Giters

extractus / article-extractor

To extract main article from given URL with Node.js

Home Page:https://extractor-demos.pages.dev/article-extractor

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

request CommonJS version

dimaslanjaka opened this issue · comments

commented

I have typescript project with article-parser, but after update got crashed because this lib using ESM. Please compile the CommonJS version.

gambar

commented

@dimaslanjaka hello, there is still commonjs version, could you try the following:

const { extract } = require('article-parser/dist/cjs/article-parser.js')
commented 
const { extract } = require('article-parser/dist/cjs/article-parser.js')

its working, but the types not found.
image

if using below codes, the definition types found.

import { extract } from 'article-parser';
commented

@dimaslanjaka yes, it seems that the types definition should be copied to dist/cjs while building commonjs version. I'm currious about your environment, are you using typescript on Node.js? which version of Node.js your application runs on?

commented

Node 16.x latest
Typescript 4.x latest

commented

@dimaslanjaka please try v7.0.2, hope that copying type definitions to commonjs folder can help.

commented

i upgraded article-parser to latest

causes:

  • error "NOT EXPORTED"
  • the definition types not solved

image

image

commented

My current sollution is using this snippet for commonJS typescript.

using article-parser 7.0.1

declare var require: any; /* if not installed @types/node */
import { writeFileSync } from 'fs-extra';
import { join } from 'path';
import { cwd } from 'process';

(async () => {
  const parser: typeof import('article-parser') =
    await require('article-parser/dist/cjs/article-parser.js');
  const extract = parser.extract;
  extract(
    'https://zilliongamer.com/chimeraland/c/basic-materials-list/mining-materials-list'
  ).then((data) => {
    writeFileSync(
      join(
        cwd(),
        'tmp/article',
        data.title.replace(/[^a-zA-Z ]/g, '-') + '.html'
      ),
      data.content
    );
  });
})();
commented

please fix 7.0.2 to be like 7.0.1 but improved with customized definition types. or give above snippet on documentation. thank you

commented

@dimaslanjaka hello, thank you for raising problem.

I've created a simple package with 3 files as below:

package.json

{
  "name": "typeart",
  "version": "1.0.0",
  "main": "index.ts",
  "scripts": {
    "prestart": "npx tsc",
    "start": "node dist/index.js"
  },
  "devDependencies": {
    "typescript": "^4.8.3"
  }
}

tsconfig.json

{
  "compilerOptions": {
    "module": "commonjs",
    "esModuleInterop": true,
    "target": "es6",
    "moduleResolution": "node",
    "sourceMap": true,
    "outDir": "dist"
  },
  "lib": ["es2015"]
}

index.ts

import { extract } from 'article-parser';

(async () => {
  const data = await extract('https://zilliongamer.com/chimeraland/c/basic-materials-list/mining-materials-list')
  console.log(`extracted article: "${data.title}"`)
})();

Then I try to use article-parser 4 versions: 7.0.1, 7.0.2, 7.0.3 and 7.1.0

pnpm i

pnpm i article-parser@7.0.1
npm start # failed

pnpm i article-parser@7.0.2
npm start # failed

pnpm i article-parser@7.0.3
npm start # success

pnpm i article-parser@7.1.0
npm start # success

Screenshot from 2022-09-17 15-26-56

It seems that you can use 7.0.3 and the latest 7.1.0 without problem.

commented

iam tried ur snippet with my project configuration (iam using ts-node to run it btw)

Using 7.0.1

image

Using 7.0.2
image
image

Using 7.0.3 (work)
image
image

tsconfig.json

{
  // Change this to match your project
  "include": [
    "*.ts",
    "./views",
    "./public",
    "./src",
    "./chimeraland",
    "./chimeraland/typings",
    "./tlon"
  ],
  "compilerOptions": {
    "module": "CommonJS",
    "target": "es2018",
    // Tells TypeScript to read JS files, as
    // normally they are ignored as source files
    "allowJs": true,
    "checkJs": false,
    // Generate d.ts files
    "declaration": true,
    // This compiler run should
    // only output d.ts files
    "emitDeclarationOnly": false,
    // Types should go into this directory.
    // Removing this would place the .d.ts files
    // next to the .js files
    "outDir": "dist",
    "esModuleInterop": true,
    "resolveJsonModule": true,
    "moduleResolution": "node",
    "allowSyntheticDefaultImports": true,
    "skipLibCheck": true,
    "skipDefaultLibCheck": true,
    "noImplicitAny": false,
    "noUnusedLocals": false,
    "allowUmdGlobalAccess": true,
    "allowUnreachableCode": true,
    "allowUnusedLabels": true,
    "noImplicitThis": false,
    "typeRoots": [
      "./node_modules/@types",
      "./tmp/typings",
      "./src/types"
    ],
    "types": [
      "datatables.net",
      "jquery",
      "node",
      "toastr",
      "bootstrap"
    ],
    "lib": [
      "DOM",
      "ES5",
      "ES6",
      "ES2015",
      "ES2016",
      "ES2017",
      "ES2018",
      "ES2019",
      "ES2020",
      "DOM.Iterable",
      "WebWorker"
    ]
  },
  "typeAcquisition": {
    "enable": true
  },
  "exclude": [
    "**/node_modules/**"
  ]
}

package.json

{
  "name": "hexo-backend",
  "version": "0.3.0",
  "description": "A sample Node.js app using Express 4",
  "engines": {
    "node": "16.x"
  },
  "main": "index.js",
  "scripts": {
    "start": "node dist/index.js",
    "dev": "cross-env-shell NODE_ENV=development node -r ts-node/register index.dev.ts",
    "prod": "cross-env-shell NODE_ENV=production node -r ts-node/register index.dev.ts",
    "fix": "git config config.pull false && git config core.autocrlf false",
    "update": "npx npm-check-updates -u -x chalk",
    "test": "node test.js",
    "push": "npm-run-all -s push:**",
    "push:build-pre": "npm run install:remote",
    "push:build": "gulp tsc copy commit",
    "push:github": "git push github hexo-backend",
    "push:heroku": "git push heroku hexo-backend:master",
    "install:local": "npm i file:../git-command-helper file:../persistent-cache --save",
    "install:remote": "npm i https://github.com/dimaslanjaka/git-command-helper https://github.com/dimaslanjaka/persistent-cache#improve2 --save",
    "gallery-deploy": "npm-run-all -s gallery gallery-push",
    "gallery": "node -r ts-node/register chimeraland/gallery/index.ts",
    "gallery-push": "node -r ts-node/register chimeraland/gallery/_deploy.test.ts",
    "heroku:pull": "git pull heroku master --recurse-submodules"
  },
  "dependencies": {
    "@algolia/autocomplete-js": "^1.7.1",
    "ansi-colors": "^4.1.3",
    "article-parser": "^7.0.3",
    "axios": "^0.27.2",
    "basic-ftp": "^5.0.2",
    "bluebird": "^3.7.2",
    "bootstrap": "^5.2.1",
    "chalk": "^1.0.0",
    "clean-css": "^5.3.1",
    "cors": "^2.8.5",
    "countries-list": "^2.6.1",
    "datatables.net": "^1.12.1",
    "debug": "^4.3.4",
    "deepmerge-ts": "^4.2.1",
    "dotenv": "^16.0.2",
    "ejs": "^3.1.8",
    "event-stream": "~4.0.1",
    "express": "^4.18.1",
    "express-session": "^1.17.3",
    "folder-hash": "^4.0.2",
    "fs-extra": "^10.1.0",
    "ftp": "^0.3.10",
    "git-command-helper": "github:dimaslanjaka/git-command-helper",
    "gulp-util": "^3.0.8",
    "hexo-util": "^2.7.0",
    "html-minifier": "^4.0.0",
    "html-minifier-terser": "^7.0.0",
    "image-validator": "^1.2.1",
    "install": "^0.13.0",
    "javascript-obfuscator": "^4.0.0",
    "jquery": "^3.6.1",
    "js-cookie": "^3.0.1",
    "jsdom": "^20.0.0",
    "kill-process-by-name": "file:packages/kill-process-by-name",
    "moment-timezone": "^0.5.37",
    "node-libcurl": "^2.3.4",
    "node-sass": "^7.0.3",
    "node-tesseract-ocr": "^2.2.1",
    "npm": "^8.19.2",
    "persistent-cache": "github:dimaslanjaka/persistent-cache#improve2",
    "select2": "^4.1.0-rc.0",
    "session-file-store": "^1.5.0",
    "sharp": "^0.31.0",
    "shell-exec": "^1.1.2",
    "ssh2-sftp-client": "^9.0.4",
    "terser": "^5.15.0",
    "through2": "^4.0.2",
    "tiny-lr": "2.0.0",
    "toastr": "^2.1.4",
    "upath": "^2.0.1"
  },
  "devDependencies": {
    "@types/bluebird": "^3.5.36",
    "@types/bootstrap": "^5.2.4",
    "@types/cors": "^2.8.12",
    "@types/ejs": "^3.1.1",
    "@types/express": "^4.17.14",
    "@types/express-session": "^1.17.5",
    "@types/folder-hash": "^4.0.2",
    "@types/fs-extra": "^9.0.13",
    "@types/ftp": "^0.3.33",
    "@types/gulp": "^4.0.9",
    "@types/gulp-util": "^3.0.36",
    "@types/hexo-util": "^0.6.5",
    "@types/html-minifier": "^4.0.2",
    "@types/html-minifier-terser": "^7.0.0",
    "@types/jquery": "^3.5.14",
    "@types/js-cookie": "^3.0.2",
    "@types/jsdom": "^20.0.0",
    "@types/moment-timezone": "^0.5.30",
    "@types/node": "^18.7.18",
    "@types/node-sass": "^4.11.3",
    "@types/prettier": "^2.7.0",
    "@types/select2": "^4.0.55",
    "@types/session-file-store": "^1.2.2",
    "@types/sharp": "^0.31.0",
    "@types/ssh2-sftp-client": "^7.1.0",
    "@types/through2": "github:dimaslanjaka/nodejs-package-types#through2",
    "@types/toastr": "^2.1.40",
    "@typescript-eslint/eslint-plugin": "^5.37.0",
    "@typescript-eslint/parser": "^5.37.0",
    "cross-env": "^7.0.3",
    "eslint": "^8.23.1",
    "eslint-config-prettier": "^8.5.0",
    "eslint-plugin-prettier": "^4.2.1",
    "got": "^12.4.1",
    "gulp": "^4.0.2",
    "nodemon": "^2.0.20",
    "npm-run-all": "^4.1.5",
    "prettier": "^2.7.1",
    "safelinkify": "file:../safelink",
    "tape": "^5.6.0",
    "ts-node": "^10.9.1",
    "typescript": "^4.8.3"
  },
  "repository": {
    "type": "git",
    "url": "https://git.heroku.com/hexo-backend"
  },
  "homepage": "https://hexo-backend.herokuapp.com/",
  "keywords": [
    "node",
    "heroku",
    "express"
  ],
  "license": "MIT"
}