溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務條款》
您好，登錄后才能下訂單哦！
這篇文章給大家分享的是有關如何解決Python3抓取微信賬單信息問題的內容。小編覺得挺實用的，因此分享給大家做個參考，一起跟隨小編過來看看吧。
一、采用傳統模擬http抓取
抓取的主要URL:https://wx.tenpay.com/userroll/userrolllist，其中后面帶上三個參數，具體參數見代碼,其中exportkey這參數是會過期的，userroll_encryption和userroll_pass_ticket 這兩個參數需要從cookie中獲得，應該是作為獲取數據的標識，通過抓包也看不出端倪，應該是微信程序內部生成的，如果使用微信開發著工具登錄后直接訪問網址有的時候可以訪問返回數據，但是只是在較短的時間內有效，而且當返回會話超時后，繼續使用網頁訪問就會被限制，一直提示會話超時，應該是在網頁和移動端中exportkey有不同的時間和訪問次數的限制。
之后想通過破解seesion的方式，研究了一下，發現這是不可能的，想要破解session需要搞定wx.login，而wx.login是微信提供的，想要破解難度應該不用我說了。
二、解決exportkey 這個key和Cookie的獲取
需要的工具：
1、安卓/蘋果手機
2、Fiddler（抓包工具）
搞過爬蟲的都知道Fiddler，具體操作就不多說了，設置好代理和開啟Fiddler后，抓取url中的exportkey和相應的Cookie，用于接下來的數據抓取。
三、上代碼
代碼寫的不是很好，若有錯誤還望各位大大指正。
# coding:utf-8 import datetime import time import urllib import urllib.request import json import sys import io import ssl from DBController import DBController #數據庫 #設置系統編碼格式 sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030') #解決訪問Https時不受信任SSL證書問題 ssl._create_default_https_context = ssl._create_unverified_context class MainCode: def __init__(self, url=""): self.url = url self.dbController = DBController() # 數據庫控制 self.userroll_encryption = "uoxQXsCenowxj0G0ppRKBg8iHRPZwZKaUZB0ka1Y5apUuQnKkZTsA/2RMhBPGyMdiHS8QXk8y2JeLgqTPqZPU9fkrCUp+TIQPkHH/uExAwKeBFLute0ztdHaC6GJUJ2+/R8NGWGe16hSKc6L1+LvAw==" self.userroll_pass_ticket = "V7oum4glDbdaAwibC8mcuTizGIKmC9A/Y/V12qASuDALdRMveHcRHv1QXamFk27Z" # self.last_bill_id = "" # self.last_bill_type = "" # self.last_create_time = "" # self.last_trans_id = "" self.last_item = {} self.num= 0 #獲取網頁信息 def get_html(self, url, maxTryNum=5): goon = True # 網絡中斷標記 obj = {} for tryNum in range(maxTryNum): try: # print(self.token) header = { "Accept": 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', "Accept-Encoding":'gzip, deflate, br', "Accept-Language":'zh-CN,zh;q=0.8', "Cache-Control":'max-age=0', "Connection": "keep-alive", "User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 10_2 like Mac OS X) AppleWebKit/602.3.12 (KHTML, like Gecko) Mobile/14C92 Safari/601.1 wechatdevtools/1.02.1810240 MicroMessenger/6.5.7 Language/zh_CN webview/15415760070117398 webdebugger port/32594", "Cookie":"userroll_encryption="+self.userroll_encryption+"; userroll_pass_ticket="+self.userroll_pass_ticket, "Host":"wx.tenpay.com", "Upgrade-Insecure-Requests":"1", } req = urllib.request.Request(url=url, headers=header) # 訪問網址 result = urllib.request.urlopen(req, timeout=5).read() break except urllib.error.HTTPError as e: if tryNum < (maxTryNum - 1): print("嘗試連接請求" + str(tryNum + 1)) # host = self.host2 time.sleep(5) else: print('Internet Connect Error!', "Error URL:" + url) goon = False break if goon: page = result.decode('utf-8') obj = json.loads(page) #print(obj) #print(page) else: print("--------------------------") return obj #保存到數據庫 def save_info_to_db(self, item): select_sql = "SELECT count(*)as num FROM wx_order2 where trans_id = '%s'" % (item["trans_id"]) results = self.dbController.ExecuteSQL_Select(select_sql) if int(results[0][0]) == 0: sql = "INSERT INTO wx_order2 (bill_id, bill_type, classify_type, fee, fee_type, out_trade_no, pay_bank_name, payer_remark, remark, order_time, title, total_refund_fee, trans_id,fee_attr) VALUES ( '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s','%s','%s')" % ( str(item['bill_id']), str(item['bill_type']), str(item['classify_type']), str(item['fee']), str(item['fee_type']) , str(item['out_trade_no']), str(item['pay_bank_name']), str(item['payer_remark']), str(item['remark']), str(item['order_time']), str(item['title']), str(item['total_refund_fee']), str(item['trans_id']), str(item['fee_attr']) ) # print(sql) try: self.dbController.ExecuteSQL_Insert(sql) # self.log.info("插入數據成功") except Exception as e: print("save_info_to_db:",e) return #從獲取的網頁信息中過濾所需要的信息 def get_data(self,url): res_obj = self.get_html(url) this_page_num = 0 #若返回的ret_code== 0 則說明獲取數據成功 if res_obj['ret_code'] == 0: record_list = res_obj['record'] self.last_bill_id = res_obj['last_bill_id'] self.last_bill_type = res_obj['last_bill_type'] self.last_create_time = res_obj['last_create_time'] self.last_trans_id = res_obj['last_trans_id'] num = 1 this_page_num = len(record_list) # order = record_list[i] for order in record_list: bill_id = order['bill_id'] bill_type = order['bill_type'] classify_type = order['classify_type'] fee = order['fee'] #賬單金額 fee = fee * 0.01 fee = round(fee, 2) #對金額保留兩位小數 fee_type = order['fee_type'] #金額類型 out_trade_no = order['out_trade_no'] #賬單編號 pay_bank_name = order['pay_bank_name'] #支付的銀行 payer_remark =order['payer_remark'] #支付說明 remark = order['remark'] #賬單說明 order_time = datetime.datetime.fromtimestamp(order['timestamp']) #將時間戳轉為時間 title = order['title'] #賬單標題 title = title.replace(',','').replace('.','').replace("'",'') #去除英文逗號和單引號 total_refund_fee = "0" trans_id = order['trans_id'] fee_attr = order['fee_attr'] #title = self.remove_emoji(title) fee_attr = order['fee_attr'] pay_type = "" if bill_type == 1: pay_type= "支付" elif bill_type == 2: pay_type = "充值" elif bill_type == 4: pay_type = "轉賬" elif bill_type == 6: pay_type="紅包" else: pay_type = str(bill_type) if fee_attr == "positive": fee_attr = "收入" elif fee_attr == "negtive": fee_attr = "支出" elif fee_attr == "neutral": fee_attr = "提現" item = {} item['bill_id'] = bill_id item['bill_type'] =bill_type item['classify_type'] = classify_type item['fee'] = fee item['fee_type'] = fee_type item['out_trade_no'] = out_trade_no item['pay_bank_name'] = pay_bank_name item['payer_remark'] = payer_remark item['remark'] = remark item['order_time'] = order_time item['title'] = title item['total_refund_fee'] = total_refund_fee item['trans_id'] = trans_id item['fee_attr'] = fee_attr # title = self.remove_emoji(title) if bill_id != '': self.last_item['last_bill_id'] = bill_id self.last_item['last_bill_type'] = bill_type self.last_item['last_create_time'] = order['timestamp'] self.last_item['last_trans_id'] = trans_id try: print(str(self.num),self.last_item,end='\n') self.num += 1 time.sleep(0.2) self.save_info_to_db(item) #print(str(num)+" 時間：" + str(order_time) + " 賬單標題：" + title + " 說明："+ str(remark)+ " " +str(pay_type) +"金額：" + str(fee) + " 支付方式："+ str(pay_bank_name)+" 類型：" + str(pay_type) +" fee_attr："+str(fee_attr)+ '\n',end='') except Exception as e: print(e,end='\n') num = num+1 else:#若獲取數據不成功，打印原因 print(res_obj) return this_page_num #實例化 maincode = MainCode(); #設置Cookie參數 maincode.userroll_encryption = "6Ow68aKrAz70mEczqeevA2gOXbr9H2a7+2ite6uuyWFdB6j1+SLhlaCNpYA6RjmaOI7IfCi9PXjQsrZPFIs1SMn38Uxr04GJsxMuSO/9wG+eBFLute0ztdHaC6GJUJ2+vmo+JIw351su8RiFxSagwA==" maincode.userroll_pass_ticket = "i0Co+55KSEjmFjfFZqMG14hasW4qtKFtbj0FiErcSzHY0afkFqHGib3YfsAZWcaG" #用于非第一頁的數據抓取 #maincode.last_item['last_bill_id'] = "2ce3d65b20a10700b2048d68" #maincode.last_item['last_bill_type'] = "4" #maincode.last_item['last_create_time'] = "1540809516" #maincode.last_item['last_trans_id'] = "1000050201201810290100731805325" #設置每次返回的數量 count = "20" #exportkey 需要從Fiddler 抓包獲取，有一定的時間限制 exportkey ="A%2BsIJaTGZksgZWPLtSKiyos%3D" #抓取的URL url ="https://wx.tenpay.com/userroll/userrolllist?classify_type=0&count="+count+"&exportkey="+exportkey+"&sort_type=1" for page in range(0,10): #記錄當前頁返回的數據數量 this_page_num = 0 #第一頁 if page == 0: this_page_num = maincode.get_data(url) #從第二頁開始需要增加上一頁最后一個item的部分參數，進行下一頁的數據的抓取 else: url = "https://wx.tenpay.com/userroll/userrolllist?classify_type=0&count="+count+"&exportkey="+exportkey+"&sort_type=1"+"&last_bill_id="+str(maincode.last_item['last_bill_id'])+"&last_bill_type="+str(maincode.last_item['last_bill_type'])+"&last_create_time="+str(maincode.last_item['last_create_time'])+"&last_trans_id="+str(maincode.last_item['last_trans_id'] + "&start_time="+str(maincode.last_item['last_create_time'])) print(url) this_page_num = maincode.get_data(url) #如果數量少于20個則跳出循環，抓取結束 if this_page_num < 20: break time.sleep(0.5) print(maincode.last_item)
因為是幫朋友抓取的，能實現就可以了。之后若有需要再繼續優化代碼吧！
感謝各位的閱讀！關于“如何解決Python3抓取微信賬單信息問題”這篇文章就分享到這里了，希望以上內容可以對大家有一定的幫助，讓大家可以學到更多知識，如果覺得文章不錯，可以把它分享出去讓更多的人看到吧！
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
