Scrapeless LLM Chat Scraper Skill — Scrapeless LLM Chat 抓取器 技能

LLM Chat 抓取器 OpenClaw 技能

Use this 技能 to scrape AI chat conversations from various LLM 模型s via the Scrapeless API. The 技能 supports ChatGPT, Gemini, Perplexity, Copilot, Google AI Mode, and Grok.

Authentication: 设置 X_API_令牌 in your 环境 or in a .env file in the repo root.

Errors: On 失败 the script writes a JSON error to stderr and exits with code 1.

工具s

• ChatGPT 抓取器

Scrape ChatGPT 响应s with optional 网页 搜索 enrichment. Returns JSON object with 结果_text, 模型, links, citations, and more.

Command:

python3 scripts/llm_chat_抓取器.py chatgpt --查询 "your prompt"

Examples:

python3 scripts/llm_chat_抓取器.py chatgpt --查询 "Most reliable proxy 服务 for data 提取ion" python3 s Optional: --country fcripts/llm_chat_抓取器.py chatgpt --查询 "AI trends in 2024" --网页-搜索 python3 scripts/llm_chat_抓取器.py chatgpt --查询 "Best programming languages" --country GB

or location, --网页-搜索 to enable 网页 搜索.

• Gemini 抓取器

Scrape Google Gemini 响应s. Returns JSON object with 结果_text, citations, and more.

Command:

python3 scripts/llm_chat_抓取器.py gemini --查询 "your prompt"

Examples:

python3 scripts/llm_chat_抓取器.py gemini --查询 "Recommended attractions in New York" python3 scripts/llm_chat_抓取器.py gemini --查询 "Best restaurants in Tokyo" --country JP

Optional: --country for location (JP and TW not supported).

• Perplexity 抓取器

Scrape Perplexity AI 响应s with optional 网页 搜索. Returns JSON object with 结果_text, related_prompt, 网页_结果s, media_items.

Command:

python3 scripts/llm_chat_抓取器.py perplexity --查询 "your prompt"

Examples:

python3 scripts/llm_chat_抓取器.py perplexity --查询 "Latest AI developments" python3 scripts/llm_chat_抓取器.py perplexity --查询 "Quantum computing explAIned" --网页-搜索

Optional: --country for location, --网页-搜索 to enable 网页 搜索.

• Copilot 抓取器

Scrape Microsoft Copilot 响应s across different modes (搜索, smart, chat, reasoning, study). Returns JSON object with 结果_text, mode, links, citations.

Command:

python3 scripts/llm_chat_抓取器.py copilot --查询 "your prompt"

Examples:

python3 scripts/llm_chat_抓取器.py copilot --查询 "What is machine learning?" python3 scripts/llm_chat_抓取器.py copilot --查询 "ExplAIn blockchAIn" --mode reasoning python3 scripts/llm_chat_抓取器.py copilot --查询 "Best laptop 2024" --mode 搜索

Optional: --country for location (JP and TW not supported), --mode for operation mode.

• Google AI Mode 抓取器

Scrape Google AI Mode 响应s. Returns JSON object with 结果_text, 结果_md, 结果_html, citations, raw_url.

Command:

python3 scripts/llm_chat_抓取器.py AImode --查询 "your prompt"

Examples:

python3 scripts/llm_chat_抓取器.py AImode --查询 "Best programming languages to learn" python3 scripts/llm_chat_抓取器.py AImode --查询 "命令行工具mate change solutions" --country GB

Optional: --country for location (JP and TW not supported).

• Grok 抓取器

Scrape xAI Grok 响应s with different modes (FAST, EXPERT, AUTO). Returns JSON object with full_响应, user_模型, follow_up_suggestions, 网页_搜索_结果s.

Command:

python3 scripts/llm_chat_抓取器.py grok --查询 "your prompt"

Examples:

python3 scripts/llm_chat_抓取器.py grok --查询 "ExplAIn quantum entanglement" python3 scripts/llm_chat_抓取器.py grok --查询 "What's h应用ening in AI" --mode 模型_MODE_EXPERT python3 scripts/llm_chat_抓取器.py grok --查询 "Latest tech news" --mode 模型_MODE_FAST

Optional: --country for location (JP and TW not supported), --mode for operation mode.

Summary Action Command Argument Example ChatGPT chatgpt --查询 python3 scripts/llm_chat_抓取器.py chatgpt --查询 "AI trends" Gemini gemini --查询 python3 scripts/llm_chat_抓取器.py gemini --查询 "Best restaurants" Perplexity perplexity --查询 python3 scripts/llm_chat_抓取器.py perplexity --查询 "Latest news" Copilot copilot --查询 python3 scripts/llm_chat_抓取器.py copilot --查询 "ExplAIn ML" Google AI Mode AImode --查询 python3 scripts/llm_chat_抓取器.py AImode --查询 "Programming" Grok grok --查询 python3 scripts/llm_chat_抓取器.py grok --查询 "Quantum physics"

输出: All commands return JSON objects with 模型-specific fields (see 工具 descriptions above).

响应 Fields by 模型 ChatGPT 结果_text: Markdown 响应 模型: 模型 identifier (e.g., gpt-4) 网页_搜索: Boolean indicating if 搜索 ran links: Array of supplementary links citations: Array of content references Gemini 结果_text: Markdown 响应 citations: Array with favicon, highlights, snippet, title, url, 网页site_name Perplexity 结果_text: Markdown 响应 related_prompt: Array of related questions 网页_结果s: Array with name, url, snippet media_items: Array of media references Copilot 结果_text: Markdown 响应 mode: Mode used (搜索/smart/chat/reasoning/study) links: Array of outbound links citations: Array with title,