Created
July 25, 2025 13:39
-
-
Save ebuildy/6516dbaf3abca1489cf3f2dc64fde125 to your computer and use it in GitHub Desktop.
Meilisearch docs scraper
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
services: | |
engine: | |
image: getmeili/meilisearch:v1.15.0 | |
ports: | |
- 7700:7700 | |
environment: | |
MEILI_MASTER_KEY: myMasterKey | |
scraper: | |
image: getmeili/docs-scraper:v0.12.12 | |
command: | |
- sh | |
- -c | |
- | | |
echo "Start scraper" | |
pipenv run ./docs_scraper /opt/doc-admin.json | |
environment: | |
MEILISEARCH_HOST_URL: http://engine:7700 | |
MEILISEARCH_API_KEY: myMasterKey | |
volumes: | |
- ./:/opt/ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"index_uid": "docs-admin", | |
"start_urls": ["https://my-doc"], | |
"sitemap_urls": ["https://my-doc/sitemap.xml"], | |
"stop_urls": [], | |
"selectors": { | |
"lvl0": { | |
"selector": "article h1", | |
"global": true, | |
"default_value": "Documentation" | |
}, | |
"lvl1": { | |
"selector": "article h1", | |
"global": true, | |
"default_value": "Chapter" | |
}, | |
"lvl2": "article h2", | |
"lvl3": "article h3", | |
"lvl4": "article h4", | |
"lvl5": "article h5", | |
"lvl6": "article h6", | |
"text": "article" | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment