- ver 1.2.47 :

- corretto errore di modifica scheda
- aggiunto scraping (fase 1)

src/server/modules/Scraping.js

@@ -0,0 +1,125 @@
+import axios from 'axios';
+import cheerio from 'cheerio';
+
+class AmazonBookScraper {
+  constructor() {
+    this.baseUrl = 'https://www.amazon.it/dp/';
+  }
+
+  async fetchPage(isbn) {
+    const url = `${this.baseUrl}${isbn}`;
+    try {
+      const { data } = await axios.get(url, {
+        headers: {
+          'User-Agent':
+            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ' +
+            'AppleWebKit/537.36 (KHTML, like Gecko) ' +
+            'Chrome/113.0.0.0 Safari/537.36',
+          // altri header se necessario
+        },
+      });
+      return data;
+    } catch (err) {
+      console.error(`Errore fetching ISBN ${isbn}:`, err.message);
+      return null;
+    }
+  }
+
+  extractData(html) {
+    const $ = cheerio.load(html);
+
+    // Titolo
+    let title = $('#productTitle').text().trim() || null;
+
+    // Sottotitolo (Amazon spesso lo mette in #productSubtitle o nel titolo, proveremo)
+    let subtitle = $('#productSubtitle').text().trim() || null;
+
+    // Numero pagine, formato, edizione
+    // Questi dati spesso sono nella tabella dettagli prodotto con id #detailBullets_feature_div o #productDetailsTable
+    // Proviamo a estrarre da #detailBullets_feature_div
+
+    let pages = null;
+    let format = null;
+    let edition = null;
+
+    $('#detailBullets_feature_div li').each((i, el) => {
+      const label = $(el).find('span.a-text-bold').text().trim().toLowerCase();
+      const value = $(el).find('span').last().text().trim();
+
+      if (label.includes('pagine') || label.includes('pagine stampate')) {
+        pages = value;
+      } else if (label.includes('formato')) {
+        format = value;
+      } else if (label.includes('edizione')) {
+        edition = value;
+      }
+    });
+
+    // fallback su #productDetailsTable (altro possibile layout)
+    if (!pages || !format || !edition) {
+      $('#productDetailsTable .content tr').each((i, el) => {
+        const label = $(el).find('th').text().trim().toLowerCase();
+        const value = $(el).find('td').text().trim();
+
+        if (!pages && (label.includes('pagine') || label.includes('pagine stampate'))) {
+          pages = value;
+        } else if (!format && label.includes('formato')) {
+          format = value;
+        } else if (!edition && label.includes('edizione')) {
+          edition = value;
+        }
+      });
+    }
+
+    return { title, subtitle, pages, format, edition };
+  }
+
+  async scrapeISBN(isbn) {
+    const html = await this.fetchPage(isbn);
+    if (!html) return null;
+
+    const data = this.extractData(html);
+    return data;
+  }
+
+  async scrapeMultiple(isbnList) {
+    const results = [];
+    for (const isbn of isbnList) {
+      console.log(`Scraping ISBN: ${isbn}`);
+      const data = await this.scrapeISBN(isbn);
+      results.push({ isbn, ...data });
+      // Per evitare blocchi, metti una pausa (es. 2 secondi)
+      await new Promise((r) => setTimeout(r, 2000));
+    }
+    return results;
+  }
+}
+
+export async function ScraperDataAmazon(idapp, options) {
+  const scraper = new AmazonBookScraper();
+  const isbn = options.isbn;
+
+  try {
+    const data = await scraper.scrapeISBN(isbn);
+    console.log(data);
+    return data;
+  } catch (e) {
+    console.error(e);
+    return res.status(400).send({ code: server_constants.RIS_CODE_ERR, msg: '' });
+  }
+}
+
+export async function ScraperMultipleDataAmazon(idapp, options) {
+  const scraper = new AmazonBookScraper();
+  const isbnList = ['8850224248']; // metti i tuoi ISBN qui
+
+  try {
+    const books = await scraper.scrapeMultiple(isbnList);
+    console.log(books);
+  } catch (e) {
+    console.error(e);
+    return res.status(400).send({ code: server_constants.RIS_CODE_ERR, msg: '' });
+  }
+}
+
+export default AmazonBookScraper;