Grok Query Scrape
Use this skill to run a repeatable Grok automation workflow:
- Load Netscape-format cookies (for logged-in session reuse)
- Open Grok in a browser session
- Submit the prompt exactly as provided
- Wait for answer generation to stabilize
- Return and save raw output only (no parsing)
Language guides:
- Chinese guide: references/usage_zh.md
- English guide: references/usage_en.md
Workflow
- Install runtime dependencies when missing:
pip install patchright
Prepare a cookie file in Netscape format (example:
H:\cookies\grok.txt).Run the script:
python E:\projectHome\skill_grok\skill\grok-query-scrape\scripts\query_grok.py `
--cookie-file H:\cookies\grok.txt `
--prompt "Find top 10 AI productivity tweets from the last 24 hours." `
--output-dir E:\ `
--basename grok_ai_top10 `
--wait-seconds 240
- Check outputs:
<stdout>: Grok response text (verbatim capture frommain)<basename>_raw.txt: same raw Grok response text saved to file<basename>_meta.json: run metadata and paths
Script
Use query_grok.py for execution.
Key flags:
--cookie-file: Netscape cookie txt path (required)--prompt: inline prompt--prompt-file: prompt text file (alternative to--prompt)--output-dir: output folder (default.)--basename: output filename prefix (defaultgrok_result)--wait-seconds: max wait for response stabilization (default180)--headless: run browser headless--new-chat: sendCtrl+Jbefore query to reduce contamination (enabled by default)
Prompting Guidance
This skill forwards the prompt as-is, so put all constraints directly into your prompt text.
Failure Handling
If the output format is not what you need:
- Keep
_raw.txtas ground truth. - Tighten the prompt and retry.
- Keep
--new-chatenabled for isolation. - Increase
--wait-secondswhen generation is long.
If login fails:
- Refresh cookie file from a valid browser session.
- Keep domain/path/secure flags intact in Netscape format.
- Retry with
--headlessdisabled to inspect behavior.
scripts/
- query_grok.py: submit prompt, wait for answer, return/save raw/meta only.