This repository has been archived by the owner on Jul 1, 2024. It is now read-only.

Rebuild Search Index #122

	name: Rebuild Search Index

	on:
	workflow_dispatch:
	workflow_run:
	workflows:
	- pages-build-deployment
	types:
	- completed

	jobs:
	scrape:
	name: Rebuild Index
	runs-on: ubuntu-latest
	container:
	image: typesense/docsearch-scraper:latest
	strategy:
	fail-fast: false
	matrix:
	node:
	- hel
	- fsn
	steps:
	-
	name: Run scraper
	env:
	HOME: /root
	TYPESENSE_API_KEY: ${{ secrets.TYPESENSE_SCRAPER_API_KEY }}
	TYPESENSE_HOST: ${{ matrix.node }}-typesense.1inch.io
	TYPESENSE_PORT: '443'
	TYPESENSE_PROTOCOL: https
	CONFIG: \|
	{
	"index_name": "1inch-docs",
	"start_urls": [
	"https://docs.1inch.io/"
	],
	"sitemap_urls": [
	"https://docs.1inch.io/sitemap.xml"
	],
	"sitemap_alternate_links": true,
	"stop_urls": [],
	"selectors": {
	"lvl0": {
	"selector": ".menu__link--sublist.menu__link--active",
	"global": true,
	"default_value": "Documentation"
	},
	"lvl1": "header h1",
	"lvl2": "article h2",
	"lvl3": "article h3",
	"lvl4": "article h4",
	"lvl5": "article h5, article td:first-child",
	"lvl6": "article h6",
	"text": "article p, article li, article td:last-child"
	},
	"strip_chars": " .,;:#",
	"custom_settings": {
	"separatorsToIndex": "_",
	"attributesForFaceting": [
	"language",
	"version",
	"type"
	],
	"attributesToRetrieve": [
	"hierarchy",
	"content",
	"anchor",
	"url",
	"url_without_anchor",
	"type"
	]
	},
	"conversation_id": [
	"1090805758"
	],
	"nb_hits": 8687
	}
	run: pipenv run python -m src.index
	working-directory: /root

Provide feedback