@crawlee/utils 4.0.0-beta.16 → 4.0.0-beta.160

package/README.md

@@ -1,23 +1,23 @@
 <h1 align="center">
     <a href="https://crawlee.dev">
         <picture>
-          <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-dark.svg?sanitize=true">
-          <img alt="Crawlee" src="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-light.svg?sanitize=true" width="500">
+          <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-dark.svg?sanitize=true" />
+          <img alt="Crawlee" src="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-light.svg?sanitize=true" width="500" />
         </picture>
     </a>
-    <br>
+    <br />
     <small>A web scraping and browser automation library</small>
 </h1>
 
-<p align=center>
-    <a href="https://trendshift.io/repositories/5179" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5179" alt="apify%2Fcrawlee | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<p align="center">
+    <a href="https://trendshift.io/repositories/5179" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5179" alt="apify%2Fcrawlee | Trendshift" width="250" height="55"/></a>
 </p>
 
-<p align=center>
-    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/v/@crawlee/core.svg" alt="NPM latest version" data-canonical-src="https://img.shields.io/npm/v/@crawlee/core/next.svg" style="max-width: 100%;"></a>
-    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/dm/@crawlee/core.svg" alt="Downloads" data-canonical-src="https://img.shields.io/npm/dm/@crawlee/core.svg" style="max-width: 100%;"></a>
-    <a href="https://discord.gg/jyEM2PRvMU" rel="nofollow"><img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on discord" data-canonical-src="https://img.shields.io/discord/801163717915574323?label=discord" style="max-width: 100%;"></a>
-    <a href="https://github.com/apify/crawlee/actions/workflows/test-ci.yml"><img src="https://github.com/apify/crawlee/actions/workflows/test-ci.yml/badge.svg?branch=master" alt="Build Status" style="max-width: 100%;"></a>
+<p align="center">
+    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/v/@crawlee/core.svg" alt="NPM latest version" data-canonical-src="https://img.shields.io/npm/v/@crawlee/core/next.svg" /></a>
+    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/dm/@crawlee/core.svg" alt="Downloads" data-canonical-src="https://img.shields.io/npm/dm/@crawlee/core.svg" /></a>
+    <a href="https://discord.gg/jyEM2PRvMU" rel="nofollow"><img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on discord" data-canonical-src="https://img.shields.io/discord/801163717915574323?label=discord" /></a>
+    <a href="https://github.com/apify/crawlee/actions/workflows/test-ci.yml"><img src="https://github.com/apify/crawlee/actions/workflows/test-ci.yml/badge.svg?branch=master" alt="Build Status" /></a>
 </p>
 
 Crawlee covers your crawling and scraping end-to-end and **helps you build reliable scrapers. Fast.**
@@ -89,7 +89,7 @@ By default, Crawlee stores data to `./storage` in the current working directory.
 We provide automated beta builds for every merged code change in Crawlee. You can find them in the npm [list of releases](https://www.npmjs.com/package/crawlee?activeTab=versions). If you want to test new features or bug fixes before we release them, feel free to install a beta build like this:
 
 ```bash
-npm install crawlee@3.12.3-beta.13
+npm install crawlee@next
 ```
 
 If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need to specify dependency overrides in your `package.json` file so that you don't end up with multiple versions of Crawlee installed:
@@ -98,9 +98,9 @@ If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need
 {
     "overrides": {
        "apify": {
-           "@crawlee/core": "3.12.3-beta.13",
-           "@crawlee/types": "3.12.3-beta.13",
-           "@crawlee/utils": "3.12.3-beta.13"
+           "@crawlee/core": "$crawlee",
+           "@crawlee/types": "$crawlee",
+           "@crawlee/utils": "$crawlee"
        }
     }
 }

package/index.d.ts

@@ -1,19 +1,11 @@
-export * from './internals/blocked.js';
-export * from './internals/cheerio.js';
-export * from './internals/chunk.js';
-export * from './internals/extract-urls.js';
-export * from './internals/general.js';
-export * from './internals/debug.js';
+export { htmlToText } from './internals/cheerio.js';
+export { downloadListOfUrls, extractUrls } from './internals/extract-urls.js';
+export { EnqueueStrategy } from './internals/url.js';
+export type { DownloadListOfUrlsOptions, ExtractUrlsOptions } from './internals/extract-urls.js';
+export { sleep, expandShadowRoots } from './internals/general.js';
 export * as social from './internals/social.js';
-export * from './internals/typedefs.js';
+export * from './internals/extract-microdata.js';
 export * from './internals/open_graph_parser.js';
 export * from './internals/robots.js';
 export * from './internals/sitemap.js';
-export * from './internals/iterables.js';
-export * from './internals/robots.js';
-export * from './internals/sitemap.js';
-export * from './internals/url.js';
-export { getCurrentCpuTicksV2, CpuSample } from './internals/system-info/cpu-info.js';
-export { getMemoryInfo, MemoryInfo } from './internals/system-info/memory-info.js';
-export { Dictionary, Awaitable, Constructor } from '@crawlee/types';
-//# sourceMappingURL=index.d.ts.map
+export * from './internals/validation.js';

package/index.js

@@ -1,18 +1,10 @@
-export * from './internals/blocked.js';
-export * from './internals/cheerio.js';
-export * from './internals/chunk.js';
-export * from './internals/extract-urls.js';
-export * from './internals/general.js';
-export * from './internals/debug.js';
+export { htmlToText } from './internals/cheerio.js';
+export { downloadListOfUrls, extractUrls } from './internals/extract-urls.js';
+export { EnqueueStrategy } from './internals/url.js';
+export { sleep, expandShadowRoots } from './internals/general.js';
 export * as social from './internals/social.js';
-export * from './internals/typedefs.js';
+export * from './internals/extract-microdata.js';
 export * from './internals/open_graph_parser.js';
 export * from './internals/robots.js';
 export * from './internals/sitemap.js';
-export * from './internals/iterables.js';
-export * from './internals/robots.js';
-export * from './internals/sitemap.js';
-export * from './internals/url.js';
-export { getCurrentCpuTicksV2 } from './internals/system-info/cpu-info.js';
-export { getMemoryInfo } from './internals/system-info/memory-info.js';
-//# sourceMappingURL=index.js.map
+export * from './internals/validation.js';

package/internal.d.ts

@@ -0,0 +1,9 @@
+export * from './internals/blocked.js';
+export type { CheerioAPI, Cheerio, Element } from './internals/cheerio.js';
+export { extractUrlsFromCheerio } from './internals/cheerio.js';
+export { tryAbsoluteURL } from './internals/extract-urls.js';
+export { URL_NO_COMMAS_REGEX, URL_WITH_COMMAS_REGEX } from './internals/general.js';
+export * from './internals/iterables.js';
+export * from './internals/url.js';
+export * from './internals/validation.js';
+export * as schemas from './internals/schemas.js';

package/internal.js

@@ -0,0 +1,8 @@
+export * from './internals/blocked.js';
+export { extractUrlsFromCheerio } from './internals/cheerio.js';
+export { tryAbsoluteURL } from './internals/extract-urls.js';
+export { URL_NO_COMMAS_REGEX, URL_WITH_COMMAS_REGEX } from './internals/general.js';
+export * from './internals/iterables.js';
+export * from './internals/url.js';
+export * from './internals/validation.js';
+export * as schemas from './internals/schemas.js';

package/internals/blocked.d.ts

@@ -7,4 +7,3 @@ export declare const RETRY_CSS_SELECTORS: string[];
  * Content of proxy errors that should trigger a retry, as the proxy is likely getting blocked / is malfunctioning.
  */
 export declare const ROTATE_PROXY_ERRORS: string[];
-//# sourceMappingURL=blocked.d.ts.map

package/internals/blocked.js

@@ -17,4 +17,3 @@ export const ROTATE_PROXY_ERRORS = [
     'ERR_TUNNEL_CONNECTION_FAILED',
     'Proxy responded with',
 ];
-//# sourceMappingURL=blocked.js.map

package/internals/cheerio.d.ts

@@ -1,5 +1,4 @@
 import type { CheerioAPI } from 'cheerio';
-export type CheerioRoot = CheerioAPI;
 export type { CheerioAPI, Cheerio } from 'cheerio';
 export type { Element } from 'domhandler';
 /**
@@ -29,7 +28,7 @@ export type { Element } from 'domhandler';
  * @param htmlOrCheerioElement HTML text or parsed HTML represented using a [cheerio](https://www.npmjs.com/package/cheerio) function.
  * @return Plain text
  */
-export declare function htmlToText(htmlOrCheerioElement: string | CheerioRoot): string;
+export declare function htmlToText(htmlOrCheerioElement: string | CheerioAPI): Promise<string>;
 /**
  * Extracts URLs from a given Cheerio object.
  *
@@ -40,4 +39,3 @@ export declare function htmlToText(htmlOrCheerioElement: string | CheerioRoot):
  * @return An array of absolute URLs
  */
 export declare function extractUrlsFromCheerio($: CheerioAPI, selector?: string, baseUrl?: string): string[];
-//# sourceMappingURL=cheerio.d.ts.map

package/internals/cheerio.js

@@ -1,4 +1,3 @@
-import * as cheerio from 'cheerio';
 import { tryAbsoluteURL } from './extract-urls.js';
 // NOTE: We are skipping 'noscript' since it's content is evaluated as text, instead of HTML elements. That damages the results.
 const SKIP_TAGS_REGEX = /^(script|style|canvas|svg|noscript)$/i;
@@ -30,10 +29,11 @@ const BLOCK_TAGS_REGEX = /^(p|h1|h2|h3|h4|h5|h6|ol|ul|li|pre|address|blockquote|
  * @param htmlOrCheerioElement HTML text or parsed HTML represented using a [cheerio](https://www.npmjs.com/package/cheerio) function.
  * @return Plain text
  */
-export function htmlToText(htmlOrCheerioElement) {
+export async function htmlToText(htmlOrCheerioElement) {
+    const { load } = await import('cheerio');
     if (!htmlOrCheerioElement)
         return '';
-    const $ = typeof htmlOrCheerioElement === 'function' ? htmlOrCheerioElement : cheerio.load(htmlOrCheerioElement);
+    const $ = typeof htmlOrCheerioElement === 'function' ? htmlOrCheerioElement : load(htmlOrCheerioElement);
     let text = '';
     const process = (elems) => {
         const len = elems ? elems.length : 0;
@@ -42,7 +42,7 @@ export function htmlToText(htmlOrCheerioElement) {
             if (elem.type === 'text') {
                 // Compress spaces, unless we're inside <pre> element
                 let compr;
-                if (elem.parent && elem.parent.tagName === 'pre')
+                if (elem.parent?.tagName === 'pre')
                     compr = elem.data;
                 else
                     compr = elem.data.replace(/\s+/g, ' ');
@@ -107,4 +107,3 @@ export function extractUrlsFromCheerio($, selector = 'a', baseUrl = '') {
     })
         .filter(Boolean);
 }
-//# sourceMappingURL=cheerio.js.map

package/internals/extract-microdata.d.ts

@@ -0,0 +1,24 @@
+import type { CheerioAPI } from 'cheerio';
+/** The value of a microdata property: either text or a nested item. */
+export type MicrodataValue = string | MicrodataItem;
+/** A single schema.org item extracted from a document. */
+export interface MicrodataItem {
+    /** Tokens of the item's `itemtype` attribute. */
+    type?: string[];
+    /** The item's `itemid` attribute. */
+    id?: string;
+    /** Values keyed by `itemprop` name, an array where the property repeats. */
+    properties: Record<string, MicrodataValue | MicrodataValue[]>;
+}
+/**
+ * Easily parse all schema.org microdata from a page with just a `CheerioAPI` object or raw HTML,
+ * following the [microdata processing model](https://html.spec.whatwg.org/multipage/microdata.html#microdata).
+ *
+ * Text values are trimmed and their inner whitespace collapsed. URL-valued attributes are returned
+ * verbatim rather than resolved against the document's base URL.
+ *
+ * @param htmlOrCheerioElement A `CheerioAPI` object, or a string of raw HTML.
+ * @returns The document's top-level items. Nested items are the property values of their parent.
+ */
+export declare function extractMicrodata(raw: string): Promise<MicrodataItem[]>;
+export declare function extractMicrodata($: CheerioAPI): Promise<MicrodataItem[]>;

package/internals/extract-microdata.js

@@ -0,0 +1,118 @@
+import { isTag } from 'domhandler';
+export async function extractMicrodata(htmlOrCheerioElement) {
+    // Dynamic so that importing `@crawlee/utils` does not pull in cheerio - see #3836.
+    const { load } = await import('cheerio');
+    const $ = typeof htmlOrCheerioElement === 'string' ? load(htmlOrCheerioElement) : htmlOrCheerioElement;
+    const context = { $ };
+    return $('[itemscope]')
+        .toArray()
+        .filter((element) => !('itemprop' in element.attribs))
+        .map((element) => parseItem(context, element, new Set()));
+}
+function parseItem(context, element, ancestors) {
+    const item = { properties: {} };
+    const type = uniqueTokens(element.attribs.itemtype);
+    const id = element.attribs.itemid;
+    if (type.length > 0) {
+        item.type = type;
+    }
+    if (id) {
+        item.id = id.trim();
+    }
+    ancestors.add(element);
+    for (const propertyElement of collectPropertyElements(context, element)) {
+        const value = getPropertyValue(context, propertyElement, ancestors);
+        for (const name of uniqueTokens(propertyElement.attribs.itemprop)) {
+            addProperty(item.properties, name, value);
+        }
+    }
+    ancestors.delete(element);
+    return item;
+}
+function collectPropertyElements(context, scope) {
+    const elements = [];
+    collectFromNodes(scope.children, elements);
+    for (const id of uniqueTokens(scope.attribs.itemref)) {
+        const referenced = (context.idIndex ??= indexIds(context.$)).get(id);
+        if (referenced) {
+            collectFromNodes([referenced], elements);
+        }
+    }
+    return elements;
+}
+function collectFromNodes(nodes, elements) {
+    for (const node of nodes) {
+        if (!isTag(node)) {
+            continue;
+        }
+        if ('itemprop' in node.attribs) {
+            elements.push(node);
+        }
+        // A nested item owns everything below it, so its subtree is not part of the enclosing item.
+        if (!('itemscope' in node.attribs)) {
+            collectFromNodes(node.children, elements);
+        }
+    }
+}
+function indexIds($) {
+    const index = new Map();
+    for (const element of $('[id]').toArray()) {
+        // Duplicate ids are invalid HTML; `getElementById` resolves them to the first element.
+        if (!index.has(element.attribs.id)) {
+            index.set(element.attribs.id, element);
+        }
+    }
+    return index;
+}
+function getPropertyValue(context, element, ancestors) {
+    if ('itemscope' in element.attribs) {
+        // `itemref` can point back at an enclosing item, which the spec treats as an error.
+        return ancestors.has(element) ? { properties: {} } : parseItem(context, element, ancestors);
+    }
+    const { attribs } = element;
+    switch (element.tagName.toLowerCase()) {
+        case 'meta':
+            return attribs.content ?? '';
+        case 'audio':
+        case 'embed':
+        case 'iframe':
+        case 'img':
+        case 'source':
+        case 'track':
+        case 'video':
+            return attribs.src ?? '';
+        case 'a':
+        case 'area':
+        case 'link':
+            return attribs.href ?? '';
+        case 'object':
+            return attribs.data ?? '';
+        case 'data':
+        case 'meter':
+            return attribs.value ?? '';
+        case 'time':
+            return attribs.datetime ?? context.$(element).text().replace(/\s+/g, ' ').trim();
+        default:
+            return context.$(element).text().replace(/\s+/g, ' ').trim();
+    }
+}
+function addProperty(properties, name, value) {
+    const existing = properties[name];
+    if (existing === undefined) {
+        properties[name] = value;
+    }
+    else if (Array.isArray(existing)) {
+        existing.push(value);
+    }
+    else {
+        properties[name] = [existing, value];
+    }
+}
+/** `itemtype`, `itemprop` and `itemref` are all unordered sets of unique space-separated tokens. */
+function uniqueTokens(value) {
+    if (!value) {
+        return [];
+    }
+    const tokens = value.split(/\s+/).filter(Boolean);
+    return tokens.length > 1 ? [...new Set(tokens)] : tokens;
+}

package/internals/extract-urls.d.ts

@@ -1,3 +1,4 @@
+import type { BaseHttpClient } from '@crawlee/http-client';
 export interface DownloadListOfUrlsOptions {
     /**
      * URL to the file
@@ -16,6 +17,10 @@ export interface DownloadListOfUrlsOptions {
     urlRegExp?: RegExp;
     /** Allows to use a proxy for the download request. */
     proxyUrl?: string;
+    /**
+     * Custom HTTP client to use for downloading the file.
+     */
+    httpClient?: BaseHttpClient;
 }
 /**
  * Returns a promise that resolves to an array of urls parsed from the resource available at the provided url.
@@ -41,4 +46,3 @@ export declare function extractUrls(options: ExtractUrlsOptions): string[];
  * Helper function used to validate URLs used when extracting URLs from a page
  */
 export declare function tryAbsoluteURL(href: string, baseUrl: string): string | undefined;
-//# sourceMappingURL=extract-urls.d.ts.map

package/internals/extract-urls.js

@@ -1,38 +1,44 @@
-import { gotScraping } from 'got-scraping';
-import ow from 'ow';
+import { FetchHttpClient } from '@crawlee/http-client';
+import { z } from 'zod';
 import { URL_NO_COMMAS_REGEX } from './general.js';
+import { httpClient as httpClientSchema } from './schemas.js';
+import { parseArgument } from './validation.js';
+const downloadListOfUrlsOptionsSchema = z.strictObject({
+    url: z.url(),
+    encoding: z.string().default('utf8'),
+    urlRegExp: z.instanceof(RegExp).default(URL_NO_COMMAS_REGEX),
+    proxyUrl: z.string().optional(),
+    httpClient: httpClientSchema.default(() => new FetchHttpClient()),
+});
+const extractUrlsOptionsSchema = z.strictObject({
+    string: z.string(),
+    urlRegExp: z.instanceof(RegExp).default(URL_NO_COMMAS_REGEX),
+});
 /**
  * Returns a promise that resolves to an array of urls parsed from the resource available at the provided url.
  * Optionally, custom regular expression and encoding may be provided.
  */
 export async function downloadListOfUrls(options) {
-    ow(options, ow.object.exactShape({
-        url: ow.string.url,
-        encoding: ow.optional.string,
-        urlRegExp: ow.optional.regExp,
-        proxyUrl: ow.optional.string,
-    }));
-    const { url, encoding = 'utf8', urlRegExp = URL_NO_COMMAS_REGEX, proxyUrl } = options;
+    const { url, encoding, urlRegExp, proxyUrl, httpClient } = parseArgument(options, downloadListOfUrlsOptionsSchema);
     // Try to detect wrong urls and fix them. Currently, detects only sharing url instead of csv download one.
-    const match = url.match(/^(https:\/\/docs\.google\.com\/spreadsheets\/d\/(?:\w|-)+)\/?/);
+    const match = /^(https:\/\/docs\.google\.com\/spreadsheets\/d\/(?:\w|-)+)\/?/.exec(url);
     let fixedUrl = url;
     if (match) {
         fixedUrl = `${match[1]}/gviz/tq?tqx=out:csv`;
     }
-    const { body: string } = await gotScraping({ url: fixedUrl, encoding, proxyUrl });
+    const response = await httpClient.sendRequest(new Request(fixedUrl, { method: 'GET' }), {
+        proxyUrl,
+    });
+    const string = new TextDecoder(encoding).decode(new Uint8Array(await response.arrayBuffer()));
     return extractUrls({ string, urlRegExp });
 }
 /**
  * Collects all URLs in an arbitrary string to an array, optionally using a custom regular expression.
  */
 export function extractUrls(options) {
-    ow(options, ow.object.exactShape({
-        string: ow.string,
-        urlRegExp: ow.optional.regExp,
-    }));
-    const lines = options.string.split('\n');
+    const { string, urlRegExp } = parseArgument(options, extractUrlsOptionsSchema);
+    const lines = string.split('\n');
     const result = [];
-    const urlRegExp = options.urlRegExp ?? URL_NO_COMMAS_REGEX;
     for (const line of lines) {
         result.push(...(line.match(urlRegExp) ?? []));
     }
@@ -49,4 +55,3 @@ export function tryAbsoluteURL(href, baseUrl) {
         return undefined;
     }
 }
-//# sourceMappingURL=extract-urls.js.map

package/internals/general.d.ts

@@ -8,25 +8,6 @@ export declare const URL_NO_COMMAS_REGEX: RegExp;
  * Note, however, that this may prevent parsing URLs from comma delimited lists, or the URLs may become malformed.
  */
 export declare const URL_WITH_COMMAS_REGEX: RegExp;
-/**
- * Returns a `Promise` that resolves to true if the code is running in a Docker container.
- */
-export declare function isDocker(forceReset?: boolean): Promise<boolean>;
-/**
- * Detects if crawlee is running in a containerized environment.
- */
-export declare function isContainerized(): Promise<boolean>;
-export declare function isLambda(): boolean;
-/**
- * gets the cgroup version by checking for a file at /sys/fs/cgroup/memory
- * @returns "V1" or "V2" for the version of cgroup or null if cgroup is not found.
- */
-export declare function getCgroupsVersion(forceReset?: boolean): Promise<"V1" | "V2" | null>;
-/**
- * Computes a weighted average of an array of numbers, complemented by an array of weights.
- * @ignore
- */
-export declare function weightedAvg(arrValues: number[], arrWeights: number[]): number;
 /**
  * Returns a `Promise` that resolves after a specific period of time. This is useful to implement waiting
  * in your code, e.g. to prevent overloading of target website or to avoid bot detection.
@@ -44,14 +25,8 @@ export declare function weightedAvg(arrValues: number[], arrWeights: number[]):
  * @param millis Period of time to sleep, in milliseconds. If not a positive number, the returned promise resolves immediately.
  */
 export declare function sleep(millis?: number): Promise<void>;
-/**
- * Converts SNAKE_CASE to camelCase.
- * @ignore
- */
-export declare function snakeCaseToCamelCase(snakeCaseStr: string): string;
 /**
  * Traverses DOM and expands shadow-root elements (created by custom components).
  * @ignore
  */
 export declare function expandShadowRoots(document: Document): string;
-//# sourceMappingURL=general.d.ts.map

package/internals/general.js

@@ -1,108 +1,14 @@
-import fs from 'node:fs/promises';
 import { setTimeout } from 'node:timers/promises';
 /**
  * Default regular expression to match URLs in a string that may be plain text, JSON, CSV or other. It supports common URL characters
  * and does not support URLs containing commas or spaces. The URLs also may contain Unicode letters (not symbols).
  */
-export const URL_NO_COMMAS_REGEX = /https?:\/\/(www\.)?([\p{L}0-9]|[\p{L}0-9][-\p{L}0-9@:%._+~#=]{0,254}[\p{L}0-9])\.[a-z]{2,63}(:\d{1,5})?(\/[-\p{L}0-9@:%_+.~#?&/=()]*)?/giu;
+export const URL_NO_COMMAS_REGEX = /https?:\/\/(www\.)?([\p{L}0-9]|[\p{L}0-9][-\p{L}0-9@:%._+~#=]{0,254}[\p{L}0-9])\.[a-z]{2,63}(:\d{1,5})?(\/[-\p{L}0-9@:%_+.~#?&/=()'*]*)?/giu;
 /**
  * Regular expression that, in addition to the default regular expression `URL_NO_COMMAS_REGEX`, supports matching commas in URL path and query.
  * Note, however, that this may prevent parsing URLs from comma delimited lists, or the URLs may become malformed.
  */
-export const URL_WITH_COMMAS_REGEX = /https?:\/\/(www\.)?([\p{L}0-9]|[\p{L}0-9][-\p{L}0-9@:%._+~#=]{0,254}[\p{L}0-9])\.[a-z]{2,63}(:\d{1,5})?(\/[-\p{L}0-9@:%_+,.~#?&/=()]*)?/giu;
-let isDockerPromiseCache;
-async function createIsDockerPromise() {
-    const promise1 = fs
-        .stat('/.dockerenv')
-        .then(() => true)
-        .catch(() => false);
-    const promise2 = fs
-        .readFile('/proc/self/cgroup', 'utf8')
-        .then((content) => content.includes('docker'))
-        .catch(() => false);
-    const [result1, result2] = await Promise.all([promise1, promise2]);
-    return result1 || result2;
-}
-/**
- * Returns a `Promise` that resolves to true if the code is running in a Docker container.
- */
-export async function isDocker(forceReset) {
-    // Parameter forceReset is just internal for unit tests.
-    if (!isDockerPromiseCache || forceReset)
-        isDockerPromiseCache = createIsDockerPromise();
-    return isDockerPromiseCache;
-}
-let isContainerizedResult;
-/**
- * Detects if crawlee is running in a containerized environment.
- */
-export async function isContainerized() {
-    // Value is very unlikley to change. Cache the result after the first execution.
-    if (isContainerizedResult !== undefined) {
-        return isContainerizedResult;
-    }
-    // return false if running in aws lambda
-    if (isLambda()) {
-        isContainerizedResult = false;
-        return isContainerizedResult;
-    }
-    const dockerenvCheck = fs
-        .stat('/.dockerenv')
-        .then(() => true)
-        .catch(() => false);
-    const cgroupCheck = fs
-        .readFile('/proc/self/cgroup', 'utf8')
-        .then((content) => content.includes('docker'))
-        .catch(() => false);
-    const [dockerenvResult, cgroupResult] = await Promise.all([dockerenvCheck, cgroupCheck]);
-    isContainerizedResult = dockerenvResult || cgroupResult || !!process.env.KUBERNETES_SERVICE_HOST;
-    return isContainerizedResult;
-}
-export function isLambda() {
-    return !!process.env.AWS_LAMBDA_FUNCTION_MEMORY_SIZE;
-}
-let _cgroupsVersion;
-/**
- * gets the cgroup version by checking for a file at /sys/fs/cgroup/memory
- * @returns "V1" or "V2" for the version of cgroup or null if cgroup is not found.
- */
-export async function getCgroupsVersion(forceReset) {
-    // Parameter forceReset is just internal for unit tests.
-    if (_cgroupsVersion !== undefined && !forceReset) {
-        return _cgroupsVersion;
-    }
-    try {
-        // If this directory does not exists, cgroups are not available
-        await fs.access('/sys/fs/cgroup/');
-    }
-    catch (e) {
-        _cgroupsVersion = null;
-        return null;
-    }
-    _cgroupsVersion = 'V1';
-    try {
-        // If this directory does not exists, assume the container is using cgroups V2
-        await fs.access('/sys/fs/cgroup/memory/');
-    }
-    catch (e) {
-        _cgroupsVersion = 'V2';
-    }
-    return _cgroupsVersion;
-}
-/**
- * Computes a weighted average of an array of numbers, complemented by an array of weights.
- * @ignore
- */
-export function weightedAvg(arrValues, arrWeights) {
-    const result = arrValues
-        .map((value, i) => {
-        const weight = arrWeights[i];
-        const sum = value * weight;
-        return [sum, weight];
-    })
-        .reduce((p, c) => [p[0] + c[0], p[1] + c[1]], [0, 0]);
-    return result[0] / result[1];
-}
+export const URL_WITH_COMMAS_REGEX = /https?:\/\/(www\.)?([\p{L}0-9]|[\p{L}0-9][-\p{L}0-9@:%._+~#=]{0,254}[\p{L}0-9])\.[a-z]{2,63}(:\d{1,5})?(\/[-\p{L}0-9@:%_+,.~#?&/=()'*]*)?/giu;
 /**
  * Returns a `Promise` that resolves after a specific period of time. This is useful to implement waiting
  * in your code, e.g. to prevent overloading of target website or to avoid bot detection.
@@ -122,19 +28,6 @@ export function weightedAvg(arrValues, arrWeights) {
 export async function sleep(millis) {
     return setTimeout(millis ?? undefined);
 }
-/**
- * Converts SNAKE_CASE to camelCase.
- * @ignore
- */
-export function snakeCaseToCamelCase(snakeCaseStr) {
-    return snakeCaseStr
-        .toLowerCase()
-        .split('_')
-        .map((part, index) => {
-        return index > 0 ? part.charAt(0).toUpperCase() + part.slice(1) : part;
-    })
-        .join('');
-}
 /**
  * Traverses DOM and expands shadow-root elements (created by custom components).
  * @ignore
@@ -164,4 +57,3 @@ export function expandShadowRoots(document) {
     replaceShadowDomsWithHtml(document.body);
     return document.documentElement.outerHTML;
 }
-//# sourceMappingURL=general.js.map