1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
import redis
import json
from es_tool import es_query
from tool import get_data_by_mysql
def get_all_city_id():
sql = "select distinct tag_id from api_city"
mysql_results = get_data_by_mysql('172.16.30.141', 3306, 'work', 'BJQaT9VzDcuPBqkd', 'zhengxing', sql)
city_tag_ids = [i["tag_id"] for i in mysql_results]
city_tag_ids.append(-1) # 没有城市的情况
return city_tag_ids
def search_diary_by_match_phrase(tag_names, city_tag_id, version):
q = dict()
if city_tag_id == -1:
sort_list = []
else:
sort_list = [
{'_script': {
'lang': 'groovy',
'script_file': 'sort_diary-recommend',
'type': 'number',
'params': {
'user_city_tag_id': city_tag_id,
},
'order': 'desc',
'_cache': True,
}}
]
if version:
sort_list += [
{'has_video_cover': {'order': 'asc'}},
{'offline_score_v1': {'order': 'desc'}},
{"good_click": {"order": "desc"}},
{'last_update_time': {'order': 'desc'}}
]
else:
sort_list += [
{'has_video_cover': {'order': 'asc'}},
{'offline_score': {'order': 'desc'}},
{"good_click": {"order": "desc"}},
{'last_update_time': {'order': 'desc'}}
]
total_query_should_list = []
for tag_name in tag_names:
term_dict = {
"match_phrase": {
"tags": {
"query": tag_name
}
}
}
total_query_should_list.append(term_dict)
q['query'] = {"bool": {
"filter": [{"term": {"is_online": True}},
{"term": {"has_cover": True}}, {"term": {"is_sink": False}},
{"term": {"has_after_cover": True}}, {"term": {"has_before_cover": True}},
{"terms": {"content_level": [5, 4, 3.5, 3]}}],
"should": total_query_should_list,
"minimum_should_match": 1}}
q['query']['bool']['must_not'] = [{"term": {"is_operate": True}}]
q['sort'] = sort_list
q["_source"] = {"includes": ["id"]}
es_res = es_query("diary", q, offset=0, size=200)
diary_ids = []
for diary_info in es_res['hits']['hits']:
diary_ids.append(diary_info['_source']['id'])
return diary_ids
def search_topic_by_match_phrase(tag_names, version=0):
q = dict()
total_query_should_list = list()
for tag_name in tag_names:
term_dict = {
"match_phrase": {
"fresh_tractate_tag_name": {
"query": tag_name
}
}
}
term_dict2 = {
"match_phrase": {
"tractate_tag_name_content": {
"query": tag_name,
'analyzer': 'gm_default_index'
}
}
}
total_query_should_list.extend([term_dict, term_dict2])
q['query'] = {"bool": {
"filter": [{"term": {"is_online": True}}, {"terms": {"content_level": [5, 4, 3.5, 3]}}],
"should": total_query_should_list,
"minimum_should_match": 1}}
q["_source"] = {
"includes": ["id"]
}
if version:
q["sort"] = [
{"is_video": {"order": "asc"}},
{"good_click_tractate_score": {"order": "desc"}},
{"good_click": {"order": "desc"}}
]
else:
q["sort"] = [
{"is_video": {"order": "asc"}},
{"tractate_score": {"order": "desc"}},
{"good_click": {"order": "desc"}}
]
es_res = es_query("tractate", q, offset=0, size=200)
topic_list = []
for topic_info in es_res['hits']['hits']:
topic_list.append(topic_info['_source']['id'])
return topic_list
def search_qa_by_match_phrase(tag_names, version=0):
if version:
sort_list = [
{'has_picture': {'order': 'desc'}},
{'smart_rank_v3': {'order': 'desc'}},
{"good_click": {"order": "desc"}}
]
else:
sort_list = [
{'has_picture': {'order': 'desc'}},
{'smart_rank_v2': {'order': 'desc'}},
{"good_click": {"order": "desc"}}
]
q = dict()
total_query_should_list = []
for tag_name in tag_names:
term_dict = {
"match_phrase": {
"tag_name": {
"query": tag_name
}
}
}
total_query_should_list.append(term_dict)
q['query'] = {"bool": {
"filter": [{"range": {"content_length": {"gte": 30}}},
{"term": {"is_online": True}},
{"terms": {"content_level": ['5', '4', '3.5', '3']}}],
"should": total_query_should_list,
"minimum_should_match": 1}}
q["_source"] = {
"includes": ["id"]
}
q['sort'] = sort_list
es_res = es_query("answer", q, offset=0, size=200)
qa_list = []
for qa_info in es_res['hits']['hits']:
qa_list.append(qa_info['_source']['id'])
return qa_list
if __name__ == "__main__":
# 获取所有的城市tag id
all_city_tag_id = get_all_city_id()
# 清空历史数据
redis_client = redis.StrictRedis.from_url('redis://:ReDis!GmTx*0aN9@172.16.40.173:6379')
# hot_search_word_topic_queue_key = "coldstart:hot:search:word:topic:queue"
# hot_search_word_qa_queue_key = "coldstart:hot:search:word:qa:queue"
# hot_search_word_diary_queue_key = "coldstart:hot:search:word:diary:queue"
light_clinic_beauty_topic_queue_key = "coldstart:light:clinic:beauty:topic:queue"
light_clinic_beauty_topic_queue_grey_key = "coldstart:light:clinic:beauty:topic:queue:grey"
light_clinic_beauty_qa_queue_key = "coldstart:light:clinic:beauty:qa:queue"
light_clinic_beauty_qa_queue_grey_key = "coldstart:light:clinic:beauty:qa:queue:grey"
light_clinic_beauty_diary_queue_key = "coldstart:light:clinic:beauty:diary:queue"
light_clinic_beauty_diary_queue_grey_key = "coldstart:light:clinic:beauty:diary:queue:grey"
card_types = ['topic', 'qa'] # 日记有400多个城市，且是hmset，因此不用重置
# word_refers = ['coldstart:hot:search:word', 'coldstart:light:clinic:beauty']
word_refers = ['coldstart:light:clinic:beauty']
for card_type in card_types:
for word_refer in word_refers:
key = word_refer + ':' + card_type + ':' + 'queue'
redis_client.delete(key)
key = word_refer + ':' + card_type + ':' + 'queue:grey'
redis_client.delete(key)
# # 热搜词的候选队列
# hot_search_word_key = "user:service_coldstart_tags2_name"
# hot_search_word = redis_client.hgetall(hot_search_word_key)
# hot_search_word = [str(tag, 'utf-8') for tag in hot_search_word]
# hot_search_word_diary_queue = dict()
#
# # 队列存储
# hot_search_word_topic_queue = search_topic_by_match_phrase(hot_search_word)
# redis_client.rpush(hot_search_word_topic_queue_key, *hot_search_word_topic_queue)
# # redis_client.lrange(hot_search_word_topic_queue_key, 0, 3)
# print("热搜词更新的帖子队列长度：%s" % str(len(hot_search_word_topic_queue)))
#
# hot_search_word_qa_queue = search_qa_by_match_phrase(hot_search_word)
# redis_client.rpush(hot_search_word_qa_queue_key, *hot_search_word_qa_queue)
# print("热搜词更新的问答队列长度：%s" % str(len(hot_search_word_qa_queue)))
# # redis_client.lrange(hot_search_word_qa_queue_key, 0, 3)
#
# for city_tag_id in all_city_tag_id:
# diary_queue = search_diary_by_match_phrase(hot_search_word, city_tag_id)
# hot_search_word_diary_queue.update({city_tag_id: json.dumps(diary_queue)})
# redis_client.hmset(hot_search_word_diary_queue_key, hot_search_word_diary_queue)
# print("热搜词更新的日记队列长度：%s" % str(len(diary_queue)))
# 轻医美的候选队列
light_clinic_beauty_key = "user:service_coldstart_tags3"
light_clinic_beauty = redis_client.hgetall(light_clinic_beauty_key)
light_clinic_beauty = [str(tag, 'utf-8') for tag in light_clinic_beauty]
light_clinic_beauty_diary_queue = dict()
# 队列存储
light_clinic_beauty_topic_queue = search_topic_by_match_phrase(light_clinic_beauty)
light_clinic_beauty_topic_grey_queue = search_topic_by_match_phrase(light_clinic_beauty, version=1)
redis_client.rpush(light_clinic_beauty_topic_queue_key, *light_clinic_beauty_topic_queue)
redis_client.rpush(light_clinic_beauty_topic_queue_grey_key, *light_clinic_beauty_topic_grey_queue)
print("轻医美词更新的帖子队列长度：%s" % str(len(light_clinic_beauty_topic_queue)))
print("轻医美词更新的灰度帖子队列长度：%s" % str(len(light_clinic_beauty_topic_grey_queue)))
light_clinic_beauty_qa_queue = search_qa_by_match_phrase(light_clinic_beauty)
light_clinic_beauty_qa_grey_queue = search_qa_by_match_phrase(light_clinic_beauty, version=1)
redis_client.rpush(light_clinic_beauty_qa_queue_key, *light_clinic_beauty_qa_queue)
redis_client.rpush(light_clinic_beauty_qa_queue_grey_key, *light_clinic_beauty_qa_grey_queue)
print("轻医美词更新的问答队列长度：%s" % str(len(light_clinic_beauty_qa_queue)))
print("轻医美词更新的灰度问答队列长度：%s" % str(len(light_clinic_beauty_qa_grey_queue)))
for city_tag_id in all_city_tag_id:
diary_queue = search_diary_by_match_phrase(light_clinic_beauty, city_tag_id, version=0)
light_clinic_beauty_diary_queue.update({city_tag_id: json.dumps(diary_queue)})
redis_client.hmset(light_clinic_beauty_diary_queue_key, light_clinic_beauty_diary_queue)
print("轻医美词更新的日记队列长度：%s" % str(len(diary_queue)))
light_clinic_beauty_diary_queue = dict()
for city_tag_id in all_city_tag_id:
diary_queue = search_diary_by_match_phrase(light_clinic_beauty, city_tag_id, version=1)
light_clinic_beauty_diary_queue.update({city_tag_id: json.dumps(diary_queue)})
redis_client.hmset(light_clinic_beauty_diary_queue_grey_key, light_clinic_beauty_diary_queue)
print("轻医美词更新的灰度日记队列长度：%s" % str(len(diary_queue)))