Python 獲取車票資訊
阿新 • • 發佈:2019-01-03
提示:該程式碼僅供學習使用,切勿濫用!!!
先來一個git地址:https://gitee.com/wang_li/li_wang
效果圖:
邏輯:
1.獲取Json檔案的內容 2.根據資訊生成URL 3.獲取URL的內容,根據時間進行分析,如果有票則傳送郵件,如果沒有,則繼續監聽
1.定義Json檔案
內容如下:
{ "_Nodes" : "定義起始站", "from_address" : "成都東", "_Nodes" : "定義終點站", "to_address" : "遂寧", "_Nodes" : "定義車次", "departure_date" : "2018-12-30", "_Nodes" : "定義時間檢查區間", "start_time" : "09:00", "_Nodes" : "定義時間結束區間", "stop_time" : "12:00", "_Nodes" : "定義列車型別 [ D:動車 Z:直達 T:特快 K:快速 A:全部 ]", "type" : "A", "_Nodes" : "定義是否傳送郵件 true為傳送 false為不傳送", "send_mail" : "false", "_Nodes" : "如果上述定義為true,則下面則定義郵箱的資訊包括,SMTP 和 認證資訊", "mail_smtp" : "smtp.qq.com", "user_name" : "[email protected]", "user_password" : "password", "mail_subject" : "僅僅是為了好玩", "_Nodes" : "將資訊傳送給誰", "mail_to_address" : "[email protected];[email protected]", "_Nodes" : "有票時,提示的最大次數,當有間隔時,則重新計數 , 這裡最大值為100", "send_mail_max" : 3, "_Nodes" : "重新整理間隔時間,單位:秒", "interval_time" : 30 }
2.Python程式碼處理Json檔案並且返回結果
程式碼如下:
#!/usr/bin/env python3 import requests import json import time import sys import email.mime.text import smtplib #解析json檔案 def Dealwith_jsonfile(jsonfile) : return_dirct = {} #定義json標題 json_title = ['from_address' , 'to_address' , 'departure_date' , 'start_time' , 'stop_time' , 'type' , 'send_mail' , 'mail_smtp' , 'user_name' , 'user_password' , 'mail_subject', 'mail_to_address' , 'send_mail_max','interval_time'] #讀取檔案 open_json_file = open(jsonfile , 'rb') #初始化send_mail引數 send_mail_on = 0 #開啟try except 捕獲json錯誤的資訊 try: dict_json_file = json.load(open_json_file) #查詢是否開啟發送郵件 if 'true' == dict_json_file['send_mail'] : send_mail_on = 1 # 0 為不開啟,則不需要記錄smtp/username/password/send_mail的資訊 if 0 == send_mail_on : for title_configure in json_title : if 'mail_smtp' == title_configure or 'user_name' == title_configure or 'user_password' == title_configure or 'send_mail_max' == title_configure or 'mail_subject' == title_configure or 'mail_to_address' == title_configure: continue else : return_dirct[title_configure] = dict_json_file[title_configure] else : for title_configure in json_title : return_dirct[title_configure] = dict_json_file[title_configure] #關閉檔案 open_json_file.close() print(return_dirct) return return_dirct except Exception as e: print("處理Json檔案失敗,詳情如下:") print(e) if __name__ == "__main__" : Dealwith_jsonfile("go_gome.json")
執行的結果如下:
{'from_address': '成都東', 'to_address': '遂寧', 'departure_date': '2019-01-04', 'start_time': '09:30', 'stop_time': '12:00', 'type': 'D', 'send_mail': 'true', 'mail_smtp': 'smtp.qq.com', 'user_name': '[email protected]', 'user_password': 'idfqdnnrfjttbjbe', 'mail_subject': '僅僅是為了好玩', 'mail_to_address': '[email protected]', 'send_mail_max': 2, 'interval_time': 10}
3.獲取站別ID
網址:https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.9085
具體內容如下:
通過分析得到,名詞的後一位就是站別ID
Python獲取站別ID如下:
#!/usr/bin/env python3 import requests def Get_Address_resolution(from_address,to_address , Address_type) : return_station_name = [] # 站點資訊可以在12306網站上找到 station_name_url = 'https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.9085' #獲取網頁資訊 station_information = requests.get(station_name_url).text #以 | 分割 list_station_information = station_information.split("|") # 獲取from_address 和 to_address 地址的ID if 1 == Address_type : address_com = 1 elif 2 == Address_type : address_com = -1 else : return return_station_name for address in from_address , to_address : try: if list_station_information.index(address): return_station_name.append( list_station_information[list_station_information.index(address) + address_com]) except Exception as e: print(e) return return_station_name if __name__ == "__main__" : print(Get_Address_resolution('成都東','遂寧',1)) print(Get_Address_resolution('ICW', 'NIW', 2))
執行結果如下:
['ICW', 'NIW'] ['成都東', '遂寧']
3.獲取實際URL
通過分析,我們可以得知,每次請求網頁,實際上實在請求一個數據包,例如:
我們只需要將資料拼接上就可以了
程式碼如下:
#!/usr/bin/env python3 def Generate_Url () : try: station_code = ['ICW', 'NIW'] #獲取最新的地址解析時間(此資訊也是固定的) return_url = "https://kyfw.12306.cn/otn/leftTicket/queryA?leftTicketDTO.train_date=%s&leftTicketDTO.from_station=%s&leftTicketDTO.to_station=%s&purpose_codes=ADULT" \ %('2019-01-03' ,station_code[0] , station_code[1] ) return return_url except Exception as e: print("生成URL失敗") print(e) if __name__ == "__main__" : print(Generate_Url())
https://kyfw.12306.cn/otn/leftTicket/queryA?leftTicketDTO.train_date=2019-01-03&leftTicketDTO.from_station=ICW&leftTicketDTO.to_station=NIW&purpose_codes=ADULT
綜合程式碼
#!/usr/bin/env python3 import requests import json import time import sys import email.mime.text import smtplib #解析json檔案 def Dealwith_jsonfile(jsonfile) : return_dirct = {} #定義json標題 json_title = ['from_address' , 'to_address' , 'departure_date' , 'start_time' , 'stop_time' , 'type' , 'send_mail' , 'mail_smtp' , 'user_name' , 'user_password' , 'mail_subject', 'mail_to_address' , 'send_mail_max','interval_time'] #讀取檔案 open_json_file = open(jsonfile , 'rb') #初始化send_mail引數 send_mail_on = 0 #開啟try except 捕獲json錯誤的資訊 try: dict_json_file = json.load(open_json_file) #查詢是否開啟發送郵件 if 'true' == dict_json_file['send_mail'] : send_mail_on = 1 # 0 為不開啟,則不需要記錄smtp/username/password/send_mail的資訊 if 0 == send_mail_on : for title_configure in json_title : if 'mail_smtp' == title_configure or 'user_name' == title_configure or 'user_password' == title_configure or 'send_mail_max' == title_configure or 'mail_subject' == title_configure or 'mail_to_address' == title_configure: continue else : return_dirct[title_configure] = dict_json_file[title_configure] else : for title_configure in json_title : return_dirct[title_configure] = dict_json_file[title_configure] #關閉檔案 open_json_file.close() return return_dirct except Exception as e: print("處理Json檔案失敗,詳情如下:") print(e) #抓取城市名稱對應的ID def Get_Address_resolution(from_address,to_address , Address_type) : #定義返回列表 return_station_name = [] # 站點資訊可以在12306網站上找到 station_name_url = 'https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.9085' #獲取網頁資訊 station_information = requests.get(station_name_url).text #以 | 分割 list_station_information = station_information.split("|") # 獲取from_address 和 to_address 地址的ID if 1 == Address_type : address_com = 1 elif 2 == Address_type : address_com = -1 else : return return_station_name for address in from_address , to_address : try: if list_station_information.index(address): return_station_name.append( list_station_information[list_station_information.index(address) + address_com]) except Exception as e: print(e) return return_station_name # try: # if list_station_information.index(from_address) : # return_station_name.append(list_station_information[list_station_information.index(from_address) + 1]) # except Exception as e: # print(e) # # try: # if list_station_information.index(to_address): # return_station_name.append(list_station_information[list_station_information.index(to_address) + 1]) # except Exception as e: # print(e) # # #將ID返回回去 # return return_station_name # # #程式碼和上述一致,可以合併為到一塊 # elif 2 == Address_type : # try: # if list_station_information.index(from_address) : # return_station_name.append(list_station_information[list_station_information.index(from_address) - 1]) # except Exception as e: # print(e) # # try: # if list_station_information.index(to_address): # return_station_name.append(list_station_information[list_station_information.index(to_address) - 1]) # except Exception as e: # print(e) # # #將ID返回回去 # return return_station_name #生成URL連線 def Generate_Url (operation_parameters) : try: station_code = Get_Address_resolution(operation_parameters['from_address'],operation_parameters['to_address'],1) #獲取最新的地址解析時間(此資訊也是固定的) return_url = "https://kyfw.12306.cn/otn/leftTicket/queryA?leftTicketDTO.train_date=%s&leftTicketDTO.from_station=%s&leftTicketDTO.to_station=%s&purpose_codes=ADULT" \ %(operation_parameters['departure_date'] ,station_code[0] , station_code[1] ) return return_url except Exception as e: print("生成URL失敗") print(e) #爬取是否有票 def Crawling_Informations (url , operation_parameters) : #初始化檢查失敗引數 check_failed = 0 #初始化票send-mail次數 send_mail_number = {} #定義無限迴圈 while True: if check_failed > 10 : print("連續10次抓取失敗,程式退出") break try: #獲取內容並且轉換為json crawling_text = requests.get(url).text crawling_json = json.loads(crawling_text) #定義空的列表用於存放票務資訊 checkmessageall = [] #便利json檔案的['data']['result']資訊 for crawling_list in crawling_json['data']['result'] : checkmessage = [] #將票務資訊按 | 分割 for split_list_json in crawling_list.split('|'): #排除長度問20字元的行 if len(split_list_json) > 20: pass else: #將其他值壓進checkmessage checkmessage.append(split_list_json) #將整個checkmessage 押進checkmessageall checkmessageall.append(checkmessage) #開始處理我們爬過來的票務資訊 for dealwithforlist in checkmessageall: # 計算列車型別 train_type = operation_parameters['type'] # 判斷 [ D:動車 Z:直達 T:特快 K:快速 A:全部 ] 如果都不是的話,預設設定為A 全部 if train_type != 'D' and train_type != 'Z' and train_type != 'T' and train_type != 'K' and train_type != 'A' : train_type = 'A' # 開始匹配列車型別 if train_type in dealwithforlist[dealwithforlist.index('預訂') + 2] or train_type == 'A' : #獲取設定的開始時間和結束時間 start_time = operation_parameters['start_time'] stop_time = operation_parameters['stop_time'] # 判斷開始時間是否大於結束時間 if stop_time <= start_time : print("開始時間不能超過結束時間") sys.exit(-1) # 開始匹配我們的 開始時間 和 結束時間 if (start_time <= dealwithforlist[dealwithforlist.index('預訂') + 7] ) and (stop_time >= dealwithforlist[dealwithforlist.index('預訂') + 7] ) : # 判斷是否有票 if 'Y' == (dealwithforlist[dealwithforlist.index('預訂') + 10]): print("有票") print(dealwithforlist) # 判斷是否傳送郵件 if 'true' == operation_parameters['send_mail']: #獲取郵件傳送最大次數 send_mail_max = operation_parameters['send_mail_max'] # 如果沒有郵件傳送計數,則重新生成 if (dealwithforlist[dealwithforlist.index('預訂') + 2]) not in send_mail_number: send_mail_number[dealwithforlist[dealwithforlist.index('預訂') + 2]] = 0 # 判斷髮送郵件 if (send_mail_number[dealwithforlist[dealwithforlist.index('預訂') + 2]]) <= send_mail_max : Send_Mail_Only_You_Yan(dealwithforlist , operation_parameters) pass if send_mail_number[dealwithforlist[dealwithforlist.index('預訂') + 2]] <= 1200 : send_mail_number[dealwithforlist[dealwithforlist.index('預訂') + 2]] = send_mail_number[dealwithforlist[dealwithforlist.index('預訂') + 2]] + 1 else: print("沒有票") print(dealwithforlist) #將sned_mail_number至0 send_mail_number[dealwithforlist[dealwithforlist.index('預訂') + 2]] = 0 # 獲取間隔時間 interval_time = operation_parameters['interval_time'] #定義睡眠時間 time.sleep(interval_time) check_failed = 0 except Exception as e: print(e) check_failed = check_failed + 1 def Send_Mail_Only_You_Yan (dealwithforlist , operation_parameters): #獲取票的資訊 network_list_info_station_address = Get_Address_resolution(dealwithforlist[dealwithforlist.index('預訂') + 3],dealwithforlist[dealwithforlist.index('預訂') + 4],2) network_list_info_train_number = dealwithforlist[dealwithforlist.index('預訂') + 2] network_list_info_start_time = dealwithforlist[dealwithforlist.index('預訂') + 7] network_list_info_stop_time = dealwithforlist[dealwithforlist.index('預訂') + 8] network_list_info_run_time = dealwithforlist[dealwithforlist.index('預訂') + 9] network_list_info_date = dealwithforlist[dealwithforlist.index('預訂') + 11] local_list_info_start_address = operation_parameters['from_address'] local_list_info_to_address = operation_parameters['to_address'] #獲取郵件資訊 local_list_info_mail_smtp = operation_parameters['mail_smtp'] local_list_info_mail_user = operation_parameters['user_name'] local_list_info_mail_password = operation_parameters['user_password'] local_list_info_mail_subject = operation_parameters['mail_subject'] local_list_info_mail_to_address = operation_parameters['mail_to_address'] HOST = local_list_info_mail_smtp SUBJECT = local_list_info_mail_subject TO = local_list_info_mail_to_address FROM = local_list_info_mail_user msg = email.mime.text.MIMEText( """ <html> <head> <title>僅僅是為了好玩</title> <style> body { width: 35em; margin: 0 auto; font-family: Tahoma, Verdana, Arial, sans-serif; } </style> </head> <body> <table style="padding: 1px;background-color: #2300f9;"> <tr> <th style="background-color: white">車次</th> <th style="background-color: white">需求出發站</th> <th style="background-color: white">需求到達站</th> <th style="background-color: white">車票出發站</th> <th style="background-color: white">車票到達站</th> <th style="background-color: white">時間</th> <th style="background-color: white">發車時間</th> <th style="background-color: white">到達時間</th> <th style="background-color: white">歷時</th> </tr> <tr> <td style="background-color: white">%s</td> <td style="background-color: white">%s</td> <td style="background-color: white">%s</td> <td style="background-color: white">%s</td> <td style="background-color: white">%s</td> <td style="background-color: white">%s</td> <td style="background-color: white">%s</td> <td style="background-color: white">%s</td> <td style="background-color: white">%s</td> </tr> </table> </body> </html> """ %(network_list_info_train_number ,local_list_info_start_address ,local_list_info_to_address , network_list_info_station_address[0] , network_list_info_station_address[1] ,network_list_info_date , network_list_info_start_time , network_list_info_stop_time , network_list_info_run_time ), "html","utf-8") msg['Subject'] = SUBJECT msg['From'] = FROM msg['TO'] = TO server = smtplib.SMTP_SSL(HOST,'465') server.login(local_list_info_mail_user,local_list_info_mail_password) server.sendmail(FROM,TO.split(';'),msg.as_string()) server.quit if __name__ == "__main__" : # #解析json檔案 # operation_parameters = Dealwith_jsonfile("go_gome.json") # # #生成URL連線 # url = Generate_Url(operation_parameters) # # #開始查詢票票 # Crawling_Informations(url , operation_parameters) Crawling_Informations(Generate_Url(Dealwith_jsonfile("go_gome.json")) , Dealwith_jsonfile("go_gome.json"))