory (and deletes them by default); that's expected for its operation.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install html-to-selenium
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /html-to-selenium 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.2
- Added full English documentation and description alongside existing Chinese content for broader accessibility. - Clarified workflow and output format sections for both languages. - Updated security warnings and dependency instructions to ensure correct usage. - No code or functional changes; documentation only.
v1.0.1
Version 1.0.1 - 增加安全与合规声明，强调仅限分析公开或有授权的网页 - 新增依赖安装和WebDriver版本要求说明 - 强调页面敏感信息风险和临时文件删除建议 - 简化和精炼“工作流程”与“输出格式要求”部分 - 移除部分操作细节，突出大模型分析和自动化脚本生成功能
v1.0.0
Initial release of universal HTML analysis and Selenium script generation skill. - Analyze any webpage's HTML structure and identify interactive elements. - Auto-detect form controls (inputs, buttons, selects) for automation. - Provides prompts and workflow for detailed large-model-driven page analysis. - Generates Python Selenium scripts covering login, search, form submission, and dynamic content handling. - Includes fetch_page.py utility for reliable HTML downloading with custom wait times.
元数据
Slug html-to-selenium
版本 1.0.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

HTML-to-Selenium 是什么？

General webpage element analysis and Selenium automation control script generation. Use cases: (1) Analyze HTML element structure of any webpage (2) Automati... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 143 次。

如何安装 HTML-to-Selenium？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install html-to-selenium」即可一键安装，无需额外配置。

HTML-to-Selenium 是免费的吗？

是的，HTML-to-Selenium 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

HTML-to-Selenium 支持哪些平台？

HTML-to-Selenium 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 HTML-to-Selenium？

由 张 庆 ( Zhang Qing )（@icestorms）开发并维护，当前版本 v1.0.2。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论