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
242
243
244
245
246
247
248
249
250
251
252
253
254
255
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import json
from pyspark.streaming.kafka import KafkaUtils
from pyspark import SparkContext
from pyspark.sql import SQLContext
from pyspark.streaming import StreamingContext
from pyspark import SparkConf
import redis
import sys
import os
import json
import pymysql
import numpy as np
import pandas as pd
import time
import datetime
def Json(x):
data = json.loads(x[1])
if 'type' in data and 'device' in data and 'params' in data and 'card_content_type' in data['params']:
if data['type'] == 'on_click_card' and data["device"]["device_id"] == "E417C286-40A4-42F6-BDA9-AEEBD8FEC3B6":
return True
else:
return False
else:
return False
def model(rdd):
try:
rdd = rdd.filter(lambda x:Json(x)).repartition(10).map(lambda x:get_data(x))\
.map(lambda x:write_redis(x[0],x[1],x[2]))
return rdd
except:
print("fail")
def get_data(x):
try:
data = json.loads(x[1])
device_id = data['device']['device_id']
diary_id = data['params']["card_id"]
card = data['params']['card_content_type']
return device_id,diary_id,card
except Exception as e:
print("get_data fail")
# send_email("get_data", "get_data", e)
def write_redis(device_id,cid,card):
if card == "diary":
diary_write(device_id, cid)
elif card == "qa":
question_write(device_id, cid)
elif card == "user_post":
tractate_write(device_id, cid)
def tractate_write(device_id, cid):
try:
db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='eagle')
sql = "select b.id from src_mimas_prod_api_tractate_tag a left join src_zhengxing_api_tag b " \
"on a.tag_id = b.id where b.tag_type = '3' and a.tractate_id = {}".format(cid)
cursor = db.cursor()
cursor.execute(sql)
result = cursor.fetchall()
if len(result) > 0:
tags = result[0][0]
if tags is not None:
sql = "select a.id from src_mimas_prod_api_tractate a left join src_mimas_prod_api_tractate_tag b " \
"on a.id=b.tractate_id left join src_zhengxing_api_tag c on b.tag_id=c.id " \
"where a.is_online = 1 and c.id = {} and c.tag_type = '3'".format(tags)
cursor.execute(sql)
result = cursor.fetchall()
db.close()
if len(result) > 0:
cids = [str(i[0]) for i in result]
r = redis.Redis(host="172.16.40.135", port=5379, password="",db = 2)
key = str(device_id) + "_dislike_tractate"
if r.exists(key):
value = json.loads(r.get(key).decode('utf-8'))
value.extend(cids)
cids = json.dumps(list(set(value)))
r.set(key, cids)
print("cunza")
else:
r.set(key, json.dumps(cids))
r.expire(key, 7 * 24 * 60 * 60)
except Exception as e:
print("tractate insert redis fail")
print(e)
def question_write(device_id,cid):
try:
db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='eagle')
sql = "select b.id from src_mimas_prod_api_questiontag a left join src_zhengxing_api_tag b " \
"on a.tag_id = b.id where b.tag_type = '3' and a.question_id = {}".format(cid)
cursor = db.cursor()
cursor.execute(sql)
result = cursor.fetchall()
if len(result) > 0:
tags = result[0][0]
if tags is not None:
sql = "select a.id from src_mimas_prod_api_question a left join src_mimas_prod_api_questiontag b " \
"on a.id=b.question_id left join src_zhengxing_api_tag c on b.tag_id=c.id " \
"where a.is_online = 1 and c.tag_type = '3' and c.id = {}".format(tags)
cursor.execute(sql)
result = cursor.fetchall()
db.close()
if len(result) > 0:
cids = [str(i[0]) for i in result]
r = redis.Redis(host="172.16.40.135", port=5379, password="", db=2)
key = str(device_id) + "_dislike_qa"
if r.exists(key):
value = json.loads(r.get(key).decode('utf-8'))
value.extend(cids)
cids = json.dumps(list(set(value)))
r.set(key, cids)
print("cunza")
else:
r.set(key, json.dumps(cids))
r.expire(key, 7 * 24 * 60 * 60)
print("bucunza")
return "question good"
except Exception as e:
print("question insert redis fail")
print(e)
def diary_write(device_id,cid):
try:
db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='eagle')
sql = "select b.id from src_mimas_prod_api_diary_tags a left join src_zhengxing_api_tag b " \
"on a.tag_id = b.id where b.tag_type = '3' and a.diary_id = {}".format(cid)
cursor = db.cursor()
cursor.execute(sql)
result = cursor.fetchall()
if len(result) > 0:
tags = result[0][0]
if tags is not None:
sql = "select a.id from src_mimas_prod_api_diary a left join src_mimas_prod_api_diary_tags b " \
"on a.id=b.diary_id left join src_zhengxing_api_tag c on b.tag_id=c.id " \
"where a.is_online = 1 and a.content_level >= '3' " \
"and c.id = {} and c.tag_type = '3'".format(tags)
cursor.execute(sql)
result = cursor.fetchall()
db.close()
if len(result) > 0:
cids = [str(i[0]) for i in result]
r = redis.Redis(host="172.16.40.135", port=5379, password="", db=2)
key = str(device_id) + "_dislike_diary"
if r.exists(key):
value = json.loads(r.get(key).decode('utf-8'))
value.extend(cids)
cids = json.dumps(list(set(value)))
r.set(key, cids)
else:
r.set(key, json.dumps(cids))
r.expire(key, 7 * 24 * 60 * 60)
except Exception as e:
print("diary insert redis fail")
print(e)
# sc = SparkContext(conf=SparkConf().setMaster("spark://nvwa01:7077").setAppName("dislike").set("spark.io.compression.codec", "lzf"))
# ssc = StreamingContext(sc,4)
# sc.setLogLevel("WARN")
# kafkaParams = {"metadata.broker.list": "172.16.44.25:9092,172.16.44.31:9092,172.16.44.45:9092",
# "group.id": "dislike",
# "socket.timeout.ms": "600000",
# "auto.offset.reset": "largest"}
#
#
# stream = KafkaUtils.createDirectStream(ssc, ["gm-maidian-data"], kafkaParams)
# transformstream = stream.transform(lambda x:model(x))
# transformstream.pprint()
#
# ssc.start()
# ssc.awaitTermination()
def make_data():
r = redis.StrictRedis.from_url("redis://redis.paas-test.env:6379/2")
device_id = "868240031404281"
city_id = "beijing"
key_head = "device_diary_queue_rerank:device_id:"
# key_head = "device_diary_queue:device_id:"
key = key_head + device_id + ":city_id:" + city_id
native = ",".join([str(i) for i in (range(100, 130))])
nearby = ",".join([str(i) for i in (range(130, 150))])
nation = ",".join([str(i) for i in (range(150, 180))])
megacity = ",".join([str(i) for i in (range(180, 200))])
r.hset(name=key, key="native_queue", value=native)
r.hset(name=key, key="nearby_queue", value=nearby)
r.hset(name=key, key="nation_queue", value=nation)
r.hset(name=key, key="megacity_queue", value=megacity)
print(r.hgetall(key))
# key_head = "device_diary_queue_rerank:device_id:"
# make_data(device_id, "beijing", key_head)
# device_id = "868663038800476"
def topic():
device_id = "78687687"
dislike_key = str(device_id) + "_dislike_tractate"
r = redis.StrictRedis.from_url("redis://redis.paas-test.env:6379/2")
r.sadd(dislike_key, *[1,2])
print(r.smembers(dislike_key))
search = "TS:search_recommend_tractate_queue:device_id:" + str(device_id)
a = [1]
a.extend(list(range(36, 50)))
r.hset(search, 'tractate_queue',json.dumps(a))
print(r.hgetall(search))
if __name__ == "__main__":
make_data()