国家级气象监测站数据解析程序.rar_国家气象站_数据解析_气象_气象监测_逐日气象数据

#!/usr/bin/env python3 # -*- coding: utf-8 -*- '''文件说明''' __author__ = "LQK" ## DateTime def GetDateArr_days(timeStart, timeEnd): TIME_Start = datetime.datetime.strptime(timeStart, "%Y-%m-%d") TIME_End = datetime.datetime.strptime(timeEnd, "%Y-%m-%d") dateArr = getDayByDay(TIME_Start, TIME_End) # print dateArr return dateArr def GetDateArr_strdays(timeStart, timeEnd, fmt="%Y-%m-%d"): days = GetDateArr_days(timeStart, timeEnd) dateArr_str = [] for d in days: dateArr_str.append(datetime.datetime.strftime(d, fmt)) return dateArr_str def getDayByDay(timeStart, timeEnd): oneday = datetime.timedelta(days=1) timeArr = [timeStart] while timeArr[len(timeArr) - 1] < timeEnd: tempday = timeArr[len(timeArr) - 1] + oneday timeArr.append(tempday) return timeArr # Remove space(' ') and indent('\t') at the begin and end of the string def StripStr(str): oldStr = '' newStr = str while oldStr != newStr: oldStr = newStr newStr = oldStr.strip('\t') newStr = newStr.strip(' ') return newStr # Split string by spliter space(' ') and indent('\t') as default def SplitStr(str, spliters=None): # spliters = [' ', '\t'] # spliters = [] # if spliter is not None: # spliters.append(spliter) if spliters is None: spliters = [' ', '\t'] destStrs = [] srcStrs = [str] while True: oldDestStrs = srcStrs[:] for s in spliters: for srcS in srcStrs: tempStrs = srcS.split(s) for tempS in tempStrs: tempS = StripStr(tempS) if tempS != '': destStrs.append(tempS) srcStrs = destStrs[:] destStrs = [] if oldDestStrs == srcStrs: destStrs = srcStrs[:] break return destStrs # Write file def WriteLog(logfile, contentlist, MODE='replace'): if os.path.exists(logfile): if MODE == 'replace': os.remove(logfile) logStatus = open(logfile, 'w') else: logStatus = open(logfile, 'a') else: logStatus = open(logfile, 'w') if isinstance(contentlist, list) or isinstance(contentlist, tuple): for content in contentlist: logStatus.write("%s%s" % (content, '\r\n')) else: logStatus.write(contentlist) logStatus.flush() logStatus.close() # Create forld def createForld(forldPath): if not os.path.isdir(forldPath): os.makedirs(forldPath) # Delete file def DeleteFile(fp): if os.path.exists(fp): os.remove(fp) import os import math import numpy import time import datetime # 创建类 class ClimateData: ''' 读取气象站点数据，格式化输出 （下载的原始逐日气象数据） ''' def __init__(self, dir, dir_out, sid, fields, period, days): self.dataDir = dir self.dataDir_out = dir_out self.sid = sid self.period = period self.days = days self.fieldName = fields # code：数据类型，ind：数据索引号，frc：真值拉伸系数，ev:异常值阈值，详见气象数据说明文档 self.fieldInfo = { "TEM": {"code": "12001", "ind": 7, "frc": 0.1, "ev": 30000}, "TMX": {"code": "12001", "ind": 8, "frc": 0.1, "ev": 30000}, "TMN": {"code": "12001", "ind": 9, "frc": 0.1, "ev": 30000}, "PRE": {"code": "13011", "ind": 9, "frc": 0.1, "ev": 30000}, # 7:8-20 8:20-8 9:20-20 "EVP": {"code": "13240", "ind": 7, "frc": 0.1, "ev": 1000}, "RHU": {"code": "13003", "ind": 7, "frc": 1.0, "ev": 300}, "WIN": {"code": "11002", "ind": 7, "frc": 0.1, "ev": 1000}, "SSD": {"code": "14032", "ind": 7, "frc": 0.1, "ev": 99}, "GST": {"code": "12030-0cm", "ind": 7, "frc": 0.1, "ev": 10000}, "PRS": {"code": "10004", "ind": 7, "frc": 0.1, "ev": 20000} } # 全部数据 self.data = {} # 数据日期 self.data_date = {} # 存储逐年数据 self.data_y = {} # 待提取日期数据 self.data_d = {} # 获得日期数组 self.GetDateArr() for i in self.fieldName: self.data[i] = [] self.data_date[i] = [] for t in self.years: self.data_y[t] = {} for i in self.fieldName: self.data_y[t][i] = [] for d in self.days: self.data_d[d] = {} for i in self.fieldName: self.data_d[d][i] = 0 def GetDateArr(self): ''' 根据起始日期，获得逐月日期 :return: ''' self.date = [] self.years = [] startDT_y = int(self.period[0][0:4]) startDT_m = int(self.period[0][4:6]) endDT_y = int(self.period[1][0:4]) endDT_m = int(self.period[1][4:6]) if startDT_y == endDT_y: self.years.append(startDT_y) for j in range(startDT_m, endDT_m + 1): if j > 9: self.date.append(str(startDT_y) + str(j)) else: self.date.append(str(startDT_y) + "0" + str(j)) else: for i in range(startDT_y, endDT_y + 1): self.years.append(i) if i == startDT_y: for j in range(startDT_m, 13): if j > 9: self.date.append(str(i) + str(j)) else: self.date.append(str(i) + "0" + str(j)) elif i < endDT_y: for j in range(1, 13): if j > 9: self.date.append(str(i) + str(j)) else: self.date.append(str(i) + "0" + str(j)) else: for j in range(1, endDT_m + 1): if j > 9: self.date.append(str(i) + str(j)) else: self.date.append(str(i) + "0" + str(j)) def ExtractData(self, sr=0): ''' Extract data :param sr: start row numbers, default is 0 :return: ''' print("Data extracting...") # Get date arr s_time = time.clock() # 遍历每个数据类型 for fn in self.fieldName: # 遍历逐月日期 for dt in self.date: print(fn, dt) yr = int(dt[0:4]) # 拼接字符串，组成数据文件路径 field = fn if fn == "TMN" or fn == "TMX": field = "TEM" fileName = self.dataDir + os.sep + "SURF_CLI_CHN_MUL_DAY-" + \ field + "-" + self.fieldInfo[fn]['code'] + "-" + dt + ".TXT" if not os.path.isfile(fileName): raise Exception("Can not find %s" % fileName) else: txtFile = open(fileName, 'r') linesList = txtFile.read().split('\n') iffind = False hasdata = True # 逐行遍历数据 for i in range(sr, len(linesList)): if len(linesList[i]) > 0: # 将每行数据拆成数组，按照索引提取数据 lineArr = SplitStr(linesList[i], spliters=' ') if int(lineArr[0]) == self.sid: iffind = Tru