Files
nanocode/skills/xiaohongshu_integration/xiaohongshu_enhanced_publisher.py
T
Ubuntu 32b43f85bd a
2026-07-03 16:58:28 +08:00

615 lines
22 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""
小红书增强版发布器
集成图片风格生成功能,实现从内容到图片到发布的全自动化流程
"""
import argparse
import logging
import sys
import os
import json
import time
import subprocess
from pathlib import Path
from typing import List, Dict, Optional, Tuple
from datetime import datetime
# 添加当前目录到Python路径
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
sys.path.append("/home/ubuntu") # 添加xhs_image_generator路径
try:
from content_converter_fixed import ContentConverterFixed
from xhs_image_generator import XHSImageGenerator, XHSStyle, XHSLayout
from xhs_api_generator_fixed import XHSAPIGenerator
except ImportError as e:
print(f"导入错误: {e}")
print("请确保相关模块已安装")
sys.exit(1)
logger = logging.getLogger(__name__)
class XiaohongshuEnhancedPublisher:
"""增强版小红书发布器 - 集成图片风格生成"""
def __init__(self, config_path: str = None):
"""
初始化增强版发布器
Args:
config_path: 配置文件路径
"""
# 初始化组件
self.content_converter = ContentConverterFixed()
self.image_generator = XHSImageGenerator()
# 加载配置
self.config = self._load_config(config_path)
# 初始化API生成器(延迟初始化,需要API密钥)
self.api_generator = None
logger.info("增强版小红书发布器初始化完成")
logger.info(f"配置: {json.dumps(self.config, ensure_ascii=False, indent=2)}")
def _load_config(self, config_path: str) -> Dict:
"""加载配置文件"""
default_config = {
"xiaohongshu": {
"cli_path": "xhs",
"max_images": 9,
"default_tags": ["#技术资讯", "#科技新闻", "#AI", "#小红书运营"],
"publish_interval": 3600,
"auto_generate_images": True,
"default_style": "notion",
"default_layout": "balanced"
},
"image_generation": {
"api_key": None,
"api_base_url": "https://ark.cn-beijing.volces.com/api/v3",
"model": "doubao-seedream-4-5-251128",
"max_retries": 3,
"timeout": 60,
"output_dir": "/home/ubuntu/xhs_generated_images"
},
"content": {
"max_title_length": 30,
"max_content_length": 1000,
"auto_generate_tags": True,
"add_source_info": True,
"extract_key_points": True
}
}
# 如果提供了配置文件,则加载
if config_path and os.path.exists(config_path):
try:
with open(config_path, 'r', encoding='utf-8') as f:
user_config = json.load(f)
# 深度合并配置
def deep_merge(base, update):
for key, value in update.items():
if key in base and isinstance(base[key], dict) and isinstance(value, dict):
deep_merge(base[key], value)
else:
base[key] = value
return base
default_config = deep_merge(default_config, user_config)
logger.info(f"从 {config_path} 加载配置")
except Exception as e:
logger.error(f"加载配置文件失败: {e}")
# 确保输出目录存在
output_dir = default_config["image_generation"]["output_dir"]
os.makedirs(output_dir, exist_ok=True)
return default_config
def _init_api_generator(self) -> bool:
"""初始化API生成器"""
if self.api_generator is not None:
return True
api_key = self.config["image_generation"]["api_key"]
if not api_key:
logger.warning("未配置API密钥,图片生成功能将不可用")
return False
try:
self.api_generator = XHSAPIGenerator(
api_key=api_key,
base_url=self.config["image_generation"]["api_base_url"],
model=self.config["image_generation"]["model"]
)
logger.info("API生成器初始化成功")
return True
except Exception as e:
logger.error(f"API生成器初始化失败: {e}")
return False
def analyze_content(self, content: str) -> Dict:
"""
分析内容,推荐最佳风格和布局
Args:
content: 内容文本
Returns:
分析结果字典
"""
return self.image_generator.analyze_content(content)
def generate_images_for_content(self, content: str, style: str = None, layout: str = None) -> List[str]:
"""
为内容生成图片
Args:
content: 内容文本
style: 风格名称(可选,自动推荐)
layout: 布局名称(可选,自动推荐)
Returns:
生成的图片路径列表
"""
# 检查是否启用图片生成
if not self.config["xiaohongshu"]["auto_generate_images"]:
logger.info("图片生成功能已禁用")
return []
# 初始化API生成器
if not self._init_api_generator():
logger.warning("API生成器不可用,跳过图片生成")
return []
# 分析内容
analysis = self.analyze_content(content)
# 确定风格和布局
if style is None:
style = analysis["recommended_style"].value
if layout is None:
layout = analysis["recommended_layout"].value
logger.info(f"为内容生成图片 - 风格: {style}, 布局: {layout}")
# 生成提示词
try:
style_enum = XHSStyle(style)
layout_enum = XHSLayout(layout)
except ValueError as e:
logger.error(f"无效的风格或布局: {e}")
return []
prompt = self.image_generator.generate_prompt(content, style_enum, layout_enum)
# 生成图片
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
output_dir = Path(self.config["image_generation"]["output_dir"])
image_path = output_dir / f"xhs_{style}_{layout}_{timestamp}.png"
logger.info(f"调用API生成图片: {image_path}")
success = self.api_generator.generate_image(prompt, str(image_path), style_enum)
if success:
logger.info(f"✅ 图片生成成功: {image_path}")
return [str(image_path)]
else:
logger.error(f"❌ 图片生成失败")
return []
def publish_with_generated_images(self, markdown_file: str, style: str = None, layout: str = None) -> bool:
"""
使用生成的图片发布到小红书
Args:
markdown_file: Markdown文件路径
style: 图片风格(可选)
layout: 图片布局(可选)
Returns:
是否成功
"""
try:
# 检查文件是否存在
if not os.path.exists(markdown_file):
logger.error(f"Markdown文件不存在: {markdown_file}")
return False
# 读取Markdown文件
with open(markdown_file, 'r', encoding='utf-8') as f:
markdown_content = f.read()
logger.info(f"读取Markdown文件: {markdown_file}")
logger.info(f"文件大小: {len(markdown_content)} 字符")
# 转换为小红书格式
xhs_content = self.content_converter.convert_markdown_to_xiaohongshu(markdown_content)
if not xhs_content:
logger.error("内容转换失败")
return False
logger.info(f"转换后内容大小: {len(xhs_content)} 字符")
# 提取关键信息用于图片生成
title = self._extract_title(markdown_content)
key_content = self._extract_key_content(markdown_content)
# 生成图片
generated_images = self.generate_images_for_content(key_content, style, layout)
# 如果没有生成图片,使用默认图片或现有图片
images_to_use = generated_images
if not images_to_use:
logger.info("使用默认图片或现有图片")
# 这里可以添加从Markdown中提取现有图片的逻辑
images_to_use = []
# 调用小红书CLI发布
return self._call_xhs_cli(title, xhs_content, images_to_use)
except Exception as e:
logger.error(f"发布过程中发生错误: {e}")
return False
def _extract_title(self, markdown_content: str) -> str:
"""从Markdown中提取标题"""
lines = markdown_content.strip().split('\n')
for line in lines:
line = line.strip()
if line.startswith('# '):
return line[2:].strip()
# 如果没有找到标题,使用第一行或默认标题
if lines and lines[0].strip():
return lines[0].strip()[:30]
return "小红书笔记"
def _extract_key_content(self, markdown_content: str) -> str:
"""从Markdown中提取关键内容用于图片生成"""
# 提取前200个字符作为关键内容
content = markdown_content.strip()
if len(content) > 200:
content = content[:200] + "..."
# 移除Markdown标记
import re
content = re.sub(r'#+\s*', '', content) # 移除标题标记
content = re.sub(r'!\[.*?\]\(.*?\)', '', content) # 移除图片标记
content = re.sub(r'\[.*?\]\(.*?\)', '', content) # 移除链接标记
content = re.sub(r'`.*?`', '', content) # 移除代码标记
content = re.sub(r'\*\*.*?\*\*', '', content) # 移除粗体标记
content = re.sub(r'\*.*?\*', '', content) # 移除斜体标记
return content.strip()
def _call_xhs_cli(self, title: str, content: str, images: List[str]) -> bool:
"""
调用小红书CLI发布内容
Args:
title: 标题
content: 内容
images: 图片路径列表
Returns:
是否成功
"""
try:
# 构建命令
cli_path = self.config["xiaohongshu"]["cli_path"]
# 创建临时文件存储内容
import tempfile
with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False, encoding='utf-8') as f:
f.write(content)
content_file = f.name
# 构建命令参数
cmd = [cli_path, "post"]
# 添加标题
if title:
cmd.extend(["--title", title])
# 添加内容文件
cmd.extend(["--content-file", content_file])
# 添加图片
for image in images:
if os.path.exists(image):
cmd.extend(["--image", image])
# 添加标签
for tag in self.config["xiaohongshu"]["default_tags"]:
cmd.extend(["--tag", tag])
logger.info(f"执行命令: {' '.join(cmd)}")
# 执行命令
result = subprocess.run(
cmd,
capture_output=True,
text=True,
encoding='utf-8',
timeout=self.config["image_generation"]["timeout"]
)
# 清理临时文件
try:
os.unlink(content_file)
except:
pass
if result.returncode == 0:
logger.info("✅ 小红书发布成功")
logger.info(f"输出: {result.stdout}")
return True
else:
logger.error(f"❌ 小红书发布失败")
logger.error(f"错误: {result.stderr}")
return False
except subprocess.TimeoutExpired:
logger.error("❌ 发布超时")
return False
except Exception as e:
logger.error(f"❌ 调用小红书CLI失败: {e}")
return False
def test_publish(self) -> bool:
"""测试发布功能"""
logger.info("开始测试增强版发布功能...")
# 创建测试内容
test_content = """# AI技术新突破:文本生成图片质量大幅提升
最近,AI图像生成技术取得了重大突破。新的模型能够生成更加逼真、细节丰富的图片,同时保持高度的创意性。
## 主要改进
1. **图像质量提升**
- 分辨率从512×512提升到1024×1024
- 细节更加丰富,纹理更加真实
- 色彩更加鲜艳自然
2. **创意控制增强**
- 支持更复杂的提示词
- 可以指定艺术风格和构图
- 支持多图生成和一致性保持
3. **生成速度优化**
- 推理时间减少30%
- 支持批量生成
- 内存占用优化
这项技术将改变内容创作的方式,让每个人都能轻松生成高质量的视觉内容。
"""
# 保存测试文件
test_file = "/tmp/test_enhanced_article.md"
with open(test_file, 'w', encoding='utf-8') as f:
f.write(test_content)
logger.info(f"创建测试文件: {test_file}")
# 测试图片生成
logger.info("测试图片生成功能...")
images = self.generate_images_for_content(test_content, "notion", "dense")
if images:
logger.info(f"✅ 图片生成成功: {images}")
else:
logger.warning("⚠️ 图片生成失败或已禁用")
# 测试发布
logger.info("测试发布功能...")
success = self.publish_with_generated_images(test_file, "notion", "dense")
if success:
logger.info("✅ 测试发布成功")
else:
logger.error("❌ 测试发布失败")
# 清理测试文件
try:
os.remove(test_file)
logger.info(f"清理测试文件: {test_file}")
except:
pass
return success
def batch_process_directory(self, directory: str, style: str = None, layout: str = None) -> Dict[str, bool]:
"""
批量处理目录中的Markdown文件
Args:
directory: 目录路径
style: 图片风格(可选)
layout: 图片布局(可选)
Returns:
处理结果字典 {文件名: 是否成功}
"""
results = {}
if not os.path.isdir(directory):
logger.error(f"目录不存在: {directory}")
return results
# 查找所有Markdown文件
md_files = []
for root, dirs, files in os.walk(directory):
for file in files:
if file.lower().endswith('.md'):
md_files.append(os.path.join(root, file))
logger.info(f"找到 {len(md_files)} 个Markdown文件")
# 逐个处理
for i, md_file in enumerate(md_files, 1):
logger.info(f"处理文件 {i}/{len(md_files)}: {md_file}")
try:
success = self.publish_with_generated_images(md_file, style, layout)
results[md_file] = success
if success:
logger.info(f"✅ 文件处理成功: {md_file}")
else:
logger.error(f"❌ 文件处理失败: {md_file}")
# 避免发布频率过高
if i < len(md_files):
interval = self.config["xiaohongshu"]["publish_interval"]
logger.info(f"等待 {interval} 秒后处理下一个文件...")
time.sleep(interval)
except Exception as e:
logger.error(f"处理文件时发生错误: {e}")
results[md_file] = False
return results
def main():
"""主函数"""
parser = argparse.ArgumentParser(description='小红书增强版发布器 - 集成图片风格生成')
subparsers = parser.add_subparsers(dest='command', help='命令')
# publish命令
publish_parser = subparsers.add_parser('publish', help='发布文章')
publish_parser.add_argument('--markdown', type=str, required=True, help='Markdown文件路径')
publish_parser.add_argument('--style', type=str, help='图片风格 (cute, fresh, notion, minimal等)')
publish_parser.add_argument('--layout', type=str, help='图片布局 (sparse, balanced, dense等)')
publish_parser.add_argument('--config', type=str, help='配置文件路径')
# batch命令
batch_parser = subparsers.add_parser('batch', help='批量处理目录')
batch_parser.add_argument('--directory', type=str, required=True, help='目录路径')
batch_parser.add_argument('--style', type=str, help='图片风格')
batch_parser.add_argument('--layout', type=str, help='图片布局')
batch_parser.add_argument('--config', type=str, help='配置文件路径')
# analyze命令
analyze_parser = subparsers.add_parser('analyze', help='分析内容')
analyze_parser.add_argument('--content', type=str, required=True, help='内容文本')
analyze_parser.add_argument('--file', type=str, help='文件路径(替代--content)')
# generate命令
generate_parser = subparsers.add_parser('generate', help='生成图片')
generate_parser.add_argument('--content', type=str, required=True, help='内容文本')
generate_parser.add_argument('--style', type=str, help='图片风格')
generate_parser.add_argument('--layout', type=str, help='图片布局')
generate_parser.add_argument('--output', type=str, help='输出文件路径')
generate_parser.add_argument('--config', type=str, help='配置文件路径')
# test命令
subparsers.add_parser('test', help='测试发布功能')
# config命令
config_parser = subparsers.add_parser('config', help='查看配置')
config_parser.add_argument('--show', action='store_true', help='显示完整配置')
args = parser.parse_args()
# 配置日志
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)
# 创建发布器
publisher = XiaohongshuEnhancedPublisher(args.config if hasattr(args, 'config') else None)
if args.command == 'publish':
success = publisher.publish_with_generated_images(
args.markdown,
args.style,
args.layout
)
sys.exit(0 if success else 1)
elif args.command == 'batch':
results = publisher.batch_process_directory(
args.directory,
args.style,
args.layout
)
# 输出结果统计
total = len(results)
success_count = sum(1 for r in results.values() if r)
failure_count = total - success_count
print(f"\n批量处理完成:")
print(f" 总计: {total} 个文件")
print(f" 成功: {success_count} 个")
print(f" 失败: {failure_count} 个")
if failure_count > 0:
print(f"\n失败的文件:")
for file, success in results.items():
if not success:
print(f" - {file}")
sys.exit(0 if failure_count == 0 else 1)
elif args.command == 'analyze':
content = args.content
if args.file:
with open(args.file, 'r', encoding='utf-8') as f:
content = f.read()
analysis = publisher.analyze_content(content)
print(f"内容分析结果:")
print(f" 内容类型: {analysis['content_type']}")
print(f" 推荐风格: {analysis['recommended_style'].value}")
print(f" 推荐布局: {analysis['recommended_layout'].value}")
print(f" 建议图片数: {analysis['image_count']}")
if 'key_points' in analysis:
print(f" 关键点: {analysis['key_points']}")
elif args.command == 'generate':
images = publisher.generate_images_for_content(
args.content,
args.style,
args.layout
)
if images:
print(f"✅ 图片生成成功:")
for img in images:
print(f" - {img}")
else:
print("❌ 图片生成失败")
sys.exit(1)
elif args.command == 'test':
success = publisher.test_publish()
sys.exit(0 if success else 1)
elif args.command == 'config':
if args.show:
print(json.dumps(publisher.config, ensure_ascii=False, indent=2))
else:
print("当前配置摘要:")
print(f" 小红书CLI路径: {publisher.config['xiaohongshu']['cli_path']}")
print(f" 自动生成图片: {publisher.config['xiaohongshu']['auto_generate_images']}")
print(f" 默认风格: {publisher.config['xiaohongshu']['default_style']}")
print(f" 默认布局: {publisher.config['xiaohongshu']['default_layout']}")
print(f" API密钥配置: {'已配置' if publisher.config['image_generation']['api_key'] else '未配置'}")
else:
parser.print_help()
sys.exit(1)
if __name__ == "__main__":
main()