|
|
# coding:utf8import os, sysimport iofrom jsonpath_ng import jsonpath, parse
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 jsonfrom django.http import HttpResponsefrom text_analysis.tools import to_kafkafrom django.views.decorators.csrf import csrf_exemptfrom log_util.set_logger import set_logger
logging = set_logger('logs/results.log')import tracebackimport queueimport requestsfrom text_analysis.tools.tool import get_dataimport timefrom datetime import datetimeimport os
# 任务队列global task_queuetask_queue = queue.Queue()# 数据队列global data_queuedata_queue = queue.Queue()
@csrf_exemptdef ASR(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() # index = raw_data["metadata"]["index"] # datasource = raw_data["metadata"]["admin"]["datasource"] # if datasource not in raw_data["data"].keys(): # logging.info("找不到相关数据源！—{}".format(raw_data)) # continue # allFile = raw_data["data"][datasource] # currentFile = eval(allFile)[index] url=raw_data["metadata"]["admin"]["fileUrl"] if '$.' in url: # json.path表达式动态获取value datasources = str(url).split(':') # 0是数据源，1是JsonPath 表达式 datasourcestr = raw_data["data"][datasources[0]] # print(datasourcestr) datasource = json.loads(datasourcestr) # 创建 JsonPath 表达式对象 expr = parse(datasources[1]) # 使用表达式来选择 JSON 元素 match = [match.value for match in expr.find(datasource)] video_url = match[0] fileName=video_url.rsplit('/')[-1] if "http" not in video_url: file = "https://caiji.percent.cn/" + video_url.lstrip("/") # print(file) # name=raw_data["metadata"]["admin"]["fileName"] # if '$.' 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={"content":"","fileName":fileName,"fileUrl":file} language = raw_data["metadata"]["admin"]["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 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) 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": currentFile, "dataKey": result} 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: logging.error(traceback.format_exc())
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() # print(raw_data) # 根据视频key访问获取结果接口 dataKey = raw_data["result"]["dataKey"] url = "https://realtime.pdeepmatrix.com/apis/media/analysis/getResult" params = {'taskId': dataKey} response = requests.get(url, params=params) # print(response.text) d = json.loads(response.text) if "code" in d.keys() and d["code"] == 200: results = "" if d["data"]["code"] == "1": for sentence in d["data"]["sentences"]: results += sentence["text"] raw_data["result"]["results"]["content"] = results raw_data["result"]["results"] = json.dumps(raw_data["result"]["results"], ensure_ascii=False) 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(raw_data["result"]["results"], ensure_ascii=False) 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(raw_data["result"]["results"], ensure_ascii=False) 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"]["results"] = "" logging.error(traceback.format_exc()) to_kafka.send_kafka(raw_data, logging)
|
