这段时间有个朋友想导出微信里面的账单信息，后来发现微信的反爬虫还是很厉害的，花了点时间去分析。
一、采用传统模拟http抓取
抓取的主要URL:https://wx.tenpay.com/userroll/userrolllist，其中后面带上三个参数，具体参数见代码,其中exportkey这参数是会过期的，userroll_encryption和userroll_pass_ticket 这两个参数需要从cookie中获得，应该是作为获取数据的标识，通过抓包也看不出端倪，应该是微信程序内部生成的，如果使用微信开发着工具登录后直接访问网址有的时候可以访问返回数据，但是只是在较短的时间内有效，而且当返回会话超时后，继续使用网页访问就会被限制，一直提示会话超时，应该是在网页和移动端中exportkey有不同的时间和访问次数的限制。
之后想通过破解seesion的方式，研究了一下，发现这是不可能的，想要破解session需要搞定wx.login，而wx.login是微信提供的，想要破解难度应该不用我说了。
二、解决exportkey 这个key和Cookie的获取
需要的工具：
1、安卓/苹果手机
2、Fiddler（抓包工具）
搞过爬虫的都知道Fiddler，具体操作就不多说了，设置好代理和开启Fiddler后，抓取url中的exportkey和相应的Cookie，用于接下来的数据抓取。
三、上代码
代码写的不是很好，若有错误还望各位大大指正。
# coding:utf-8
import datetime
import time
import urllib
import urllib.request
import json
import sys
import io
import ssl
from DBController import DBController #数据库
#设置系统编码格式
sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')
#解决访问Https时不受信任SSL证书问题
ssl._create_default_https_context = ssl._create_unverified_context
class MainCode:
def __init__(self, url=""):
self.url = url
self.dbController = DBController() # 数据库控制
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
#获取网页信息
def get_html(self, url, maxTryNum=5):
goon = True # 网络中断标记
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)
# 访问网址
result = urllib.request.urlopen(req, timeout=5).read()
break
except urllib.error.HTTPError as e:
if tryNum < (maxTryNum - 1):
print("尝试连接请求" + 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
#保存到数据库
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("插入数据成功")
except Exception as e:
print("save_info_to_db:",e)
return
#从获取的网页信息中过滤所需要的信息
def get_data(self,url):
res_obj = self.get_html(url)
this_page_num = 0
#若返回的ret_code== 0 则说明获取数据成功
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'] #账单金额
fee = fee * 0.01
fee = round(fee, 2) #对金额保留两位小数
fee_type = order['fee_type'] #金额类型
out_trade_no = order['out_trade_no'] #账单编号
pay_bank_name = order['pay_bank_name'] #支付的银行
payer_remark =order['payer_remark'] #支付说明
remark = order['remark'] #账单说明
order_time = datetime.datetime.fromtimestamp(order['timestamp']) #将时间戳转为时间
title = order['title'] #账单标题
title = title.replace(',','').replace('.','').replace("'",'') #去除英文逗号和单引号
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 = "转账"
elif bill_type == 6:
pay_type="红包"
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 = "提现"
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)+" 时间：" + str(order_time) + " 账单标题：" + title + " 说明："+ str(remark)+ " " +str(pay_type) +"金额：" + str(fee) + " 支付方式："+ str(pay_bank_name)+" 类型：" + str(pay_type) +" fee_attr："+str(fee_attr)+ '\n',end='')
except Exception as e:
print(e,end='\n')
num = num+1
else:#若获取数据不成功，打印原因
print(res_obj)
return this_page_num
#实例化
maincode = MainCode();
#设置Cookie参数
maincode.userroll_encryption = "6Ow68aKrAz70mEczqeevA2gOXbr9H2a7+2ite6uuyWFdB6j1+SLhlaCNpYA6RjmaOI7IfCi9PXjQsrZPFIs1SMn38Uxr04GJsxMuSO/9wG+eBFLute0ztdHaC6GJUJ2+vmo+JIw351su8RiFxSagwA=="
maincode.userroll_pass_ticket = "i0Co+55KSEjmFjfFZqMG14hasW4qtKFtbj0FiErcSzHY0afkFqHGib3YfsAZWcaG"
#用于非第一页的数据抓取
#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"
#设置每次返回的数量
count = "20"
#exportkey 需要从Fiddler 抓包获取，有一定的时间限制
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):
#记录当前页返回的数据数量
this_page_num = 0
#第一页
if page == 0:
this_page_num = maincode.get_data(url)
#从第二页开始需要增加上一页最后一个item的部分参数，进行下一页的数据的抓取
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)
#如果数量少于20个则跳出循环，抓取结束
if this_page_num < 20:
break
time.sleep(0.5)
print(maincode.last_item)
因为是帮朋友抓取的，能实现就可以了。之后若有需要再继续优化代码吧！
若有需要回答问题，可以加我QQ：573111256。
1808
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
