Update app.py

app.py

@@ -35,98 +35,149 @@ USER_AGENTS = [
 
 fail_lock = threading.Lock()
 
+def random_headers(referer):
+    return {
+        "User-Agent": random.choice(USER_AGENTS),
+        "Referer": referer,
+        "Accept": "image/webp,image/apng,image/*,*/*;q=0.8",
+    }
+def count_links(workbook_file):
+    if not workbook_file:
+        return ""
+    try:
+        links = read_links_from_workbook(workbook_file.name)
+        return f"🔗 Detected {len(links)} image link(s)."
+    except Exception as e:
+        return f"❌ Error reading workbook: {e}"
+
 def thread_log_failure(failures, msg):
     with fail_lock:
         failures.append(msg)
 
-def download_image(url, out_path, code, suf, failures):
-    import traceback
-    from selenium.common.exceptions import TimeoutException
+def download_direct_image(url, out_path):
+    try:
+        r = requests.get(url, stream=True, timeout=30)
+        r.raise_for_status()
+        if "image" in r.headers.get("Content-Type", "").lower():
+            with open(out_path, "wb") as f:
+                for chunk in r.iter_content(8192):
+                    f.write(chunk)
+            return True
+        return False
+    except Exception as e:
+        print(f"Direct download failed: {e}")
+        return False
+
+
+from io import BytesIO
+from PIL import Image
+
+def download_image(url, out_path, fail_log, code, suf):
+    """
+    Tries multiple methods to download an image, logs failures with ItemCode names.
+    Order:
+      1) cloudscraper
+      2) requests
+      3) public proxy (weserv)
+      4) Selenium canvas fallback
+    Returns True on success, False on all failures.
+    """
+    import requests, cloudscraper, random, time, base64, os
+    from urllib.parse import urlparse, quote
+    from selenium import webdriver
+    from selenium.webdriver.chrome.options import Options
+    from selenium.webdriver.chrome.service import Service
+    from webdriver_manager.chrome import ChromeDriverManager
 
     def log(msg):
         entry = f"{code}{suf}: {msg}"
-        print(entry)
-        with fail_lock:
-            failures.append(entry)
+        with open(fail_log, "a") as f:
+            f.write(entry + "\n")
+
+    USER_AGENTS = [
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
+        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7)",
+        "Mozilla/5.0 (Linux; Android 10)",
+        "Mozilla/5.0 (iPhone; CPU iPhone OS 14_6 like Mac OS X)",
+    ]
 
     parsed = urlparse(url)
     referer = f"{parsed.scheme}://{parsed.netloc}/"
     headers = {
         "User-Agent": random.choice(USER_AGENTS),
-        "Referer": referer,
-        "Accept": "image/webp,image/apng,image/*,*/*;q=0.8",
+        "Referer":    referer,
+        "Accept":     "image/webp,image/apng,image/*,*/*;q=0.8",
     }
 
     log(f"Starting download: {url}")
 
     # 1) cloudscraper
     try:
-        scraper = cloudscraper.create_scraper(browser={"browser": "chrome", "platform": "windows"})
+        scraper = cloudscraper.create_scraper(browser={"browser":"chrome","platform":"windows"})
         r = scraper.get(url, headers=headers, stream=True, timeout=30)
         r.raise_for_status()
-        if "image" in r.headers.get("Content-Type", "").lower():
+        if "image" in r.headers.get("Content-Type","").lower():
             with open(out_path, "wb") as f:
                 for chunk in r.iter_content(8192):
                     f.write(chunk)
             return True
-        log(f"Cloudscraper non-image content-type: {r.headers.get('Content-Type')}")
+        log(f"Cloudscraper non-image: {r.headers.get('Content-Type')}")
     except Exception as e:
-        log(f"Cloudscraper error: {e}\n{traceback.format_exc()}")
+        log(f"Cloudscraper error: {e}")
 
-    # 2) requests fallback
+    # 2) requests
     try:
-        r = requests.get(url, headers=headers, stream=True, timeout=60, allow_redirects=True, verify=False)
+        r = requests.get(url, headers=headers, stream=True,
+                         timeout=60, allow_redirects=True, verify=False)
         r.raise_for_status()
-        if "image" in r.headers.get("Content-Type", "").lower():
+        if "image" in r.headers.get("Content-Type","").lower():
             with open(out_path, "wb") as f:
                 for chunk in r.iter_content(8192):
                     f.write(chunk)
             return True
-        log(f"Requests non-image content-type: {r.headers.get('Content-Type')}")
+        log(f"Requests non-image: {r.headers.get('Content-Type')}")
     except Exception as e:
-        log(f"Requests error: {e}\n{traceback.format_exc()}")
+        log(f"Requests error: {e}")
 
-    # 3) public proxy fallback
+    # 3) public proxy
     try:
         proxy_target = parsed.netloc + parsed.path + (f"?{parsed.query}" if parsed.query else "")
-        proxy_url = f"https://images.weserv.nl/?url={quote(proxy_target, safe='')}"
+        proxy_url    = f"https://images.weserv.nl/?url={quote(proxy_target, safe='')}"
         r = requests.get(proxy_url, headers=headers, stream=True, timeout=30)
         r.raise_for_status()
-        if "image" in r.headers.get("Content-Type", "").lower():
+        if "image" in r.headers.get("Content-Type","").lower():
             with open(out_path, "wb") as f:
                 for chunk in r.iter_content(8192):
                     f.write(chunk)
             return True
-        log(f"Proxy non-image content-type: {r.headers.get('Content-Type')}")
+        log(f"Proxy non-image: {r.headers.get('Content-Type')}")
     except Exception as e:
-        log(f"Proxy error: {e}\n{traceback.format_exc()}")
+        log(f"Proxy error: {e}")
 
-    # 4) Selenium fallback - improved wait & error handling
-    driver = None
+    # 4) Selenium canvas fallback
     try:
         opts = Options()
         opts.add_argument("--headless")
         opts.add_argument("--disable-gpu")
         opts.add_argument("--no-sandbox")
         opts.add_argument(f"user-agent={headers['User-Agent']}")
-        opts.add_argument("--disable-dev-shm-usage")  # fix some Linux errors
 
-        driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=opts)
-        driver.set_page_load_timeout(30)
+        driver = webdriver.Chrome(
+            service=Service(ChromeDriverManager().install()),
+            options=opts
+        )
         driver.get(url)
+        time.sleep(5)  # allow JS & image to load
 
-        wait = WebDriverWait(driver, 20)
-        img_el = wait.until(EC.presence_of_element_located((By.TAG_NAME, "img")))
-
-        # Execute JS to get image data URL
+        img_el = driver.find_element("tag name", "img")
         data_url = driver.execute_script("""
             const img = arguments[0];
             const c = document.createElement('canvas');
-            c.width = img.naturalWidth; 
-            c.height = img.naturalHeight;
-            c.getContext('2d').drawImage(img, 0, 0);
+            c.width = img.naturalWidth;  c.height = img.naturalHeight;
+            c.getContext('2d').drawImage(img,0,0);
             return c.toDataURL('image/png');
         """, img_el)
+        driver.quit()
 
         header, b64 = data_url.split(",", 1)
         raw = base64.b64decode(b64)
@@ -134,14 +185,12 @@ def download_image(url, out_path, code, suf, failures):
             f.write(raw)
         return True
 
-    except TimeoutException:
-        log("Selenium timeout: Image element not found in time.")
     except Exception as e:
-        log(f"Selenium error: {e}\n{traceback.format_exc()}")
-    finally:
-        if driver:
-            driver.quit()
+        try: driver.quit()
+        except: pass
+        log(f"Selenium error: {e}")
 
+    # All methods failed
     log("Download failed for all methods")
     return False