Manually resove eslint problems

packages/basic-crawler/src/internals/basic-crawler.ts

@@ -684,7 +684,6 @@ export class BasicCrawler<Context extends CrawlingContext = BasicCrawlingContext
         if (this.retryOnBlocked) {
             this.sessionPoolOptions.blockedStatusCodes = sessionPoolOptions.blockedStatusCodes ?? [];
             if (this.sessionPoolOptions.blockedStatusCodes.length !== 0) {
-                // eslint-disable-next-line max-len
                 log.warning(
                     `Both 'blockedStatusCodes' and 'retryOnBlocked' are set. Please note that the 'retryOnBlocked' feature might not work as expected.`,
                 );
@@ -825,7 +824,6 @@ export class BasicCrawler<Context extends CrawlingContext = BasicCrawlingContext
             let message: string;
 
             if (operationMode === 'ERROR') {
-                // eslint-disable-next-line max-len
                 message = `Experiencing problems, ${
                     this.stats.state.requestsFailed - previousState.requestsFailed || this.stats.state.requestsFailed
                 } failed requests in the past ${this.statusMessageLoggingInterval} seconds.`;
@@ -952,7 +950,6 @@ export class BasicCrawler<Context extends CrawlingContext = BasicCrawlingContext
         }
 
         periodicLogger.stop();
-        // eslint-disable-next-line max-len
         await this.setStatusMessage(
             `Finished! Total ${this.stats.state.requestsFinished + this.stats.state.requestsFailed} requests: ${
                 this.stats.state.requestsFinished
@@ -966,8 +963,8 @@ export class BasicCrawler<Context extends CrawlingContext = BasicCrawlingContext
 
     async getRequestQueue() {
         if (!this.requestQueue && this.requestList) {
-            // eslint-disable-next-line max-len
             this.log.warningOnce(
+                // eslint-disable-next-line max-len
                 'When using RequestList and RequestQueue at the same time, you should instantiate both explicitly and provide them in the crawler options, to ensure correctly handled restarts of the crawler.',
             );
         }
@@ -1540,8 +1537,8 @@ export class BasicCrawler<Context extends CrawlingContext = BasicCrawlingContext
     protected _augmentContextWithDeprecatedError(context: Context, error: Error) {
         Object.defineProperty(context, 'error', {
             get: () => {
-                // eslint-disable-next-line max-len
                 this.log.deprecated(
+                    // eslint-disable-next-line max-len
                     "The 'error' property of the crawling context is deprecated, and it is now passed as the second parameter in 'errorHandler' and 'failedRequestHandler'. Please update your code, as this property will be removed in a future version.",
                 );
 

packages/browser-crawler/src/internals/browser-crawler.ts

@@ -457,8 +457,8 @@ export abstract class BrowserCrawler<
     protected override async isRequestBlocked(crawlingContext: Context): Promise<string | false> {
         const { page, response } = crawlingContext;
 
-        // eslint-disable-next-line dot-notation
         const blockedStatusCodes =
+            // eslint-disable-next-line dot-notation
             (this.sessionPool?.['blockedStatusCodes'].length ?? 0) > 0
                 ? // eslint-disable-next-line dot-notation
                   this.sessionPool!['blockedStatusCodes']
@@ -803,8 +803,8 @@ export async function browserCrawlerEnqueueLinks({
  * Extracts URLs from a given page.
  * @ignore
  */
-// eslint-disable-next-line @typescript-eslint/ban-types
 export async function extractUrlsFromPage(
+    // eslint-disable-next-line @typescript-eslint/ban-types
     page: { $$eval: Function },
     selector: string,
     baseUrl: string,

packages/browser-pool/src/browser-pool.ts

@@ -369,8 +369,8 @@ export class BrowserPool<
                 const firstPluginName = firstPluginConstructor.name;
                 const providedPluginName = (providedPlugin as BrowserPlugin).constructor.name;
 
-                // eslint-disable-next-line max-len
                 throw new Error(
+                    // eslint-disable-next-line max-len
                     `Browser plugin at index ${i} (${providedPluginName}) is not an instance of the same plugin as the first plugin provided (${firstPluginName}).`,
                 );
             }

packages/core/src/crawlers/crawler_commons.ts

@@ -12,9 +12,9 @@ import type { Session } from '../session_pool/session';
 import type { RequestQueueOperationOptions, Dataset, RecordOptions } from '../storages';
 import { KeyValueStore } from '../storages';
 
-// we need `Record<string & {}, unknown>` here, otherwise `Omit<Context>` is resolved badly
-// eslint-disable-next-line
 export interface RestrictedCrawlingContext<UserData extends Dictionary = Dictionary>
+    // we need `Record<string & {}, unknown>` here, otherwise `Omit<Context>` is resolved badly
+    // eslint-disable-next-line
     extends Record<string & {}, unknown> {
     /**
      * The original {@apilink Request} object.
@@ -160,8 +160,11 @@ export interface CrawlingContext<Crawler = unknown, UserData extends Dictionary
 export class RequestHandlerResult {
     private _keyValueStoreChanges: Record<string, Record<string, { changedValue: unknown; options?: RecordOptions }>> =
         {};
+
     private pushDataCalls: Parameters<RestrictedCrawlingContext['pushData']>[] = [];
+
     private addRequestsCalls: Parameters<RestrictedCrawlingContext['addRequests']>[] = [];
+
     private enqueueLinksCalls: Parameters<RestrictedCrawlingContext['enqueueLinks']>[] = [];
 
     constructor(

packages/core/src/enqueue_links/shared.ts

@@ -171,10 +171,7 @@ export function createRequests(
         .filter(({ url }) => {
             return !excludePatternObjects.some((excludePatternObject) => {
                 const { regexp, glob } = excludePatternObject;
-                return (
-                    (regexp && url.match(regexp)) || // eslint-disable-line
-                    (glob && minimatch(url, glob, { nocase: true }))
-                );
+                return (regexp && url.match(regexp)) || (glob && minimatch(url, glob, { nocase: true }));
             });
         })
         .map(({ url, opts }) => {
@@ -184,10 +181,7 @@ export function createRequests(
 
             for (const urlPatternObject of urlPatternObjects) {
                 const { regexp, glob, ...requestRegExpOptions } = urlPatternObject;
-                if (
-                    (regexp && url.match(regexp)) || // eslint-disable-line
-                    (glob && minimatch(url, glob, { nocase: true }))
-                ) {
+                if ((regexp && url.match(regexp)) || (glob && minimatch(url, glob, { nocase: true }))) {
                     const request =
                         typeof opts === 'string'
                             ? { url: opts, ...requestRegExpOptions, enqueueStrategy: strategy }
@@ -214,10 +208,7 @@ export function filterRequestsByPatterns(requests: Request[], patterns?: UrlPatt
         for (const urlPatternObject of patterns) {
             const { regexp, glob } = urlPatternObject;
 
-            if (
-                (regexp && request.url.match(regexp)) || // eslint-disable-line
-                (glob && minimatch(request.url, glob, { nocase: true }))
-            ) {
+            if ((regexp && request.url.match(regexp)) || (glob && minimatch(request.url, glob, { nocase: true }))) {
                 filtered.push(request);
                 // Break the pattern loop, as we already matched this request once
                 break;

packages/core/src/session_pool/session_pool.ts

@@ -240,8 +240,8 @@ export class SessionPool extends EventEmitter {
         }
 
         if (!this.persistStateKeyValueStoreId) {
-            // eslint-disable-next-line max-len
             this.log.debug(
+                // eslint-disable-next-line max-len
                 `No 'persistStateKeyValueStoreId' options specified, this session pool's data has been saved in the KeyValueStore with the id: ${this.keyValueStore.id}`,
             );
         }

packages/core/src/storages/request_provider.ts

@@ -741,6 +741,7 @@ declare class BuiltRequestProvider extends RequestProvider {
     override fetchNextRequest<T extends Dictionary = Dictionary>(
         options?: RequestOptions<Dictionary> | undefined,
     ): Promise<Request<T> | null>;
+
     protected override ensureHeadIsNonEmpty(): Promise<void>;
 }
 

packages/http-crawler/src/internals/http-crawler.ts

@@ -32,14 +32,14 @@ import { RETRY_CSS_SELECTORS, gotScraping } from '@crawlee/utils';
 import * as cheerio from 'cheerio';
 import type { RequestLike, ResponseLike } from 'content-type';
 import contentTypeParser from 'content-type';
-// @ts-expect-error This throws a compilation error due to got-scraping being ESM only but we only import types, so its alllll gooooood
 import type {
     OptionsInit,
     Method,
     Request as GotRequest,
     Options,
     PlainResponse,
     TimeoutError as TimeoutErrorClass,
+    // @ts-expect-error This throws a compilation error due to got-scraping being ESM only but we only import types, so its alllll gooooood
 } from 'got-scraping';
 import iconv from 'iconv-lite';
 import mime from 'mime-types';
@@ -599,7 +599,6 @@ export class HttpCrawler<
         if (gotOptions.headers?.Cookie && gotOptions.headers?.cookie) {
             const { Cookie: upperCaseHeader, cookie: lowerCaseHeader } = gotOptions.headers;
 
-            // eslint-disable-next-line max-len
             this.log.warning(
                 `Encountered mixed casing for the cookie headers in the got options for request ${request.url} (${request.id}). Their values will be merged`,
             );

packages/memory-storage/test/fs-fallback.test.ts

@@ -69,16 +69,20 @@ describe('fallback to fs for reading', () => {
         });
     });
 
-    test('attempting to read "other" key value store with no "__metadata__" present should read from fs, even if accessed without generating id first', async () => {
-        const otherStore = storage.keyValueStore('other');
-
-        const input = await otherStore.getRecord('INPUT');
-        expect(input).toStrictEqual<KeyValueStoreRecord>({
-            key: 'INPUT',
-            value: { foo: 'bar but from fs' },
-            contentType: 'application/json; charset=utf-8',
-        });
-    });
+    test(
+        'attempting to read "other" key value store with no "__metadata__" present should read from fs, ' +
+            'even if accessed without generating id first',
+        async () => {
+            const otherStore = storage.keyValueStore('other');
+
+            const input = await otherStore.getRecord('INPUT');
+            expect(input).toStrictEqual<KeyValueStoreRecord>({
+                key: 'INPUT',
+                value: { foo: 'bar but from fs' },
+                contentType: 'application/json; charset=utf-8',
+            });
+        },
+    );
 
     test('attempting to read non-existent "default_2" key value store should return undefined', async () => {
         await expect(storage.keyValueStore('default_2').get()).resolves.toBeUndefined();

packages/playwright-crawler/src/internals/utils/playwright-utils.ts

@@ -806,7 +806,6 @@ export function registerUtilsToContext(context: PlaywrightCrawlingContext): void
     context.infiniteScroll = async (options?: InfiniteScrollOptions) => infiniteScroll(context.page, options);
     context.saveSnapshot = async (options?: SaveSnapshotOptions) =>
         saveSnapshot(context.page, { ...options, config: context.crawler.config });
-    // eslint-disable-next-line max-len
     context.enqueueLinksByClickingElements = async (
         options: Omit<EnqueueLinksByClickingElementsOptions, 'page' | 'requestQueue'>,
     ) =>

packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts

@@ -275,7 +275,6 @@ export async function sendCDPCommand<T extends keyof ProtocolMapping.Commands>(
     const jsonPath = require.resolve('puppeteer/package.json');
     const parsed = JSON.parse(await readFile(jsonPath, 'utf-8'));
 
-    // eslint-disable-next-line max-len
     throw new Error(
         `Cannot detect CDP client for Puppeteer ${parsed.version}. You should report this to Crawlee, mentioning the puppeteer version you are using.`,
     );
@@ -1007,7 +1006,6 @@ export function registerUtilsToContext(context: PuppeteerCrawlingContext): void
         await injectJQuery(context.page, { surviveNavigations: false });
     };
     context.parseWithCheerio = async () => parseWithCheerio(context.page);
-    // eslint-disable-next-line max-len
     context.enqueueLinksByClickingElements = async (
         options: Omit<EnqueueLinksByClickingElementsOptions, 'page' | 'requestQueue'>,
     ) =>

packages/utils/src/internals/general.ts

@@ -5,19 +5,21 @@ 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).
  */
+// eslint-disable-next-line
 export const URL_NO_COMMAS_REGEX = RegExp(
     'https?://(www\\.)?[\\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',
-); // eslint-disable-line
+);
 
 /**
  * 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.
  */
+// eslint-disable-next-line
 export const URL_WITH_COMMAS_REGEX = RegExp(
     'https?://(www\\.)?[\\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',
-); // eslint-disable-line
+);
 
 let isDockerPromiseCache: Promise<boolean> | undefined;
 

packages/utils/src/internals/social.ts

@@ -3,8 +3,8 @@ import cheerio from 'cheerio';
 import { htmlToText } from './cheerio';
 
 // Regex inspired by https://zapier.com/blog/extract-links-email-phone-regex/
-// eslint-disable-next-line max-len
 const EMAIL_REGEX_STRING =
+    // eslint-disable-next-line max-len
     '(?:[a-z0-9!#$%&\'*+/=?^_`{|}~-]+(?:\\.[a-z0-9!#$%&\'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?|\\[(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\\])';
 
 /**
@@ -167,11 +167,9 @@ export function phonesFromUrls(urls: string[]): string[] {
 // - They use a negative lookbehind and lookahead assertions, which are only supported in Node 8+.
 //   They are used to prevent matching URLs in strings like "blahttps://www.example.com"
 
-// eslint-disable-next-line max-len
 const LINKEDIN_REGEX_STRING =
     '(?<!\\w)(?:(?:http(?:s)?:\\/\\/)?(?:(?:(?:[a-z]+\\.)?linkedin\\.com\\/(?:in|company)\\/)([a-z0-9\\-_%=]{2,60})(?![a-z0-9\\-_%=])))(?:\\/)?';
 
-// eslint-disable-next-line max-len
 const INSTAGRAM_REGEX_STRING =
     '(?<!\\w)(?:http(?:s)?:\\/\\/)?(?:(?:www\\.)?(?:instagram\\.com|instagr\\.am)\\/)(?!explore|_n|_u)([a-z0-9_.]{2,30})(?![a-z0-9_.])(?:/)?';
 
@@ -180,26 +178,26 @@ const TWITTER_RESERVED_PATHS =
 // eslint-disable-next-line max-len
 const TWITTER_REGEX_STRING = `(?<!\\w)(?:http(?:s)?:\\/\\/)?(?:www.)?(?:twitter.com)\\/(?!(?:${TWITTER_RESERVED_PATHS})(?:[\\'\\"\\?\\.\\/]|$))([a-z0-9_]{1,15})(?![a-z0-9_])(?:/)?`;
 
-// eslint-disable-next-line max-len
 const FACEBOOK_RESERVED_PATHS =
+    // eslint-disable-next-line max-len
     'rsrc\\.php|apps|groups|events|l\\.php|friends|images|photo.php|chat|ajax|dyi|common|policies|login|recover|reg|help|security|messages|marketplace|pages|live|bookmarks|games|fundraisers|saved|gaming|salesgroups|jobs|people|ads|ad_campaign|weather|offers|recommendations|crisisresponse|onthisday|developers|settings|connect|business|plugins|intern|sharer';
 // eslint-disable-next-line max-len
 const FACEBOOK_REGEX_STRING = `(?<!\\w)(?:http(?:s)?:\\/\\/)?(?:www.)?(?:facebook.com|fb.com)\\/(?!(?:${FACEBOOK_RESERVED_PATHS})(?:[\\'\\"\\?\\.\\/]|$))(profile\\.php\\?id\\=[0-9]{3,20}|(?!profile\\.php)[a-z0-9\\.]{5,51})(?![a-z0-9\\.])(?:/)?`;
 
-// eslint-disable-next-line max-len
 const YOUTUBE_REGEX_STRING =
+    // eslint-disable-next-line max-len
     '(?<!\\w)(?:https?:\\/\\/)?(?:youtu\\.be\\/|(?:www\\.|m\\.)?youtube\\.com(?:\\/(?:watch|v|embed|user|c(?:hannel)?)(?:\\.php)?)?(?:\\?[^ ]*v=|\\/))([a-zA-Z0-9\\-_]{2,100})';
 
-// eslint-disable-next-line max-len
 const TIKTOK_REGEX_STRING =
+    // eslint-disable-next-line max-len
     '(?<!\\w)(?:http(?:s)?:\\/\\/)?(?:(?:www|m)\\.)?(?:tiktok\\.com)\\/(((?:(?:v|embed|trending)(?:\\?shareId=|\\/))[0-9]{2,50}(?![0-9]))|(?:@)[a-z0-9\\-_\\.]+((?:\\/video\\/)[0-9]{2,50}(?![0-9]))?)(?:\\/)?';
 
-// eslint-disable-next-line max-len
 const PINTEREST_REGEX_STRING =
+    // eslint-disable-next-line max-len
     '(?<!\\w)(?:http(?:s)?:\\/\\/)?(?:(?:(?:(?:www\\.)?pinterest(?:\\.com|(?:\\.[a-z]{2}){1,2}))|(?:[a-z]{2})\\.pinterest\\.com)(?:\\/))((pin\\/[0-9]{2,50})|((?!pin)[a-z0-9\\-_\\.]+(\\/[a-z0-9\\-_\\.]+)?))(?:\\/)?';
 
-// eslint-disable-next-line max-len
 const DISCORD_REGEX_STRING =
+    // eslint-disable-next-line max-len
     '(?<!\\w)(?:https?:\\/\\/)?(?:www\\.)?((?:(?:(?:canary|ptb).)?(?:discord|discordapp)\\.com\\/channels(?:\\/)[0-9]{2,50}(\\/[0-9]{2,50})*)|(?:(?:(?:canary|ptb).)?(?:discord\\.(?:com|me|li|gg|io)|discordapp\\.com)(?:\\/invite)?)\\/(?!channels)[a-z0-9\\-_]{2,50})(?:\\/)?';
 
 /**

test/core/crawlers/browser_crawler.test.ts

@@ -158,7 +158,6 @@ describe('BrowserCrawler', () => {
         let isEvaluated = false;
 
         const browserCrawler = new (class extends BrowserCrawlerTest {
-            // eslint-disable-next-line max-len
             protected override async _navigationHandler(
                 ctx: PuppeteerCrawlingContext,
                 gotoOptions: PuppeteerGoToOptions,
@@ -292,7 +291,6 @@ describe('BrowserCrawler', () => {
         });
         let optionsGoto: PuppeteerGoToOptions;
         const browserCrawler = new (class extends BrowserCrawlerTest {
-            // eslint-disable-next-line max-len
             protected override async _navigationHandler(
                 ctx: PuppeteerCrawlingContext,
                 gotoOptions: PuppeteerGoToOptions,
@@ -941,9 +939,10 @@ describe('BrowserCrawler', () => {
             await crawler.run([serverAddress]);
 
             expect(spy).toBeCalled();
-            // eslint-disable-next-line max-len
             expect(spy.mock.calls[0][0]).toEqual(
-                'When using RequestList and RequestQueue at the same time, you should instantiate both explicitly and provide them in the crawler options, to ensure correctly handled restarts of the crawler.',
+                'When using RequestList and RequestQueue at the same time, ' +
+                    'you should instantiate both explicitly and provide them in the crawler options, ' +
+                    'to ensure correctly handled restarts of the crawler.',
             );
             expect(spy.mock.calls[1][0]).toEqual(expect.stringContaining(proxyError));
         });

test/core/crawlers/cheerio_crawler.test.ts

@@ -191,9 +191,9 @@ describe('CheerioCrawler', () => {
             maxConcurrency: 2,
         });
 
-        // eslint-disable-next-line max-len
         await expect(cheerioCrawler.run()).rejects.toThrow(
-            "Route not found for label 'undefined'. You must set up a route for this label or a default route. Use `requestHandler`, `router.addHandler` or `router.addDefaultHandler`.",
+            "Route not found for label 'undefined'. You must set up a route for this label or a default route. " +
+                'Use `requestHandler`, `router.addHandler` or `router.addDefaultHandler`.',
         );
     });
 

test/core/crawlers/puppeteer_crawler.test.ts

@@ -154,8 +154,8 @@ describe('PuppeteerCrawler', () => {
 
     test('should throw if launchOptions.proxyUrl is supplied', async () => {
         try {
+            // eslint-disable-next-line
             new PuppeteerCrawler({
-                //eslint-disable-line
                 requestList,
                 maxRequestRetries: 0,
                 maxConcurrency: 1,

test/core/error_tracker.test.ts

@@ -1,6 +1,3 @@
-/* eslint-disable no-multi-spaces */
-import exp from 'node:constants';
-
 import { ErrorTracker } from '../../packages/utils/src/internals/error_tracker';
 
 const random = () => Math.random().toString(36).slice(2);

test/core/puppeteer_request_interception.test.ts

@@ -173,7 +173,7 @@ describe('utils.puppeteer.addInterceptRequestHandler|removeInterceptRequestHandl
                     // Override headers
                     const headers = {
                         ...request.headers(),
-                        accept: 'text/html',
+                        'accept': 'text/html',
                         'accept-language': 'en-GB',
                         'upgrade-insecure-requests': '2',
                     };