from common import configs import common import pandas as pd import datetime # # def re_match(city, region, name): # json = common.match(city, name, region) # print(json) # if json["credit"] > 0: # return [json["city"], json["district"], json["name"], json["category"]] # else: # return ['', '', '', ''] # # open_uri_log = common.get_mongodb_collection(configs.SEAWATER_MONGO_URI, "business", "open_uri_log") query = { "user_id": "1007705", "request_uri": "/property/detail", "data_status": 1, 'c_date': {'$gt': datetime.datetime.strptime("20190301", "%Y%m%d")} } logs = list() for log in open_uri_log.find(query): result = log["res_map"]["result"] logs.append({"name": result["name"], "city": result["city"], "district": result["district"], "avgPrice": result["avgPrice"]}) df = pd.DataFrame(logs) df.drop_duplicates() df.to_excel("D:\\亲邻均价.xlsx") # # logs[["输入城市", "输入区域", "输入名称", 'c_date']] = logs.apply(lambda x: # # [x["parameter_map"]["city"], x["parameter_map"]["district"], # # x["parameter_map"]["name"], x['c_date'].strftime("%Y-%m-%d %H:%M:%S")], axis=1, result_type="expand") # # logs[["匹配城市", "匹配区域", "匹配名称", "匹配类型"]] = logs.apply(lambda x: re_match(x['输入城市'], x['输入区域'], x['输入名称']), # # axis=1, result_type="expand") # # del logs['res_map'] # # del logs['parameter_map'] # # del logs['code'] # # del logs['data_status'] # # del logs['ip'] # # del logs['request_uri'] # # del logs['msg'] # # logs.to_excel("D:\\亲邻未匹配数据.xlsx", index=False) # logs = pd.read_excel("D:\\亲邻未匹配数据.xlsx") # logs.drop_duplicates(["输入城市", "输入区域", "输入名称"], keep='first', inplace=True) # logs.to_excel("D:\\亲邻未匹配数据1.xlsx")