LLM Chat Scraper OpenClaw Skill

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

Authentication: Set X_API_TOKEN in your environment or in a .env file in the repo root.

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

Tools

1. ChatGPT Scraper

Scrape ChatGPT responses with optional web search enrichment. Returns JSON object with result_text, model, links, citations, and more.

Command:
CODEBLOCK0

Examples:

python3 scripts/llm_chat_scraper.py chatgpt --query "Most reliable proxy service for data extraction"
python3 s
Optional: `--country` fcripts/llm_chat_scraper.py chatgpt --query "AI trends in 2024" --web-search
python3 scripts/llm_chat_scraper.py chatgpt --query "Best programming languages" --country GB

2. Gemini Scraper

Scrape Google Gemini responses. Returns JSON object with result_text, citations, and more.

Command:
CODEBLOCK2

Examples:
CODEBLOCK3

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

3. Perplexity Scraper

Scrape Perplexity AI responses with optional web search. Returns JSON object with result_text, related_prompt, web_results, media_items.

Command:
CODEBLOCK4

Examples:
CODEBLOCK5

Optional: --country for location, --web-search to enable web search.

4. Copilot Scraper

Scrape Microsoft Copilot responses across different modes (search, smart, chat, reasoning, study). Returns JSON object with result_text, mode, links, citations.

Command:
CODEBLOCK6

Examples:
CODEBLOCK7

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

5. Google AI Mode Scraper

Scrape Google AI Mode responses. Returns JSON object with result_text, result_md, result_html, citations, raw_url.

Command:
CODEBLOCK8

Examples:
CODEBLOCK9

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

6. Grok Scraper

Scrape xAI Grok responses with different modes (FAST, EXPERT, AUTO). Returns JSON object with full_response, user_model, follow_up_suggestions, web_search_results.

Command:
CODEBLOCK10

Examples:
CODEBLOCK11

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

Summary

Output: All commands return JSON objects with model-specific fields (see tool descriptions above).

Response Fields by Model

ChatGPT

• - result_text: Markdown response
• INLINECODE53: Model identifier (e.g., gpt-4)
• INLINECODE54: Boolean indicating if search ran
• INLINECODE55: Array of supplementary links
• INLINECODE56: Array of content references

Gemini

• - result_text: Markdown response
• INLINECODE58: Array with favicon, highlights, snippet, title, url, website_name

Perplexity

• - result_text: Markdown response
• INLINECODE60: Array of related questions
• INLINECODE61: Array with name, url, snippet
• INLINECODE62: Array of media references

Copilot

• - result_text: Markdown response
• INLINECODE64: Mode used (search/smart/chat/reasoning/study)
• INLINECODE65: Array of outbound links
• INLINECODE66: Array with title, url

Google AI Mode

• - result_text: Answer body
• INLINECODE68: Markdown version
• INLINECODE69: HTML version
• INLINECODE70: Original URL
• INLINECODE71: Array with snippet, thumbnail, title, url, website_name, favicon

Grok

• - full_response: Response content
• INLINECODE73: Model used
• INLINECODE74: Array of suggested questions
• INLINECODE75: Array with preview, title, url
• INLINECODE76: Object with conversation metadata

Notes

⚠️ Regional Restrictions:

• - Gemini, Copilot, Google AI Mode, and Grok do not support Japan (JP) and Taiwan (TW)

⚠️ Result Expiry:

• - Task results are available for 12 hours

⚠️ Rate Limits:

• - 429 errors indicate rate limit exceeded. Reduce request frequency or upgrade plan.