Skip to content

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

fix(filter): 支持全局过滤词中的正则表达式 (#1199)

s4kura965f6b2c0aa0
diff --git a/tests/test_frequency.py b/tests/test_frequency.py
new file mode 100644
index 0000000000..680e535d35
--- /dev/null
+++ b/tests/test_frequency.py
@@ -0,0 +1,42 @@
+import tempfile
+import unittest
+from pathlib import Path
+
+from trendradar.core.frequency import load_frequency_words, matches_word_groups
+
+
+class GlobalFilterTests(unittest.TestCase):
+ def test_global_filter_supports_regular_expressions(self):
+ config = """[GLOBAL_FILTER]
+/spam|clickbait/
+
+[WORD_GROUPS]
+news
+"""
+
+ with tempfile.TemporaryDirectory() as temp_dir:
+ config_path = Path(temp_dir) / "frequency_words.txt"
+ config_path.write_text(config, encoding="utf-8")
+ word_groups, filter_words, global_filters = load_frequency_words(
+ str(config_path)
+ )
+
+ self.assertFalse(
+ matches_word_groups(
+ "Breaking news: spam", word_groups, filter_words, global_filters
+ )
+ )
+ self.assertFalse(
+ matches_word_groups(
+ "Clickbait news", word_groups, filter_words, global_filters
+ )
+ )
+ self.assertTrue(
+ matches_word_groups(
+ "Breaking news", word_groups, filter_words, global_filters
+ )
+ )
+
+
+if __name__ == "__main__":
+ unittest.main()
diff --git a/trendradar/core/frequency.py b/trendradar/core/frequency.py
index 561741ac28..7fe3a2c979 100644
--- a/trendradar/core/frequency.py
+++ b/trendradar/core/frequency.py
@@ -95,7 +95,7 @@ def _word_matches(word_config: Union[str, Dict], title_lower: str) -> bool:
def load_frequency_words(
frequency_file: Optional[str] = None,
-) -> Tuple[List[Dict], List[str], List[str]]:
+) -> Tuple[List[Dict], List[Dict], List[Dict]]:
"""
加载频率词配置
@@ -161,13 +161,13 @@ def load_frequency_words(
# 处理全局过滤区域
if current_section == "GLOBAL_FILTER":
- # 直接添加所有非空行到全局过滤列表
+ # 解析所有非空行,支持普通词和正则语法
for line in lines:
# 忽略特殊语法前缀,只提取纯文本
if line.startswith(("!", "+", "@")):
continue # 全局过滤区不支持特殊语法
if line:
- global_filters.append(line)
+ global_filters.append(_parse_word(line))
continue
# 处理词组区域
@@ -247,7 +247,7 @@ def matches_word_groups(
title: str,
word_groups: List[Dict],
filter_words: List,
- global_filters: Optional[List[str]] = None
+ global_filters: Optional[List[Union[str, Dict]]] = None,
) -> bool:
"""
检查标题是否匹配词组规则
@@ -271,7 +271,9 @@ def matches_word_groups(
# 全局过滤检查(优先级最高)
if global_filters:
- if any(global_word.lower() in title_lower for global_word in global_filters):
+ if any(
+ _word_matches(global_item, title_lower) for global_item in global_filters
+ ):
return False
# 如果没有配置词组,则匹配所有标题(支持显示全部新闻)