@d-zero/beholder 2.0.0 → 2.0.1

package/CHANGELOG.md

@@ -3,6 +3,10 @@
 All notable changes to this project will be documented in this file.
 See [Conventional Commits](https://conventionalcommits.org) for commit guidelines.
 
+## [2.0.1](https://github.com/d-zero-dev/tools/compare/@d-zero/beholder@2.0.0...@d-zero/beholder@2.0.1) (2026-03-11)
+
+**Note:** Version bump only for package @d-zero/beholder
+
 # [2.0.0](https://github.com/d-zero-dev/tools/compare/@d-zero/beholder@0.1.29...@d-zero/beholder@2.0.0) (2026-02-26)
 
 - feat(beholder)!: replace SubProcessRunner with in-process Scraper ([eaf2768](https://github.com/d-zero-dev/tools/commit/eaf276898d96dccf6b504b22b7c8f0234162e82e))

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@d-zero/beholder",
-	"version": "2.0.0",
+	"version": "2.0.1",
 	"description": "Page-level scraper for web crawling and auditing",
 	"author": "D-ZERO",
 	"license": "MIT",
@@ -20,13 +20,12 @@
 		"clean": "tsc --build --clean"
 	},
 	"dependencies": {
-		"@d-zero/puppeteer-page-scan": "4.4.5",
-		"@d-zero/shared": "0.20.1",
+		"@d-zero/puppeteer-page-scan": "4.4.6",
+		"@d-zero/shared": "0.21.0",
 		"debug": "4.4.3",
 		"puppeteer": "24.37.5"
 	},
 	"devDependencies": {
 		"@types/debug": "4.1.12"
-	},
-	"gitHead": "a6b5eb0a0a327c003053f7c25be4c075ed319c76"
+	}
 }

package/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2024 D-ZERO Co., Ltd.
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

package/dist/debug.d.ts

@@ -1,9 +0,0 @@
-import debug from 'debug';
-/** Root debug logger for the beholder package. */
-export declare const scraperLog: debug.Debugger;
-/** Debug logger for resource fetching. */
-export declare const resourceLog: debug.Debugger;
-/** Debug logger for DOM evaluation. */
-export declare const domLog: debug.Debugger;
-/** Debug logger for detailed DOM evaluation output. */
-export declare const domDetailsLog: debug.Debugger;

package/dist/debug.js

@@ -1,9 +0,0 @@
-import debug from 'debug';
-/** Root debug logger for the beholder package. */
-export const scraperLog = debug('Beholder');
-/** Debug logger for resource fetching. */
-export const resourceLog = scraperLog.extend('Resource');
-/** Debug logger for DOM evaluation. */
-export const domLog = scraperLog.extend('DOM');
-/** Debug logger for detailed DOM evaluation output. */
-export const domDetailsLog = domLog.extend('Details');

package/dist/dom-evaluation.d.ts

@@ -1,109 +0,0 @@
-/**
- * DOM evaluation functions for extracting structured data from Puppeteer pages.
- *
- * These functions are called by {@link ./scraper.ts | Scraper.#fetchData} to extract
- * anchors, images, and meta information after page navigation completes.
- * @see {@link ./types.ts} for the data types returned by these functions
- */
-import type { AnchorData, ImageElement, ParseURLOptions } from './types.js';
-import type { ElementHandle, Page } from 'puppeteer';
-/**
- * Parameters for {@link getProp}.
- * @template T - The expected type of the property value.
- */
-export interface GetPropParams<T> {
-    /** The Puppeteer element handle to read the property from. */
-    readonly $el: ElementHandle<Element>;
-    /** The name of the DOM property to retrieve (e.g., `"href"`, `"textContent"`). */
-    readonly propName: string;
-    /** The default value to return if the property cannot be read or times out. */
-    readonly fallback: T;
-}
-/**
- * Retrieves a DOM property value from a Puppeteer element handle with a timeout.
- *
- * Races the actual property retrieval against a 10-second timeout.
- * If the property cannot be read or the timeout expires, the fallback value is returned.
- * @template T - The expected type of the property value.
- * @param params - Parameters containing the element, property name, and fallback.
- * @returns The property value, or the fallback if retrieval fails.
- */
-export declare function getProp<T>(params: GetPropParams<T>): Promise<T>;
-/**
- * Parameters for {@link getPropBySelector}.
- * @template T - The expected type of the property value.
- */
-export interface GetPropBySelectorParams<T> {
-    /** The Puppeteer page to query. */
-    readonly page: Page;
-    /** A CSS selector to find the target element. */
-    readonly selector: string;
-    /** The DOM property name to read from the matched element. */
-    readonly propName: string;
-    /** The default value if no element matches or the property cannot be read. */
-    readonly fallback: T;
-}
-/**
- * Retrieves a DOM property value from the first element matching a CSS selector.
- *
- * Combines `page.$()` with {@link getProp} for convenient single-element lookups.
- * @template T - The expected type of the property value.
- * @param params - Parameters containing the page, selector, property name, and fallback.
- * @returns The property value, or the fallback if the element is not found or retrieval fails.
- */
-export declare function getPropBySelector<T>(params: GetPropBySelectorParams<T>): Promise<T>;
-/**
- * Extracts all `<img>` elements from the page and returns their properties.
- *
- * For each image, collects the `src`, `currentSrc`, `alt`, bounding box dimensions,
- * natural dimensions, lazy-loading status, and the outer HTML source code.
- * @param page - The Puppeteer page to extract images from.
- * @param viewportWidth - The current viewport width in pixels, recorded alongside each image entry.
- * @returns An array of {@link ImageElement} objects describing each image on the page.
- */
-export declare function getImageList(page: Page, viewportWidth: number): Promise<ImageElement[]>;
-/**
- * Extracts all anchor (`<a>` and `<area>`) elements with `href` attributes from the page.
- *
- * For each anchor, resolves the `href` to an `ExURL` via `parseUrl`, retrieves
- * the accessible name (from the accessibility tree, falling back to `textContent`),
- * and filters out non-HTTP links.
- * @param page - The Puppeteer page to extract anchors from.
- * @param options - Optional URL parsing options (e.g., `disableQueries`).
- * @returns An array of {@link AnchorData} objects for all HTTP(S) links found on the page.
- */
-export declare function getAnchorList(page: Page, options?: ParseURLOptions): Promise<AnchorData[]>;
-/**
- * Extracts comprehensive meta information from the page's `<head>`.
- *
- * Collects the following metadata:
- * - `title` - The document title.
- * - `lang` - The `lang` attribute of the `<html>` element.
- * - `description` - The `<meta name="description">` content.
- * - `keywords` - The `<meta name="keywords">` content.
- * - `noindex` / `nofollow` / `noarchive` - Parsed from the `<meta name="robots">` directives.
- * - `canonical` - The `<link rel="canonical">` content.
- * - `alternate` - The `<link rel="alternate">` content.
- * - Open Graph tags: `og:type`, `og:title`, `og:site_name`, `og:description`, `og:url`, `og:image`.
- * - `twitter:card` - The Twitter Card type.
- * @param page - The Puppeteer page to extract meta information from.
- * @returns An object containing all extracted meta properties.
- */
-export declare function getMeta(page: Page): Promise<{
-    title: string;
-    lang: string;
-    description: string;
-    keywords: string;
-    noindex: boolean;
-    nofollow: boolean;
-    noarchive: boolean;
-    canonical: string;
-    alternate: string;
-    'og:type': string;
-    'og:title': string;
-    'og:site_name': string;
-    'og:description': string;
-    'og:url': string;
-    'og:image': string;
-    'twitter:card': string;
-}>;

package/dist/dom-evaluation.js

@@ -1,273 +0,0 @@
-/**
- * DOM evaluation functions for extracting structured data from Puppeteer pages.
- *
- * These functions are called by {@link ./scraper.ts | Scraper.#fetchData} to extract
- * anchors, images, and meta information after page navigation completes.
- * @see {@link ./types.ts} for the data types returned by these functions
- */
-import { domDetailsLog, domLog } from './debug.js';
-import { parseUrl } from './parse-url.js';
-const pid = `${process.pid}`;
-const log = domLog.extend(pid);
-const dLog = domDetailsLog.extend(pid);
-/**
- * Retrieves a DOM property value from a Puppeteer element handle with a timeout.
- *
- * Races the actual property retrieval against a 10-second timeout.
- * If the property cannot be read or the timeout expires, the fallback value is returned.
- * @template T - The expected type of the property value.
- * @param params - Parameters containing the element, property name, and fallback.
- * @returns The property value, or the fallback if retrieval fails.
- */
-export async function getProp(params) {
-    const { $el, propName, fallback } = params;
-    return Promise.race([
-        _getProp($el, propName, fallback),
-        new Promise((res) => setTimeout(() => res(fallback), 10 * 1000)),
-    ]);
-}
-/**
- * Internal implementation of property retrieval without timeout.
- * @template T - The expected type of the property value.
- * @param $el - The Puppeteer element handle.
- * @param propName - The DOM property name.
- * @param fallback - The default value on failure.
- * @returns The property value cast to `T`, or the fallback.
- */
-async function _getProp($el, propName, fallback) {
-    try {
-        const prop = await $el.getProperty(propName);
-        if (!prop) {
-            return fallback;
-        }
-        const value = (await prop.jsonValue());
-        return value;
-    }
-    catch {
-        return fallback;
-    }
-}
-/**
- * Retrieves a DOM property value from the first element matching a CSS selector.
- *
- * Combines `page.$()` with {@link getProp} for convenient single-element lookups.
- * @template T - The expected type of the property value.
- * @param params - Parameters containing the page, selector, property name, and fallback.
- * @returns The property value, or the fallback if the element is not found or retrieval fails.
- */
-export async function getPropBySelector(params) {
-    const { page, selector, propName, fallback } = params;
-    const $el = await page.$(selector);
-    if (!$el) {
-        return fallback;
-    }
-    return getProp({ $el, propName, fallback });
-}
-/**
- * Extracts all `<img>` elements from the page and returns their properties.
- *
- * For each image, collects the `src`, `currentSrc`, `alt`, bounding box dimensions,
- * natural dimensions, lazy-loading status, and the outer HTML source code.
- * @param page - The Puppeteer page to extract images from.
- * @param viewportWidth - The current viewport width in pixels, recorded alongside each image entry.
- * @returns An array of {@link ImageElement} objects describing each image on the page.
- */
-export async function getImageList(page, viewportWidth) {
-    log('Getting images (Viewport: %dpx)', viewportWidth);
-    const $images = await page.$$('img');
-    const imageList = [];
-    for (const $image of $images) {
-        const boundingBox = await $image.boundingBox();
-        const width = boundingBox?.width || 0;
-        const height = boundingBox?.height || 0;
-        const src = await getProp({ $el: $image, propName: 'src', fallback: '' });
-        const currentSrc = await getProp({
-            $el: $image,
-            propName: 'currentSrc',
-            fallback: '',
-        });
-        const alt = await getProp({ $el: $image, propName: 'alt', fallback: '' });
-        const naturalWidth = await getProp({
-            $el: $image,
-            propName: 'naturalWidth',
-            fallback: 0,
-        });
-        const naturalHeight = await getProp({
-            $el: $image,
-            propName: 'naturalHeight',
-            fallback: 0,
-        });
-        const loading = await getProp({ $el: $image, propName: 'loading', fallback: '' });
-        const sourceCode = await getProp({
-            $el: $image,
-            propName: 'outerHTML',
-            fallback: '',
-        });
-        const isLazy = loading.toLowerCase().trim() === 'lazy';
-        imageList.push({
-            src,
-            currentSrc,
-            alt,
-            width,
-            height,
-            naturalWidth,
-            naturalHeight,
-            isLazy,
-            viewportWidth,
-            sourceCode,
-        });
-    }
-    log('Got %d images (Viewport: %dpx)', imageList.length, viewportWidth);
-    dLog('Images are: %O', imageList.map((i) => i.src));
-    return imageList;
-}
-/**
- * Extracts all anchor (`<a>` and `<area>`) elements with `href` attributes from the page.
- *
- * For each anchor, resolves the `href` to an `ExURL` via `parseUrl`, retrieves
- * the accessible name (from the accessibility tree, falling back to `textContent`),
- * and filters out non-HTTP links.
- * @param page - The Puppeteer page to extract anchors from.
- * @param options - Optional URL parsing options (e.g., `disableQueries`).
- * @returns An array of {@link AnchorData} objects for all HTTP(S) links found on the page.
- */
-export async function getAnchorList(page, options) {
-    log('Getting anchors');
-    const $anchors = await page.$$('a[href], area[href]');
-    const anchorList = [];
-    for (const $anchor of $anchors) {
-        const $href = await getProp({ $el: $anchor, propName: 'href', fallback: '' });
-        const hrefVal = $href.toString();
-        const href = parseUrl(hrefVal, options);
-        if (!href || !href.isHTTP) {
-            continue;
-        }
-        const axNode = await page.accessibility.snapshot({ root: $anchor });
-        const textContent = await getProp({
-            $el: $anchor,
-            propName: 'textContent',
-            fallback: '',
-        });
-        const accessibleName = axNode ? axNode.name || '' : textContent.trim();
-        const link = {
-            href,
-            textContent: accessibleName,
-        };
-        anchorList.push(link);
-    }
-    log('Got %d anchors', anchorList.length);
-    dLog('Anchors are: %O', anchorList.map((a) => a.href.href));
-    return anchorList;
-}
-/**
- * Extracts comprehensive meta information from the page's `<head>`.
- *
- * Collects the following metadata:
- * - `title` - The document title.
- * - `lang` - The `lang` attribute of the `<html>` element.
- * - `description` - The `<meta name="description">` content.
- * - `keywords` - The `<meta name="keywords">` content.
- * - `noindex` / `nofollow` / `noarchive` - Parsed from the `<meta name="robots">` directives.
- * - `canonical` - The `<link rel="canonical">` content.
- * - `alternate` - The `<link rel="alternate">` content.
- * - Open Graph tags: `og:type`, `og:title`, `og:site_name`, `og:description`, `og:url`, `og:image`.
- * - `twitter:card` - The Twitter Card type.
- * @param page - The Puppeteer page to extract meta information from.
- * @returns An object containing all extracted meta properties.
- */
-export async function getMeta(page) {
-    log('Getting Meta');
-    const robotsVal = await getPropBySelector({
-        page,
-        selector: 'meta[name="robots"]',
-        propName: 'content',
-        fallback: '',
-    });
-    const robots = new Set(robotsVal.split(',').map((robot) => robot.trim().toLowerCase()));
-    const meta = {
-        title: await getPropBySelector({
-            page,
-            selector: 'title',
-            propName: 'textContent',
-            fallback: '',
-        }),
-        lang: await getPropBySelector({
-            page,
-            selector: 'html',
-            propName: 'lang',
-            fallback: '',
-        }),
-        description: await getPropBySelector({
-            page,
-            selector: 'meta[name="description"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        keywords: await getPropBySelector({
-            page,
-            selector: 'meta[name="keywords"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        noindex: robots.has('noindex'),
-        nofollow: robots.has('nofollow'),
-        noarchive: robots.has('noarchive'),
-        canonical: await getPropBySelector({
-            page,
-            selector: 'link[rel="canonical"]',
-            propName: 'href',
-            fallback: '',
-        }),
-        alternate: await getPropBySelector({
-            page,
-            selector: 'link[rel="alternate"]',
-            propName: 'href',
-            fallback: '',
-        }),
-        'og:type': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:type"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:title': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:title"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:site_name': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:site_name"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:description': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:description"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:url': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:url"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:image': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:image"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'twitter:card': await getPropBySelector({
-            page,
-            selector: 'meta[name="twitter:card"]',
-            propName: 'content',
-            fallback: '',
-        }),
-    };
-    log('Got meta');
-    dLog('Meta data are: %O', meta);
-    return meta;
-}

package/dist/index.d.ts

@@ -1,21 +0,0 @@
-/**
- * @module @d-zero/beholder
- *
- * The beholder package provides page-level scraping capabilities for web crawlers.
- * It handles browser page navigation, DOM data extraction (anchors, images, meta tags),
- * network resource monitoring, and keyword-based page exclusion.
- *
- * Results are returned as values from `scrapeStart()`, not emitted as events.
- * Only streaming events (changePhase, resourceResponse) are emitted for progress monitoring.
- *
- * The main entry point is the `Scraper` class (default export).
- */
-export { default as default } from './scraper.js';
-export { isError } from './is-error.js';
-export { detectCompress } from '@d-zero/shared/detect-compress';
-export type { CompressType } from '@d-zero/shared/detect-compress';
-export { detectCDN } from '@d-zero/shared/detect-cdn';
-export type { CDNType } from '@d-zero/shared/detect-cdn';
-export type { ScrapeResult, ResourceEntry, PageData } from './types.js';
-export type { ScraperOptions, ChangePhaseEvent, ScraperEventTypes } from './types.js';
-export type { Resource, AnchorData, Meta, ImageElement, SkippedPageData, NetworkLog, } from './types.js';

package/dist/index.js

@@ -1,16 +0,0 @@
-/**
- * @module @d-zero/beholder
- *
- * The beholder package provides page-level scraping capabilities for web crawlers.
- * It handles browser page navigation, DOM data extraction (anchors, images, meta tags),
- * network resource monitoring, and keyword-based page exclusion.
- *
- * Results are returned as values from `scrapeStart()`, not emitted as events.
- * Only streaming events (changePhase, resourceResponse) are emitted for progress monitoring.
- *
- * The main entry point is the `Scraper` class (default export).
- */
-export { default as default } from './scraper.js';
-export { isError } from './is-error.js';
-export { detectCompress } from '@d-zero/shared/detect-compress';
-export { detectCDN } from '@d-zero/shared/detect-cdn';

package/dist/is-error.d.ts

@@ -1,8 +0,0 @@
-/**
- * Determines whether an HTTP status code represents an error.
- * Status codes in the range 200-399 (inclusive) are considered successful;
- * all others are considered errors.
- * @param status - HTTP status code to evaluate
- * @returns `true` if the status code indicates an error (< 200 or >= 400)
- */
-export declare function isError(status: number): boolean;

package/dist/is-error.js

@@ -1,10 +0,0 @@
-/**
- * Determines whether an HTTP status code represents an error.
- * Status codes in the range 200-399 (inclusive) are considered successful;
- * all others are considered errors.
- * @param status - HTTP status code to evaluate
- * @returns `true` if the status code indicates an error (< 200 or >= 400)
- */
-export function isError(status) {
-    return !(200 <= status && status < 400);
-}

package/dist/keyword-check.d.ts

@@ -1,8 +0,0 @@
-/**
- * Checks whether the given HTML content contains any of the specified exclude keywords.
- * Each keyword is converted to a regular expression via `strToRegex` before testing.
- * @param html - The raw HTML string to search within.
- * @param excludeKeywords - An array of keyword strings or regex patterns to match against the HTML.
- * @returns The first matched keyword string if a match is found, or `false` if none match.
- */
-export declare function keywordCheck(html: string, excludeKeywords: string[]): string | false;

package/dist/keyword-check.js

@@ -1,17 +0,0 @@
-import { strToRegex } from '@d-zero/shared/str-to-regex';
-/**
- * Checks whether the given HTML content contains any of the specified exclude keywords.
- * Each keyword is converted to a regular expression via `strToRegex` before testing.
- * @param html - The raw HTML string to search within.
- * @param excludeKeywords - An array of keyword strings or regex patterns to match against the HTML.
- * @returns The first matched keyword string if a match is found, or `false` if none match.
- */
-export function keywordCheck(html, excludeKeywords) {
-    for (const keyword of excludeKeywords) {
-        const pattern = strToRegex(keyword);
-        if (pattern.test(html)) {
-            return keyword;
-        }
-    }
-    return false;
-}

package/dist/parse-url.d.ts

@@ -1,14 +0,0 @@
-import type { ExURL, ParseURLOptions } from '@d-zero/shared/parse-url';
-/**
- * Parses a URL string into an ExURL object, filtering out non-HTTP URLs
- * that lack a hostname and protocol. If the input is already an ExURL object,
- * it is returned as-is without re-parsing.
- *
- * WHY null return: Bare fragment-only strings (e.g. `"#section"`) and
- * protocol-relative paths without a host are not meaningful URLs for crawling.
- * @param url - A URL string or an already-parsed ExURL object
- * @param options - URL parsing options (e.g. `disableQueries` to strip query strings)
- * @returns The parsed ExURL, or `null` if the URL is not navigable
- * @see `@d-zero/shared/parse-url` for the underlying parser
- */
-export declare function parseUrl(url: string | ExURL, options?: ParseURLOptions): ExURL | null;

package/dist/parse-url.js

@@ -1,23 +0,0 @@
-import { parseUrl as sharedParseUrl } from '@d-zero/shared/parse-url';
-/**
- * Parses a URL string into an ExURL object, filtering out non-HTTP URLs
- * that lack a hostname and protocol. If the input is already an ExURL object,
- * it is returned as-is without re-parsing.
- *
- * WHY null return: Bare fragment-only strings (e.g. `"#section"`) and
- * protocol-relative paths without a host are not meaningful URLs for crawling.
- * @param url - A URL string or an already-parsed ExURL object
- * @param options - URL parsing options (e.g. `disableQueries` to strip query strings)
- * @returns The parsed ExURL, or `null` if the URL is not navigable
- * @see `@d-zero/shared/parse-url` for the underlying parser
- */
-export function parseUrl(url, options) {
-    if (typeof url !== 'string') {
-        return url;
-    }
-    const result = sharedParseUrl(url, options);
-    if (!result.isHTTP && !result.hostname && !result.protocol) {
-        return null;
-    }
-    return result;
-}

package/dist/scraper.d.ts

@@ -1,41 +0,0 @@
-import type { ScraperEventTypes, ScraperOptions, ScrapeResult, ExURL } from './types.js';
-import type { Page } from 'puppeteer';
-import { TypedAwaitEventEmitter as EventEmitter } from '@d-zero/shared/typed-await-event-emitter';
-/**
- * Page-level scraper that extracts data from a single browser page.
- *
- * The scraper returns results as values from `scrapeStart()` rather than
- * emitting them as events. Only streaming events (changePhase, resourceResponse)
- * are emitted for progress monitoring.
- *
- * The Puppeteer `Page` object is injected externally, and page lifecycle
- * (including `page.close()`) is managed by the caller.
- * @example
- * ```ts
- * const scraper = new Scraper();
- * scraper.on('changePhase', (e) => console.log(e.name));
- * const result = await scraper.scrapeStart(page, url, { isExternal: false });
- * ```
- */
-export default class Scraper extends EventEmitter<ScraperEventTypes> {
-    #private;
-    /** Number of retries for `@retryable`-decorated methods. Set per-scrape from options. */
-    retries?: number;
-    /**
-     * Begins the scraping process for a given URL on the provided Puppeteer page.
-     *
-     * Returns a `ScrapeResult` containing the outcome:
-     * - `type: "success"` with `pageData` on success
-     * - `type: "skipped"` with `ignored` details when the page is excluded
-     * - `type: "error"` with `error` details when scraping fails
-     *
-     * Sub-resources are collected via the `resourceResponse` event and
-     * included in the returned `ScrapeResult.resources`.
-     * @param page - The Puppeteer page instance to use for navigation and DOM evaluation.
-     * @param url - The extended URL to scrape.
-     * @param options - Optional scraper configuration overriding defaults.
-     * @param isSkip - When `true`, the page is immediately skipped without any network requests.
-     * @returns The scrape result containing the outcome and captured resources.
-     */
-    scrapeStart(page: Page, url: ExURL, options?: Partial<ScraperOptions>, isSkip?: boolean): Promise<ScrapeResult>;
-}