基本可用的分发模块

scripts/distribute_content.py

@@ -13,6 +13,7 @@ import json
 import smtplib
 import zipfile
 import time
+import glob
 from email.mime.text import MIMEText
 from email.mime.multipart import MIMEMultipart
 from email.mime.application import MIMEApplication
@@ -72,9 +73,38 @@ def parse_arguments():
                         help='上一次分发结果CSV或报告文件路径，用于避免重复发送')
     parser.add_argument('--skip-sent-success', action='store_true',
                         help='跳过上次成功发送的文章')
+    parser.add_argument('--zip-filename', type=str, default=None,
+                        help='指定ZIP压缩包的基本文件名（不含扩展名），如"文旅小红书带货笔记内容0512"')
     
     return parser.parse_args()
 
+def find_additional_images(file_path):
+    """查找与文章相关的所有额外图片"""
+    if not file_path or pd.isna(file_path) or not os.path.exists(file_path):
+        return []
+        
+    # 获取文章目录
+    article_dir = os.path.dirname(file_path)
+    
+    # 查找可能的额外图片目录
+    additional_images_dir = os.path.join(article_dir, "additional_images")
+    if not os.path.exists(additional_images_dir):
+        # 尝试向上一级寻找
+        parent_dir = os.path.dirname(article_dir)
+        additional_images_dir = os.path.join(parent_dir, "additional_images")
+        if not os.path.exists(additional_images_dir):
+            return []
+    
+    # 查找所有图片文件
+    image_patterns = ["*.jpg", "*.jpeg", "*.png", "*.gif", "*.webp"]
+    image_files = []
+    
+    for pattern in image_patterns:
+        image_files.extend(glob.glob(os.path.join(additional_images_dir, pattern)))
+    
+    logger.info(f"找到 {len(image_files)} 张额外图片: {additional_images_dir}")
+    return image_files
+
 def read_user_csv(user_csv_path, email_column, username_column):
     """读取用户CSV文件"""
     try:
@@ -239,12 +269,17 @@ def prepare_distribution_csv(users_with_content, output_dir):
         rows = []
         for user in users_with_content:
             for content in user['contents']:
+                # 查找额外图片
+                output_txt_path = content['OutputTxtPath']
+                additional_images = find_additional_images(output_txt_path)
+                
                 rows.append({
                     'email': user['email'],
                     'username': user['username'],
                     'file_path': content['OutputTxtPath'],
                     'poster_path': content['PosterPath'],
                     'article_json_path': content['ArticleJsonPath'],
+                    'additional_images': ';'.join(additional_images),  # 保存为分号分隔的字符串
                     'entry_id': content['EntryID'],
                     'topic_index': content.get('TopicIndex', ''),
                     'variant_index': content.get('VariantIndex', ''),
@@ -271,6 +306,9 @@ def create_zip_file(files, output_path):
         os.makedirs(os.path.dirname(output_path), exist_ok=True)
         with zipfile.ZipFile(output_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
             for file_path in files:
+                if not file_path or pd.isna(file_path):
+                    continue
+                    
                 if os.path.exists(file_path):
                     arcname = os.path.basename(file_path)
                     zipf.write(file_path, arcname=arcname)
@@ -325,7 +363,7 @@ def send_single_email(from_addr, password, to_addr, subject, content, attachment
         return False
 
 def send_emails(distribution_csv, output_dir, email_from, email_password, 
-                subject, smtp_server, smtp_port, use_ssl, test_mode, delay=2):
+                subject, smtp_server, smtp_port, use_ssl, test_mode, delay=2, zip_filename=None):
     """发送邮件"""
     try:
         # 确保输出目录存在
@@ -365,13 +403,22 @@ def send_emails(distribution_csv, output_dir, email_from, email_password,
                 # 收集所有文件路径
                 files = []
                 for row in rows:
+                    # 收集文本文件
                     file_path = row.get('file_path')
-                    if file_path and os.path.exists(file_path):
+                    if file_path and not pd.isna(file_path) and os.path.exists(file_path):
                         files.append(file_path)
                     
+                    # 收集海报图片
                     poster_path = row.get('poster_path')
-                    if poster_path and os.path.exists(poster_path):
+                    if poster_path and not pd.isna(poster_path) and os.path.exists(poster_path):
                         files.append(poster_path)
+                        
+                    # 收集所有额外图片
+                    additional_images = row.get('additional_images', '')
+                    if additional_images and not pd.isna(additional_images):
+                        for img_path in additional_images.split(';'):
+                            if img_path.strip() and os.path.exists(img_path):
+                                files.append(img_path)
                 
                 if not files:
                     logger.warning(f"邮箱 {email} 没有有效的附件文件，跳过")
@@ -385,8 +432,14 @@ def send_emails(distribution_csv, output_dir, email_from, email_password,
                     continue
                 
                 # 创建ZIP文件
-                zip_filename = f"content_{datetime.now().strftime('%Y%m%d_%H%M%S')}_{hash(email) % 10000}.zip"
+                if zip_filename:
-                zip_path = os.path.join(output_dir, "temp_zips", zip_filename)
+                    # 使用指定的文件名
+                    zip_filename_with_ext = f"{zip_filename}.zip"
+                else:
+                    # 使用默认的时间戳文件名
+                    zip_filename_with_ext = f"content_{datetime.now().strftime('%Y%m%d_%H%M%S')}_{hash(email) % 10000}.zip"
+                    
+                zip_path = os.path.join(output_dir, "temp_zips", zip_filename_with_ext)
                 
                 zip_file = create_zip_file(files, zip_path)
                 if zip_file:
@@ -406,12 +459,8 @@ def send_emails(distribution_csv, output_dir, email_from, email_password,
                 files_count = len(files)
                 entries_count = len(rows)
                 
-                email_content = f"""尊敬的用户：
+                email_content = f"""您好！请查收今日带货笔记（文案+配图），内容在文件压缩包内。具体挂载商品等操作流程请查看对应达人微信群内信息。
 
-您好！附件中是您的旅游内容创作成果，请查收。
-本次发送了 {entries_count} 篇文章，共 {files_count} 个文件。
-
-祝好！
 """
                 
                 # 发送邮件
@@ -662,7 +711,7 @@ def main():
     send_result_csv = send_emails(
         distribution_csv, args.output_dir, args.email_from, args.email_password,
         args.subject, args.smtp_server, args.smtp_port, args.use_ssl, args.test_mode,
-        args.delay
+        args.delay, args.zip_filename
     )
     
     # 生成分发报告

scripts/distribute_example.sh

@@ -14,9 +14,11 @@ USER_CSV="$BASE_DIR/output/5.12 copy.csv"
 MANIFEST_CSV="$BASE_DIR/output/2025-05-12_09-33-12/manifest_2025-05-12_09-33-12.csv"
 EMAIL_FROM="zwysendemail@163.com"
 EMAIL_PASSWORD="NMhVGFmCJkGEy3B5"
-SUBJECT="您的旅游内容创作"
+SUBJECT="文旅小红书带货笔记内容0512"
 # 上一次分发结果文件（如果存在）
 PREVIOUS_DIST="$BASE_DIR/distribution_results/distribution_summary_20250512_183328.csv"
+# 压缩包文件名
+ZIP_FILENAME="文旅小红书带货笔记内容0512"
 
 # 创建必要的目录
 mkdir -p "$LOG_DIR"
@@ -41,9 +43,9 @@ python scripts/distribute_content.py \
   --subject "$SUBJECT" \
   --article-per-user 1 \
   --judge-only-success \
-  --test-mode \
   --previous-distribution "$PREVIOUS_DIST" \
-  --skip-sent-success
+  --skip-sent-success \
+  --zip-filename "$ZIP_FILENAME"
 
 # 实际发送邮件的命令（取消注释以启用）
 # echo "开始实际发送邮件..."
@@ -60,7 +62,8 @@ python scripts/distribute_content.py \
 #   --judge-only-success \
 #   --max-send-count 10 \  # 限制最多发送给10个用户
 #   --previous-distribution "$PREVIOUS_DIST" \
-#   --skip-sent-success
+#   --skip-sent-success \
+#   --zip-filename "$ZIP_FILENAME"
 
 # 不使用过滤功能的示例
 # python scripts/distribute_content.py \
@@ -71,6 +74,7 @@ python scripts/distribute_content.py \
 #   --email-password "$EMAIL_PASSWORD" \
 #   --subject "$SUBJECT" \
 #   --article-per-user 3 \
-#   --judge-only-success
+#   --judge-only-success \
+#   --zip-filename "$ZIP_FILENAME"
 
 echo "脚本执行完成 - $(date)"