Update main.py

main.py

@@ -3,11 +3,11 @@ import time
 import json
 import requests
 from huggingface_hub import upload_file
+from urllib.parse import urlparse
 
 # === CONFIGURATION ===
 HF_TOKEN = os.environ.get("HF_TOKEN")
 ZEROUPLOAD_TOKEN = "vcIXZnfFfZlPg5GEw4JqeqZTroJh4nst0WqFvun37SNr1wtzwsu6wC9pZ4x8ze4z"
-ZEROUPLOAD_BASE = "https://zeroupload.com/api/v2/file/download"
 REPO_ID = "Fred808/BG1"
 DATA_PATH = "AEffects"
 PROCESSED_FILE = "processed.json"
@@ -17,23 +17,23 @@ HEADERS = {
     "Authorization": f"Bearer {ZEROUPLOAD_TOKEN}"
 }
 
-# === YOUR DOWNLOAD LIST ===
-DOWNLOAD_LIST = [
-    {"filename": "video1.mp4", "file_id": "abc123"},
-    {"filename": "video2.mp4", "file_id": "xyz456"},
-    # Add more files here
+# === Only list of ZeroUpload URLs ===
+DOWNLOAD_URLS = [
+    "https://zeroupload.com/e7a5f338b6db8987f1735378ad164c79",
+    "https://zeroupload.com/91d9a79cc6cf4ae1a3fb15c16a062fb4",
+    # Add more...
 ]
 
-# === Load processed files ===
+# === Load processed ===
 if os.path.exists(PROCESSED_FILE):
     with open(PROCESSED_FILE, "r") as f:
-        processed_ids = set(json.load(f))
+        processed_urls = set(json.load(f))
 else:
-    processed_ids = set()
+    processed_urls = set()
 
 def save_processed():
     with open(PROCESSED_FILE, "w") as f:
-        json.dump(list(processed_ids), f, indent=2)
+        json.dump(list(processed_urls), f, indent=2)
 
 def upload_to_dataset(filepath):
     try:
@@ -48,43 +48,43 @@ def upload_to_dataset(filepath):
     except Exception as e:
         print(f"[!] Upload failed: {filepath} — {e}")
 
-# === Create output folder ===
+# === Prepare output directory ===
 os.makedirs(OUTPUT_DIR, exist_ok=True)
 
-# === Download and upload ===
-for item in DOWNLOAD_LIST:
-    filename = item.get("filename")
-    file_id = item.get("file_id")
-
-    if not filename or not file_id:
-        print("[!] Skipping invalid entry.")
-        continue
-
-    if file_id in processed_ids:
-        print(f"[✔] Already processed: {file_id}")
+# === Main loop ===
+for url in DOWNLOAD_URLS:
+    if url in processed_urls:
+        print(f"[✔] Already processed: {url}")
         continue
 
-    file_url = f"{ZEROUPLOAD_BASE}/{file_id}"
-    local_path = os.path.join(OUTPUT_DIR, filename)
-
     try:
-        print(f"[*] Downloading {filename}...")
-        with requests.get(file_url, headers=HEADERS, stream=True) as r:
+        print(f"[*] Requesting: {url}")
+        with requests.get(url, headers=HEADERS, stream=True) as r:
             r.raise_for_status()
+
+            # Try to extract filename from headers, fallback to last URL segment
+            cd = r.headers.get("content-disposition")
+            if cd and "filename=" in cd:
+                filename = cd.split("filename=")[1].strip('"')
+            else:
+                filename = os.path.basename(urlparse(url).path) + ".mp4"
+
+            local_path = os.path.join(OUTPUT_DIR, filename)
+
             with open(local_path, "wb") as f:
                 for chunk in r.iter_content(chunk_size=8192):
                     f.write(chunk)
+
         print(f"[✓] Downloaded: {filename}")
 
         upload_to_dataset(local_path)
-
-        processed_ids.add(file_id)
+        processed_urls.add(url)
         save_processed()
         os.remove(local_path)
 
     except Exception as e:
-        print(f"[!] Error downloading/uploading {filename}: {e}")
+        print(f"[!] Error with {url}: {e}")
 
-    time.sleep(2)  # small pause between files
+    time.sleep(2)
 
-print("\n✅ Done. All downloads and uploads completed.")
+print("\n✅ All ZeroUpload files processed.")