hmo/MoFin
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

xiaoguo_news_processor: 正文去200字限制，全文发

Browse Source
This commit is contained in:
知微
2026-06-21 00:40:08 +08:00
parent a42d564f9d
commit 3942356a17
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
xiaoguo_news_processor.py
+1 -1
View File
@@ -97,7 +97,7 @@ def call_xiaoguo(articles):
for a in articles: for a in articles:
title = re.sub(r'\b\d{6}\b', '', a['title']).strip() title = re.sub(r'\b\d{6}\b', '', a['title']).strip()
title = re.sub(r'\s+', ' ', title) title = re.sub(r'\s+', ' ', title)
content = (a.get('content') or '')[:200] content = a.get('content') or ''
# 给正文加标点分隔（akshare正文无标点，模型推理会卡） # 给正文加标点分隔（akshare正文无标点，模型推理会卡）
if content and not any(c in content for c in '。，！？；'): if content and not any(c in content for c in '。，！？；'):
content = '。'.join([content[i:i+20] for i in range(0, len(content), 20)]) content = '。'.join([content[i:i+20] for i in range(0, len(content), 20)])