mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-14 20:40:33 +00:00
27 lines
774 B
YAML
27 lines
774 B
YAML
loaders:
|
|
- type: loaders.CustomPythonLoader
|
|
search_path: [../../../haystack/nodes/connector]
|
|
modules: ["crawler"]
|
|
ignore_when_discovered: ["__init__"]
|
|
processors:
|
|
- type: filter
|
|
expression:
|
|
documented_only: true
|
|
do_not_filter_modules: false
|
|
skip_empty_modules: true
|
|
- type: smart
|
|
- type: crossref
|
|
renderer:
|
|
type: renderers.ReadmeRenderer
|
|
excerpt: The Crawler scrapes the text from a website, creates a Haystack Document object out of it, and saves it to a JSON file.
|
|
category_slug: haystack-classes
|
|
title: Crawler API
|
|
slug: crawler-api
|
|
order: 10
|
|
markdown:
|
|
descriptive_class_title: false
|
|
descriptive_module_title: true
|
|
add_method_class_prefix: true
|
|
add_member_class_prefix: false
|
|
filename: crawler_api.md
|