xscrape/dist/index.d.cts

A flexible and powerful library designed to extract and transform data from HTML documents using user-defined schemas

import { StandardSchemaV1 } from '@standard-schema/spec';
import { Element } from 'domhandler';

type ExtractDescriptorFn = (el: Element, key: string, obj: Record<string, unknown>) => unknown;
interface ExtractDescriptor {
    selector: string;
    value?: string | ExtractDescriptorFn | ExtractMap;
}
type ExtractValue = string | ExtractDescriptor | [string | ExtractDescriptor];
type ExtractMap = Record<string, ExtractValue>;

type SchemaAwareExtractMap<T> = {
    [K in keyof T]: ExtractMap[string];
};
type ScraperConfig<S extends StandardSchemaV1, R extends StandardSchemaV1.InferOutput<S> = StandardSchemaV1.InferOutput<S>> = {
    schema: S;
    extract: SchemaAwareExtractMap<StandardSchemaV1.InferOutput<S>>;
    transform?: (data: StandardSchemaV1.InferOutput<S>) => Promise<R> | R;
};
type ValidationResult<T> = {
    success: boolean;
    data?: T;
    error?: unknown;
};
type ScraperResult<T> = {
    data?: T;
    error?: unknown;
};

declare function defineScraper<S extends StandardSchemaV1, T extends StandardSchemaV1.InferOutput<S> = StandardSchemaV1.InferOutput<S>, R extends T = T>(config: ScraperConfig<S, R>): (html: string) => Promise<ScraperResult<R>>;

export { type ScraperConfig, type ScraperResult, type ValidationResult, defineScraper };