|
@@ -277,7 +277,8 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank
|
|
|
# log_.info('filtered_videos count = {}'.format(len(filtered_videos)))
|
|
|
|
|
|
# 屏蔽视频过滤
|
|
|
- shield_key_name_list = config_.SHIELD_CONFIG.get(region, None)
|
|
|
+ shield_config = param.get('shield_config', config_.SHIELD_CONFIG)
|
|
|
+ shield_key_name_list = shield_config.get(region, None)
|
|
|
if shield_key_name_list is not None:
|
|
|
filtered_videos = filter_shield_video(video_ids=filtered_videos, shield_key_name_list=shield_key_name_list)
|
|
|
# log_.info(f"shield filtered_videos count = {len(filtered_videos)}")
|
|
@@ -323,16 +324,17 @@ def video_rank(df, now_date, now_h, rule_key, param, region, data_key, rule_rank
|
|
|
# 与其他召回视频池去重,存入对应的redis
|
|
|
dup_to_redis(h_video_ids=h_video_ids, now_date=now_date, now_h=now_h, rule_key=rule_key,
|
|
|
region_24h_rule_key=region_24h_rule_key, by_24h_rule_key=by_24h_rule_key, by_48h_rule_key=by_48h_rule_key,
|
|
|
- region=region, data_key=data_key, rule_rank_h_flag=rule_rank_h_flag, political_filter=political_filter)
|
|
|
+ region=region, data_key=data_key, rule_rank_h_flag=rule_rank_h_flag, political_filter=political_filter,
|
|
|
+ shield_config=shield_config)
|
|
|
|
|
|
|
|
|
-def dup_data(h_video_ids, initial_key_name, dup_key_name, region, political_filter):
|
|
|
+def dup_data(h_video_ids, initial_key_name, dup_key_name, region, political_filter, shield_config):
|
|
|
redis_helper = RedisHelper()
|
|
|
if redis_helper.key_exists(key_name=initial_key_name):
|
|
|
initial_data = redis_helper.get_all_data_from_zset(key_name=initial_key_name, with_scores=True)
|
|
|
# 屏蔽视频过滤
|
|
|
initial_video_ids = [int(video_id) for video_id, _ in initial_data]
|
|
|
- shield_key_name_list = config_.SHIELD_CONFIG.get(region, None)
|
|
|
+ shield_key_name_list = shield_config.get(region, None)
|
|
|
if shield_key_name_list is not None:
|
|
|
initial_video_ids = filter_shield_video(video_ids=initial_video_ids,
|
|
|
shield_key_name_list=shield_key_name_list)
|
|
@@ -354,7 +356,7 @@ def dup_data(h_video_ids, initial_key_name, dup_key_name, region, political_filt
|
|
|
|
|
|
|
|
|
def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by_24h_rule_key, by_48h_rule_key,
|
|
|
- region, data_key, rule_rank_h_flag, political_filter):
|
|
|
+ region, data_key, rule_rank_h_flag, political_filter, shield_config):
|
|
|
"""将地域分组小时级数据与其他召回视频池去重,存入对应的redis"""
|
|
|
# ##### 去重更新地域分组小时级24h列表,并另存为redis中
|
|
|
region_24h_key_name = \
|
|
@@ -364,7 +366,8 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{config_.RECALL_KEY_NAME_PREFIX_DUP1_REGION_24H_H}{region}:{data_key}:{rule_key}:" \
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=region_24h_key_name,
|
|
|
- dup_key_name=region_24h_dup_key_name, region=region, political_filter=political_filter)
|
|
|
+ dup_key_name=region_24h_dup_key_name, region=region, political_filter=political_filter,
|
|
|
+ shield_config=shield_config)
|
|
|
|
|
|
if rule_rank_h_flag == '48h':
|
|
|
|
|
@@ -375,7 +378,8 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{config_.RECALL_KEY_NAME_PREFIX_DUP2_REGION_48H_H}{region}:{data_key}:{rule_key}:" \
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=h_48h_key_name,
|
|
|
- dup_key_name=h_48h_dup_key_name, region=region, political_filter=political_filter)
|
|
|
+ dup_key_name=h_48h_dup_key_name, region=region, political_filter=political_filter,
|
|
|
+ shield_config=shield_config)
|
|
|
|
|
|
# ##### 去重小程序相对48h 筛选后剩余数据 更新结果,并另存为redis中
|
|
|
if by_48h_rule_key == 'rule1':
|
|
@@ -386,7 +390,7 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=other_h_48h_key_name,
|
|
|
dup_key_name=other_h_48h_dup_key_name, region=region,
|
|
|
- political_filter=political_filter)
|
|
|
+ political_filter=political_filter, shield_config=shield_config)
|
|
|
|
|
|
else:
|
|
|
# ##### 去重小程序相对24h更新结果,并另存为redis中
|
|
@@ -396,7 +400,8 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{config_.RECALL_KEY_NAME_PREFIX_DUP2_REGION_24H_H}{region}:{data_key}:{rule_key}:" \
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=h_24h_key_name,
|
|
|
- dup_key_name=h_24h_dup_key_name, region=region, political_filter=political_filter)
|
|
|
+ dup_key_name=h_24h_dup_key_name, region=region, political_filter=political_filter,
|
|
|
+ shield_config=shield_config)
|
|
|
|
|
|
# ##### 去重小程序相对24h 筛选后剩余数据 更新结果,并另存为redis中
|
|
|
# if by_24h_rule_key in ['rule3', 'rule4']:
|
|
@@ -406,7 +411,8 @@ def dup_to_redis(h_video_ids, now_date, now_h, rule_key, region_24h_rule_key, by
|
|
|
f"{config_.RECALL_KEY_NAME_PREFIX_DUP3_REGION_24H_H}{region}:{data_key}:{rule_key}:" \
|
|
|
f"{datetime.datetime.strftime(now_date, '%Y%m%d')}:{now_h}"
|
|
|
h_video_ids = dup_data(h_video_ids=h_video_ids, initial_key_name=other_h_24h_key_name,
|
|
|
- dup_key_name=other_h_24h_dup_key_name, region=region, political_filter=political_filter)
|
|
|
+ dup_key_name=other_h_24h_dup_key_name, region=region, political_filter=political_filter,
|
|
|
+ shield_config=shield_config)
|
|
|
|
|
|
# ##### 去重小程序模型更新结果,并另存为redis中
|
|
|
# model_key_name = get_rov_redis_key(now_date=now_date)
|