Update app.py

app.py

@@ -95,70 +95,55 @@ def read_links_from_workbook(path):
                     tasks.append((code, str(val).strip(), f"_{i}"))
     return tasks
 
-def download_image(url, out_path, fail_log, code, suf):
+def download_image(url, out_path, failures, code, suf, fail_lock):
+    from urllib.parse import urlparse
+    import cloudscraper
+    import traceback
+
     def log(msg):
         entry = f"{code}{suf}: {msg}"
         print(entry)
-        with open(fail_log, "a") as f:
-            f.write(entry + "\n")
+        with fail_lock:
+            failures.append(entry)
 
     parsed = urlparse(url)
     referer = f"{parsed.scheme}://{parsed.netloc}/"
-    headers = random_headers(referer)
+    headers = {
+        "User-Agent": random.choice(USER_AGENTS),
+        "Referer": referer,
+        "Accept": "image/webp,image/apng,image/*,*/*;q=0.8",
+    }
 
     log(f"Starting download: {url}")
 
-    # Try requests direct download
+    # 1) Direct requests
     try:
-        r = requests.get(url, headers=headers, stream=True, timeout=30)
+        r = requests.get(url, headers=headers, stream=True, timeout=30, verify=False)
         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
-        log(f"Requests non-image content-type: {r.headers.get('Content-Type')}")
+        else:
+            log(f"Requests non-image content-type: {r.headers.get('Content-Type')}")
     except Exception as e:
-        log(f"Requests error: {e}")
+        log(f"Requests error: {e}\n{traceback.format_exc()}")
 
-    # Selenium fallback (headless)
-    driver = None
+    # 2) cloudscraper 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")
-
-        driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=opts)
-        driver.set_page_load_timeout(30)
-        driver.get(url)
-        time.sleep(5)  # let JS/images load
-
-        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);
-            return c.toDataURL('image/png');
-        """, img_el)
-
-        header, b64 = data_url.split(",", 1)
-        import base64
-        raw = base64.b64decode(b64)
-        with open(out_path, "wb") as f:
-            f.write(raw)
-        return True
-
+        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():
+            with open(out_path, "wb") as f:
+                for chunk in r.iter_content(8192):
+                    f.write(chunk)
+            return True
+        else:
+            log(f"Cloudscraper non-image content-type: {r.headers.get('Content-Type')}")
     except Exception as e:
-        log(f"Selenium error: {e}")
-    finally:
-        if driver:
-            driver.quit()
+        log(f"Cloudscraper error: {e}\n{traceback.format_exc()}")
 
     log("Download failed for all methods")
     return False