You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
108 lines
4.5 KiB
108 lines
4.5 KiB
#coding:utf8
|
|
import os, sys
|
|
import io
|
|
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf8')
|
|
cur_dir = os.path.dirname(os.path.abspath(__file__)) or os.getcwd()
|
|
par_dir = os.path.abspath(os.path.join(cur_dir, os.path.pardir))
|
|
sys.path.append(cur_dir)
|
|
sys.path.append(par_dir)
|
|
import json
|
|
from django.http import HttpResponse
|
|
from text_analysis.tools import to_kafka,tool
|
|
from text_analysis.tools import pred
|
|
from django.views.decorators.csrf import csrf_exempt
|
|
from log_util.set_logger import set_logger
|
|
logging=set_logger('logs/results.log')
|
|
import traceback
|
|
import queue
|
|
from text_analysis.cusException import userFile_Exception,chainFile_Exception
|
|
import requests
|
|
import time
|
|
from datetime import datetime
|
|
import os
|
|
import joblib
|
|
#任务队列
|
|
global task_queue
|
|
task_queue = queue.Queue()
|
|
|
|
|
|
@csrf_exempt
|
|
def fakeNewIdentification(request):
|
|
if request.method == 'POST':
|
|
try:
|
|
raw_data = json.loads(request.body)
|
|
task_queue.put(raw_data)
|
|
return HttpResponse(json.dumps({"code": 1, "msg": "请求正常！"}, ensure_ascii=False))
|
|
except:
|
|
logging.error(traceback.format_exc())
|
|
return HttpResponse(json.dumps({"code": 0, "msg": "请求json格式不正确！"}, ensure_ascii=False))
|
|
else:
|
|
return HttpResponse(json.dumps({"code": 0, "msg": "请求方式错误，改为post请求"}, ensure_ascii=False))
|
|
|
|
def predict_news(dbConfig):
|
|
while True:
|
|
if task_queue.qsize() > 0:
|
|
try:
|
|
logging.info("取任务队列长度{}".format(task_queue.qsize()))
|
|
raw_data = task_queue.get()
|
|
logging.info("原始数据-{}".format(raw_data))
|
|
res = {"successCode": "1", "errorLog": "", "results": {}}
|
|
# 账号数据
|
|
userData = tool.mysqlData(raw_data, logging,"1",dbConfig)
|
|
# if not userData:
|
|
# raise userFile_Exception
|
|
logging.info("账号数据获取完毕!-长度{}".format(len(userData)))
|
|
# 传播链数据
|
|
postChain=tool.mysqlData(raw_data, logging,"0",dbConfig)
|
|
if not postChain:
|
|
raise chainFile_Exception
|
|
logging.info("传播链数据获取完毕!-长度{}".format(len(postChain)))
|
|
news=pred.predict_news(userData,postChain,logging)
|
|
# 结束标识
|
|
res['isLast'] = True
|
|
for i in range(len(news)):
|
|
row_dict = news.iloc[i].to_dict()
|
|
row_dict['pageType'] = 'fakeNewsPage'
|
|
# postId
|
|
row_dict['postId'] = userData[0]['postId']
|
|
res["results"] = json.dumps(row_dict,ensure_ascii=False)
|
|
raw_data["result"] = res
|
|
logging.info("共{}条数据，第{}条数据输出-{}".format(len(news),i+1,raw_data))
|
|
to_kafka.send_kafka(raw_data, logging)
|
|
except userFile_Exception:
|
|
res = {"successCode": "0", "errorLog": "用户数据为空！", "results": {}}
|
|
results={}
|
|
results['pageType'] = 'fakeNewsPage'
|
|
results['recognitionResult'] = '用户数据为空'
|
|
|
|
res['results'] = json.dumps(results)
|
|
raw_data["result"] = res
|
|
logging.info("该条请求用户数据为空-{}".format(raw_data))
|
|
to_kafka.send_kafka(raw_data, logging)
|
|
except chainFile_Exception:
|
|
res = {"successCode": "0", "errorLog": "关系链数据为空！", "results": {}}
|
|
results={}
|
|
results['pageType'] = 'fakeNewsPage'
|
|
results['recognitionResult'] = '关系链数据为空'
|
|
res['results'] = json.dumps(results)
|
|
raw_data["result"] = res
|
|
logging.info("该条请求关系链数据为空-{}".format(raw_data))
|
|
to_kafka.send_kafka(raw_data, logging)
|
|
except:
|
|
res = {"successCode": "0", "errorLog": "", "results": {}}
|
|
results={}
|
|
results['pageType'] = 'fakeNewsPage'
|
|
results['recognitionResult'] = ""
|
|
res['results'] = json.dumps(results)
|
|
raw_data["result"] = res
|
|
raw_data["result"]["error"] = traceback.format_exc()
|
|
logging.info(traceback.format_exc())
|
|
to_kafka.send_kafka(raw_data, logging)
|
|
else:
|
|
# 暂无任务，进入休眠
|
|
time.sleep(10)
|
|
|
|
|
|
|
|
|
|
|