fix: 三平台内容差异化 + admin敏感词管理表格化

- writer.py: _expand_section() 去除 <100字阈值,始终调用 LLM 平台专属扩写
- prompt_loader.py: 新增 section_expansion_zhihu/wechat/xiaohongshu 三个独立 prompt
- admin.html: 配置管理标签页 + 敏感词/清理规则子标签 + 敏感词表格化管理(编辑/删除)
- config_items.py: PUT /sensitive-words/{id} 支持更新 word/category
- compliance_checker.py: AI 套话从 DB 加载 + 人称规则修正
- initial_data.py: PlatformConfig 字数迁移 + 新种子
- 各前端页面: LLM 配置 rate_limit 字段 + 供应商列表排序
This commit is contained in:
Yuzhiran Dev
2026-06-08 13:51:35 +08:00
parent d0896ef10e
commit 23ff63baa9
26 changed files with 582 additions and 93 deletions
+19 -19
View File
@@ -43,9 +43,9 @@ logger = logging.getLogger(__name__)
_md_parser = mistune.create_markdown()
_FALLBACK_PLATFORM_CONFIG = {
"zhihu": {"max_chars": 3000, "style": "深度长文分析", "min_chars": 1500},
"wechat": {"max_chars": 1500, "style": "亲切口语化", "min_chars": 800},
"xiaohongshu": {"max_chars": 800, "style": "图文笔记,emoji+标签", "min_chars": 300},
"zhihu": {"max_chars": 8000, "style": "深度长文分析", "min_chars": 3000},
"wechat": {"max_chars": 4000, "style": "个人叙事对话感", "min_chars": 2000},
"xiaohongshu": {"max_chars": 1000, "style": "图文笔记,精炼实用", "min_chars": 400},
}
def _load_platform_config() -> dict:
@@ -144,28 +144,30 @@ class Writer:
bullet_count = sum(1 for l in lines if l.startswith(('- ', '* ', '**', '+ ')))
return bullet_count / len(lines) > 0.4
def _expand_section(self, section: Dict) -> str:
def _expand_section(self, section: Dict, platform: str = "zhihu") -> str:
content = section.get('content', '').strip()
# 大纲要点格式(>40% 行以 -/*/** 开头)或内容过短(<100字)应由 LLM 展开为连贯段落
if HAVE_LLM and (self._is_bullet_only(content) or (content and len(content) < 100)):
logger.info(f"使用 LLM 扩写章节(要点→段落): {section['title']}")
prompt = get_prompt("section_expansion",
platform_prompt_key = f"section_expansion_{platform}"
if platform not in ("zhihu", "wechat", "xiaohongshu"):
platform_prompt_key = "section_expansion_zhihu"
if HAVE_LLM and content:
logger.info(f"LLM 扩写 [{platform}]: {section['title']} ({len(content)} chars)")
prompt = get_prompt(platform_prompt_key,
topic_title=self.topic['title'],
section_title=section['title'],
date=datetime.datetime.now().strftime('%Y年%m月%d'),
content=content,
)
try:
params = get_prompt_params("section_expansion")
params = get_prompt_params(platform_prompt_key) or {"temperature": 0.75, "max_tokens": 3000}
expanded = call_llm(prompt, temperature=params.get("temperature", 0.75), max_tokens=params.get("max_tokens", 3000))
if expanded:
cleaned = self._clean_markdown(expanded.strip())
if cleaned:
return cleaned
except Exception as e:
logger.warning(f"LLM 扩写失败: {e}")
logger.warning(f"LLM 扩写失败 [{platform}]: {e}")
# Fallback: 将 bullet points 展开为段落(过滤噪音行)
lines = [l.strip() for l in content.split('\n') if not self._is_outline_noise(l)]
if lines:
sentences = []
@@ -185,17 +187,16 @@ class Writer:
return self._clean_markdown(result)
return ''
def generate_full_markdown(self) -> str:
def generate_platform_markdown(self, platform: str = "zhihu") -> str:
sections = self._parse_outline_sections()
parts = []
for sec in sections:
if sec['level'] == 1:
if sec.get('content'):
expanded = self._expand_section(sec)
expanded = self._expand_section(sec, platform)
if expanded:
parts.append(expanded + "\n")
continue
# 跳过大纲结构噪音节点
title_stripped = sec['title'].strip()
if title_stripped in ('文章大纲', '大纲', '文章结构', '结构'):
continue
@@ -204,7 +205,7 @@ class Writer:
heading = f"{'#' * sec['level']} {sec['title']}"
parts.append(heading)
if sec.get('content'):
expanded = self._expand_section(sec)
expanded = self._expand_section(sec, platform)
parts.append(expanded + "\n")
full_md = "\n".join(parts).strip()
# 收集所有引用来源,统一添加到文末
@@ -286,8 +287,6 @@ class Writer:
if platform == "wechat":
result = []
for line in lines:
# 人称统一:我们→我,你们→你
line = line.replace('我们', '').replace('你们', '').replace('', '')
if line.startswith('### '):
result.append(f"\n**{line[4:]}**\n")
elif line.startswith('## '):
@@ -370,6 +369,7 @@ class Writer:
prompt = get_prompt("title_optimize_wechat",
title=original,
core=self.topic.get('core_concept', ''),
field=self.topic.get('field', ''),
)
elif platform == "xiaohongshu":
prompt = get_prompt("title_optimize_xhs",
@@ -459,10 +459,10 @@ class Writer:
logger.info(f"选题 {self.topic_id} 状态已更新为待审查(数据库)")
def run(self):
logger.info("开始撰写阶段")
markdown = self.generate_full_markdown()
logger.info("开始撰写阶段(三平台独立展开)")
results = {}
for platform in ["zhihu", "wechat", "xiaohongshu"]:
markdown = self.generate_platform_markdown(platform)
html = self.generate_platform_html(markdown, platform)
results[platform] = str(self.save_html(html, platform))
self.mark_draft()