es6-crawler-detect 3.3.0 → 4.0.0-beta.2

package/src/lib/crawler/{exclusions.js → exclusions.ts}

@@ -1,62 +1,56 @@
-'use strict';
-
-const Provider = require('./provider');
-
-class Exclusions extends Provider {
-  constructor() {
-    super();
-
-    this.data = [
-      'Safari.[\\d\\.]*',
-      'Firefox.[\\d\\.]*',
-      ' Chrome.[\\d\\.]*',
-      'Chromium.[\\d\\.]*',
-      'MSIE.[\\d\\.]',
-      'Opera\\/[\\d\\.]*',
-      'Mozilla.[\\d\\.]*',
-      'AppleWebKit.[\\d\\.]*',
-      'Trident.[\\d\\.]*',
-      'Windows NT.[\\d\\.]*',
-      'Android [\\d\\.]*',
-      'Macintosh.',
-      'Ubuntu',
-      'Linux',
-      '[ ]Intel',
-      'Mac OS X [\\d_]*',
-      '(like )?Gecko(.[\\d\\.]*)?',
-      'KHTML,',
-      'CriOS.[\\d\\.]*',
-      'CPU iPhone OS ([0-9_])* like Mac OS X',
-      'CPU OS ([0-9_])* like Mac OS X',
-      'iPod',
-      'compatible',
-      'x86_..',
-      'i686',
-      'x64',
-      'X11',
-      'rv:[\\d\\.]*',
-      'Version.[\\d\\.]*',
-      'WOW64',
-      'Win64',
-      'Dalvik.[\\d\\.]*',
-      ' \\.NET CLR [\\d\\.]*',
-      'Presto.[\\d\\.]*',
-      'Media Center PC',
-      'BlackBerry',
-      'Build',
-      'Opera Mini\\/\\d{1,2}\\.\\d{1,2}\\.[\\d\\.]*\\/\\d{1,2}\\.',
-      'Opera',
-      ' \\.NET[\\d\\.]*',
-      'cubot',
-      '; M bot',
-      '; CRONO',
-      '; B bot',
-      '; IDbot',
-      '; ID bot',
-      '; POWER BOT',
-      'OCTOPUS-CORE',
-    ];
-  }
-}
-
-module.exports = Exclusions;
+import { Provider } from './provider';
+
+export class Exclusions implements Provider {
+  getAll(): string[] {
+    return [
+      'Safari.[\\d\\.]*',
+      'Firefox.[\\d\\.]*',
+      ' Chrome.[\\d\\.]*',
+      'Chromium.[\\d\\.]*',
+      'MSIE.[\\d\\.]',
+      'Opera\\/[\\d\\.]*',
+      'Mozilla.[\\d\\.]*',
+      'AppleWebKit.[\\d\\.]*',
+      'Trident.[\\d\\.]*',
+      'Windows NT.[\\d\\.]*',
+      'Android [\\d\\.]*',
+      'Macintosh.',
+      'Ubuntu',
+      'Linux',
+      '[ ]Intel',
+      'Mac OS X [\\d_]*',
+      '(like )?Gecko(.[\\d\\.]*)?',
+      'KHTML,',
+      'CriOS.[\\d\\.]*',
+      'CPU iPhone OS ([0-9_])* like Mac OS X',
+      'CPU OS ([0-9_])* like Mac OS X',
+      'iPod',
+      'compatible',
+      'x86_..',
+      'i686',
+      'x64',
+      'X11',
+      'rv:[\\d\\.]*',
+      'Version.[\\d\\.]*',
+      'WOW64',
+      'Win64',
+      'Dalvik.[\\d\\.]*',
+      ' \\.NET CLR [\\d\\.]*',
+      'Presto.[\\d\\.]*',
+      'Media Center PC',
+      'BlackBerry',
+      'Build',
+      'Opera Mini\\/\\d{1,2}\\.\\d{1,2}\\.[\\d\\.]*\\/\\d{1,2}\\.',
+      'Opera',
+      ' \\.NET[\\d\\.]*',
+      'cubot',
+      '; M bot',
+      '; CRONO',
+      '; B bot',
+      '; IDbot',
+      '; ID bot',
+      '; POWER BOT',
+      'OCTOPUS-CORE',
+    ];
+  }
+}

package/src/lib/crawler/{headers.js → headers.ts}

@@ -1,12 +1,8 @@
-'use strict';
+import { Provider } from './provider';
 
-const Provider = require('./provider');
-
-class Headers extends Provider {
-  constructor() {
-    super();
-
-    this.data = [
+export class Headers implements Provider {
+  getAll(): string[] {
+    return [
       'USER-AGENT',
       'X-OPERAMINI-PHONE-UA',
       'X-DEVICE-USER-AGENT',
@@ -20,5 +16,3 @@ class Headers extends Provider {
     ];
   }
 }
-
-module.exports = Headers;

package/src/lib/crawler/provider.ts

@@ -0,0 +1,3 @@
+export interface Provider {
+  getAll(): string[];
+}

package/src/lib/crawler.ts

@@ -0,0 +1,128 @@
+import { Request } from 'express-serve-static-core';
+import { IncomingHttpHeaders } from 'http2';
+
+import { Crawlers } from './crawler/crawlers';
+import { Exclusions } from './crawler/exclusions';
+import { Headers } from './crawler/headers';
+
+export class Crawler {
+  private crawlers: Crawlers;
+  private headers: Headers;
+  private exclusions: Exclusions;
+
+  private request: Request | NodeJS.Dict<string | string[]>;
+  private compiledRegexList: RegExp;
+  private compiledExclusions: RegExp;
+  private httpHeaders: string | string[] | IncomingHttpHeaders;
+  private userAgent: string;
+  private matches?: RegExpExecArray | null;
+
+  constructor(
+    request?: Request,
+    headers?: IncomingHttpHeaders,
+    userAgent?: string
+  ) {
+    this.crawlers = new Crawlers();
+    this.headers = new Headers();
+    this.exclusions = new Exclusions();
+
+    this.request = request ?? {};
+
+    // The regex-list must not be used with g-flag!
+    // See: https://stackoverflow.com/questions/1520800/why-does-a-regexp-with-global-flag-give-wrong-results
+    this.compiledRegexList = this.compileRegex(this.crawlers.getAll(), 'i');
+
+    // The exclusions should be used with g-flag in order to remove each value.
+    this.compiledExclusions = this.compileRegex(this.exclusions.getAll(), 'gi');
+
+    this.httpHeaders = this.setHttpHeaders(headers);
+    this.userAgent = this.setUserAgent(userAgent);
+  }
+
+  public compileRegex(patterns: string[], flags?: string): RegExp {
+    return new RegExp(patterns.join('|'), flags);
+  }
+
+  private setHttpHeaders(
+    headers?: string | string[] | IncomingHttpHeaders
+  ): string | string[] | IncomingHttpHeaders {
+    // Use the Request headers if httpHeaders is not defined
+    if (!headers || Object.keys(headers).length === 0) {
+      if (Object.keys(this.request).length) {
+        if (this.request.headers) {
+          return this.request.headers;
+        }
+      }
+
+      return '';
+    }
+
+    // Save the headers.
+    return headers;
+  }
+
+  private setUserAgent(userAgent?: string): string {
+    if (!userAgent?.length) {
+      userAgent = '';
+      for (const header of this.getUaHttpHeaders()) {
+        if (
+          typeof this.httpHeaders === 'object' &&
+          !Array.isArray(this.httpHeaders)
+        ) {
+          if (Object.hasOwn(this.httpHeaders, header.toLowerCase())) {
+            const headerValue = this.httpHeaders[header.toLowerCase()];
+
+            if (typeof headerValue === 'string') {
+              const separator = userAgent.length > 0 ? ' ' : '';
+              userAgent += separator + headerValue;
+            } else if (Array.isArray(headerValue)) {
+              const separator = userAgent.length > 0 ? ' ' : '';
+              userAgent += separator + headerValue.join(' ');
+            }
+          }
+        }
+      }
+    }
+
+    return userAgent;
+  }
+
+  private getUaHttpHeaders() {
+    return this.headers.getAll();
+  }
+
+  public getMatches(): string | null | object {
+    if (this.matches !== undefined) {
+      if (this.matches?.length) {
+        return this.matches[0];
+      }
+
+      return null;
+    }
+
+    return {};
+  }
+
+  public isCrawler(userAgent?: string): boolean {
+    if (Buffer.byteLength(userAgent ?? '', 'utf8') > 4096) {
+      return false;
+    }
+
+    let agent = userAgent ?? this.userAgent;
+
+    // test on compiled regx
+    agent = agent.replace(this.compiledExclusions, '');
+
+    if (agent.trim().length === 0) {
+      return false;
+    }
+
+    const matches = this.compiledRegexList.exec(agent);
+
+    if (matches) {
+      this.matches = matches;
+    }
+
+    return matches !== null && matches.length > 0;
+  }
+}

package/src/types.ts

@@ -0,0 +1,15 @@
+import { NextFunction, Request, Response } from 'express-serve-static-core';
+
+import { Crawler } from './lib/crawler';
+
+export type Middleware = (
+  request: Request,
+  response: Response,
+  next: NextFunction
+) => Promise<Response>;
+
+declare module 'express-serve-static-core' {
+  interface Request {
+    Crawler: Crawler;
+  }
+}

package/test/lib/crawler.spec.ts

@@ -0,0 +1,116 @@
+import assert from 'assert';
+import { Request } from 'express-serve-static-core';
+import * as fs from 'fs';
+import * as readline from 'readline';
+
+import { Crawler } from '../../src';
+
+declare module 'express-serve-static-core' {
+  interface Request {
+    Crawler: Crawler;
+  }
+}
+
+let crawler = new Crawler();
+
+describe('regex-compilation', () => {
+  it('will join list of patterns with pipes', () => {
+    assert.strictEqual(
+      crawler.compileRegex(['some', 'patterns']).source,
+      'some|patterns'
+    );
+    assert.strictEqual(crawler.compileRegex(['single']).source, 'single');
+  });
+
+  it('keeps the whitespace', () => {
+    assert.strictEqual(
+      crawler.compileRegex(['  keep-whitespaces ']).source,
+      '  keep-whitespaces '
+    );
+  });
+
+  it('will accept regex-flags for compilation', () => {
+    const patterns = ['some', 'patterns'];
+    assert.strictEqual(crawler.compileRegex(patterns, 'g').flags, 'g');
+    assert.strictEqual(crawler.compileRegex(patterns, 'i').flags, 'i');
+  });
+
+  it('should be case insensitive', () => {
+    assert.strictEqual(crawler.isCrawler('Facebot\\1.0'), true);
+    assert.strictEqual(
+      crawler.getMatches(),
+      'Facebot',
+      'Crawler was not able to identify crawler correctly'
+    );
+  });
+});
+
+describe('crawler-identification', () => {
+  it('should be able to identify crawlers', async () => {
+    const rl = readline.createInterface({
+      input: fs.createReadStream('./test/lib/database/crawlers.txt'),
+      crlfDelay: Infinity,
+    });
+
+    for await (const line of rl) {
+      assert.strictEqual(
+        crawler.isCrawler(line),
+        true,
+        `${line} is not a crawler`
+      );
+    }
+
+    rl.close();
+  });
+
+  it('should be able to identify devices', async () => {
+    const rl = readline.createInterface({
+      input: fs.createReadStream('./test/lib/database/devices.txt'),
+      crlfDelay: Infinity,
+    });
+
+    for await (const line of rl) {
+      assert.strictEqual(
+        crawler.isCrawler(line),
+        false,
+        `${line} is not a device`
+      );
+    }
+
+    rl.close();
+  });
+
+  it('should identify the crawler from given headers', async () => {
+    crawler = new Crawler(undefined, {
+      host: '127.0.0.1:3000',
+      'user-agent': 'curl/7.73.0',
+      accept: '*/*',
+    });
+
+    assert.strictEqual(crawler.isCrawler(), true);
+  });
+
+  it('should identify the crawler from request headers', async () => {
+    crawler = new Crawler({
+      headers: { 'user-agent': 'curl/7.73.0', accept: '*/*' },
+    } as Request);
+
+    assert.strictEqual(crawler.isCrawler(), true);
+  });
+
+  it('should identify the crawler from request headers with exact pattern', async () => {
+    crawler = new Crawler({
+      headers: { 'user-agent': 'b0t', accept: '*/*' },
+    } as Request);
+
+    assert.strictEqual(crawler.isCrawler(), true);
+  });
+
+  it('should not throw an exception on empty request header', async () => {
+    crawler = new Crawler({
+      headers: { accept: '*/*' },
+    } as Request);
+
+    assert.doesNotThrow(() => crawler.isCrawler());
+  });
+});

package/tsconfig.json

@@ -0,0 +1,28 @@
+{
+    "$schema": "https://json.schemastore.org/tsconfig",
+    "display": "Node 20",
+    "_version": "20.1.0",
+  
+    "compilerOptions": {
+      "lib": ["es2023"],
+      "module": "node16",
+      "target": "es2022",
+  
+      "declaration": true,
+      "declarationMap": true,
+      "sourceMap": true,
+      "emitDeclarationOnly": false,
+      "outDir": "dist",
+
+      "strict": true,
+      "esModuleInterop": true,
+      "skipLibCheck": true,
+      "moduleResolution": "node16"
+    },
+    "ts-node": {
+      "esm": true,
+    },
+
+    "include": ["src/**/*"],
+    "exclude": ["node_modules", "dist"]
+}

package/.eslintignore

@@ -1,6 +0,0 @@
-!.*
-coverage/
-junit/
-dist/
-mobiles/
-**/node_modules/*

package/.eslintrc.json

@@ -1,30 +0,0 @@
-{
-  "extends": ["eslint:recommended", "plugin:prettier/recommended"],
-  "env": {
-    "browser": false,
-    "commonjs": true,
-    "es6": true,
-    "node": true,
-    "mocha": true
-  },
-  "rules": {
-    "max-len": [
-      "warn",
-      {
-        "code": 80,
-        "tabWidth": 2,
-        "comments": 80,
-        "ignoreComments": false,
-        "ignoreTrailingComments": true,
-        "ignoreUrls": true,
-        "ignoreStrings": true,
-        "ignoreTemplateLiterals": true,
-        "ignoreRegExpLiterals": true
-      }
-    ]
-  },
-  "parser": "@babel/eslint-parser",
-  "parserOptions": {
-    "requireConfigFile": false
-  }
-}