asrNew/text_analysis/views.py_20240819

# coding:utf8
import os, sys
import io
from jsonpath_ng import jsonpath, parse
import uuid
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
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
import requests
from text_analysis.tools.tool import parse_data
import time
from datetime import datetime
import os
from kazoo.client import KazooClient
from kazoo.protocol.states import EventType
# 任务队列
# global task_queue
task_queue = queue.Queue()
# 数据队列
# global data_queue
data_queue = queue.Queue()
stop_dict={}

@csrf_exempt
def ASRNew(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 upload():
    while True:
        try:
            if task_queue.qsize() > 0:
                logging.info("取任务队列长度{}".format(task_queue.qsize()))
                raw_data = task_queue.get()
                output=raw_data["output"]
                res_tmp={key: "" for key in output}
                if "id" in res_tmp.keys():
                    res_tmp["id"]=str(uuid.uuid4())
                logging.info("任务数据为：{}".format(raw_data))
                logging.info("当前version信息为：{}".format(stop_dict))
                task_id=raw_data["scenes_id"]
                task_version=raw_data["version"]
                if task_id in stop_dict.keys() and task_version!=stop_dict[task_id]["version"]:
                    logging.info("已暂停任务上传，过滤掉。{}".format(raw_data))
                    continue

                url=raw_data["input"]["fileUrl"]
                if "json" in url:
                    parm = url.split("#")
                    data1 = parse_data(raw_data, parm[0])
                    data1_json = json.loads(data1)
                    expr = parse(parm[2])
                    match = [match.value for match in expr.find(data1_json)]
                    video_url = match[0]
                else:
                    video_url = parse_data(raw_data, url)
                fileName=video_url.rsplit('/')[-1]
                if "http" not in video_url:
                    file = "https://caiji.percent.cn/" + video_url.lstrip("/")
                else:
                    file=video_url
                # name=raw_data["metadata"]["admin"]["fileName"]
                # if '$.' in name:
                #     # json.path表达式动态获取value
                #     datasources = str(name).split(':')
                #     # 0是数据源，1是JsonPath 表达式
                #     datasourcestr = raw_data["data"][datasources[0]]
                #     datasource = json.loads(datasourcestr)
                #     # 创建 JsonPath 表达式对象
                #     expr = parse(datasources[1])
                #     # 使用表达式来选择 JSON 元素
                #     match = [match.value for match in expr.find(datasource)]
                #     fileName = match[0]

                currentFile={"fileName":fileName,"fileUrl":file}
                language = raw_data["input"]["fromLanguage"]
                # 从gofast获取视频
                myfile = requests.get(file)
                starttime = datetime.now().strftime('%Y-%m-%d')
                path = 'inputdata/' + starttime
                if not os.path.exists(path):
                    os.makedirs(path)
                with open(path + '/' + fileName, 'wb') as f:
                    f.write(myfile.content)
                logging.info("视频从gofast下载完毕，开始上传-{}".format(fileName))
                # 访问视频上传接口
                # video=1视频，0音频。
                video=1
                if fileName[-3:]=="m4a" or fileName[-3:]=="mp3" or fileName[-3:]=="wav":
                    url="https://realtime.pdeepmatrix.com/apis/file/asr/upload"
                    video=0
                else:
                    url = "https://realtime.pdeepmatrix.com/apis/media/analysis/upload"
                data = {'fromLanguage': language}
                f = open(path + '/' + fileName, 'rb')
                files = {'file': f}
                response = requests.post(url, data=data, files=files,verify=False)
                logging.info("上传后接口返回值：{}-{}".format(response,response.text))
                d = json.loads(response.text)
                if "code" in d.keys() and d["code"] == 200:
                    # 接口返回值data中存放视频获取结果的key
                    result = d["data"]
                    raw_data["result"] = {"successCode": "1", "errorLog": "", "results": "", "dataKey": result,"video":video,"file":currentFile}
                    data_queue.put(raw_data)
                    logging.info("视频上传成功{}".format(raw_data))
                    # to_kafka.send_kafka(raw_data,logging)
                else:
                    logging.info("视频上传失败{}-{}".format(raw_data, d))
                f.close()
                # Todo删除视频文件
            else:
                # 暂无任务，进入休眠
                time.sleep(10)
        except:
            raw_data["result"]={}
            raw_data["result"]["successCode"] = "0"
            raw_data["result"]["status"]=2
            raw_data["result"]["message"]="视频/音频上传异常"
            raw_data["result"]["errorLog"] = traceback.format_exc()
            raw_data["result"]["results"] = json.dumps(res_tmp, ensure_ascii=False)
            logging.error(traceback.format_exc())
            to_kafka.send_kafka(raw_data, logging)


def getResult():
    while True:
        # 3秒钟结果获取一次
        time.sleep(3)
        try:
            if data_queue.qsize() > 0:
                logging.info("取数据队列长度{}".format(data_queue.qsize()))
                raw_data = data_queue.get()
                logging.info("任务数据为：{}".format(raw_data))
                task_id=raw_data["scenes_id"]
                task_version=raw_data["version"]
                if task_id in stop_dict.keys() and task_version!=stop_dict[task_id]["version"]:
                    logging.info("已暂停获取结果任务，过滤掉。{}".format(raw_data))
                    continue
                output=raw_data["output"]
                res_tmp={key: "" for key in output}
                if "id" in res_tmp.keys():
                    res_tmp["id"]=str(uuid.uuid4())
                res_tmp["isLast"]=1
                res_tmp["fileName"]=raw_data["result"]["file"]["fileName"]
                # 根据视频key访问获取结果接口
                dataKey = raw_data["result"]["dataKey"]
                params = {'taskId': dataKey}
                language = raw_data["input"]["fromLanguage"]
                data = {'fromLanguage': language,'taskId': dataKey}
                if raw_data["result"]["video"]==1:
                    url = "https://realtime.pdeepmatrix.com/apis/media/analysis/getResult"
                    response = requests.get(url, params=params, verify=False)
                else:
                    url ="https://realtime.pdeepmatrix.com/apis/file/asr/getResult"
                    response = requests.post(url, data=data, verify=False)
                logging.info("ASR网站返回值：{}-{}".format(response,response.text))
                d = json.loads(response.text)
                if "code" in d.keys() and d["code"] == 200:
                    results = ""
                    if d["data"]["code"] == "1" and d["data"]["sentences"]:
                        for sentence in d["data"]["sentences"]:
                            if results:
                                results += ' ' + sentence["text"]
                            else:
                                results = sentence["text"]
                        if "content" in res_tmp.keys():
                            res_tmp["content"]=results
                        raw_data["result"]["results"] = json.dumps(res_tmp, ensure_ascii=False)
                        raw_data["result"]["status"]=1
                        raw_data["result"]["message"]="成功"
                        logging.info("视频解析获取结果成功{}".format(raw_data))
                        to_kafka.send_kafka(raw_data, logging)
                    elif d["data"]["code"] == "1" and not d["data"]["sentences"]:
                        results =""
                        if "content" in res_tmp.keys():
                            res_tmp["content"]=results
                        raw_data["result"]["results"] = json.dumps(res_tmp, ensure_ascii=False)
                        raw_data["result"]["status"]=1
                        raw_data["result"]["message"]="成功"
                        logging.info("视频解析获取结果成功{}".format(raw_data))
                        to_kafka.send_kafka(raw_data, logging)
                    elif d["data"]["code"] == "0":
                        # 正在解析中，将任务再次放回数据队列
                        data_queue.put(raw_data)
                        logging.info("视频未解析完毕，放回队列等待{}-{}".format(raw_data, d))
                    else:
                        # 解析失败
                        raw_data["result"]["successCode"] = "0"
                        raw_data["result"]["errorLog"] = response.text
                        raw_data["result"]["results"] = json.dumps(res_tmp, ensure_ascii=False)
                        raw_data["result"]["status"]=2
                        raw_data["result"]["message"]="视频/音频解析异常"
                        logging.info("视频解析获取结果失败,数据{},接口返回值{}".format(raw_data, d))
                        to_kafka.send_kafka(raw_data, logging)
                else:
                    raw_data["result"]["successCode"] = "0"
                    raw_data["result"]["errorLog"] = response.text
                    raw_data["result"]["results"] = json.dumps(res_tmp, ensure_ascii=False)
                    raw_data["result"]["status"] = 2
                    raw_data["result"]["message"] = "视频/音频解析异常"
                    logging.info("视频解析获取结果失败,数据{},接口返回值{}".format(raw_data, d))
                    to_kafka.send_kafka(raw_data, logging)
            else:
                # 暂无任务，进入休眠
                time.sleep(10)
        except:
            raw_data["result"]["successCode"] = "0"
            raw_data["result"]["errorLog"] = traceback.format_exc()
            raw_data["result"]["status"] = 2
            raw_data["result"]["message"] = "视频/音频解析异常"
            raw_data["result"]["results"] = json.dumps(res_tmp, ensure_ascii=False)
            logging.error(traceback.format_exc())
            to_kafka.send_kafka(raw_data, logging)


def zk_monitoring():
    try:
        #线上环境
        zk = KazooClient(hosts='172.18.1.146:2181,172.18.1.147:2181,172.18.1.148:2181')
        #测试环境
        # zk = KazooClient(hosts='172.16.12.55:2181,172.16.12.56:2181,172.16.12.57:2181')
        zk.start()
        # 设置监听器
        @zk.DataWatch("/analyze")
        def watch_node(data, stat, event):
            if event is not None and event.type == EventType.CHANGED:
                data, stat = zk.get("/analyze")
                logging.info("执行删除操作：{}".format(data))
                d = json.loads(data)
                id = d["scenes_id"]
                stop_dict[id] = {}
                stop_dict[id]["version"] = d["version"]
                stop_dict[id]["operation"] = d["operation"]
        # 保持程序运行以监听节点变化
        try:
            while True:
                time.sleep(1)
        except:
            logging.info("Stopping...")
        # 关闭连接
        zk.stop()
        zk.close()
    except:
        logging.error(traceback.format_exc())