1. 程式人生 > 實用技巧 >jupyterLab學習第一天

jupyterLab學習第一天

jupyterLab執行.py檔案

這裡的test.py是寒假在家裡是學習的疫情爬取並匯入mysql中

首先要在cmd控制檯,下載安裝PyMySQL ,PyMySQL 是在 Python3.x 版本中用於連線 MySQL 伺服器的一個庫

pip install pymysql

jupyterLab中執行.py檔案

需要在執行的name.py檔案目錄頁面中,新建python檔案也就是.ipynb檔案

 %load test2.py

輸入上述語句(即 載入程式碼)

載入完後執行程式碼

%run test2.py

這裡附上test.py程式碼

import time

import requests

import pymysql

 

def build_connection_from_sourcedb():

    
return pymysql.connect(host="localhost",database="sys",user="root",password="123456",port=3306,charset='utf8') def get_province_list(): conn = build_connection_from_sourcedb() cur = conn.cursor() sql = "select province_short_name from dict_zone_province" # 請注意資料表中應事先儲存此資料. cur.execute(sql) result
= cur.fetchall() cur.close() conn.close() province_list = [] for i in result: province_list.append(str(i[0])) return province_list ############################################################### # 目標資料庫操作 ############################################################### def target_database_operation(sql): conn
= build_connection_from_sourcedb() cur = conn.cursor() cur.execute(sql) conn.commit() cur.close() conn.close() def record_time_slot(): return time.strftime("%m.%d") def delta_load(): today = record_time_slot() url_prefix = "https://api.inews.qq.com/newsqa/v1/query/pubished/daily/list?province=" province_list = get_province_list() province_list.append("香港") province_list.append("澳門") province_list.append("臺灣") i = 0 len_province_list = len(province_list) conn = build_connection_from_sourcedb() cur = conn.cursor() sql_prefix = "insert into info_copy1(Date,Province,Confirmed_num,Yisi_num,Cured_num,Dead_num) values('" sql_prefix_all = "insert into ncovi2019_daily_all(date,province,confirm,dead,heal,confirm_add) values('" while i < len_province_list: url = url_prefix + province_list[i] response = requests.get(url) data_province_i = response.json()["data"] len_data_province_i = len(data_province_i) j = 0 while j < len_data_province_i: Date = str(data_province_i[j]["date"]) Province = str(data_province_i[j]["province"]) Confirmed_num = str(data_province_i[j]["confirm"]) Yisi_num = str(data_province_i[j]["confirm_add"]) Dead_num = str(data_province_i[j]["dead"]) Cured_num = str(data_province_i[j]["heal"]) # 如果是今天,那麼插入資料到ncovi2019_daily if today == Date: fields = Date + "','" + Province + "'," + Confirmed_num + "," + Yisi_num + "," + Dead_num + "," + Cured_num +")" sql = sql_prefix + fields print(sql) cur.execute(sql) Date = "" Province = "" Confirmed_num = "" Yisi_num = "" Dead_num = "" Cured_num = "" j = j + 1 conn.commit() print("",str(i),"個省份-",province_list[i],""+today+"的疫情資料已插入ncovi2019_daily") i = i + 1 target_database_operation("delete from ncovi2019_daily_all where date = '"+today+"'") print("今天"+today+"的資料已經從ncovi2019_daily_all表中刪除") # 在ncovi2019_daily 中插入全國彙總數 print("將今天的資料彙總插入到ncovi2019_daily") sql = """ insert into info_copy1(Date,Province,Confirmed_num,Yisi_num,Cured_num,Dead_num) SELECT Date, '全國' as Province, sum(Confirmed_num) AS Confirmed_num, sum(Yisi_num) AS Yisi_num, sum(Cured_num) AS Cured_num, sum(Dead_num) AS Dead_num, FROM info_copy1 GROUP BY Date ORDER BY 1 """ cur.execute(sql) conn.commit() print("將今天的資料插入到ncovi2019_daily_all") sql_today = """ insert into ncovi2019_daily_all(date,province,confirm,dead,heal,confirm_add) SELECT date, province as province, confirm AS confirm, dead AS dead, heal AS heal, confirm_add AS confirm_add FROM ncovi2019_daily where province != '全國' """ print("上步結束後進行全國彙總") cur.execute(sql_today) conn.commit() sql_all_summary = """ insert into ncovi2019_daily_all(date,province,confirm,dead,heal,confirm_add) SELECT date, '全國' as province, sum(confirm) AS confirm, sum(dead) AS dead, sum(heal) AS heal, sum(confirm_add) AS confirm_add FROM ncovi2019_daily_all where province != '全國' GROUP BY date ORDER BY 1 """ cur.execute(sql_all_summary) conn.commit() print("全國疫情資料已彙總插入ncovi2019_daily_all") target_database_operation("update info_copy1 set report_date = Date(concat('2020',left(Date,2),right(Date,2))) ") target_database_operation("update ncovi2019_daily_all set report_date = date(concat('2020',left(date,2),right(date,2))) ") cur.close() conn.close() if __name__ == "__main__": print("今天日期:"+record_time_slot()) target_database_operation("truncate table info_copy1") print("清空ncovi2019_daily") delta_load()

這裡需要先建好表dict_zone_province和info_copy1

執行程式碼後