'commit'

DouYin/batch_download.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import os
+import time
+import re
+from VideoDownloader import VideoDownloader
+
+def main():
+    url_file = r"d:\dsWork\aiData\DouYin\Url.txt"
+    save_dir = r"d:\dsWork\aiData\DouYin\DownloadedVideos"
+    
+    if not os.path.exists(url_file):
+        print(f"Error: File not found: {url_file}")
+        return
+
+    if not os.path.exists(save_dir):
+        os.makedirs(save_dir)
+        
+    with VideoDownloader() as downloader:
+        with open(url_file, 'r', encoding='utf-8') as f:
+            lines = f.readlines()
+            
+        print(f"Found {len(lines)} lines in {url_file}")
+        
+        count = 0
+        failed_urls = []
+        
+        # Log to file
+        log_file = open(os.path.join(save_dir, "batch_log.txt"), "a", encoding="utf-8")
+        log_file.write(f"\n--- Batch Download Started at {time.strftime('%Y-%m-%d %H:%M:%S')} ---\n")
+        
+        try:
+            for i, line in enumerate(lines):
+                line = line.strip()
+                if not line:
+                    continue
+                    
+                msg = f"[{i+1}/{len(lines)}] Processing line..."
+                print(msg)
+                log_file.write(msg + "\n")
+                log_file.flush()
+                
+                # Extract URL using regex (matches https://v.douyin.com/...)
+                match = re.search(r'https?://v\.douyin\.com/[a-zA-Z0-9\-_]+/?', line)
+                if match:
+                    url = match.group(0)
+                    msg = f"  Found URL: {url}"
+                    print(msg)
+                    log_file.write(msg + "\n")
+                    log_file.flush()
+                    
+                    success = False
+                    # Retry logic
+                    for attempt in range(3):
+                        try:
+                            success = downloader.download(url, save_dir)
+                            if success:
+                                break
+                            msg = f"    Attempt {attempt+1} failed. Retrying in 2s..."
+                            print(msg)
+                            log_file.write(msg + "\n")
+                            log_file.flush()
+                            time.sleep(2)
+                        except Exception as e:
+                            msg = f"    Error on attempt {attempt+1}: {e}"
+                            print(msg)
+                            log_file.write(msg + "\n")
+                            log_file.flush()
+                            time.sleep(2)
+                    
+                    if success:
+                        count += 1
+                        log_file.write(f"  SUCCESS: {url}\n")
+                    else:
+                        msg = f"  FAILED to download: {url}"
+                        print(msg)
+                        failed_urls.append(url)
+                        log_file.write(msg + "\n")
+                    
+                    # Sleep to be nice
+                    time.sleep(1)
+                else:
+                    msg = f"  No valid URL found in line: {line[:50]}..."
+                    print(msg)
+                    log_file.write(msg + "\n")
+        except Exception as e:
+            msg = f"CRITICAL ERROR in batch loop: {e}"
+            print(msg)
+            log_file.write(msg + "\n")
+        finally:
+            log_file.write(f"--- Batch Download Ended at {time.strftime('%Y-%m-%d %H:%M:%S')} ---\n")
+            log_file.close()
+            
+    print(f"Batch download completed. Successfully downloaded {count} videos.")
+    if failed_urls:
+        print(f"Failed to download {len(failed_urls)} videos:")
+        for u in failed_urls:
+            print(f"  {u}")
+
+if __name__ == "__main__":
+    main()