browser-automation
>
它会碰到什么
这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。
技能内容
Browser Automation
> Category: Engineering
> Domain: Web Automation
Overview
The Browser Automation skill provides tools for building robust web automation, checking scripts for bot detection signatures, generating form automation code, and creating web scraping solutions with rate limiting and best practices.
Clarify First
Before generating automation, confirm these inputs. If any is unknown or vague, ASK — do not assume:
- [ ] Target site & task — the URL and exactly what to automate or scrape (drives the generated selectors and flow)
- [ ] Which tool — audit an existing script, build form automation, or generate a scraper (selects
anti_detection_checker.pyvsform_automation_builder.pyvsscraping_toolkit.py) - [ ] Politeness strategy & authorization — polite vs aggressive, robots.txt compliance, and that you are permitted to automate this target (sets request delays and backoff in the generated code)
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Quick Start
# Check automation script for detection signatures
python scripts/anti_detection_checker.py --file ./my_scraper.py
# Generate form automation code from HTML
python scripts/form_automation_builder.py --url https://example.com/form --output form_script.py
# Generate scraping code with rate limiting
python scripts/scraping_toolkit.py --url https://example.com --strategy polite --output scraper.py
Tools Overview
| Tool | Purpose | Key Flags |
|------|---------|-----------|
| anti_detection_checker.py | Audit automation code for bot detection signatures | --file, --format |
| form_automation_builder.py | Generate form filling scripts from HTML analysis | --url, --html-file, --output |
| scraping_toolkit.py | Generate web scraping code with rate limiting | --url, --strategy, --output |
Workflows
Build Reliable Scraper
- Analyze target with
scraping_toolkit.pyto generate base code - Check generated code with
anti_detection_checker.py - Address any detection signatures found
- Test with progressive rate limiting
Automate Form Submission
- Provide form HTML to
form_automation_builder.py - Review generated script for field mappings
- Customize data sources and validation
- Run anti-detection check on final script
Reference Documentation
- [Browser Automation Guide](references/browser-automation-guide.md) - Anti-detection techniques, rate limiting strategies, ethical scraping practices
Common Patterns
Polite Scraping
- Respect robots.txt directives
- Implement exponential backoff on errors
- Use 2-5 second delays between requests
- Identify your bot with a descriptive User-Agent
- Cache responses to minimize repeat requests
Anti-Detection Best Practices
- Rotate User-Agent strings realistically
- Randomize request timing (avoid fixed intervals)
- Handle cookies and sessions properly
- Avoid headless browser fingerprinting tells
想直接用这个技能?
本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。