# 请求数据
def requestData(data_file):# 输入str，返回json数据json_res = json.loads(data_file, encoding='utf-8')# 输入json，返回str，目的是排序encodedjson = json.dumps(json_res, sort_keys=True)# 输入str，返回json，务必要以utf-8加载json数据decodejson = json.loads(encodedjson, encoding='utf-8')return decodejson# 输出数据
def out_data(out_file, d):if not os.path.exists(out_file):print(out_file)header = Falseelse:header = Truef = codecs.open(out_file, 'a', 'gbk')dictWriter = csv.DictWriter(f, list(d.keys()))# only write header when create a new csvif not header:dictWriter.writeheader()dictWriter.writerow(d)f.close()# 主程序
if __name__ == '__main__':# data_file  = open(r'c:\Python33\all_data',encoding='utf_8_sig').read()nowstrp = time.localtime()out_file = time.strftime('%Y%m%d', nowstrp) + '.csv'd = collections.OrderedDict()headers = {'User-Agent': 'Mozilla/5.0(compatible;MSIE 9.0;Windows NT 6.1;Trident/5.0)'}chaper_url = 'http://www.pm25.in/api/querys/all_cities.json?token=appkey(appkey自己去申请，5工作日给答复)'# ie9:Mozilla/5.0(compatible;MSIE 9.0;Windows NT 6.1;Trident/5.0)# 创建request请求url_request = urllib.request.Request(chaper_url, data=None, headers=headers)# 打开网址url_file = urllib.request.urlopen(url_request)if (url_file.getcode() == 200):chaper_url = 'http://www.pm25.in/api/querys/all_cities.json?token=appkey'else:chaper_url = 'http://www.pm25.in/api/querys/all_cities.json?token=appkey'try:print(chaper_url)headers = {'User-Agent': 'Mozilla/5.0(compatible;MSIE 9.0;Windows NT 6.1;Trident/5.0)'}# ie9:Mozilla/5.0(compatible;MSIE 9.0;Windows NT 6.1;Trident/5.0)# 创建request请求url_request = urllib.request.Request(chaper_url, data=None, headers=headers)# 打开网址url_file = urllib.request.urlopen(url_request)data_file = url_file.read().decode('utf-8')# status code: 200 OKwhile (url_file.getcode() != 200):raise Exception('Server connection error, status code:' + ' ')# request again after 3mintime.sleep(3 * 60)headers = {'User-Agent': 'Mozilla/5.0(compatible;MSIE 9.0;Windows NT 6.1;Trident/5.0)'}# ie9:Mozilla/5.0(compatible;MSIE 9.0;Windows NT 6.1;Trident/5.0)
url_request = urllib.request.Request(chaper_url, data=None, headers=headers)url_file = urllib.request.urlopen(url_request)data_file = url_file.read().decode('utf-8')# 返回数据为json格式# json_res = data_file.read().decode('utf-8')
decodejson = requestData(data_file)# 存储json天气数据为data_json.txtf = open('data_json.txt', 'w', encoding='utf-8')json.dump(decodejson, f)f.close()# 下面一句是当数据文件为本机的文件时，才用到的必须加utf_8_sig# data_final=open(r'c:\Python33\11.txt',encoding='utf_8_sig').read()for element in decodejson:print(element)d['area'] = element['area']d['position_name'] = element['position_name']d['aqi'] = element['aqi']d['co'] = element['co']d['co_24h'] = element['co_24h']d['no2'] = element['no2']d['no2_24h'] = element['no2_24h']d['o3'] = element['o3']d['o3_24h'] = element['o3_24h']d['o3_8h'] = element['o3_8h']d['o3_8h_24h'] = element['o3_8h_24h']d['pm10'] = element['pm10']d['pm10_24h'] = element['pm10_24h']d['pm2_5'] = element['pm2_5']d['pm2_5_24h'] = element['pm2_5_24h']d['primary_pollutant'] = element['primary_pollutant']d['quality'] = element['quality']d['so2'] = element['so2']d['so2_24h'] = element['so2_24h']d['station_code'] = element['station_code']d['time_point'] = element['time_point']# 逐行写excel文件
            out_data(out_file, d)# os.system('pause')# time.sleep(180)except Exception as e:error = traceback.format_exc() + '\r\n'print(error)print('\r\n')f = codecs.open('error.log', 'a', 'utf-8')f.writelines(error)f.close()os.system('pause')