First adaptation pass
This commit is contained in:
@@ -0,0 +1,131 @@
|
||||
#!/usr/bin/env node
|
||||
|
||||
import https from 'https';
|
||||
import http from 'http';
|
||||
import fs from 'fs';
|
||||
import path from 'path';
|
||||
import { URL } from 'url';
|
||||
|
||||
const BASE_URL = 'https://corvanis.wiki';
|
||||
const PAGES_LIST_FILE = './tools/wikiPagesList.txt';
|
||||
const OUTPUT_DIR = './wiki-downloads';
|
||||
|
||||
// Create output directory
|
||||
if (!fs.existsSync(OUTPUT_DIR)) {
|
||||
fs.mkdirSync(OUTPUT_DIR, { recursive: true });
|
||||
}
|
||||
|
||||
/**
|
||||
* Make an HTTP(S) request
|
||||
* @param {string} url The URL to request
|
||||
* @returns {Promise<{data: string, statusCode: number}>} The response data and status code
|
||||
*/
|
||||
function makeRequest(url) {
|
||||
return new Promise((resolve, reject) => {
|
||||
const urlObj = new URL(url);
|
||||
const protocol = urlObj.protocol === 'https:' ? https : http;
|
||||
|
||||
protocol
|
||||
.get(url, (res) => {
|
||||
let data = '';
|
||||
|
||||
res.on('data', (chunk) => {
|
||||
data += chunk;
|
||||
});
|
||||
|
||||
res.on('end', () => {
|
||||
resolve({ data, statusCode: res.statusCode });
|
||||
});
|
||||
})
|
||||
.on('error', (err) => {
|
||||
reject(err);
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Sanitize filename
|
||||
* @param {string} str The string to sanitize
|
||||
* @returns {string} Sanitized filename
|
||||
*/
|
||||
function sanitizeFilename(str) {
|
||||
return str
|
||||
.replace(/^\//, '') // Remove leading slash
|
||||
.replace(/[^a-z0-9_\-+()]/gi, '_')
|
||||
.replace(/_+/g, '_')
|
||||
.replace(/^_|_$/g, '');
|
||||
}
|
||||
|
||||
/**
|
||||
* Download a page
|
||||
* @param {string} pagePath The path of the page to download
|
||||
* @returns {Promise<boolean>} Success status
|
||||
*/
|
||||
async function downloadPage(pagePath) {
|
||||
console.log(`Téléchargement: ${pagePath}`);
|
||||
|
||||
try {
|
||||
const url = BASE_URL + pagePath;
|
||||
const { data, statusCode } = await makeRequest(url);
|
||||
|
||||
if (statusCode !== 200) {
|
||||
console.error(` ❌ Erreur ${statusCode} pour ${pagePath}`);
|
||||
return false;
|
||||
}
|
||||
|
||||
// Save the HTML file
|
||||
const filename = `${sanitizeFilename(pagePath)}.html`;
|
||||
const filepath = path.join(OUTPUT_DIR, filename);
|
||||
fs.writeFileSync(filepath, data, 'utf-8');
|
||||
console.log(` ✓ Sauvegardé: ${filename}`);
|
||||
|
||||
// Wait a bit to avoid overwhelming the server
|
||||
await new Promise((resolve) => {
|
||||
setTimeout(resolve, 500);
|
||||
});
|
||||
|
||||
return true;
|
||||
} catch (error) {
|
||||
console.error(` ❌ Erreur lors du téléchargement de ${pagePath}:`, error.message);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Main function
|
||||
*/
|
||||
async function main() {
|
||||
console.log('🚀 Début du téléchargement des pages wiki...');
|
||||
console.log(` Base URL: ${BASE_URL}`);
|
||||
console.log(` Liste des pages: ${PAGES_LIST_FILE}`);
|
||||
console.log(` Répertoire de sortie: ${OUTPUT_DIR}\n`);
|
||||
|
||||
// Read the list of pages
|
||||
let pages = [];
|
||||
if (fs.existsSync(PAGES_LIST_FILE)) {
|
||||
const content = fs.readFileSync(PAGES_LIST_FILE, 'utf-8');
|
||||
pages = content
|
||||
.split('\n')
|
||||
.map((line) => line.trim())
|
||||
.filter((line) => line && !line.startsWith('#'));
|
||||
} else {
|
||||
console.error(`❌ Fichier de liste introuvable: ${PAGES_LIST_FILE}`);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
console.log(`📄 ${pages.length} page(s) à télécharger\n`);
|
||||
|
||||
let successCount = 0;
|
||||
for (const page of pages) {
|
||||
const success = await downloadPage(page);
|
||||
if (success) {
|
||||
successCount += 1;
|
||||
}
|
||||
}
|
||||
|
||||
console.log(`\n✅ Téléchargement terminé!`);
|
||||
console.log(` Pages réussies: ${successCount}/${pages.length}`);
|
||||
console.log(` Fichiers sauvegardés dans: ${OUTPUT_DIR}`);
|
||||
}
|
||||
|
||||
main().catch(console.error);
|
||||
Reference in New Issue
Block a user