mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-07-12 22:42:13 +02:00
7ba77c6b86
- Introduced a `docs_url` field to the Google Maps reviews, scrape, YouTube comments, YouTube scrape, and web crawl capabilities for improved documentation access. - Simplified descriptions for each capability to enhance clarity and user understanding.
22 lines
744 B
Python
22 lines
744 B
Python
"""``web.crawl`` capability registration."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from app.capabilities.core import BillingUnit, Capability, register_capability
|
|
from app.capabilities.web.crawl.executor import build_crawl_executor
|
|
from app.capabilities.web.crawl.schemas import CrawlInput, CrawlOutput
|
|
|
|
WEB_CRAWL = Capability(
|
|
name="web.crawl",
|
|
description=(
|
|
"Scrape pages or crawl websites for clean markdown, links, metadata, "
|
|
"and contact signals. Use startUrls and crawl-depth controls."
|
|
),
|
|
input_schema=CrawlInput,
|
|
output_schema=CrawlOutput,
|
|
executor=build_crawl_executor(),
|
|
billing_unit=BillingUnit.WEB_CRAWL,
|
|
docs_url="/docs/connectors/native/web-crawl",
|
|
)
|
|
|
|
register_capability(WEB_CRAWL)
|