|
@@ -13,21 +13,20 @@ def get_level_up_articles() -> set:
|
|
|
"""
|
|
|
:return:
|
|
|
"""
|
|
|
- pool_level2 = "20240804003153130851174"
|
|
|
- pool_level1 = "20240802171417146947657"
|
|
|
- pool_level0 = "20240802143345289374071"
|
|
|
- pool_level2_result = get_generated_article_list(pool_level2)
|
|
|
- title_list_2 = [i[1] for i in pool_level2_result]
|
|
|
- pool_level1_result = get_generated_article_list(pool_level1)
|
|
|
- title_list_1 = [i[1] for i in pool_level1_result]
|
|
|
- pool_level0_result = get_generated_article_list(pool_level0)
|
|
|
- title_list_0 = [i[1] for i in pool_level0_result]
|
|
|
- title_list = title_list_1 + title_list_0 + title_list_2
|
|
|
- good_title_set = set(title_list)
|
|
|
+ generate_pool_ids = [
|
|
|
+ "20240804003153130851174",
|
|
|
+ "20240802171417146947657",
|
|
|
+ "20240802143345289374071",
|
|
|
+ ]
|
|
|
+ good_title_set = set()
|
|
|
+ for pool_id in generate_pool_ids:
|
|
|
+ articles = get_generated_article_list(pool_id)
|
|
|
+ titles = [article[1] for article in articles]
|
|
|
+ good_title_set.update(titles)
|
|
|
return good_title_set
|
|
|
|
|
|
|
|
|
-class ArticleExitWithTitle(object):
|
|
|
+class ArticleTitleStatusManager(object):
|
|
|
"""
|
|
|
文章退场表格维护
|
|
|
"""
|
|
@@ -68,7 +67,7 @@ class ArticleExitWithTitle(object):
|
|
|
)
|
|
|
return True
|
|
|
|
|
|
- def bad_article_manager(self, read_times_on_avg_threshold, discovery_times_threshold) -> list[str]:
|
|
|
+ def get_bad_articles(self, read_times_on_avg_threshold, discovery_times_threshold) -> list[str]:
|
|
|
"""
|
|
|
找出质量很差的文章标题,将该标题设置为退场状态
|
|
|
:return:
|
|
@@ -85,7 +84,7 @@ class ArticleExitWithTitle(object):
|
|
|
articles = self.lam_client.select(sql)
|
|
|
return [i[0] for i in articles]
|
|
|
|
|
|
- def record_title_list(self, title_list, status) -> int:
|
|
|
+ def save_titles(self, title_list, status) -> int:
|
|
|
"""
|
|
|
修改标题状态
|
|
|
:param status:
|
|
@@ -122,7 +121,7 @@ class ArticleExitWithTitle(object):
|
|
|
error_msg = traceback.format_exc()
|
|
|
log(
|
|
|
task="article_exit_with_title",
|
|
|
- function="record_title_list",
|
|
|
+ function="save_titles",
|
|
|
status="fail",
|
|
|
data={
|
|
|
"e": str(e),
|
|
@@ -151,32 +150,35 @@ def main():
|
|
|
READ_TIMES_ON_AVG_THRESHOLD = 0.5
|
|
|
DISCOVERY_TIMES_THRESHOLD = 10
|
|
|
|
|
|
- article_title_manager = ArticleExitWithTitle()
|
|
|
+ article_title_manager = ArticleTitleStatusManager()
|
|
|
article_title_manager.init_database()
|
|
|
|
|
|
# 处理晋级标题
|
|
|
up_level_title = get_level_up_articles()
|
|
|
- up_level_success_count = article_title_manager.record_title_list(title_list=up_level_title, status=UP_LEVEL_STATUS)
|
|
|
- # up_level_success_count = 0
|
|
|
+ up_level_success_count = article_title_manager.save_titles(
|
|
|
+ title_list=up_level_title,
|
|
|
+ status=UP_LEVEL_STATUS
|
|
|
+ )
|
|
|
|
|
|
# 处理退场标题
|
|
|
- exit_article_list = article_title_manager.bad_article_manager(
|
|
|
+ exit_article_list = article_title_manager.get_bad_articles(
|
|
|
read_times_on_avg_threshold=READ_TIMES_ON_AVG_THRESHOLD,
|
|
|
discovery_times_threshold=DISCOVERY_TIMES_THRESHOLD
|
|
|
)
|
|
|
- exit_success_count = article_title_manager.record_title_list(title_list=exit_article_list, status=ARTICLE_EXIT_STATUS)
|
|
|
-
|
|
|
- if exit_success_count >= 0 and up_level_success_count >= 0:
|
|
|
- bot(
|
|
|
- title="冷启动文章晋级, 退场完成",
|
|
|
- detail={
|
|
|
- "已经晋级文章数量": up_level_success_count,
|
|
|
- "已经退场文章数控": exit_success_count,
|
|
|
- "阅读均值倍数阈值": READ_TIMES_ON_AVG_THRESHOLD,
|
|
|
- "探索次数阈值": DISCOVERY_TIMES_THRESHOLD
|
|
|
- },
|
|
|
- mention=False
|
|
|
- )
|
|
|
+ exit_success_count = article_title_manager.save_titles(
|
|
|
+ title_list=exit_article_list,
|
|
|
+ status=ARTICLE_EXIT_STATUS)
|
|
|
+
|
|
|
+ bot(
|
|
|
+ title="冷启动文章晋级/退场完成",
|
|
|
+ detail={
|
|
|
+ "晋级文章数量": up_level_success_count,
|
|
|
+ "退场文章数量": exit_success_count,
|
|
|
+ "阅读均值倍数阈值": READ_TIMES_ON_AVG_THRESHOLD,
|
|
|
+ "探索次数阈值": DISCOVERY_TIMES_THRESHOLD
|
|
|
+ },
|
|
|
+ mention=False
|
|
|
+ )
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|