puppet

src/pages/api/user-comics.ts

@@ -0,0 +1,267 @@
+import type { APIRoute } from "astro";
+import puppeteer from 'puppeteer';
+
+// Helper function to extract comic slugs from a ComicK user list page
+async function scrapeComicList(userId: string, limit: number = 10): Promise<string[]> {
+  const browser = await puppeteer.launch({
+    headless: true,
+    args: ['--no-sandbox', '--disable-setuid-sandbox']
+  });
+  
+  try {
+    const page = await browser.newPage();
+    
+    // Set a user agent to mimic a real browser
+    await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36');
+    
+    console.log(`Navigating to ComicK user page: ${userId}`);
+    
+    // Navigate to the user's list page
+    await page.goto(`https://comick.io/user/${userId}/list`, {
+      waitUntil: 'networkidle0', // Wait until there are no network connections for at least 500ms
+      timeout: 60000 // Longer timeout to ensure everything loads
+    });
+    
+    // Try different waiting strategies
+    console.log('Waiting for page to load completely...');
+    
+    // First try waiting for specific elements that might be present
+    const selectors = ['.book', '[data-testid="comic-item"]', '.comics-grid', '.comic-list', '.md-list'];
+    let foundSelector = false;
+    
+    for (const selector of selectors) {
+      try {
+        console.log(`Trying to wait for selector: ${selector}`);
+        await page.waitForSelector(selector, { timeout: 5000 });
+        console.log(`Found element with selector: ${selector}`);
+        foundSelector = true;
+        break;
+      } catch (e) {
+        console.log(`Selector ${selector} not found`);
+      }
+    }
+    
+    // If no specific selector worked, wait for any links that might be comics
+    if (!foundSelector) {
+      console.log('Waiting for any comic links to appear...');
+      try {
+        await page.waitForSelector('a[href*="/comic/"]', { timeout: 5000 });
+        console.log('Found comic links on the page');
+      } catch (e) {
+        console.log('No comic links found, continuing anyway');
+      }
+    }
+    
+    // Interact with the page to ensure all content is loaded
+    console.log('Interacting with page to ensure content is loaded...');
+    
+    // Scroll down to trigger any lazy loading
+    await page.evaluate(() => {
+      // Scroll to the bottom of the page
+      window.scrollTo(0, document.body.scrollHeight);
+    });
+    await new Promise(resolve => setTimeout(resolve, 2000));
+    
+    // Scroll back up
+    await page.evaluate(() => {
+      window.scrollTo(0, 0);
+    });
+    await new Promise(resolve => setTimeout(resolve, 1000));
+    
+    // Try clicking any buttons that might reveal the content
+    try {
+      const buttons = await page.$$('button, .button, [role="button"]');
+      console.log(`Found ${buttons.length} buttons on the page`); 
+      
+      // Try clicking buttons that might be related to viewing the list
+      for (const button of buttons.slice(0, 5)) { // Limit to first 5 buttons to avoid clicking too many
+        const buttonText = await page.evaluate(el => el.textContent?.toLowerCase() || '', button);
+        console.log(`Found button with text: ${buttonText}`);
+        if (buttonText.includes('list') || buttonText.includes('view') || 
+            buttonText.includes('show') || buttonText.includes('load')) {
+          console.log(`Clicking button: ${buttonText}`);
+          await button.click().catch(e => console.log(`Failed to click button: ${e.message}`));
+          await new Promise(resolve => setTimeout(resolve, 1000));
+        }
+      }
+    } catch (e) {
+      console.log(`Error interacting with buttons: ${e.message}`);
+    }
+    
+    // Give extra time for JavaScript to execute and everything to render
+    console.log('Waiting additional time for page to stabilize...');
+    await new Promise(resolve => setTimeout(resolve, 3000));
+    
+    console.log('Page loaded, extracting comic data...');
+    
+    // Extract the HTML structure for debugging
+    const pageHtml = await page.content();
+    console.log('Page HTML length:', pageHtml.length);
+    
+    // Extract comic slugs from the page with multiple selector attempts
+    const slugs = await page.evaluate(() => {
+      // Try multiple selectors to find comics
+      const selectors = [
+        // Try different selectors that might match comics
+        '.book a[href^="/comic/"]',
+        'a[href^="/comic/"]',
+        '.md-comic',
+        '.comics-grid a',
+        '.comic-list a',
+        '.md-list a',
+        '[data-testid="comic-item"] a',
+        // Generic link selector targeting comic URLs as fallback
+        'a[href*="/comic/"]'
+      ];
+      
+      // Try each selector and use the first one that returns results
+      for (const selector of selectors) {
+        console.log('Trying selector:', selector);
+        const elements = document.querySelectorAll(selector);
+        console.log(`Found ${elements.length} elements with selector: ${selector}`);
+        
+        if (elements.length > 0) {
+          // We found matching elements, extract the slugs
+          const results = Array.from(elements).map(element => {
+            const href = element.getAttribute('href');
+            if (!href || !href.includes('/comic/')) return null;
+            return href.replace('/comic/', '').split('/')[0]; // Get just the slug part
+          }).filter(Boolean);
+          
+          if (results.length > 0) {
+            console.log(`Found ${results.length} comics with selector: ${selector}`);
+            return results;
+          }
+        }
+      }
+      
+      // If all selectors failed, try a generic approach to find any links to comics
+      const allLinks = document.querySelectorAll('a');
+      console.log(`Trying generic approach with ${allLinks.length} links`);
+      
+      const comicLinks = Array.from(allLinks).filter(link => {
+        const href = link.getAttribute('href');
+        return href && href.includes('/comic/');
+      });
+      
+      console.log(`Found ${comicLinks.length} potential comic links using generic approach`);
+      
+      return comicLinks.map(link => {
+        const href = link.getAttribute('href');
+        return href ? href.replace('/comic/', '').split('/')[0] : null;
+      }).filter(Boolean);
+    });
+    
+    // Limit the number of comics to the specified limit
+    const limitedSlugs = slugs.slice(0, limit);
+    
+    console.log(`Extracted ${slugs.length} comics from page, returning ${limitedSlugs.length} (limit: ${limit})`);
+    return limitedSlugs as string[];
+  } finally {
+    await browser.close();
+  }
+}
+
+export const GET: APIRoute = async ({ request }) => {
+  try {
+    const url = new URL(request.url);
+    const userId = url.searchParams.get('userId');
+    
+    // Get limit parameter from query string (default to 10 if not provided)
+    const limitParam = url.searchParams.get('limit');
+    const limit = limitParam ? parseInt(limitParam, 10) : 10;
+    
+    // Ensure limit is a valid number
+    const validLimit = isNaN(limit) || limit <= 0 ? 10 : Math.min(limit, 100);
+
+    if (!userId) {
+      return new Response(JSON.stringify({ error: 'Missing user ID' }), {
+        status: 400,
+        headers: {
+          'Content-Type': 'application/json'
+        }
+      });
+    }
+
+    // Extract user ID from URL if full URL was provided
+    let cleanUserId = userId;
+    if (userId.includes('comick.io/user/')) {
+      const match = userId.match(/comick\.io\/user\/([a-zA-Z0-9-]+)/);
+      if (match && match[1]) {
+        cleanUserId = match[1];
+      }
+    }
+
+    // Validate the UUID format
+    const uuidRegex = /^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$/i;
+    if (!uuidRegex.test(cleanUserId)) {
+      return new Response(JSON.stringify({ error: 'Invalid user ID format. Must be a UUID like: 8da7d6cf-a2ac-4972-a465-770ba975ee2a' }), {
+        status: 400,
+        headers: {
+          'Content-Type': 'application/json'
+        }
+      });
+    }
+
+    console.log(`Scraping comics for user: ${cleanUserId} with limit: ${validLimit}`);
+    
+    // Use Puppeteer to scrape the user's comic list with the specified limit
+    const comics = await scrapeComicList(cleanUserId, validLimit);
+    
+    // Calculate total
+    const totalComics = comics.length;
+    
+    // Check if the list is empty
+    if (totalComics === 0) {
+      return new Response(JSON.stringify({ 
+        comics: [], 
+        totalComics: 0,
+        message: "No comics found in user's list"
+      }), {
+        status: 200,
+        headers: {
+          'Content-Type': 'application/json'
+        }
+      });
+    }
+
+    return new Response(JSON.stringify({ comics, totalComics }), {
+      status: 200,
+      headers: {
+        'Content-Type': 'application/json',
+        'Cache-Control': 'max-age=3600' // Cache for 1 hour
+      }
+    });
+  } catch (error) {
+    console.error('Error fetching user comics:', error);
+    
+    // Try to generate a helpful error message based on the error
+    let errorMessage = 'Failed to fetch user comics';
+    let statusCode = 500;
+    
+    if (error instanceof Error) {
+      // Handle specific error types
+      if (error.message.includes('Failed to fetch') || 
+          error.message.includes('network') ||
+          error.message.includes('ECONNREFUSED')) {
+        errorMessage = 'Could not connect to ComicK API. Please try again later.';
+      } else if (error.message.includes('timeout')) {
+        errorMessage = 'Request timed out. The ComicK API might be experiencing high load.';
+      } else if (error.message.includes('parsing')) {
+        errorMessage = 'Received invalid data from ComicK API. Their API structure might have changed.';
+      }
+    }
+    
+    return new Response(
+      JSON.stringify({ 
+        error: errorMessage,
+        details: error instanceof Error ? error.message : String(error)
+      }), {
+        status: statusCode,
+        headers: {
+          'Content-Type': 'application/json'
+        }
+      }
+    );
+  }
+};