Update scraper.js

scraper.js

@@ -15,12 +15,10 @@ async function getPinterestVideos(query) {
         const searchUrl = `https://www.pinterest.com/search/pins/?q=${encodeURIComponent(query)}&rs=typed`;
         await page.goto(searchUrl, { waitUntil: 'networkidle2', timeout: 30000 });
 
-        // --- SCROLLING LOGIC TO FIND MORE PINS ---
+        // Scroll a bit
         await page.evaluate(async () => {
-            for (let i = 0; i < 3; i++) { // Scroll 3 times to load ~60 pins
-                window.scrollBy(0, window.innerHeight * 2);
-                await new Promise(r => setTimeout(r, 1500));
-            }
+            window.scrollBy(0, 1000);
+            await new Promise(r => setTimeout(r, 1000));
         });
 
         const pinUrls = await page.evaluate(() => {
@@ -28,33 +26,39 @@ async function getPinterestVideos(query) {
                 .map(a => a.href).filter(href => href.includes('/pin/'));
         });
 
-        // Get up to 60 unique pins to check
-        const uniquePins = [...new Set(pinUrls)].slice(0, 60);
-        console.error(`Found ${uniquePins.length} potential pins. Checking for video files...`);
+        const uniquePins = [...new Set(pinUrls)].slice(0, 40);
 
         for (const pinUrl of uniquePins) {
             const pPage = await browser.newPage();
             try {
-                // We go to each pin and try to find the video source
                 await pPage.goto(pinUrl, { waitUntil: 'domcontentloaded', timeout: 10000 });
-                const content = await pPage.content();
+                
+                const data = await pPage.evaluate(() => {
+                    // Extract Title and Description
+                    const title = document.querySelector('h1')?.innerText || "";
+                    const desc = document.querySelector('div[data-test-id="main-pin-description-text"]')?.innerText || "";
+                    const html = document.body.innerHTML;
+                    return { title, desc, html };
+                });
+
                 const videoRegex = /https:\/\/v1\.pinimg\.com\/videos\/mc\/[^\s"']+/g;
-                const matches = content.match(videoRegex);
+                const matches = data.html.match(videoRegex);
 
                 if (matches) {
                     let rawUrl = matches[0].replace(/\\u002F/g, '/').replace(/[奖励"']/g, '');
                     const hashMatch = rawUrl.match(/([a-f0-9]{32})/);
                     if (hashMatch) {
                         const h = hashMatch[1];
-                        // Output the 720p URL for Python to check
-                        process.stdout.write(`https://v1.pinimg.com/videos/mc/720p/${h.substring(0,2)}/${h.substring(2,4)}/${h.substring(4,6)}/${h}.mp4\n`);
+                        const finalUrl = `https://v1.pinimg.com/videos/mc/720p/${h.substring(0,2)}/${h.substring(2,4)}/${h.substring(4,6)}/${h}.mp4`;
+                        // Output format: URL | TITLE | DESCRIPTION
+                        process.stdout.write(`${finalUrl}|${data.title.replace(/\n/g, ' ')}|${data.desc.replace(/\n/g, ' ')}\n`);
                     }
                 }
             } catch (e) {} 
             await pPage.close();
         }
     } catch (error) {
-        console.error("Scraper Error: " + error.message);
+        process.stderr.write(error.message);
     } finally {
         if (browser) await browser.close();
     }